UNIVERSITY OF GONDAR COLLEGE OF INFORMATICS SCHOOL OF GRADUATE STUDIES DEPARTMENT OF INFORMATION TECHNOLOGY KNOWLEDGE BASED SYSTEM FOR DIAGNOSIS AND TREATMENT OF MANGO DISEASES BY WALTENGUS BIRHHANIE JUNE 2018 GONDAR

UNIVERSITY OF GONDAR
COLLEGE OF INFORMATICS
SCHOOL OF GRADUATE STUDIES
DEPARTMENT OF INFORMATION TECHNOLOGY
KNOWLEDGE BASED SYSTEM FOR DIAGNOSIS AND TREATMENT OF MANGO DISEASES
BY
WALTENGUS BIRHHANIE
JUNE 2018
GONDAR, ETHIOPI
UNIVERSITY OF GONDAR
COLLEGE OF INFORMATICS
SCHOOL OF GRADUATE STUDIES
DEPARTMENT OF INFORMATION TECHNOLOGY
KNOWLEDGE BASED SYSTEM FOR DIAGNOSIS AND TREATMENT OF MANGO DISEASES
A Thesis Submitted to the Department of Information Technology of University of Gondar in Partial Fulfillment of the Requirements for Degree of Master of Science in Information Technology.

BY
WALTENGUS BIRHANIE
Advisor: Dr. Tesfa (Phd.)
JUNE 2018
GONDAR, ETHIOPIA
UNIVERSITY OF GONDAR
COLLEGE OF INFORMATICS
SCHOOL OF GRADUATE STUDIES
DEPARTMENT OF INFORMATION TECHNOLOGY
KNOWLEDGE BASED SYSTEM FOR DIAGNOSIS AND TREATMENT OF MANGO DISEASES
BY
WALTENGUS BIRHHANIE
Name and Signature of Members of the Examining Board
Name Title Signature Date
__________________________, Chairperson, _______________, _____________
__________________________, Advisor, _______________, _____________
__________________________, Examiner, _______________, _____________
__________________________, Examiner, _______________, _____________
DEDICATIONI would like to dedicate my thesis work to my beloved mother W/ro Shashitu Simegni. Thank you for all you have done. God bless you, My Mom!
ACKNOWLEDGMENTFirst and foremost, I would like to give a special gratitude to the Lord of Lords, King of Kings and merciful God who provided me everything to finish this thesis work.
I gratefully acknowledge my advisor, Dr. Tesfa T.(PhD) for his commitment and patience reading for each and every section of the thesis, his valuable comments, encouragement and guidance from the initial to the final level of the research that enabled me to finish the thesis work.
I would like to express my thanks to all my friends as well as to my staff members of Assosa University department of information Science for their priceless supports, moral and encouragements.
Finally, I would like to thank my family for their encouragement and support. Without their support, the work on this thesis would never have been completed. I would like to thank especially to my parents for raising me, inspiring me and praying for me in all their time since my birth till now.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

TOC o “1-3” h z u DEDICATION PAGEREF _Toc514410972 h iACKNOWLEDGMENT PAGEREF _Toc514410973 h iiList of Tables PAGEREF _Toc514410974 h vList of Figures PAGEREF _Toc514410975 h viACRONYMS PAGEREF _Toc514410976 h viiABSTRACT PAGEREF _Toc514410977 h ixCHAPTER ONE PAGEREF _Toc514410978 h 1INTRODUCTION PAGEREF _Toc514410979 h 11.1.BACKGROUND OF THE STUDY PAGEREF _Toc514410980 h 11.2 STATEMENT OF THE PROBLEM PAGEREF _Toc514410981 h 61.3. OBJECTIVE OF THE STUDY PAGEREF _Toc514410982 h 121.3.1. GENERAL OBJECTIVE PAGEREF _Toc514410983 h 121.3.2 SPECIFIC OBJECTIVES PAGEREF _Toc514410984 h 121.4.SCOPE OF THE STUDY PAGEREF _Toc514410985 h 121.5.SIGNIFICANCE OF THE STUDY PAGEREF _Toc514410986 h 131.6.METHODOLOGY OF THE STUDY PAGEREF _Toc514410987 h 141.6.1. RESEARCH DESIGN PAGEREF _Toc514410988 h 141.6.2 LITERATURE REVIEW PAGEREF _Toc514410989 h 151.6.3 KNOWLEDGE ACQUISITION PAGEREF _Toc514410990 h 151.6.4. KNOWLEDGE MODELING METHOD PAGEREF _Toc514410991 h 151.6.5. KNOWLEDGE REPRESENTATION METHOD PAGEREF _Toc514410992 h 161.6.6. KNOWLEDGE BASED SYSTEM DEVELOPMENT TOOLS PAGEREF _Toc514410993 h 171.6.7. EVALUATION TECHNIQUES PAGEREF _Toc514410994 h 17CHAPTER TWO PAGEREF _Toc514410995 h 18LITERATURE REVIEW PAGEREF _Toc514410996 h 182.1. INTRODUCTION PAGEREF _Toc514410997 h 182.2. HISTORY OF MANGO AND FRUIT CROP IN ETHIOPIA PAGEREF _Toc514410998 h 19CONSTRAINTS AND OPPORTUNITIES IN FRUIT CROP AGRICULTURE PAGEREF _Toc514410999 h 212.3.MAJOR MANGO DISEASES IN ETHIOPIA PAGEREF _Toc514411000 h 222.4. ECONOMIC IMPORTANCE OF FRUIT CROP IN ETHIOPIA PAGEREF _Toc514411008 h 312.5. AN OVERVIEW OF ARTIFICIAL INTELLIGENCE AND KBS PAGEREF _Toc514411009 h 322.5.1. Overview PAGEREF _Toc514411010 h 332.5.2. Artificial Intelligence (AI) PAGEREF _Toc514411011 h 332.5.3. Knowledge Based Systems (KBS) PAGEREF _Toc514411012 h 342.5.4. ADVANTAGES OF KBS PAGEREF _Toc514411013 h 352.5.5 KBS Architecture and its Components PAGEREF _Toc514411014 h 352.5.6. KBS Development Phases PAGEREF _Toc514411015 h 382.5.7. Evaluation and Testing of KBS PAGEREF _Toc514411016 h 442.5.8. KBS Development Tools PAGEREF _Toc514411017 h 452.5.9. Application of KBS PAGEREF _Toc514411018 h 462.6. Related Research Works to Agriculture and Plant Disease Diagnosis PAGEREF _Toc514411019 h 47CHAPTER THREE PAGEREF _Toc514411020 h 563.1 KNOWLEDGE ACQUISITION IN KBS DEVELOPMENT PAGEREF _Toc514411021 h 563.2STEPS IN KNOWLEDGE ACQUISITION PAGEREF _Toc514411022 h 573.2.1KNOWLEDGE ELICITATION PAGEREF _Toc514411023 h 573.2.2KNOWLEDGE STRUCTURING PAGEREF _Toc514411024 h 573.3KNOWLEDGE OF MANGO DISEASES PAGEREF _Toc514411025 h 583.3.1TYPES OF MANGO DISEASES PAGEREF _Toc514411026 h 583.3.2MANAGEMENT OF MANGO DISEASE PAGEREF _Toc514411027 h 633.4CONCEPTUAL MODELING PAGEREF _Toc514411028 h 633.4.1CONCEPTS OF SYMPTOMS PAGEREF _Toc514411029 h 643.5KNOWLEDGE REPRESENTATION PAGEREF _Toc514411030 h 67CHAPTER FOUR PAGEREF _Toc514411031 h 71IMPLEMENTATION AND EXPERMENTATION PAGEREF _Toc514411032 h 714.1.ARCHITECTURE OF THE PROTOTYPE SYSTEM PAGEREF _Toc514411033 h 714.2 P history PAGEREF _Toc514411034 h 734.3.DIAGNOSIS AND TREATMENT PAGEREF _Toc514411035 h 734.4.EXPLANATION FACILITY BY PROTOTYPE SYSTEM PAGEREF _Toc514411037 h 734.5.TESTING AND EVALUATION OF THE PROTOTYPE SYSTEM PAGEREF _Toc514411038 h 744.5.1.SYSTEM PERFORMANCE EVALUATION PAGEREF _Toc514411039 h 744.5.2.USER ACCEPTANCE TESTING (UAT) PAGEREF _Toc514411040 h 76CHAPTER FIVE PAGEREF _Toc514411041 h 80CONCLUSION AND RECOMMENDATIONS PAGEREF _Toc514411042 h 805.1CONCLUSION PAGEREF _Toc514411043 h 805.2 RECOMMENDATIONS PAGEREF _Toc514411044 h 80Reference PAGEREF _Toc514411045 h 82List of Tables TOC h z c “Table” Table 1 Confusion matrix concept PAGEREF _Toc514354087 h 75Table 2 Confusion matrix of the prototype system PAGEREF _Toc514354088 h 75Table 3 Accuracy of the prototype system PAGEREF _Toc514354089 h 76Table 4 Performance evaluations by domain experts PAGEREF _Toc514354090 h 78
List of Figures TOC h z c “Figure” Figure 1 Anthracnose infections start as small, angular, brown to black spots in leaves and fruits PAGEREF _Toc514354226 h 24Figure 2 Mango panicles with powdery mildew PAGEREF _Toc514354227 h 26Figure 3 a whitish-gray haze covers a normally reddish mango panicle. PAGEREF _Toc514354228 h 26Figure 4 Symptoms of mango powdery mildew and mango anthracnose compared. PAGEREF _Toc514354229 h 27Figure 5 Characteristic symptoms of mango powdery mildew on mango leaves PAGEREF _Toc514354230 h 28Figure 6 Late- state powdery mildew infection on underside of mango leaf. PAGEREF _Toc514354231 h 28Figure 7 Alga spot in mango leaf. PAGEREF _Toc514354232 h 29Figure 8 Basic Structure of KBS (adopted from 40 65) PAGEREF _Toc514354233 h 36Figure 9 Semantic networks for table 50 73 PAGEREF _Toc514354234 h 41Figure 10 Decision trees for diagnosis and treatment of Mango Disease PAGEREF _Toc514354235 h 67Figure 11 Architecture of the developed prototype system PAGEREF _Toc514354236 h 71Figure 12 How prototype system diagnosis and treatment PAGEREF _Toc514354237 h 73Figure 13 How prototype system gives explanation facility PAGEREF _Toc514354238 h 74
ACRONYMSAI = Artificial Intelligence
SNNPR = South Nation Nationalities of People Representative
CBR = Case-based reasoning
UAAIE = Upper Awash Agro Industry Enterprise
MT=Meter Ton
DM = Data Mining
ES = Expert System
GDP= Domestic Product
CSA= Central Intelligence Agency
WHO= World Health Organization
JESS = Java Expert System Shell
KBS = Knowledge Based System
KA= Knowledge Acquisition
KR= Knowledge Representation
CCKBS=Cereal Crop Knowledge Based System
KE = Knowledge Engineer
TP= True Positive
TN=True Negative
FP=False Positive
FN=False Negative
RAD = Rapid Application Development
KDD = Knowledge Discovery in Database
ABSTRACTIn this study, a prototype with self-learning knowledge based system (KBS) to support mango disease diagnosis and treatment is proposed. So, in order to develop the proposed knowledge based system an implicit and explicit knowledge used and acquired through interview and document analysis respectively. The knowledge acquired through document analysis and interview is modeled using decision tree, used for diagnosis as well as for data triangulation in the development of the self-learning KBS.

The mango diseases types are identified through interview and document analysis. The data are collected from Ambo Plant Protection Research Center. Experiments conducted using rule based technique.

Finally, performance testing and user acceptance evaluation is performed in order to make sure whether the proposed solution meets its objectives, to measure the accuracy during problem solving process and to measure user acceptance during user interaction. The performance according to the domain expert’s evaluation is scored total of 82.3% and the user acceptance testing scored 83.21% performance. However, this study needs a further effort to increase the system accuracy by collecting more data with high number of attributes and the study recommend it for further study.

CHAPTER ONEINTRODUCTIONBACKGROUND OF THE STUDYAgriculture is the corner stone of the development policy of the Government of Ethiopia. The country’s economic development will depend, in large part on sustainable improvements in agriculture. Agriculture remains by far the most important sector in the Ethiopian economy for the following reasons: (i) It directly supports about 85% of the population in terms of employment and livelihood; (ii) It contributes about 50% of the country’s gross domestic product (GDP); (iii) It generates about 90% of the export earnings. Agriculture is also the major source of food for the population and hence the prime contributing sector to food security 1.

In addition, agriculture is expected to play a key role in generating surplus capital to speed up the overall socio economic development of the country. A high rate of agricultural growth has far reaching positive implications for economic development of low income countries in terms of increasing employment and accelerating poverty reduction 2.

The majority of the Ethiopian populations live in rural areas where agriculture is the main occupation and source of livelihood. It contributes for about 47.3% of GDP and 90% of export earnings 3.
Ethiopia is one of the developing countries with high population and food insecurity. The country has been implementing different strategies to achieve food security. Diversification of crops, increasing the availability of food production, and encouraging the production of early maturing and high yielding crops in different agro-ecologies of the country are some of such strategies 4. Food security is one of the most important problems for the rural population of Ethiopia, whose life is almost entirely dependent on agricultural products.

Ethiopia is characterized by having different agro-ecological zones and it accounts about a total area of 1.13 million km2 5. A variety of fruit crops has been growing in different agro ecological Zones by small farmers, for subsistence and income generation. About 61,972.60 hectares of land is under fruit crops in Ethiopia. Bananas (Musa paradisiaca) contributed about 58.11% of the fruit crop area followed by avocados (Persea americana) and mangoes (Mangifera indica) that contributed 14.42% and 14.21% of the area respectively. More than 4,793,360.64 quintals of fruits was produced in the country. Bananas (Musa paradisiaca), Mangoes (Mangifera indica), Papayas (Carica papaya), Oranges and Avocados (Persea americana) took up 63.11%, 14.55%, 8.07%, 7.46% and 5.35% of the fruit production, respectively 6.
Mango is one of the world’s most important fruits of the tropical and subtropical countries and cultivated extensively as a commercial fruit crop in India, China, Indonesia, Thailand and Mexico. By virtue of its wide range of cultivation, delicious taste, super flavour, very high nutritive and medicinal value as well as great religion historical significance, it is regarded as the “King of the fruits” 7. Mango is the most important fruit and it is the second in area coverage after banana in southern region of Ethiopia 8.
The production of mango firstly ranked in the world is India. India produces 65% of the world’s mango crop 10,800 (70% of its fruit-growing area). Following India in volume of production China 3673, Thailand 1800, Mexico 1679, Pakistan 1674, Indonesia 1478, Brazil 1000 and Philippines 985 and all are in 1,000MT 9. Nigeria is first from Africa it produce 730000 MT and Egypt is second 380000MT of mango produced per year 9.

The mango crop is also cultivated in Ethiopia and, mango is the first fruit crop grown while in southwest Ethiopia 10.
The area of mango production in the different regions is about 3789.47 ha in Oromia, 3375.89 ha in SNNPR, 652.56 ha in Benishangul Gumz, 246.85 ha in Amahara, 180.41 ha in Gambella, 44.5 ha in Dire Dawa, 33.52 ha in Somali, 118.20 in Tigray and 367.24 ha in Harari. The total area allotted for mango is about 8808.64 ha and the country annual production of mango from all mango grower regions is about 697,507 quintals 11.
Mango trees in most parts of Ethiopia are developed from seedlings and are inferior in productivity and in fruit quality. To alleviate these problems improved varieties named Kent, Keit and Tommy Atkins were introduced from Israel in 1983 and are being commercially produced by the Upper Awash Agro Industry Enterprise (UAAIE). These varieties are widely distributed to different parts of Ethiopia by UAAIE. In 2001/2002, a private farm called Green Focus Ethiopia Limited introduced a new mango cultivar called Alphanso from India and planted in its farm at Loko in Guto Gida district of East Wollega zone of Oromia, western Ethiopia. Many farmers are growing mango trees used as a source of income and for shading purpose 12.

Mango tree is attacked by different insects and diseases such as , Anthracnose, Bacterial Black spot, Fruit fly, mango gall flies, Mango leaf coating, Mites, Mango seed weevil, Mealy bug,
Powdery mildew, Scale, Spider mites, Mango tip borer, Stem-end rot, Termite, Thrips and White flies. The major insect pest of mango is the white mango scale insect, Aulacaspis tubercularis (Hemiptera: Diaspididae). It has been recorded mainly from plants belonging to four families: Palmae, Lauraceae, Rutaceae and Anacardiaceae 13. This insect is a serious pest in mango especially on the late cultivars 14 15.
White mango scale insect is a serious pest that injures mangoes by feeding on the plant sap through leaves, branches and fruits, causing defoliation, drying up of young twigs, poor blossoming and so affecting the commercial value of fruits and their export potential especially to late cultivars where it causes conspicuous pink blemishes around the feeding sites of the scales. In nurseries, severe early stage infestation retards growth. Young trees are particularly vulnerable to excessive leaf loss and death of twigs, during hot dry weather. The heavily infested premature fruits dropping and the mature fruits became small in size with lacking of juice 15. A. tubercularis is a tropical species that may have Abo-Shanab, A.S.H.originated in Asia. It has been recorded mainly from hosts belonging to four plant families: Palmae, Lauraceae, Rutaceae, Anacardiaceae, particularly on mangoes and cinnamon 13.
Agriculture is one of the most important inventions of human civilization. The development of human civilization and development of agriculture technology were the two wheels of the cart. Unfortunately, it has been witnessed that the development of agriculture technology is not in the same ratio as human civilization is developed. Traditional tools and techniques used for forming are neither sufficient to predict nor, to optimize production results of yield. The agricultural data is diversified, complex and non-standard and information available about agriculture is in the form of static maps or tables or reports 16.

Agriculture and plantation is an important and interesting research area everywhere in the world and Ethiopia is no exception. Nowadays available land area for a plantation is becoming scarce. This scarce resource is frequently wasted through our bad practices and improper management. Cultivation is a more economical but complex process. Diagnosis and treatment of mango fruit diseases for the maximum profit involves a sequence of tasks. These tasks and the whole process need a lot of expert knowledge and experience. But unfortunately, people having this type of knowledge are very limited. Their assistance is not available when the person who is going to cultivate needs it.

Expert System is one of the important application-oriented branches of Artificial Intelligence. The Expert Systems approach attempts to model the domain knowledge of experts in their respective areas of specialization, for example, diagnosis, planning, forecasting etc. Expert System is based on the knowledge including not only models and data, but more emphasizing on experiences of domain experts. An expert system is a computer application that solves complicated problems that would otherwise require extensive human expertise. It can be operated by a less educated person or a layman in a particular field of knowledge 17.
The need of expert systems for technical information transfer in agriculture can be identified by recognizing the problems in using the traditional system for technical information transfer, and by proving that expert systems can help to overcome the problems addressed, and are feasible to be developed.

An Expert System is an intelligent computer program that uses knowledge and inference procedures to solve problems that are difficult enough to require human expertise for their solution. The knowledge necessary to perform at such level plus the inference procedures used can be thought of as a model of the expertise or the best practitioners in the field. An expert system is based on an extensive body of knowledge about a specific problem area. Characteristically this knowledge may be organized as a collection of rules, which allow the system to draw conclusions from given data or premises or in the form of Ontology which may be accessed for inference. Collection of facts and rules about some specialized knowledge domain is called as Knowledge Base. This knowledge is organized in such a way that separates this knowledge about the problem domain from the system’s other knowledge, such as general knowledge about how to solve problems or knowledge about how to interact with user. The general problem solving knowledge is called Inference Engine. I.e. how user input Queries will be handled, response will be generated, etc. and using this dynamic information with static knowledge present in the knowledgebase to come to a conclusion. A program with knowledge organized in this way i.e. in the form of Knowledgebase and Inference Engine, is called Knowledge Based System 18.

Knowledge base systems (KBS) are artificial intelligence based tools designed to provide expert level solutions in a narrow based problem area. Frenster 19 stated that KBS provide pre-selected rules for decision-making within specialized domains of knowledge but are limited by the fixed choices and by the date of the expert opinions embodied in the decision rules. However, according to Duda and Shortliffe 20, knowledge base systems must be understandable and flexible enough to accommodate new knowledge. They act as data points out of which a cumulative body of knowledge commonly derived from human experts is developed. The human knowledge is made of a body of facts of the real world.

With this, KBS can explain the reasoning process through back-traces and forward chaining and handle high levels of confidence and uncertainty, which provides an additional feature difficult to conventional programming.

The knowledge of knowledge base systems is represented as data or rules that appear in syntax as physical patterns in electronic form in the knowledge base. The knowledge is represented as production rules in the form of condition-action pairs of IF—THEN format 21. Therefore, from the syntax and semantics of these rules the inference of an agent that uses a particular language is derived. Sound inference is got if the inference steps respect the semantics of the sentences they operate upon in the knowledgebase 22. But conventional computer programs perform tasks by use of conventional decision-making logic, which are represented in the symbolic state.

Knowledge base systems have become widely useful application in many complex tasks. Their ability to use domain knowledge to speedily solve difficult problems makes them indispensible in, for example, medical diagnostics, manufacturing and agricultural industry and in finance and banking. 20 Described knowledge base system to be often more effective than other computer-based advising systems because they are goal oriented, efficient, adaptive, and able to explain their information requests and suggestions. This is one of the reasons therefore that they are widely applied, greatly marketable and of high commercial value in the developed world today 22.

Agriculture, being a very vast and varied domain of knowledge with over a hundred crops distributed in different geographic regions having varied climatic conditions, building such a team in every domain of knowledge of agriculture is itself a challenging and huge task. Knowledge engineers gather knowledge from domain experts and put it in such a form that system can use for inferring and reasoning using a knowledge representation technique.

In this study, the researcher proposed knowledge based system for Mango fruit Disease Diagnosis and Treatment, an expert system that will use for recommending farmers and agronomy experts about disease diagnosis and treatment. It enables domain experts to build effective expert system in their fruit with minimal intervention of knowledge engineers and programmers.

Farmers and agronomy expert require timely, accurate and location specific information in relation with different aspects of farming like the pests, diseases, weeds and fertilizer management, etc. for their crops from agricultural experts. On the other side, the complexity of a whole farming process is growing because it is constrained by many factors such as requirements, goals, regulations, etc. that farmer must satisfy or consider. To provide such information and to achieve an optimal crop plan, the automation is provided by computer-based systems termed as advisory systems. An advisory system supports the farmers and experts in getting advices on many activities in farming process 23.

Expert Systems (ES) can be used for extending the research to farmers and it can work as a problem-solving tool for them. ES on agriculture can have a powerful mechanism with extensive potential to solve the problems related to agriculture. ES are designed to emulate the logic and reasoning processes that an expert would use to solve a problem 24.

1.2 STATEMENT OF THE PROBLEMAgriculture is the predominant activity for most rural households in Ethiopia. The sector is mainly based on small holder farms and contributes about half to the total Gross Domestic Product (GDP) of Ethiopia and the livelihoods of more than 80% of the citizens 25. The small-scale farming accounts for 95% of the total area under crop and more than 90% of crop output.
Fruit crops play an important role in the national food security of people around the world. They are generally delicious and highly nutritious, mainly of vitamins and minerals that can balance cereal-based diets. Fruits supply raw materials for local industries and could be sources of foreign currency. Moreover, the development of fruit industry will create employment opportunities, particularly for farming communities. In general, Ethiopia has great potential and encouraging policy to expand fruit production for fresh market and processing both for domestic and export markets. Besides, fruit crops are friendly to nature, sustain the environment, provide shade, and can easily be incorporated in any agro-forestry programs 26.

The mango, because of its attractive appearance and the very pleasant taste of selected cultivars, is claimed to be the most important fruit of the tropics and has been touted as ‘king of all fruits’. The fruit contains almost all the known vitamins and many essential minerals. The protein content is generally a little higher than that of other fruits except the avocado. Mangos are also a fairly good source of thiamine and niacin and contain some calcium and iron 27.

Mango is one of the world’s most important fruits of the tropical and subtropical countries and is cultivated extensively as a commercial fruit crop in India, China, Indonesia, Thailand and Mexico. By virtue of its wide range of cultivation, delicious taste, super flavour, very high nutritive and medicinal value as well as great religion historical significance, it is regarded as the “King of the fruits” 28. Mango is the most important fruit and it is the second in area coverage after banana in southern region of Ethiopia 29.
The mango crop is also cultivated in Ethiopia and while in southwest Ethiopia, mango is the first fruit crop grown 10. The area of mango production in the different regions is about 3789.47 ha in Oromia, 3375.89 ha in SNNPR, 652.56 ha in Benishangul Gumz, 246.85 ha in Amahara, 180.41 ha in Gambella, 44.5 ha in Dire Dawa, 33.52 ha in Somali, 118.20 in Tigray and 367.24 ha in Harari. The total area allotted for mango is about 8808.64 ha and the country annual production of mango from all mango grower regions is about 697,507 quintals 11.

Mango tree is attacked by different insects and diseases such as , Anthracnose, Bacterial Black spot, Fruit fly, mango gall flies, Mango leaf coating, Mites, Mango seed weevil, Mealy bug,
Powdery mildew, Scale, Spider mites, Mango tip borer, Stem-end rot, Termite, Thrips and White flies. The major insect pest of mango is the white mango scale insect, Aulacaspis tubercularis (Hemiptera: Diaspididae). It has been recorded mainly from plants belonging to four families: Palmae, Lauraceae, Rutaceae and Anacardiaceae 13. This insect is a serious pest in mango especially on the late cultivars 14.

White mango scale insect is a serious pest that injures mangoes by feeding on the plant sap through leaves, branches and fruits, causing defoliation, drying up of young twigs, poor blossoming and so affecting the commercial value of fruits and their export potential especially to late cultivars where it causes conspicuous pink blemishes around the feeding sites of the scales. In nurseries, severe early stage infestation retards growth.

Plant diseases are one of the most important reasons that lead to the destruction of plants and crops. Detecting those diseases at early stages enables us to overcome and treat them appropriately 30. This process requires an expert to identify the disease, describe the methods of treatment and protection. Identifying the treatment accurately depends on the method that is used in diagnosing the diseases. Expert systems help a great deal in identifying those diseases and describing methods of treatment to be carried out taking into account the user capability in order to deal and interact with expert system easily and clearly. This requires that the users should be competent using expert systems. An expert system was developed using two different methods of plant diagnosis: step by step descriptive and graphical representational methods. Present expert system plays the role of an agricultural engineer and provides the user with different methods of diagnosis and treatment 30.
Identifying the plant diseases is not easy task; it needs experience and knowledge of plant and their diseases. Moreover, it requires accuracy in describing the symptoms of plant diseases. A person can depend on a system that posses experience and knowledge (expert systems) to enable him/or her in identifying and type of disease, making the right decision and choosing the right treatment like the disease.

The methods that expert system uses differ from one system to another because that depends on the user’s primary knowledge of the case. Decision making depends mainly on the way of receiving that knowledge 30.
The major production constraints indicated by Tewodros Bezu 31 were water shortage or erratic rainfall (79%) followed by pest (75.7%) problems. Lack of knowledge and recommended production practices (nutrition, pruning, pest management etc.) and post-harvest losses were also noted as major problems of the mango growers. It is in agreement with CSA 4 report that stated mango production in Ethiopia fluctuates because of occurrence of diseases and lack of proper management 4.
Agriculture requires information and application of knowledge from different interacting fields of science and engineering to make a suitable decision-making that in turn depends on interplay of these data and knowledge. This needs agricultural specializations and technical awareness in farmer or a human expert to help the farmers in decision making. Existence of agricultural specialization and full awareness with technological progress in a farmer is a very rare thing in our country 32. Human experts are not always available, may not be accessible to every famer or if available consultation may be very expensive. The other complications are that the decisions in agricultural practice depend on large number of factors. Thus even for a human experts it becomes awkward to take all factors into consideration while making a decision. All such problems have resulted in the development and evolution of the concept of expert system 32.

The use of information technologies improved the knowledge base and increased the capacity to control the production practices which in turn reduces the thereat and uncertainty, improved the efficiency of decision making and better recognized the variations in divers influencing features thus depicting enhanced management policy for the farm 33. In addition, it is possible to store much of the information that an expert needs to make decisions and can make them on hand for others; therefore the notion knowledge based agriculture has an adequate prospective to improve the agricultural production 30.

The purpose of human to do cultivation is to meet the needs of growing food along with the increase of population. In addition the plant also serves as a provider of oxygen to the human respiratory system as well as the aesthetic and the beauty that can be enjoyed by humans.

Therefore, research on plant cultivation continues to be done to get a high yielding plant that is superior, responsive to fertilization and resistance to pests and plant diseases. Studies on the pests control and diseases of plants grow rapidly along with grower efforts to get optimal results from its cultivated plants. Pest and disease attack and destroy crop cultivation efforts and result in reduced quality and quantity of the results obtained 34.
Problems of pests and plant diseases are the main obstacles in increasing agricultural production. An estimated one-third of the world’s agricultural production has been marred by more than 20,000 species of destructive organisms including pests and plant diseases 34.

Damage occurs, both on the field during the cultivation process and warehouse storage. These conditions will significantly affect the income of farmers and the world’s food supply. Destructive organisms cover all forms of life that can destroy plants and classified into 3 groups. The first group is the pest, i.e. animal or nuisance animals and destroying plants such as insects, mollusks and mammals. The second category is a disease caused by micro bodies such as fungi, bacteria and viruses. The third is the weed plants that are not expected its presence on an agricultural area 34. Pests and plant diseases are still a complicated issue for owners of the plants, especially for those who do not have the basic knowledge of crop cultivation. The problem becomes more complex due to many types of pests and plant diseases. To differentiate the cause of damage to crops, long enough experience are needed so there is no error in concluding the cause in order to take the right decision in an effort to control 34.
On the other hand, a number of difficulties have been encountered in developing countries like Ethiopia. First, in agriculture decision making, an agronomist expert cannot make a diagnosis with high accuracy due to lack of modern equipment caused by restricted financial resources.

Second, there are not sufficient good agronomist expert to serve the whole population or to cover the whole area of agronomy area. Third, in the country, only traditional treatment and techniques are also employed which are based on experience which is often not documented for the next generation of agronomy expert or farmers.

There are several major application areas of expert system such as agriculture, education, environment and medicine. These four applications are widely used among the practitioners. The components and application of expert system for agriculture is same as that of other three applications. The experience and knowledge of a human expert is captured in the form of IF-THEN rules and facts which are used to solve problems by answering questions typed at a keyboard attached to a computer on such diversified topics, for example, in pest control, the need to spray, selection of a chemical to spray, mixing and application, optimal machinery management practices, weather damage recovery such as freeze, frost or drought, etc. Now-a-days expert system in agriculture is employed more for diagnosis and management of economically significant pest problems like diseases and insects of crop plants 35.
Now-a-days, expert system is widely used in agriculture exclusively for diagnosing and managing pests. These pest problems are mainly dependent upon human experts for their diagnosis and getting recovery. The involved human experts are very scarce, inconsistent in their day-to-day decisions, unable to comprehend large amounts of data quickly, unable to retain large amounts of data in memory, subject to deliberate or inadvertent bias in their actions and can deliberately avoid decision responsibilities. Human experts are not always available whereas the computer based expert system can be used anywhere, any time. Expert system offers an environment where the good capabilities of humans and the power of computers can be incorporated to overcome many of the limitations. Expert system increases the probability, frequency and consistency of making good decisions, additive effect of knowledge of many domain experts, facilitates real-time, low-cost expert-level decisions by the non-expert, enhance the utilization of most of the available data and free the mind and time of the human expert to enable him or her to concentrate on more creative activities 35.
Therefore the researcher has been developed knowledge based system in mango fruit in order to diagnose various pests and taking management decisions for the benefit of farmers and experts.
Agriculture and plantation is an important and interesting research area everywhere in the world and Ethiopia is no exception. Nowadays available land area for a plantation is becoming scarce. This scarce resource is frequently wasted through our bad practices and improper management. Cultivation is a more economical but complex process. Identifying, diagnosis and treating the mango diseases for the maximum yield production involves a sequence of tasks. These tasks and the whole process need a lot of expert knowledge and experience. But unfortunately, people having this type of knowledge are very limited. Their assistance is not available when the person who is going to cultivate needs it.

It is therefore the purpose of this study is to explore appropriate rule based approaches for developing and implementing knowledge based system for mango diseases diagnosis and treatment.
To this end, this study will attempt to explore and answer the following research questions:
What type of knowledge is required to design a knowledge base system which can assist experts in diagnosis and treatment of Mango diseases?
What suitable domain knowledge exists in an explicit and tacit form for diagnosis and treatment of Mango diseases?
How to design KBS for Mango disease to advice agronomy experts?
What are the appropriate trends or techniques taken by experts to diagnosis mango disease?
How the qualities of Mango disease diagnosis and treatment processes improved using knowledge based system?
How to acquire, model, represent, and implement KBS prototype for diagnosis and treatment of Mango diseases?
How to evaluate the performance of KBS prototype developed for mango diseases diagnosis?
1.3. OBJECTIVE OF THE STUDY1.3.1. GENERAL OBJECTIVEThe main objective of this study is to develop a knowledge based system for mango diseases diagnosis and treatment using rule based reasoning approach.

1.3.2 SPECIFIC OBJECTIVESTo review related literatures on concept of knowledge based system and available algorithms and techniques that give deep understanding to conduct this research work.
To acquire the necessary tacit and explicit knowledge required for developing knowledge base system
To model and represent knowledge acquired from domain experts and codified sources.
To build prototype knowledge based system for mango diseases diagnosis and treatment.

To evaluate the performance of the prototype knowledge based system.
SCOPE OF THE STUDYThe scope of this study was developing prototype knowledge base system and evaluating its application for mango diseases diagnosis and treatment for agronomy experts and farmers found in Ethiopia. There are a number of different approaches for designing knowledge based system but this system only focuses on rule based approach. The focus area of this study was Ambo Plant Protection Research Center for the purpose of data collection. This study is limited to diagnosis and treat related to diseases and providing possible suggestions for symptoms for decision making in mango diseases diagnosis. There are different problems related to fruit crop production but including all diseases diagnosis and treatment issues influence the effectiveness of fruit crop production in Ethiopia. Due to this reason this study focused on Mango diseases.

The task involved in conducting this work includes literature review, problem identification, knowledge acquisition, modeling, representation and implementation or encoding. The prototype is consists of knowledge base, inference engine, user interface, explanation facility and rule based reasoning mechanism. Even though the prototype includes all these components this system has limitation in automatic updating of the knowledge base by the user when the new factors are introduced, that is due to time limitation the learning component of the knowledge base is not developed in this study.

Generally, the study is intended to develop rule based prototype system that diagnosis mango diseases and giving advisory services or treatment primarily for domain experts and then for any interested party capable of reading English language.

SIGNIFICANCE OF THE STUDYThe result of this thesis work is expected to contribute a lot to the development of knowledge based advisory expert system for mango diseases diagnosis and treatment and motivate further researches to be conducted in the area of agricultural expert system. Furthermore, it can also help to initiate advisory expert system researches in Ethiopian. The system that researcher has proposed can help farmers in critical times where access to an agricultural expert is not forthcoming due to the unavailability of agriculture extension worker in the area. The system is especially useful in the country and the rural areas where the ratio of extension workers to the farmers is a small number and where the access to such experts is not feasible.

The immediate beneficiaries of the study are primary agriculture workers and agriculture professionals or agronomist. Particularly, the prototype will have great significance to teach primary agriculture extension workers, general agronomy experts in order to have well understanding about mango diseases. As a result, those agriculture workers can use the system in diagnosing mango diseases on primary agriculture sectors where highly qualified mental professionals are unavailable. The developed prototype knowledge based system is used to give advising services for diagnosing mango diseases. The prototype knowledge based system is developed using the knowledge of multiple domain experts and documentary sources to be preserved for in case experts soon retire or unavailable. Therefore, it gives better advisory services where highly qualified agronomists are occupied or where they are not found.

Additionally, the prototype can be used for agriculture professionals as a guide. Even though those professionals are highly qualified persons, they may get difficulty of remembering all the critical symptoms and signs of diseases.

Identifying the right diseases and giving diagnosis and treatment is the difficult task in mango diagnoses. Since the prototype is already codified by using appropriate domain knowledge, it solves the problem of forgetting the important issues and concepts of the domain knowledge by remembering the facts and rules already feed.

METHODOLOGY OF THE STUDYIn order to achieve the objectives of the study and address the stated problems successfully, methods suitable for gathering information, knowledge acquisition, knowledge representation, KBS development tools selection and system evaluation are identified. Here under the detail is presented.

1.6.1. RESEARCH DESIGNDipanwita et al. 40 were used experimental research design to develop intelligent medical system for diagnosis of common disease by acquiring tacit and explicit knowledge from domain knowledge expert. The domain knowledge was acquired and then represented. The acquired and represented knowledge was inserted into the knowledge base. Based on the result of evaluation of inserted knowledge it changed again and again. In addition, during prototype development stages the sequence of the facts and rules were changes again and again until it fitted the best sequence. Moreover, the way to test and evaluate the performance of the prototype system by feeding the cases and records the result to compare it against with the decision made by domain experts in similar settings.
The process of acquiring knowledge from experts and building a knowledge base is called knowledge engineering. The process of developing computational knowledge based systems is called knowledge engineering. This process involves assessing the problem, developing a structure for the knowledge base and implementing actual knowledge into the knowledge base. Knowledge engineering and system engineering methodologies were used to develop the system. To accomplish the knowledge engineering task three main activities were done. These are knowledge acquisition/elicitation, knowledge verification & knowledge modeling and representation.

1.6.2 LITERATURE REVIEWIn order to have deep understanding on the problem of this study, it is vital to review several literatures that have been conducted in the field so far. For this reason, related literature such as books, articles, proceeding papers and related research works done by local and international scholars, and other relevant publications have been reviewed in detail and are consulted so as to understand the domain knowledge, concepts, tools, techniques, principles and methods that are important for developing knowledge-based systems.

1.6.3 KNOWLEDGE ACQUISITIONIn this study explicit and tacit knowledge is acquired from both codified (documented) sources and non-codified (non-documented) sources respectively. Non-codified sources of knowledge are acquired from agronomy experts (agronomists) who work in the Ambo Plant Protection Research Center by using interview and critique knowledge elicitation methods to filter the acquired knowledge. Similarly, codified sources of knowledge such as agricultural books, training manuals and journal agriculture articles are acquired by using document analysis technique.

Interview (both structured and unstructured) is used to collect tacit knowledge from the domain experts. In addition, critiquing (analyzing) elicitation methods are used to purify the collected knowledge. The acquired knowledge is refined with the consultation of the experts. Moreover, secondary sources of knowledge are gathered from the Internet, fruit crop diseases diagnosis guidelines, research papers and articles by using document analysis technique.

1.6.4. KNOWLEDGE MODELING METHODKnowledge modeling is a cross disciplinary approach to capture and model knowledge. Knowledge models view the knowledge based system using diagram and other structured representations such as trees, maps, and KBS construction methods typically provide tools for knowledge analysis in the form of conceptual models of knowledge. So, knowledge model provides an implementation independent specification of knowledge in an application domain 39. In this study the acquired knowledge was modeled using decision tree and represented using production rule which is one of the knowledge representation techniques. Decision trees models by constructing a tree based on training instances with leaves having class labels is used. These are easy to interpret (can be represented as if–then-else rules). Production rules are easy for a human expert to read, understand and maintain. Production rules contain simple syntax that is flexible and easy to understand and are reasonably efficient in diagnosing problems of the form: IF (condition), THEN (conclusion). The reasons for using productions rules for this study are because of its ease of encapsulation of knowledge and ease of extensions to the knowledge base in the future 36. The prototype system uses backward chaining also called goal-driven chaining which begins with possible solutions or goals and tries to gather information that verifies the solution. 36
1.6.5. KNOWLEDGE REPRESENTATION METHODIn knowledge based system there are many reasoning mechanisms; among that the most commonly used are rule based approach, case based approach or the combination of the two. Case based approaches are designed to work in the way that the basic idea of similar problems having similar solutions 37. It is a rule based System that solves problems by remembering past situations and reusing its solution and lesson learned from it. Case based approach represents situations or domain knowledge in the form of cases and it uses case based reasoning techniques to solve new problems or to handle new situations 38. Rule based reasoning, on the other hand reason from domain knowledge represented in a set of rules. The basic format of a rule is
IF <condition> THEN <conclusion>, where <condition> represents premises and <conclusion> represent associated action for the given premises 39.
In this study after the knowledge is acquired it is represented using rule based knowledge representation method. For this research the knowledge representation method, rule based is chosen because it clearly demonstrates the domain knowledge. In a rule based system much of the knowledge is represented as a rule that is as conditional sentences relating statements of facts with one another. Most factors and symptoms of diseases that affect mango crop growth are predefined sets of rules. There are already defined sets of criteria that enable to diagnosis the diseases of mango. As a result rule based representation method is more appropriate to represent and demonstrate the real domain knowledge in mango diseases diagnosis and treatment. Additionally, rule based systems are the most commonly used knowledge representation language in agriculture.

1.6.6. KNOWLEDGE BASED SYSTEM DEVELOPMENT TOOLSTo develop the knowledge-based system, Prolog programming language is used. Specifically, SWI-Prolog editor has been chosen for this study. SWI-Prolog editor has debugging tool and flexible help system. Moreover, the code is readable and easier to update and maintain. It offers backward reasoning capability, which is found to be suitable for diagnostic and treatment problems. The reason of the selection of this programming language is the features and abilities of the language that incorporate it. Prolog is a declarative language (we specify what problem we want to solve rather than how to solve it) and has the capacity to describe the real world.

In addition, it is easy to learn the design tools; it has rule based programming and built in pattern matching features; it has comprehensive help system on each feature and it is readable code that will also make updating of the system a relatively manageable task.

SWI Prolog is the most inclusive and widely used Prolog development environment.

It has flexible and fast interface. In addition, it is portable to many platforms, including almost all UNIX/Linux platforms and Windows Vista. Additionally, it is non-commercial version of Prolog. So, it can be easily accessed. Therefore, the prototype knowledge based system is developed in SWI Prolog.

1.6.7. EVALUATION TECHNIQUESThe evaluation of knowledge based system is an important aspect of knowledge based system development that is required to prove whether a system fulfills its original objective 64. The evaluation is carried out by considering knowledge representation scheme such as adequacy, the right answers that the system come up with, knowledge consistency, its easiness to interact with the users and the facilities and capabilities do users need 63. In this study, the performance of knowledge based system is evaluated and validated by assessing user acceptance through visual interaction. Similarly users? acceptance is assessed and analyzed through questionnaire after users are exposed to interact with the system.

The developed prototype rule based system is tested and evaluated to ensure the performance of the system in meeting towards established objectives. The evaluation process is more concerned with system user acceptance and validations of the prototype. User acceptance efforts are concerned with issues impacting how well the system addresses the needs of the user whereas validation efforts determine if the system performs the intended task satisfactorily.CHAPTER TWOLITERATURE REVIEWThis chapter tries to discuss review of literatures on Knowledge based system for mango disease diagnosis. It deeply elaborates knowledge based systems concepts, architecture, knowledge acquisition and representation methods. It also discusses knowledge based systems development tools and the application of knowledge based system and its challenges.

2.1. INTRODUCTIONAgriculture is the mainstay of the Ethiopian economy and a major source of employment for about 80% of the population. Ethiopia has the soils and climate required for the production of a variety of food crops. Ethiopia has also more than 80 million hectares of arable land out of which 16% is under cultivation. Over all irrigation development potential is estimated at 3.7 million hectares of land while only 5-6% of this area is currently utilized. Irrigable large scale farms such as in the Rift Valley have big potential for the expansion of cash crops such as sugar, oil seeds and horticulture(Agriculture: investment Opportunities).

Biruk Ambachew 42 stated that agriculture is the corner stone of the development policy of the Government of Ethiopia. The country’s economic development will depend, in large part on sustainable improvements in agriculture. Agriculture remains by far the most important sector in the Ethiopian economy for the following reasons 41:
It directly supports about 85% of the population in terms of employment and livelihood;
It contributes about 50% of the country’s gross domestic product (GDP);
It generates about 90% of the export earnings.
Agriculture is also the major source of food for the population and hence the prime contributing sector to food security.
As per the information obtained from the document in the five year development strategic plan for sustainable development to end poverty (GTP), the Ethiopian government has been giving significant focus and attention for agriculture and rural development. This is accomplished by offering over 8 million acres of land to commercial farming investors. Expansion will open up opportunities for advanced farming technology, high value crops, progressive irrigation techniques, improved seeds, increased fertilizer use, and strategies to yield multiple harvests each year 41.

Furthermore, the productivity of the sub-sector is affected by poor management system and shortage of skilled experts who provide advice for farmers at Woreda level. Despite the importance of agriculture in its economy, Ethiopia has been a food deficit country since the early 1970s. A closer look at the performance of the Ethiopian agriculture reveals that over the last three decades it has been unable to produce sufficient quantity to feed the country’s rapidly growing human population 41, 42.

Even though 85 percent of the country’s population lives in the rural areas, the performance of the agricultural sector in Ethiopia has remained weak and it is heavily influenced by weather condition 41, 43.

To date, a fair amount of knowledge exists on pest management of several crop pests in Ethiopia. But there is still a problem of improper pest management practice by Ethiopian farmers 44.

2.2. HISTORY OF MANGO AND FRUIT CROP IN ETHIOPIA Mango (Mangifera indica) is a fleshy stone fruit belonging to the panes Mangifera, consisting of numerous tropical fruiting trees in the flowering plant family Anacardiaceae. The mango is native to the south Asia from where it was distributed worldwide to become one of the most cultivated fruit in the tropics. Mango (Mangifera indica) is produce in most frost free tropical and sub tropical climates, more than 85 countries in the world cultivate mango. The total production area of mango in the world is around 3.69 million hectares. The total amount of mango production in the world is around 35 million tons by the year 2009 45.

Mango (Mangifera indica L.) is an ever green fruit crop native to Southern Asia, especially Eastern India, Burma and the Andaman Islands. It is grown in more than 85 countries of the world with total area coverage and annual production of 3.69 million hectares and 35 million tons, respectively 46. Currently, mango is one of the most widely cultivated and traded tropical and subtropical fruit crops in the world. Therefore, it is usually named as king of tropical fruit crops.

The amount of mango production in Africa during 2009 is 13.6 million tones. Nigeria is the leading country followed by Egypt 46. In Ethiopia mango produced mainly in west and east of Oromia, SNNPR, Benshangul and Amhara 47. Mango production in Ethiopia is in fluctuated conditions, because of occurrence of diseases, lack of proper management and also weather conditions 45.

Ethiopia has large tract of suitable land for mango production. It is mainly produced in Oromia, SNNPR, Benishangul Gumuz, Amhara, Harari and Gambela regions. Mango ranked 2nd and 3rd in total production and area coverage among fruit crops grown in Ethiopia, respectively. From 2003/4 to 2013/14, both its area coverage and total production increased by 208.4% and 247%, respectively. Despite this improvement in the last one decade, its productivity is very low, 7 tons/ha and Ethiopia produced only 72,187 tons fresh mango in 2013/14 48. Therefore, its potential has not yet been fully utilized and markets in different parts of the country are not sufficiently supplied with the demanded quantity and quality of mango.

EDUCATION STATUS OF MANGO PRODUCERS
The result Y. Dessalegn 48 study indicated that the educational status of mango growers 54.3% were illiterate, and 31.4% and 14.3% attended elementary and secondary education, respectively. Similarly, 80% of mango growers in Bati district of Oromia zone did not attended formal education 45. These results indicated that most mango growers in the study area and other parts of Ethiopia did not attended formal education. Hence, they are not benefitting from mango production knowledge and technologies promoted through written materials 48. Therefore, they need practical training, experience sharing visit and on site demonstration to improve their knowledge and skill on different mango production practices 48.

INSECT PEST AND DISEASE MANAGEMENT PRACTICESResults of field observation by Yigzaw Dessalegn 48 indicated that anthracnose and powdery mildew as the two most common and wide spread fungal disease of mango in the study area. Sooty mold and parasitic algae also observed in some fields. The prevalence of powdery mildew increased since farmers intercrop mango with most powdery mildew susceptible crop, chat and since most mango producers did not prune their mango trees. Mango growers as well as most development agents were not able to identify different diseases using their symptoms. Therefore, they have disease identification knowledge gap to apply effective prevention & control measures 48.

CONSTRAINTS AND OPPORTUNITIES IN FRUIT CROP AGRICULTUREInadequate knowledge & skill, disease & insect pest problem, low market price, land and irrigation water shortage, and inadequate grafted seedling supply were identified as the top six important mango production constraints of smallholder mango growers. Lack of effective pesticide and Lack of access to equipments are other constraints 48.

48 Yigzaw Dessalegn stated that farmer’s awareness about the importance of different agronomic and pest management practices is very low. Therefore, theoretical and practical training on canopy management, proper spacing, time, rate and method of fertilizer application, disease and insect pest identification and management methods, and irrigation methods and interval should be provided to mango growers and development agents.

48 Indicated the existing of technological gaps for mango production in the study area and also Ethiopia. Therefore, farmers need to be trained and improved mango production technologies should have to be introduced in order to improve the quality and boost the productivity of mango in Ethiopia.

The adoption of improved mango production practices by famers largely depends on the availability of knowledgeable extension workers in the area. Even though agriculture is the main stay of Ethiopian economy, level of agricultural productivity in general and crop productivity in particular is very low. Given capital constraint in the country, it is difficult to adopt new technology to enhance productivity.

Seid Hussen 45 study indicated 85% of the respondents/farmers replied that they did not control diseases and most of the producer control birds during the fruit matured. Other pests are present on mango orchards but the producers not aware for control those pests and diseases. Some of the respondents/farmers replied that they report the problem for agricultural office and measures taken to control the pest and diseases.

Irrigation water scarcity, pest and disease, limited technologies are the main factors that reduce mango production.
For most developing countries, enhancing the total production and productivity is not an option rather it is a must and the first priority in their policies. Production and productivity can be basically boosted using two ways. The first method is through increased use of inputs and/or improvement in technology given some level of input. The other option of improving productivity is to enhance the efficiency of producers or firms, given fixed level of inputs and technology.
Seid Hussen 45 concluded that farmer awareness about spacing of orchards, pruning, fertilizer application, access of new varieties and pest and disease control is very low. In order to increase the production of mango, many actions have to be taken. Training about agronomic practices such as proper spacing, time of pruning, methods and time of fertilizer application, identification of pest and disease and control mechanism, methods and time of harvesting, kind of packing materials used, are vital to increase the productivity of mango.

2.3.MAJOR MANGO DISEASES IN ETHIOPIAThe mango crop is among the crops cultivated in Ethiopia and in southwest Ethiopia, while in
South-west Ethiopia, mango is the first fruit crop grown (Edossa et al., 2006). The area of mango
Production in the different regions is about 3789.47 ha in Oromia, 3375.89 ha in SNNPR, 652.56
ha in Benishangul Gumz, 246.85 ha in Amahara, 180.41 ha in Gambella, 44.5 ha in Dire Dawa,
33.52 ha in Somali, 118.20 in Tigray and 367.24 ha in Harari. The total area allotted for mango is about 8808.64 ha and the country annual production of mango from all mango grower regions is about 697,507 quintals 11.

Mango trees in most parts of Ethiopia are developed from seedlings and are inferior in productivity and in fruit quality. To alleviate these problems improved varieties named Kent, Keit and Tommy Atkins were introduced from Israel in 1983 and are being commercially produced by the Upper Awash Agro Industry Enterprise (UAAIE) 12. These varieties are widely distributed to different parts of Ethiopia by UAAIE. In 2001/2002, a private farm called Green Focus Ethiopia Limited introduced a new mango cultivar called Alphanso from India and planted in its farm at Loko in Guto Gida district of East Wollega zone of Oromia, western Ethiopia. Many farmers are growing mango trees used as a source of income and for shading purpose 12 15.

After all the risks considered and assumptions made, 15 described failure of mango production was envisaged due to the infestation of fruit, either by insect /pest and diseases. This risk was escaped at this stage for lack of adequate information on the pest at that time.

Tesfaye Hailu 15 described as Mango tree is attacked by different insects and diseases such as , Anthracnose, Bacterial Black spot, Fruit fly, mango gall flies, Mango leaf coating, Mites, Mango seed weevil, Mealy bug, Powdery mildew, Scale, Spider mites, Mango tip borer, Stem-end rot, Termite, Thrips and White flies.

Mango suffers from several diseases at all stages of its life. All the parts of the plant, namely, trunk, branch, twig, leaf, petiole, flower and fruit are attacked by a number of pathogens including fungi, bacteria and algae. They cause several kinds of rot, die back, anthracnose, malformation, scab, necrosis, blotch, spots, mildew, etc 49.

ANTHRACNOSEAnthracnose (Colletotrichum gloeosporioïdes) is the most widespread fungal disease of the mango tree, bearing in mind that it also affects many tropical fruit trees (avocado, papaya, citruses, etc.). It attacks the flowers, leaves, twigs and fruits 95. The main symptom is the appearance of brown to black spots on the leaves and/or twigs, which join up as they expand, forming circular necrotic black spots. They eventually result in the leaves and/or twigs completely drying up. On the inflorescences, it is expressed as miniscule brown or black dots which as they expand cause the death of the flower, or even the entire panicle 50.
“The disease appears at various stages of development of the fruit, in the form of black dots generally on the upper part, fairly close to the stalk. As they expand, these dots become spots which join up, and can thereby cover a large area of the fruit 94. They can also take the form of a “tear flow”, generated by run-off from contaminated branches or leaves above the fruit. The spores can penetrate the lenticels, where they find conditions favourable for their development. In this case, even post-harvest washing of the fruits does not prevent the attacks. Moisture is a factor boosting parasite pressure, especially upon the first rainfall in regions with an alternating dry/wet season 49 50.

Destruction by incineration of the affected parts is effective, but a lengthy and recurrent treatment. Synthetic organic fungicides are used to contain the disease. On fruits, copper-based solutions may be effective, as well as other synthetic products, but in this case the products used will need to be authorised, and the residual contents will need to comply with regulations in force” 50.
Anthracnose is usually more serious in years when rain and heavy dews are more frequent during the critical periods of infection from the onset of flowering until fruit are about half size 49. Severe infection destroys the entire inflorescence resulting in no setting of fruits. Young infected fruits develop black spots, shrivel and drop off 49 45. Fruits infected at mature stage carry the fungus into storage and cause considerable loss during storage, transit and marketing.

Figure SEQ Figure * ARABIC 1 Anthracnose infections start as small, angular, brown to black spots in leaves and fruitsThe largest problem of mango is anthracnose because it attacks all parts of the tree and is probably most damaging to the flower panicles 49. On maturing fruit, the fungus causes irregular black spots that may be sunken slightly and show surface cracks. A grouping of spots forms a large, damaged area. Tear streaking is common, resulting from fungal spores that wash down the fruit from infected twigs or flower stalks. The disease can be controlled with fungicides.

Get some ‘Kocide’ (brand name for copper sulfate fungicide) from us and spray the trees thoroughly in humid/warm conditions twice a week!
Follow the directions on the bag. Add a teaspoonful of spreader sticker or liquid dish washing detergent in each sprayer load to make it stick.

Mango Powdery Mildew Powdery mildew is caused by the fungus Oidium mangiferae 51. Although a some what
Sporadic disease, it can cause severe crop loss due to flower and panicle infection and subsequent failure of fruit set 51 96.

The diagnostic key in the identification of this disease is the appearance of a whitish, powdery growth of the fungus on panicles and young fruit. Young infected fruit turn brown and fall. The white growth can also be seen on the undersurface of young infected leaves. Severe infection of young leaves results in premature leaf drop. On mature leaves, the spots turn purplish brown, as the white fungal mass eventually disappears 49 51. Mango powdery mildew is an easily recognizable problem; the symptoms are very apparent and are diagnostic. However, it is not easily controlled with cultural practices alone. If susceptible mango cultivars are grown in mildew-prone areas, growers should expect the disease to recur yearly or seasonally. To achieve good yields, such growers must act with control measures during flowering, before it is too late to prevent the loss of the current season’s crop 96.

Powdery mildew tends to occur yearly in areas where this disease predominates and must be controlled in order to obtain acceptable fruit yields. Powdery mildew is more common in lower-rainfall areas than in higher-rainfall areas 49 96.

Symptoms on panicles
Infected panicles (flowers, flower stalks, and young fruits) become coated with the whitish powdery growth of the pathogen (photo, below). Infected flowers and fruits eventually turn brown and dry. The dead flowers can easily crumble in one’s hand. Infection often causes flowers and small fruits to abort and fall off 96.

Figure SEQ Figure * ARABIC 2 Mango panicles with powdery mildew
Figure SEQ Figure * ARABIC 3 a whitish-gray haze covers a normally reddish mango panicle (from 96).This haze is the diagnostic symptom of mango powdery mildew, caused by Oidium mangiferae. This fungus can infect and colonize all parts of the panicle, including flowers and young fruits. Infected young fruits may have a purplish haze 96. Here, the disease is so advanced that it may be too late for any control measures to have an effect upon poor fruit set and yield.

Figure SEQ Figure * ARABIC 4 Symptoms of mango powdery mildew and mango anthracnose compared.Left, powdery mildew caused by Oidium mangiferae: panicles have a whitish-gray haze; killed flowers turn brown and gray. Right, anthracnose caused by Colletotrichum gloeosporiodes: black, pin-prick spots on flowers and panicles; killed flowers turn inky black 94 49 96.

Fruits that become infected after they have set have purple-brown blotchy lesions that crack and form corky tissue as the fruitlet enlarges. The full-bloom stage is the most susceptible to infection 49.

Symptoms on leaves
On some cultivars, new flushes of growth and younger leaves are highly susceptible and may curl up and become distorted 94. Older leaves are more resistant to infection. Grayish, necrotic lesions or large, irregularly shaped spots may form on leaves (photo below, center). On very susceptible cultivars, the youngest leaves may become completely covered with fungal spores and mycelium, and eventually die (photo below, left). On some cultivars, the whitish residue of the fungus tends to appear on the lower leaf surface, along the leaf midrib (photo below, right) 96.

Figure SEQ Figure * ARABIC 5 Characteristic symptoms of mango powdery mildew on mango leavesPathogen dissemination
Conidia of O. mangiferae are wind-disseminated from other mango trees or from within an infected tree’s canopy. The environmental conditions for spread of powdery mildew occur across a broad daily range of temperature (50–88°F, 10–31°C) and relative humidity (60–90%) 95.

Figure SEQ Figure * ARABIC 6 Late- state powdery mildew infection on underside of mango leaf 95.Powdery mildew occurs in the spring and is particularly destructive in years when the weather is cool and dry. Control is fungicide treatment 95.
Alga Spot (Red Rust, Green Scurf)A parasitic alga, Cephaleuros virescens, incites this relatively minor disease of mango. Leaf spots start as circular green-gray areas that eventually turn rust red as the alga produces a profusion of rust-colored microscopic “spores” on the leaf surface (Figure 7).

Figure SEQ Figure * ARABIC 7 Alga spot in mango leaf.The alga is at the stage where it is producing great masses of red “spores” on the leaf surface.

Infection of stem tissue can also occur and is much more serious than leaf infection. Cankers develop in the bark and stem-thickening can take place at infection sites 94 95. Rust-red “spore” masses will also develop on infected stems. Severely diseased branches may have to be pruned from the tree 49 50. Alga spot only becomes a serious problem when growers are overly dependent on organic fungicides for general foliar disease control. It normally is not a problem where copper fungicides are used periodically 50 95.

Stem-end rots are fungal infestations which affect the twigs and leaves. They are transmitted to the fruit by attacking the stalk area in the form of greyish-brown spots. Very quickly reaching the lower layers of the skin, they cause rapid alteration of the flesh. The high volatility of the spores and their varied origin (Dothiorella sp., Lasiodiplodia theobromae, Phomopsis mangiferae, Pestalotiopsis microspora, etc.) facilitate dissemination. High post-harvest storage temperatures can promote their development 50.
A post-harvest heat treatment can limit rot. Some synthetic products can also be used, such as thiabendazole, provided that the persistence of the products is taken into account, in order to comply with regulations in force 50.

Bacteriosis is widespread in mango cultivation areas. It is caused by a bacterium of the species Xanthomonas citri which damages the plant and fruit by developing dark angular and oily spots, accompanied by yellowish rings 94. They grow along the leaf veins until completely drying them out. The bacterium forms cankers and purulent wounds on the twigs and fruits, and can kill the plant. Isolated individuals must be destroyed, in order to limit contagion 49. Copper-based products seem to impede its development 50.

Phytophthora canker affects the mango tree trunks with dark longitudinal wounds in the bark, which conceal brown necrosis of the underlying tissues, bleeding gum. It spreads over the trunk, disrupting the tree’s nutrient supply 49 50.

Scab, caused by the fungus Elsinoe mangifera, attacks leaves, flowers, young shoots and fruits. Brown, black or greyish spots appear on the leaves. At a more advanced stage, the centre of the spot gives way to leaf perforation. Greyish pustules form on the trunk bark. Spots similar to those on the leaves develop on the fruits. They can become corky and cracking in the centre, promoting spore penetration 50. Copper-based solutions help combat this disease. Soft nose is not a mango tree disease, but a physiological disorder of the fruit frequently observed in certain production regions. It is manifested by alteration of the flesh in the apical zone, which exhibits an over-mature appearance, whereas the rest of the fruit is still green. At an advanced stage, the flesh has a spongy brownish appearance 50.

DIEBACKThe disease on the tree may be noticed at any time of the year but it is most conspicuous during Oct.-Nov. The disease is characterized by drying of twigs and branches followed by complete defoliation, which gives the tree an appearance of scorching by fire 49 95. Tip die back disease occurs on the branches/ trunk of infested trees that start drying slowly at first and suddenly branches become completely dried / killed resulting gummy substance oozes out or remains hanging on the tree .The dark area advances and young green twigs start withering first at the base and then extending outwards along the veins of leaf edges 49.

The affected leaf turns brown and its margins roll upwards. At this stage, the twig or branch dies, shrivels and falls. This may be accompanied by exudation of gum. In old branches, brown streaking of vascular tissue is seen on splitting it longitudinally. The areas of cambium and phloem show brown discolorations and yellow gum like substance is found in some of the cells 49 50 94.

BACTERIAL CANKERCanker disease of mango, caused by a bacterium (Xanthomonas campestris pv. mangiferaeindicae). Bacterial leaf spot is noticed on the leaves as angular water soaked spots or lesions, surrounded by clear holes. These become necrotic and dark brown and viscous bacterial exudates deposit on these necrotic portions that become corky and hard after drying 49 94.

Sometimes, longitudinal cracks also develop on the petioles. Some of the similar signs are present in suffering mango orchards. Cankerous lesions appear on petioles, twigs and young fruits. The water soaked lesions also develop on fruits which later turn dark brown to black. They often burst open, releasing highly contagious gummy ooze containg bacterial cells. The fresh lesions on branches and twigs are water soaked which later become raised and dark brown in color with longitudinal cracks but without any ooze 49.

ROOT ROTRoot rot is also prevalent in almost all orchards; manifest itself as withering and drying of the plant from top to bottom and whole plant die up. Initially rootlets are affected and are rotten, later on the smaller, tertiary roots and ultimately the bigger, secondary and primary- main roots are infected which result in gradual decline of the plant and the plant die 49 .

2.4. ECONOMIC IMPORTANCE OF FRUIT CROP IN ETHIOPIA Ethiopia’s wide range of agro climatic conditions and soil types make it suitable for the production of diverse verities of fruits including temperate, tropical and subtropical fruits. Pineapples, passion fruits, bananas, avocados, citrus fruits, mangoes, mandarin, papayas, guava, grapes, asparagus etc., are produced in Ethiopia. Around 47 thousand hectare of land is under fruit production in Ethiopia. Banana contributed about 60.6 % of fruit areas followed by mango that contributed about 12.61 % of the area 52. Total fruit production in Ethiopia is about 500 thousand tones. Fruits have significant importance with a potential for domestic and export markets and industrial processing in Ethiopia. The main fruits produced and exported are banana, citrus fruits, mango, avocado, papaya and grape fruits 52.
Tropical and sub-tropical fruit can make a significant direct contribution to the subsistence of small-scale farmers by providing locally generate nutritious food that is often available when other agricultural crops have not yet been harvested. Fruit are a versatile product that, depending on need, can be consumed within the household or sold 46. Marketing fresh and processed fruit products generates income which can act as an economic buffer and seasonal safety net for poor farm households. Diversification into fruit production can generate employment and enable small-scale farmers to embark on a range of production, processing and marketing activities to complement existing income-generating activities 46.

Fruits in different forms such as whole fruit, fruit juice, fruit pulp, and fruit concentrate have a vital role for health. They are dietary sources of nutrients, micronutrients and vitamins for human and are thus vital for health and well being. Well balanced diet rich in fruits are especially valuable for their ability to prevent deficiency diseases and are also reported to reduce the risk of several diseases 52. For many countries fruit products have become valuable, making a substantial contribution to the economy as well as to the health of country population.
Fruits contain vitamin C, foliate and dietary fibers and other bioactive components such as carotenoids and flovonoids which are suggested to be responsible for the prevention of degenerative diseases. Studies have shown that if fruits are consumed daily in sufficient amount, it could help to prevent major diseases such as cardio vascular and certain cancers 52. According to 53 WHO report, low fruit and vegetable intake is estimated to cause about 31 % of heart disease and 11 % of stroke worldwide and around 2.7 million lives could potentially be saved each year if fruits and vegetable consumption was sufficiently increased. Many farmers are growing mango trees used as a source of income and for shading purpose 12 Mango is one of the main fruit crop produced and exported in Ethiopia 46.

2.5. AN OVERVIEW OF ARTIFICIAL INTELLIGENCE AND KBSArtificial intelligence is the study of creating machines that can perform an action which requires human intelligence. It deals with the principles and techniques that enable computers to tackle problems that have previously been thought possible only for humans to solve 54 64. It is sub field of computer science, concerned with symbolic reasoning and problem solving. The main concern of artificial intelligence is to enable computers to behave like human beings and imitate the reasoning power of humans to do tasks that necessitate human being’s intelligence by making machines smarter, which is a primary goal, understand what intelligence is all about make machines more intelligent and useful 54.
2.5.1. Overview
Since the invention of computers or machines, their capability to perform various tasks went on growing exponentially. Humans have developed the power of computer systems in terms of their diverse working domains, their increasing speed, and reducing size with respect to time. A branch of Computer Science named AI pursues creating the computers or machines as intelligent as human beings 55. The ability of the intelligent systems to capture and redistribute expertise has significant implications on development of a nation, commodity or population. Such systems allow documentation of one or more expert knowledge and utilize the knowledge for problem solving in cost effective way 56. KBS is one of the major family members of the AI group. With availability of advanced computing facilities and other resources, attention is now turning to more and more demanding tasks, which might require intelligence 56.
Since the researcher is working on developing and designing knowledge based system to support the diagnosis and treatment of mango disease, in this chapter the researcher attempts to give basic understanding of mango diseases and artificial intelligence particularly knowledge based system.
So, in the very beginning of this chapter the researcher briefly reviewed knowledge based system by stating their development phases, architectures, advantages and disadvantages, development tools, application areas as well as their related works and then the researcher attempts to review what mango diseases are, world food program report, mango diseases in Ethiopia, symptoms of mango disease and its treatment mechanisms. In addition, through this extensive literature review the researcher tried to identify the gap on developing KBS for agriculture and computer troubleshooting.
2.5.2. Artificial Intelligence (AI)
AI refers to the activity of building intelligent systems. The main concern of AI is to enable computers to behave like human beings and imitate the reasoning power of humans to do tasks that necessitate human being’s intelligence by making machines smarter, which is a primary goal, understand what intelligence is all about make machines more intelligent and useful 57. As in 58, AI can be viewed from a variety of perspectives such as from the perspective of intelligence, from the perspective of business and from a programming perspective. From the perspective of intelligence AI is making machines “intelligent” — acting as we would expect people to act. From a business perspective AI is a set of very powerful tools, and methodologies for using those tools to solve business problems. From a programming perspective, AI includes the study of symbolic programming, problem solving, and search.
According to Avneet 59, in the future, intelligent machines will replace or enhance human capabilities in many areas. AI technologies have matured to the point in offering real practical benefits in many of their applications. Major AI areas are Expert Systems (knowledge based system), Natural Language Processing, Speech Understanding, Robotics and Sensory Systems, Computer Vision and Scene Recognition, Intelligent Computer Aided Instruction, Neural Computing. From these AI areas Avneet 59 states that KBS is a rapidly growing technology which is having a huge impact on various fields of life.

2.5.3. Knowledge Based Systems (KBS)
KBS is sophisticated interactive computer programs which use high quality, specialized knowledge in some narrow problem domain to solve complex problems in that domain 43. KBS are a branch of AI, which is a computer program that attempts to replicate the reasoning processes of a human expert and it can make decisions and recommendations and perform tasks based on user input Ejigu 43. It is concerned with the concepts and methods of symbolic inference, or reasoning, by a computer, and how the knowledge used to make those inferences will be represented inside the machine.
According to Saja et al. 56 KBS can act as an expert on demand without wasting time, anytime and anywhere. KBS can save money by leveraging expert, allowing users to function at higher level and promoting consistency. One may consider the KBS as productive tool, having knowledge of more than one expert for long period of time. In fact, a KBS is a computer based system, which uses and generates knowledge from data, information and knowledge. These systems are capable of understanding the information under process and can take decision based on the residing information/knowledge in the system whereas the traditional computer systems do not know or understand the data/information they process.

In the same way, Gabriela 60 defines KBS as it is a program for extending and/or querying a knowledge base. A knowledge base is a collection of knowledge expressed using some formal knowledge representation language. A knowledge base forms part of a KBS”. Or a computer system that is programmed to imitate human problem-solving by means of AI and reference to a database of knowledge on a particular subject.
Similarly, Edward 61 defines KBSs also called Expert Systems or simply Knowledge Systems, are computer programs that use expertise to assist people in performing a wide variety of functions, including diagnosis, planning, scheduling and design. ESs are distinguished from conventional computer programs in two essential ways: Expert systems reason with domain-specific knowledge that is symbolic as well as numerical; and Expert systems use domain-specific methods that are heuristic (i.e., plausible) as well as algorithmic (i.e., certain).
And according to Babar et al. 62 defines KBS is an application program that makes decision or solves problem in particular fields such as Finance, Medicine, Agriculture etc. , by using knowledge and analytical rules defined by Experts in particular fields.
All the above definitions about KBS have similar meaning but in different way of expressions. As summery of the above definitions, KBS is an intelligent computer programs that employee domain expert’s knowledge to solve problems and make decisions on behalf of human experts in a particular domain. So that KBS can act as an expert on demand without wasting time, anytime and anywhere. And the aim of this research is to develop knowledge based system (KBS) that take this advantage.

2.5.4. ADVANTAGES OF KBS
The primary intent of KBS technology is to realize the incorporation of human expertise into computer processes. This incorporation not only helps to preserve the human expertise but also allows humans to be freed from performing the more routine activities that might be associated with interactions with a computer-based system 63. According to Ejigu 43 KBS is more useful in many situations than the traditional computer based information systems. Ejigu 43 highlighted the advantages of KBS such as time saving, quality improvement, Practical knowledge made available, infallible and complete, replication and all day and every day available.

2.5.5 KBS Architecture and its Components
Architecture is a blue print that helps to represent the structure of an object or a system. Architecture of a system helps to describe sets of conventions, rules, and standards that should be incorporated in the corresponding system 64. According Demissie 65 the KBS structure is composed of the following main components as illustrated in figure 3 below:
Figure SEQ Figure * ARABIC 8 Basic Structure of KBS (adopted from 65) i. User interface
The user can interact with the knowledge base system via user interface. User can enter commands, respond to questions, etc. Advanced interfaces make heavy use of pop-menus, natural language, GUI or any other style of interaction 65.
ii. Explanation subsystems
Explanation subsystem is a subsystem that explains the system’s actions. The explanation can range from how the final or intermediate solutions were arrived to justifying the need for additional data 65.

iii. Knowledge engineer
Building an expert system is known as knowledge engineering and its practitioners are called knowledge engineers. The knowledge engineer must make sure that the computer has all the knowledge needed to solve a problem. The knowledge engineer must choose one or more forms in which to represent the required knowledge as symbol patterns in the memory of the computer — that is, he (or she) must choose a knowledge representation 61.
The knowledge engineer must also ensure that the computer can use the knowledge efficiently by selecting from a handful of reasoning methods. The practice of knowledge engineering is described later. We first describe the components of expert systems 61.
iv. Knowledge Base:
The Knowledge-base is created by the knowledge engineer, who conducts a series of interviews with the expert and organizes the knowledge in a form that can be directly used by the system. It is the heart of KBS, which contains the problem solving knowledge of a particular application. This knowledge base stores all relevant information, data, “domain knowledge”, rules of inference, cases and related factual information. It combines the knowledge of multiple human experts and contains the domain-specific knowledge required to solve a particular problem 64.
Apart from storing information about the subject domain, the knowledge–base contains symbolic representation of expert’s knowledge, definitions of domain terms, interconnections of component entities, and cause-effect relationships between these components. The knowledge base is formalized and organized with a technique called knowledge representation. There are several techniques to represent knowledge in the knowledge base. Representing knowledge in form of rules and cases are examples of the techniques 66.
v. Inference Engine
For KBS having a knowledge base alone is not of much use if there are no facilities for navigating through and manipulating the knowledge to deduce something from facts stored in knowledgebase. Therefore, an inference engine in the KBS is a need to solve the actual problems in generating solution from the facts to arrive at some conclusion 66. The inference engine uses the knowledge provided to come to some conclusions and/or give advice about the specific problem. To arrive at conclusions about a problem, the inference engine must search for a solution in an efficient and effective manner.
It is also known as rule interpreter and is the problem-solving component. It allows new inferences to be made from the case specific data and the knowledge in the knowledge base. These new facts represent conclusions about the state of the domain given the observations.
In a KBS, inference can be done in a number of ways depending on the types of applications they are aimed at. According to T. Point 55, to recommend a solution, the interface engine uses the following strategies: Forward Chaining and Backward Chaining.
Forward Chaining: It is a strategy of an expert system to answer the question, “What can happen next?”
Here, the interface engine follows the chain of conditions and derivations and finally deduces the outcome. It considers all the facts and rules, and sorts them before concluding to a solution. This strategy is followed for working on conclusion, result, or effect. For example, prediction of share market status as an effect of changes in interest rates 55.
Backward Chaining: With this strategy, an expert system finds out the answer to the question, “Why this happened?”
On the basis of what has already happened, the interface engine tries to find out which conditions could have happened in the past for this result. This strategy is followed for finding out cause or reason, for example diagnosis of blood cancer in humans 55.
2.5.6. KBS Development Phases
The knowledge of the expert(s) is stored in his mind in a very abstract way. Also every expert may not be familiar with KBSs terminology and the way to develop an intelligent system. The Knowledge Engineer (KE) is responsible person to acquire, transfer and represent the experts’ knowledge in form of computer system. People, Experts, Teachers, Students and Testers are the main users’ groups of KBS 56.
To build an expert system is known as Knowledge Engineering. If an ES solution is appropriate, one should approach the development in a systematic fashion much like the systems methodology steps and the model development steps examined earlier in the semester 67. The main phases in knowledge engineering are Knowledge acquisition, knowledge representation and evaluation and testing. Because the development process of the model on this study passes through these most basic three phases they are discussed briefly in the following section 67.
2.5.6.1. Knowledge Acquisition
In the development of KBS knowledge acquisition is the process of acquiring knowledge from the domain expert, books, documents, sensors, or computer files and structuring and organizing that knowledge into suitable form for knowledge representation 68. The knowledge acquisition process incorporates typical fact finding methods like interviews, questionnaires, record reviews and observation to acquire factual and explicit knowledge. Knowledge acquisition is the bottleneck in KBS development today because, the trustworthiness and the performance of the KBS mainly depends upon the acquired knowledge 69.
Knowledge acquisition is the most important as well as the most difficult task in the development of expert system 68. Knowledge can be classified in many different ways, tacit knowledge, explicit knowledge, hidden knowledge, factual knowledge, procedural knowledge, commonsense knowledge, domain knowledge, Meta knowledge and etc. Particularly, acquiring tacit knowledge is the tricky activity 64. According to Seblewongel 64 there are many factors that make knowledge acquisition a complex task. Some of them are 64:
experts may not know how to express and communicate their knowledge or may be unable to do so;
experts may be unwilling to share their knowledge; testing and refining knowledge is complicated;
system builders tend to collect knowledge from one source, but the relevant knowledge may be scattered across several sources;
experts may change their behavior when they are observed or interviewed and
Problematic interpersonal communication factors may affect the knowledge engineer and the expert.

2.5.6.2. Knowledge Representation
The next task after knowledge acquisition is representing knowledge. The acquired knowledge should be immediately documented in a knowledge representation scheme. Knowledge representation is a way of representing a validated knowledge collected from experts or induced from a set of data in a manner understandable by humans and executable on computers. It is a systematic means of encoding knowledge of human experts in an appropriate medium 70.
The purpose of knowledge representation is to organize the acquired and modeled knowledge into a form that a KBS can readily access for decision making 64. Any intelligent system has to know a great deal about the environment in which it is situated. It is generally accepted in AI and cognitive science that knowledge has to be represented in some form in order for it to be used 72.
To develop KBS there are several knowledge representation techniques. The same piece of knowledge can be represented using more than one formal scheme, but with varying degrees of difficulty 64. It is responsibility of the knowledge engineer to select appropriate knowledge presentation scheme that is natural, efficient, transparent, and developer friendly 56. According Solomon to 71, the common techniques of knowledge representation are: semantic network, logic, rules, cases and frames.
i. Frames
A frame is a data structure that includes all the knowledge about a particular object. It is a hierarchical knowledge structures convenient for representing knowledge on concepts and their relationships. A frame consists of its name and a set of slots or attributes. Each of the slots has its own name and value that can be a reference to some other frame or frames 73. Basically it is a group of slots and fillers that defines a stereotypical object. A single frame is not much useful. Frame systems usually have collection of frames connected to each other. Value of an attribute of one frame may be another frame 74.
Natural language understanding requires inference i.e., assumptions about what is typically true of the objects or situations under consideration. Such information can be coded in structures known as frames 75.
The knowledge in a frame is partitioned into slots. A slot can describe declarative knowledge (e.g., the color of a car) or procedural knowledge (e.g., “activate a certain rule if a value exceeds a given level”) 63.

ii. Semantic Networks
Briefly, a semantic network is a graphical method of representing real world concepts via nodes in a directed graph. Knowledge and meaning between concepts, is implied through the interconnection between each concept. By reading this directed graph, a language or semantic structure of the knowledge can be formed and hence can be abstracted through a computer language. Such methods have been used successfully to model knowledge which is well defined, as in classification problems, and in applications such as in medical prognosis 44.
An object can be any physical item, such as a book, a car, a desk, or even a person. Nodes can also be concepts, events, or actions. A concept might be the relationship between supply and demand in economics, an event such as a picnic or an election, or an action such as building a house or writing a book. Attributes of an object can also be used as nodes. These might represent size, color, class, age, origin, or other characteristics. In this way, detailed information about objects can be presented. Nodes are interconnected by links, or arcs, that show the relationships between the various objects and descriptive factors. Some of the most common arcs are of the IS-A or HAS-A type. IS-A is used to show a class relationship (i.e., that an object belongs to a larger class or category of objects). HAS-A links are used to identify characteristics or attributes of object nodes. Other arcs are used for definitional purposes 63. Example of semantic network is shown in Figure 9 below.

Figure SEQ Figure * ARABIC 9 Semantic networks for table 73iii. Logic
Logic can be defined as the study of correct inference, of what follows from what. Logic usually consists of syntaxes, semantics and proof theory. The syntax of logic defines a formal language of the logic. The semantics of logic specifies the meanings of the well-formed expressions of the logical language. The proof theory of logic provides a purely formal specification of the notion of correct inference 76.
The basic notion of logic has been known already to old Greeks. It is a system that defines a framework for representing relational knowledge and reasoning about it. Unlike rule based systems, logic is a very suitable tool for representing real world models. It can represent very complex relationships among objects, it can represent hierarchies, and it is very extensible. The main problem of reasoning with logic is that inference is usually an NP-complete problem, and there have not been many successful methods of expressing heuristic knowledge using logics. The reasoning is performed according to strictly defined rules of inference. The various types of logic are: propositional logic, first-order-predicate logic and modal logics 76.
For example 57:
“Black” represents any black color
“My-hair” represents hair
“Black (My-hair)” represents the fact that my hair is black color.
iv. Rule Based Representation
Rule based representation is one of the most popular and widely used knowledge representation languages. Early expert systems used production rule as their main knowledge representation language. Rules are the most applicable and relatively easier ways of knowledge representation in the development of a KBS 65.
A rule based system consists of a set of IFTHEN rules, a set of facts and an interpreter controlling the application of the rules, given the facts. So, a rule consists of three components, i.e., working memory i.e., a fact base, rule base and interpreter. The fact base contains the information that the system has gained about the problem thus far. The rules base contains information that applies to all the problems that the system may be asked to solve. The interpreter solves the control problem, i.e., decide which rule to execute on each selection-execute cycle 65.
It is important to distinguish between facts and their representations. Facts are part of the world, whereas their representations must been coded in some way that can be physically stored within an agent. We cannot put the world inside a computer (nor can we put it inside a human), so all reasoning mechanisms must operate on representations of facts, rather than on the facts themselves. Because sentences are physical configurations of parts of the agent, reasoning must be a process of constructing new physical configurations from old ones. Proper reasoning should ensure that the new configurations represent facts that actually follow from the facts that the old configurations represent 72.
v. Case-Based Representation
Case-based reasoning means using old experiences to understand and solve new problems. In case-based reasoning, a reasoned remembers a previous situation similar to the current one and uses that to solve the new problem. Case based reasoning can mean adapting old solutions to meet new demands; using old cases to explain new situations; using old cases to critique new solutions; or reasoning from precedents to interpret a new situation (much like lawyers do) or create an equitable solution to a new problem 43.
While rule-based systems represent domain knowledge mainly as rules that can be applied to various situations whenever certain conditions are satisfied, Case-based reasoning (CBR) treats domain knowledge as consists of concrete cases, which are records of typical problems and their solutions collected in the past. When a new problem shows up, it is compared with the solved problems. After the most similar case is located, the corresponding solution is adapted to the new problem 77.
According to 78 Compared to rule-based systems, case-based systems use experience with more details, though at the price of losing generality. A suitable domain for CBR typically has the following properties:
A large volume of historical data already exists.
Experts talk about their domain by giving examples.
Experience is as valuable as textbook knowledge.
Problems are not fully understood (weak models, little domain knowledge available).
There are a lot of exceptions to rules.
There is a need to build a corporate memory and transfer expertise among personnel.
2.5.7. Evaluation and Testing of KBS
The evaluation of KBS is an important aspect of KBS development that is required to prove whether a system fulfils it original objective. The evaluation is carried out by considering knowledge representation scheme such as adequacy, the right answers that the system come up with, knowledge consistency, its easiness to interact with the users and the facilities and capabilities do users need 43.
Analysis of KBS evaluation and assessment helps to identify the main points in the evaluation and assessment of the knowledge base system. The important features of knowledge base system evaluation is the absence of a well-defined and well-structured set of requirements at the beginning of the development process, continuous changes in the requirements during the whole development phase is required to make the system full-fledged KBS 57.
According to Seblewongel 64 effective KBS evaluation process, especially medical KBS, incorporates both non-human (technical) and human (non-technical) aspects. Some of the non-human aspects include exploring of the code, examining the correctness of reasoning techniques, checking the efficiency and performance of the system and detecting errors in the early age of a system 64. On the other hand, some of non-technical issues include systems compatible with users’ needs and desires, the easiness of the system for users, the quality of the user interface and the fitness of the system in the real working environments of the domain area 64.
States that to evaluate a system, there are two most common and general existing approaches. These are 64:
Qualitative (objectivist) approach employs subjective comparisons of performance, and it assumes observation results that depend on contexts and observers. Due to this, a system value depends on individual’s preferences and opinions. This approach is the most commonly used and effective approach to evaluate KBS.

Quantitative (subjectivist) approach uses statistical techniques to compare a system performance against either test cases or human experts. This approach focuses on important attributes of a system, which can be measured and interpreted. Both approaches comprise many KBS evaluation methods which help to answer the above “How to evaluate?” question.
2.5.8. KBS Development Tools
A Knowledge Base System tool is a set of software instructions and utilities taken to be a software package designed to assist the development of KBSs 63. Personal computers, typical programming languages like java and framework like .NET can be used in KBS development. These programming languages are general purpose and also being used to develop other application than AI applications. KBS shell with the readymade utilities of self-learning; explanation and inference like Java Expert System Shell (JESS), GURU, Vidwan are more specific and can also be useful to develop KBS 43.
KBS can be built using programming languages namely LISP and Prolog. KBS programs and the conventional or traditional programs have their own distinguishing features. The major distinguishing features of KBS programs as compared to conventional programming language is; the simplicity, use of few rules and memory management capabilities. KBS programs work by instantiate rules when activated by conditions in a set of facts 57.
LISP is one of the oldest programming languages, and it is most useful for symbolic representation. However, using LISP to develop an expert system requires the most development time because desirable characteristics such as the user interface, inheritance and method of reasoning need to be specifically coded. Recently, expert system development tools (e.g., shells) developed in LISP, C, or Prolog offer built-in functions that have significantly simplified the task of building expert system. Prolog is a logic-based language based on first-order predicate calculus. It has its roots in formal logic, and unlike many other programming languages. The program logic is expressed in terms of relations, and execution is triggered by running queries over these relations 43.
Prolog is an abbreviation for PROgramming in LOGic. It is designed basically to handle/manipulate knowledge representation using First Order Predicate Logic (FOPL) (Max, 2005). The expressiveness of Prolog is due to three major features of the language: rule-based programming, built-in pattern matching, and backtracking execution. The rule based programming allows the program code to be written in a form which is more declarative than procedural. This is made possible by the built-in pattern matching and backtracking which automatically provide for the flow of control in the program. Together these features make it possible to elegantly implement many types of KBSs 76.
Prolog allows a program to be read either declaratively or procedurally. This dual semantics is attractive. Procedural programming requires that the programmer tell the computer what to do. That is, how to get the output for the range of required inputs. The Programmer must know an appropriate algorithm. Declarative programming requires a more descriptive style. The programmer must know what relationships hold between various entities 76.
2.5.9. Application of KBS
There are several major application areas of KBS such as agriculture, education, environment, law, manufacturing, medicine, power systems, geology, telephone cable maintenance,…etc 76.
As KBSs applications are divided into two broad categories namely 56:
Pure KBSs applications: Pure applications include research contributing in KBS and AI development techniques such as knowledge acquisition, knowledge representation, models of automated KBS development (knowledge engineering approaches, models and CASE tools for KBS), knowledge discovery and knowledge management types of tools.
Integrated KBSs application: The KBS can be used for interpretation, prediction, diagnosis, design, planning, monitoring, debugging, repair, instruction, and control. Such advanced technology should be made available in urban and rural areas to utilize expert knowledge for holistic development. Such systems export knowledge in underdeveloped and remote area where expertise is rare and costly. The integrated application of KBS can be used in the development process of Economic, Social, Physical and Health sectors.
Expert systems or KBS have been applied to problems in sub fields of forestry including plant pathology, entomology, horticulture, plant selection and plant identification into a framework that best addresses the specific, on-site needs of researchers, taxonomists, technicians and farmers 42. KBS in such area combines the experimental and experiential knowledge with the intuitive reasoning skills of a multitude of specialists to aid the involved parties for making the best decisions.
Nationally there are limited number works related to plant disease diagnosis and treatment using rule based techniques and knowledge based system. But as per the researchers knowledge there is no a study that knowledge based system in mango disease domain.

The application of knowledge based system in Agriculture are the same as other KBS approach as they use the rule based approach which the experience and knowledge of human expert is captured in the form of IF-THEN rules and facts. These rules and facts are used to solve problem by answering questions on such diversified topics as pest control, the need spray, selection of chemicals to spray, mixing and application, on optimal machinery management practice, weather damage recovery such as freeze for drought etc 42 43.
2.6. Related Research Works to Agriculture and Plant Disease Diagnosis
There are various knowledge-based systems developed by different scholars all over the world. Expert systems and decision support systems were dominant in 1970s followed by knowledge-based systems in the 1980s 43. Mainly, KBS is applicable in problem solving areas such as planning, scheduling, troubleshooting, diagnosing and designing of specific area systems, interpretation systems, prediction systems, repair systems, monitoring systems, debugging systems, instruction systems and controlling systems. Here are some examples of related KBS research works in diagnosis and treatment of mango diseases and agricultural knowledge based system.
Knowledge based reasoning for agricultural crop Management decisions has been developed by Tsegaw kelela 79. 79 Conducted a study to develop an expert system model as an attempt to automate the reasoning strategy of human vegetable experts. There are a number of approaches to develop expert systems ranging from rule based methods that represent knowledge in the form of IF-THEN rules to systems that employ machine learning techniques.
The approach adopted in his 79 research was the combination of the rule based and neural network methods with an aim to exploit the best features of the two methods. The system is modeled to have hybrid architecture by integrating rule based and neural network modules as a component of one single system. In the course of building the hybrid model, knowledge acquisition, data preprocessing, rule generation, knowledge representation and model integration tasks had been performed 79. In the rule based module of the hybrid model, knowledge of vegetable experts was represented as rules. To build the neural network module and perform the integration with the rule based module, the fast artificial neural network libraries written in the C language were used after compiling and importing them in the prolog environment. The neural network module is built to handle user requests that may go beyond the capability of the rule based module 79. The artificial neural network module was integrated with the rule based module to create the hybrid vegetable expert system.

To measure the effect on performance after integration, ten random queries of consultation requests were presented to both the rule based module and the hybrid system. The hybrid system responded to eight of them while the rule based module alone provided answers to only five of these questions. The performance gain observed in the hybrid system is due to the neural network module embedded in it. The result obtained in this work showed that integration of the two approaches into one system produced better result and it is encouraging to advance the system into fully functional vegetable expert system. The general objective of 79 research was to explore the potential application of the expert system technology and develop a rule based – Artificial neural network hybrid model that can assist expert decision making in the production of vegetable crops.

For representation of the rules, visual prolog version 7.1 was selected and used. For training the neural network model, artificial neural network libraries were compiled and imported. In addition, Microsoft visual C++ 6.0 was used to compile the neural network libraries and create the library files that were imported for use in the visual prolog environment. The selection criteria of all of these software tools are their performance and convenience on the part of the researcher 79. The prototype system was developed using hybrid approach. By integrating the rule based approach with neural network, efforts have been made to exploit the strength of these two methods.

An expert system for the diagnosis and control of diseases in pulse crops (PulsExpert) was developed by Devraj, Renu Jain 80. PulsExpert is an operational automatic diagnostic tool that helps farmers/ extension workers to identify diseases of major pulse crops viz., Chickpea, Pigeonpea, Mungbean and Urdbean (highly consumed pulse crops) and suggests the appropriate control measures. Automatic knowledge acquisition system of PulsExpert provides user-friendly interface to the domain experts for entering, storing and structuring the domain specific knowledge. The knowledge base has been designed after examining the type and structure of the knowledge from different sources like literatures, books, databases, farmers, extension workers, etc 80. For a particular crop, knowledge can be entered by more than one expert using an automatic knowledge acquisition system and system automatically integrates the knowledge to build a consistent knowledge base. The knowledge base of PulsExpert contains up-to-date knowledge about 19 major diseases of pulses appearing right from seedling to maturity. The system provides user-friendly interface to farmers and asks the textual as well as pictorial questions 80. The order of questions to be asked is decided dynamically depending upon the answers of the farmer. On the basis of answers, PulsExpert diagnosis the pulse crop diseases along with its confidence factor and suggests most appropriate control measures which are composed of cultural practices as well as chemical controls 80. PulsExpert was evaluated by a team of field farmers and State Agriculture Officers and it was considered good with an average rank of 2.745 by farmers and 2.075 by State Agriculture Officers with a statistic mode ranking 3 in both the cases 80.

An Expert System for Pulses (PulsExpert) has been designed and developed to provide online help to pulse growers and extension workers of the country 80. Automatic knowledge acquisition system of PulsExpert provides user-friendly interface to the domain expert for entering, storing and structuring the domain specific knowledge. System automatically builds an integrated and consistent knowledge base combining all the knowledge fed by the multiple experts for the diagnosing the pulse crop disease. The inference engine of PulsExpert uses forward chaining methods that automatically matches facts against conditions and determines which rules are applicable 80. The order of the multiple-choice questions to be asked by the system is not predefined but varies according to the user’s response. PulsExpert handles uncertainty associated with the disease diagnosis and treatment knowledge base by using fuzzy logic approach 80. The ‘User Feedback’ form serves as an effective and efficient mechanism to collect the user performance, problems and suggestions. The image illustrations were considered a very useful tool in final diagnosis. The evaluation results given by the evaluators (farmers as well as State Agriculture Officers) revealed that the performance of the system was good and it can be implemented at the farmer’s field 80.

JAPIEST is an integral intelligent system for the diagnosis and control of tomatoes diseases and pests in hydroponic greenhouses was designed and developed by V. Lo´pez-Morales et al 81.

Automated Hydroponic Greenhouses represent novel food production systems which include modules for supervising the cultivated soil, packaging plans, as well as prevention, diagnosis and control of pests and diseases. In this setting, they proposed the design and implementation of an Integral Intelligent System called JAPIEST, which is focused on the prevention, diagnosis and control of diseases that affect tomatoes (Licopersicumexculentum) 81. Plants are farmed inside hydroponic greenhouses, whose particular conditions of temperature, humidity and nutrient consumption rates can influence directly the surge of plagues or diseases. It is relevant to detect and control the occurrence of any given pest or disease because plants are utterly sensitive to variations of environmental conditions and they have a short induced lifecycle. JAPIEST is a novel and valuable tool for farmers to make an early decision of the candidate disease, and then apply a suitable control treatment, based on Integrated Pest Management 81.

In 81 study Knowledge acquisition methodology to facilitate the construction of JAPIEST, domain experts were trained to master a technique for representing and acquiring knowledge, called dependency networks. This technique yields easily a graphical representation of the resultant rule base, since knowledge acquisition is a critical step in developing expert system 81.

S. J. Yelapure 82 designed and developed a prototype Knowledge Based System to suggest pesticide treatment for Tomato to farmers. This Knowledge Based System helps farmers to control attack of different pests with help of the pesticide treatment. Researcher has developed workable Knowledge Based System to identify the pests and to suggest pesticide treatment to control it. The rules were developed by considering different growth stages of Tomato, symptoms of disease, insects attacks on crop 82. In this expert system, the knowledge is collected by Knowledge Engineer from experts and store it into Rule base in the form of “if – then” rule. These rules are also called as Production Rules. The rule have two parts, first is Antecedents (if part) and consequents (then part). If Antecedents evaluate to true then the action within Consequent will be executed 82.

For this proposed system, Author had a choice of many expert system shells whose inference engine support to forward chaining. By using these shell, knowledge engineer can built an expert system for particular domain. However Author developed a program in ASP.net, comprising user interface, inference engine and explanation subsystem 82. Working memory stores information related to problem like stage of Tomato life cycle, symptoms of pest. Inference engine uses Forward Chaining to reach up to pesticide treatment. In future, there is possibility of attack of new pests, so that system is flexible to accommodate such changes. At present, this system considers all possible symptoms of pests found on Tomato during different stages to identify pest and to suggest pesticide treatment 82.

This Knowledge Based System is helpful to farmers to take decision related to pesticides that they have to use to control pests which attack on Tomato. As a pesticide treatment, this system suggests different pesticide to control single pest. So here farmers get choice of selecting pesticide by considering different companies and their prices 82.

Berhanu Aebissa 63 developed knowledge based system for coffee disease and pest control where it is intended for the diagnosis of common diseases and pests occurring in the coffee plant. The system integrates a structured knowledge base that contains knowledge about symptoms and medication of diseases and pests in the coffee plant appearing during their life span. Agricultural officers and planters who involve directly with coffee plantation may use this system as an assistant for helping them in managing the crop activities especially in diseases and pest control. For development purposes, knowledge engineering methodology was selected as a guide. Perhaps, this system may become the most popular alternative for performing and work as an assistant to produce a better quality of coffee product. The system was evaluated using visual interactive method; it was shown that the system agreed with human expert opinions in 83.6 percent of the decision 63.

The general objective of Berhanu Aebissa 63 research was to develop a prototype knowledge based system for coffee diseases and pests diagnosis and treatment in order to provide better information for non-experts (farmers), directly or indirectly, about major pests and diseases that threaten coffee production in Ethiopia, especially at places where there are less number of experts to assist them and, as a consequence, to empower them to take actions on the constraints occurred as required. For that developed system the knowledge representation method, rule based was chosen because it clearly demonstrates the domain knowledge. In a rule based system much of the knowledge is represented as a rule that is as conditional sentences relating statements of facts with one another. Most plant disease is predefined sets of rules 63. There are already defined sets of symptoms that enable to identify the infection. As a result rule based representation method is more appropriate to represent and demonstrate the real domain knowledge in diagnosing coffee infections. Additionally, rule based systems are the most commonly used knowledge representation language in agriculture 63. They used Prolog programming language to develop the prototype knowledge based system.

The developed prototype rule based system has been tested and evaluated to ensure the performance of the system in meeting towards established objectives. The evaluation process was more concerned with system user acceptance validations of the prototype. User acceptance efforts are concerned with issues impacting how well the system addresses the need of the user 63. To assess human factors visual interaction together with questionnaires methods are used. Domain expert evaluators interact with the system by using appropriate cases. Then they evaluated the system by using closed ended questionnaires 63.

Bethlehem Asferi 44 developed a knowledge base prototype system that identifies and diagnoses pepper diseases.Her work presents survey results of farmers’ current pest management practice and knowledge and associated problems. It presents a knowledge base system in the area of agriculture and describes the design and development of the rule based expert system using prolog shell. The designed system is intended for the diagnosis of common diseases occurring in pepper plant 44. A knowledge base system is a computer program composed of a knowledge base, an inference engine and a user interface. The proposed knowledge base system has a user interface and provides diagnosis knowledge on the basis of response(s) of the user made against the queries related to particular disease symptoms 44. The system integrates a structured knowledge base that contains knowledge about symptoms and remedies of diseases in the pepper plant appearing during their life span. Survey results of current pest management practice and associated problems are included in the research to show the importance of developing a knowledge base system 44. The system has been tested with domain dataset, and results given by the system have been validated with domain experts. The assessment was conducted in order to explore pest management practices of farmers, the level of perception of farmers on pest control mechanisms and to explore problems faced by farmers. Abela, a small village around Awassa, was chosen for the survey 44. The region was chosen because it is characterized by rugged mountains and flat landscapes and rain fed pepper and other vegetable crops are commonly produced. Selected participants answered a survey questionnaire structured in Likert format. Data gathered from 44 research instrument were then computed for interpretation.
The woody plant species identification KBS is developed by Dejen Alemu 73 and was the first of its kind in the country in the dendrology field identifying species with knowledge contains few numbers of key features. The system can also be adapted to other herbaceous species with simple modification and establishment of knowledge base for the respective plant species. The system needs to be updatable to incorporate the new woody plant species when it is infrequently introduced 73.

In his 73 study, new knowledge/rule with minimum length and smallest set of features of the species was constructed through laddering modeling technique, based on which a KBS for woody plant species identification was developed. The system shows that KBS brings quicker identification and it is applicable and essential in forestry in general and in species identification in particular 73. The prototype can easily be full-fledged by incorporating identification characteristic keys for all tree species with minimum cost and can readily be available for the potential users with simple technology. The other advantage of the woody plant species KBS was that the users can check the accuracy of the identification procedure by making comparison between the characteristics of the plant species under investigation with the descriptions that will be displayed at the end of the identification 73.

Ejigu Tefera 43 developed (CCKBS) knowledge based system for cereal crop disease diagnosis and treatment that assists agriculture experts and development agents to make timely decisions. CCKBS was developed in the case of kulumsa agriculture research center, Ethiopia
To develop cereal crop diagnosis and treatment knowledge based system, important knowledge was acquired through interview and document analysis 43. Five domain experts were interviewed to elicit the required knowledge about major cereal crops diseases that affect wheat, barley and the symptoms of these diseases as well as treatment methods undertaken to control such diseases 43. The acquired knowledge was modeled using decision tree that represents the cause effect relationships of symptoms of cereal crop diseases and the pathogens that could be the cause of diseases occurrence.
The knowledge was represented using production rule as if-then rules and implemented using swi prolog programming tool 43. Cereal crop diagnosis knowledge based system (CCKBS) reasons using backward chaining inference mechanism. The inference engine identifies a type of cereal crop diseases as goals and checks the symptoms of cereal crop diseases caused by particular pathogens to diagnose the possible crop disease and provide description and treatment 43. To determine its applicability in the domain area, the prototype CCKBS has been evaluated by the domain experts through visual interaction based on the criteria of easiness to use, time efficiency, accuracy in diagnosing cereal crop diseases and providing description and treatments. According to the evaluation through visual interaction 80.9% system performance was obtained 43.

His 43 proposed system was applicable and promising for assisting development agents who are working in remote areas where skilled agricultural experts are unavailable for an early treatment to the infected crops before the condition get worse. The cereal crop diagnosis knowledge based system is efficient in solving agriculture problems to make immediate decisions for the outbreak of cereal crop diseases using the type of diseases and their symptoms stored as rules and facts in the knowledge base 43. The advisory system will improve the productivity of farmers by assisting development agents who advise farmers on their daily needs.
Further study conducted that incorporates the image of infested crops in the knowledge base to illustrate severity of infected crops and the economic threshold 43.

To assess its performance and users acceptance in the domain area, the CCKBS was evaluated using users? feed-back through visual interaction method. After the users were exposed to interact with system, their opinion and suggestions were gathered 43.

The rule based knowledge based system developed in Ejigu Tefera 43 research work reasons to diagnose cereal crop diseases based on represented fact and rules extracted from the domain expert.

A web based expert system for diagnosing infectious and non-infectious cattle diseases has been developed by DEREJAW LAKE 68. The system integrates a structured knowledge base that contains knowledge about symptoms of cattle diseases. In addition to diagnosing diseases, the system allows the users to view diseases detail, post and view current dangerous cattle diseases. The system has been evaluated by domain experts (veterinarians) and animal health assistants and the analysis of the result shows that the system is acceptable 68.

The knowledge base contains the knowledge about different infectious and non-infectious diseases of cattle. Such system is useful especially for those animal health assistants who give first aid for cattle. The system has been developed using java (e2gRuleRule engine and applet), php and WamServer. It contains disease diagnosis, detail of diseases, administrate KB and views notifications. The disease diagnose link helps the user to diagnose common infectious and non-infectious cattle diseases in Ethiopia. It has both English and Amharic knowledge base 68.

A web-based Agronomy advisory system for Cereal Crops has been developed by Feidu Akmel Gobena 83. The system was intended to help extension workers and farmers by solving the problems they faced when experts help is not available. The system was bilingual data base and rule-based advisory System which covers pre cultivation, farm preparation, diseases and pest management, fertilizer application and variety selection which are necessary for crop production. It provides proper consultation and recommendation throughout crop production cycle. The system has been evaluated by domain experts and the analysis result shows that, the system was acceptable 83.

The system solved problems like site selection, farm preparation, variety selection, fertilizer application, diagnosis and treatment of disease, insect/pest and weed. It is also used to transfer new technology in agro management to farmers 83. This will lead to increasing the production and the national income, on one hand, and reducing the production cost on the other hand 83.

CHAPTER THREE3.1 KNOWLEDGE ACQUISITION IN KBS DEVELOPMENTKnowledge acquisition is backbone for the development of knowledge based system from different source whether from human experts or documents. Knowledge acquisition is the process of eliciting, structuring and organizing knowledge from human experts, books, documents, and sensors. On the other hand, it refers computer files and transferring to the knowledge base using knowledge representation techniques used in knowledge-based system; namely, logic, production rules, semantic nets, frames and cases 71.

For this study it is very necessary to acquire tacit and explicit knowledge which is very important for the development of the prototype system. Even though, there is no powerful method for knowledge acquisition, interview and observation are the most popular methods. The researcher collected tacit and explicit from domain experts and static knowledge from documents.

The acquired knowledge may be specific to the problem domain and the problem solving procedures, or it may be general knowledge (e.g., knowledge about business), meta-knowledge (knowledge about knowledge). In this field, many professionals have disclosed a common understanding that knowledge acquisition is a very difficult task to carry out 85.

The acquisition of knowledge is the most important and decisive phase in building knowledge-based systems. However, it is an extremely hard and capable of making an error task that knowledge engineer does while developing a knowledge-based system. As a result of the challenges and difficulties confronted in the transfer of expertise knowledge, knowledge acquisition has been depicted as the obstruction of knowledge based systems development 84.

In this chapter, the knowledge engineer collects Mango disease symptoms or cases and models it by using decision tree structure. The major features concerning to mango diseases diagnosis and the essential concepts are identified about the diagnosis procedures. This aids to develop the prototype using rule-based reasoning. The study explores the applicability of rule-based reasoning in agriculture particularly for diagnosis and treatment of mango diseases. The knowledge for this study is acquired from domain experts by using interviewing and critiquing knowledge elicitation methods and from relevant documents by using documents analysis technique which has been employed to purify the acquired knowledge.

STEPS IN KNOWLEDGE ACQUISITIONAccording to Jones 86, there are two main steps in knowledge acquisition process that are accomplished by the knowledge engineer so as to develop knowledge-based system. These are knowledge elicitation and knowledge structuring.

KNOWLEDGE ELICITATIONIn knowledge elicitation, domain knowledge is obtained through various means including interviews with experts and book and journal references. Methods of collecting, organizing, and formalizing knowledge are many and vary widely depending on the source 44. When knowledge is extracted from human specialists, the acquisition process is often called knowledge elicitation. The job of knowledge elicitation from human experts can be very difficult due to the inexplicit nature of human knowledge. There is no universal agreement on which knowledge elicitation technique to use when. It is most common to start with interviews and then use other methods when considered useful. The knowledge engineer must be versatile and willing to weigh the various methods in order to please the experts and elicit the most information 44.
Knowledge elicitation involves extracting knowledge from human experts, and/or written documents to build a knowledge-based system. In this study, the knowledge required to build a knowledge-based system was elicited from both tacit and explicit sources of knowledge. Tacit knowledge is collected from four experts in the domain area from Ambo Plant Protection Research Center (that are working as -Internist and Diabetologist, Internist and Endocrinologist, Internist and Endocrinologist, and Nurse) by using structured and unstructured interviews (the sample interview questions used are found in Appendix I). Domain experts are chosen purposefully for wide-ranging discussion using structured and unstructured interviews to understand the domain knowledge. These experts are essentially taking part during the study and asked to verify the rightness of the acquired knowledge. Moreover, explicit source of knowledge has been collected from the internet, manuals, research papers and journal articles, etc.
KNOWLEDGE STRUCTURINGIt involves using concepts discovered during the knowledge elicitation session to build a model or representation of the domain experts. It is a process where knowledge engineer uses concepts discovered during the knowledge elicitation phase to build a model of the domain. The knowledge used for building of the knowledge-based system in this study focused on knowledge regarding the diagnosis and treatment of mango diseases cases.

KNOWLEDGE OF MANGO DISEASESFruit crops play an important role in the national food security of people around the world. They are generally delicious and highly nutritious, mainly of vitamins and minerals that can balance cereal-based diets. Fruits supply raw materials for local industries and could be sources of foreign currency 31. Moreover, the development of fruit industry will create employment opportunities, particularly for farming communities. In general, Ethiopia has great potential and encouraging policy to expand fruit production for fresh market and processing both for domestic and export markets. Besides, fruit crops are friendly to nature, sustain the environment, provide shade, and can easily be incorporated in any agro-forestry programs 26.
The mango, because of its attractive appearance and the very pleasant taste of selected cultivars, is claimed to be the most important fruit of the tropics and has been touted as ‘king of all fruits’. The fruit contains almost all the known vitamins and many essential minerals. The protein content is generally a little higher than that of other fruits except the avocado. Mangos are also a fairly good source of thiamine and niacin and contain some calcium and iron 27 31.

According to CSA (2012/2013) 11 31, about 61,972.6 hectares of land is under fruit crops in Ethiopia; mangoes contributed 14.2% of the area. Moreover, out of 479,336 tons of fruits produced in the country, mangoes accounted 14.5% fruit production.

TYPES OF MANGO DISEASESMango tree is attacked by different insects and diseases such as , Anthracnose, Bacterial Black spot, Fruit fly, mango gall flies, Mango leaf coating, Mites, Mango seed weevil, Mealy bug, Powdery mildew, Scale, Spider mites, Mango tip borer, Stem-end rot, Termite, Thrips and White flies. The major insect pest of mango is the white mango scale insect, Aulacaspis tubercularis (Hemiptera: Diaspididae). It has been recorded mainly from plants belonging to four families: Palmae, Lauraceae, Rutaceae and Anacardiaceae 13. This insect is a serious pest in mango especially on the late cultivars 15.
The following are the major diseases that affect the productivity of mango fruit crop production in Ethiopia.

Anthracnose
The disease is incited by Colletotrichum gloeosporioides Penz. ( Glomerella cingulata (Stons.) Spauld & Schrenk). It affects all the above ground parts of the plant particularly leave, petioles, twigs, blossoms and fruits. It is one of the important post-harvest diseases of mango 87. Disease may be reduced by removal of diseased parts from the tree and its destruction by burning. Infection on blossom could be reduced effectively by 2 sprays of Carbendazim (0.1%) at 15 day intervals. Its foliar infection can be managed by 2 sprays of Copper oxychliride (0.3%), while latent infection of the pathogen on fruits could be reduced by pre-harvest sprays of Thiophanate methyl or Carbendazim (0.1%) 87.
“Post-harvest infection of this pathogen can be managed by post-harvest dip of fruits either with hot water alone (45 ± 20°C ) or hot water in combination of fungicides, Thiophanate methyl or Carbendazim (0.05%). Covering of fruits on tree, 15-days prior to harvest with news or brown paper bags and use of bio-control organism, Streptisporangium pseudovulgare were also found effective in management of its post-harvest phase” 87. From paper Mango Diseases and Pests_ Mango Resources Information System.htm1
Anthracnose is recognized as the most important field and post-harvest disease of mango worldwide which is caused by Glomerella cingulata (anamorph) and Colletotrichum gloeosporioides and C. acutatum 88. It is the major disease, limiting factor for fruit production in all countries where mangoes are grown, especially where high humidity prevails during the cropping season. The post harvest phase is the most damaging and economically significant disease in worldwide as the disease directly affects the marketable fruits rendering them worthless 88 95.
Postharvest anthracnose appears as rounded brown to black lesions with an indefinite border on the fruit surface. Infection in larger fruit does not normally develop into lesions. After initial establishment in the fruit, the fungus remains latent or dormant until the fruit begins to ripen. Dark depressed circular lesions then develop on the ripening fruit and increase rapidly in size. They may even cover the entire fruit surface in extreme severe cases. Lesions larger than two cm are fairly common on severely infected fruit 88. However, lesions of different sizes can coalesce and cover extensive areas of the fruit, typically in a tear-stain pattern, developing from the basal toward the distal end of the fruit. Lesions are usually restricted to the peel, but in severe cases the fungus can penetrate even the fruit pulp. In advanced stages of infection, the fungus produces abundant orange to salmon pink masses of conidia appear on the lesions 88.

Powdery Mildew
The disease is caused by Oidium mangiferae Berthet. The disease affects inflorescence, leaves and young fruits. The characteristic symptom of the disease is the white superficial powdery growth of the fungus comprising a large number of conidia borne on conidiophores. “The disease can be managed by pruning of diseased leaves and malformed panicles and three sprays of fungicides at different stages starting with Wettable Sulphur (0.2%) at the panicle size of 7.50 -10.00 cm followed by Dinocap (0.1%) after 15-20 days of first spray and Tridemorph (0.1%) after15-20days of second spray”. Wettable Sulphur (0.2%) can be used in all the three sprays and number of sprays may be reduced as per appearance time of disease 87.

Dieback
The disease is characterized by drying back of twigs from top downwards particularly in older trees followed by dying of leaves. Dark patches are seen on young green twigs. Cracks are seen on branches and gum exudes from the cracks before its death. Graft union of nursery plants is also affected by the disease and it dies. Nodal infection below growing point results in death of growing twigs. The causal pathogen of the disease is Lasodiplodia theobromae (Pat.) Griffon & Mouble (Botryodiplodia theobromae Pat.) 87. The gummosis is found more prominent during winter after rainy season. This pathogen also attacks ripe fruit in storage at the base of pedicle (stem end rot) and the circular brown area near the stem end further develops towards the lower portion of the fruit. Later entire fruit surface is covered with the dark brown to black area and complete fruit rots in 2 to 3 days. The disease may also start from injured portion on the fruit surface. “The disease can be reduced by pruning of infected plant parts from 7- 10 cm below the infection site and pasting the cut ends with clay mixed cow dung or Copper oxychloride or Bordeaux mixture. In case of gummosis diseased parts may be cleaned / removed and pasted either with Bordeaux or Copper oxychloride paste. Application of Copper sulphate (500 g t -1 ) in soil around the tree trunk is also found effective in reducing gummosis” 87. The stem end rot can be minimized by pre-harvest spray of Carbendazim or Thiophanate methyl (0.1%) 15 days prior to fruit harvest. Fruit should be harvested with stalk (5 cm), if not, the opening must be sealed with wax 87. Post-harvest phase of the disease can also be controlled by dipping the fruit in hot water (52 ± 10°C) with Carbendazim for 5 minutes. Covering fruits with brown or news paper bags and use of bio-control agent, Streptisporangium pseudovulgare have also been found effective in management of stem end rot 87.

Phoma Blight
The disease is caused by Phoma glomerata (Corda) Woll. & Hochapf and generally noticed on old mature leaves only. Disease initially starts as minute, irregular, yellow to light brown scattered spots on all over the leaf lamina 87. Characteristic feature of fully developed spots are dark brown margin and dull necrotic grey centers. In severe cases spot coalesce and form big patches resulting in withering and defoliation of infected leaves. The disease can be managed by application of balanced nutrients to the plants. Spraying of Copper oxychloride (0.3%) has also been found effective against the disease 87.
Scab
The causal pathogen of the disease is Elsino mangiferae Bitancourt and Jenkins (= Sphaceloma mangiferae Bitancourt and Jenkins).It affects leaves, panicles, blossoms, twigs, stem bark and fruits 87. The symptom produced by the pathogen is almost similar to anthracnose but lesions produced are smaller than anthracnose on leaves and down surface is covered by delicate velvety growth. The disease may cause crinkling, distortion and premature shedding of leaves under severe conditions. Sometimes irregular shot holes are also observed on leaves. The blotches on the stem bark are grayish and irregular in shape. The disease can be controlled by regular sprays of Copper oxychloride (0.3%) 87.
Black Banded
The causal pathogen of this disease is Rhinocladium corticolum Massee (perfect state Peziotrichum corticolum (Massee) Subramanian). Disease symptoms appear in the form of black velvety fungal growth on midribs, twigs and branches of mango tree. Since the disease is seen in to black colour bands, hence named as black banded 87. The infected portion of the bark contains mycelial growth and cluster of conidiophores which confined to upper layer only. Removal of black growth by rubbing, application of Bordeaux / Copper oxychloride paste and spraying of Bordeaux mixture (1%)/Copper oxychloride (0.3%) helps in management of this disease 87.
Mango Malformation
The disease is caused by Fusarium subglutinans and it produces two types of symptoms, i.e., vegetative and floral. Vegetative malformation is more pronounced on young mango seedlings and plants. The affected plants develop swollen abnormal vegetative growth with short internodes. Leaves are small, narrow and often produced on the top of seedlings in clusters, giving it a bunchy appearance 87. The characteristic symptoms of the floral malformation are compact and clustery appearance of flowers. The flower buds transform in vegetative form and leaves. The flower bud seldom opens and remains dull green in colour. Some malformed panicles are not compact but both types of malformed panicles do not bear fruit. Mango malformation can be minimized with removal of malformed panicles and its destruction, removal of late December and early January flowers and application of NAA (200 ppm) in the first week of October 87.
Mango Bacterial Canker Disease (MBCD)
MBCD is incited by Xanthomonas campestris pv . mangiferaeindicae (Patel, Moniz & Kulkarni) Robbs, Ribiero& Kimura and affects all the above ground parts of plant, i. e., leaves, petioles, twigs, branches and fruits. Lesions on leaves are angular to irregular, dark brown to black, cankerous on lower side but occasionally on both the sides and surrounded by chlorotic halo. Cankers on petioles are raised and dark brown to black in colour, while on twigs and branches are raised with longitudinal fissures. Lesions on fruits are raised and dark brown to black which gradually develop in to cankers 87. Under favorable condition lesions increase in size and sometimes cover complete fruit. Such lesions often burst extruding gummy substances containing bacterial cells of the pathogen. Fruits may drop off, if infection comes at stem end. MBCD can be minimized by regular inspection of orchards and its sanitation, use of healthy stones for root stock, 3 sprayings of Streptocycline (200ppm) or Copper oxychloride (0.3%) alone or its combination and use of bio-control agents, Bacillus coagulans , B. amyloliquifaciens , B. subtilis and fluorescent pseudomonads 87.

Red Rust
The disease is caused by an algae, Cephaleuros virescens Kunze and manifests itself in the form of rusty red fructification of the alga on the surface of leaves, petioles and twigs. Initially the spots are greenish grey and velvety in texture which finally turn to reddish brown. After shedding the spore the algal matrix remains attached to leaf surface, leaving a creamy white mark at the original rust spot. The disease can be reduced by supply of balanced nutrients to the plants and two sprays of Bordeaux mixture (1%) or Copper oxychloride (0.3%) in the month of July at 15 days interval 87.

Black Rot
It is a post-harvest disease and caused by Aspergillus niger Van Tiegh. Affected fruits show yellowing with irregular grayish spots, which develops into black necrotic area with growth of black mould 87. Tissues around and beneath the spots disintegrates and emits foul odour. The disease can be managed by avoidance of injury to fruits and its contact to soil, dipping of fruits in hot water (52±1 0 C) with Carbendazim (0.5%) for 5 minutes and covering of fruits with brown or news paper bags on the tree itself 15 days prior to harvest 87.

MANAGEMENT OF MANGO DISEASEDuring the knowledge acquisition process, the knowledge engineer attempts to understand both the explicit and tacit part of the knowledge. It uses simple visual diagrams to motivate discussion with domain experts. This discussion process creates thoughts and understandings with regard to how the knowledge is applied, how decisions are reached, and the factors that stimulate. The knowledge engineer then has to build the conceptual model from what has been discussed throughout the knowledge acquisition phase so as to ease knowledge representation in the knowledge base 71.

CONCEPTUAL MODELINGConceptual modeling is extensively acknowledged as the critical stage of knowledge acquisition. Before a knowledge-based system can be constructed, knowledge should be identified and collected, and a model of domain knowledge should be built. Models are applied to acquire the important characteristics of problem domains by decomposing them into more controllable parts that are simple to know and to use. Models are very related with the domain they denote 89. “A model is a simplification of reality” 90. Models support individuals to increase in value and know such complexity by allowing them to investigate each specific area of the system successively. Models are applied in systems development tasks to depict the designs of the system and to simplify communication between disparate individuals in the group at disparate levels of abstraction. Individuals have disparate opinions of the system and models can aid them know these opinions in a combined way.

According to S. Gebremariam 71, one of the most extensively applied methods of conceptual modeling is called decision tree. Decision tree commonly acts a key role in a knowledge modeling process. Decision tree is used for the search space of a certain problem and presented by a graph. A node in the tree denotes a decision to be attained when finding a solution of a certain problem, and the branches extended from the node show the potential values of the decision. To find the solution of a certain problem, anyone then traces by way of its tree using data of a certain problem to select a branch at every node.
In this study the knowledge used for diagnosis and treatment of mango diseases is acquired from domain experts and relevant documents analysis. In the following sections the model of concepts in the diagnosis and treatment of mango diseases are discussed.

CONCEPTS OF SYMPTOMSIn the diagnosis of mango diseases, the domain experts have a concept of symptoms that is used to differentiate the related symptoms of the diseases and the non-related symptoms of mango diseases. For the related symptoms of mango diseases, the domain experts have a general knowledge about the common symptoms of the six types of mango diseases. In the process of knowledge gathering through interview, the domain experts (agronomist) explained that there are symptoms that are used for identifying and diagnosing the diseases for treatment. The possible symptoms used for the domain experts to identify whether the mango has a chance to be infected or not are the following:
Anthracnose symptoms
Flower blight,
Fruit rot,
Leaf spots
The panicles (flower clusters) start to show as a small black or dark-brown spots
Coalescence of lesions along midrib
“Tear staining” is that develops when spore-laden water droplets from infected twigs and panicles wash over and infects the fruit.

Black, pin-prick spots on flowers and panicles; killed flowers turn inky black.

Alga Spot (Red Rust, Green Scurf)
Leaf spots start as circular green-gray areas that eventually turn rust red as the alga produces a profusion of rust-colored microscopic “spores” on the leaf surface
Rust-red “spore” masses will also develop on infected stems
Severely diseased branches may have to be pruned from the tree.

Cankers develop in the bark and stem-thickening can take place at infection sites
Mango Powdery Mildew
Infected panicles (flowers, flower stalks, and young fruits) become coated with the whitish powdery growth of the pathogen
Infected flowers and fruits eventually turn brown and dry.

The dead flowers can easily crumble in one’s hand.

A whitish-gray haze covers a normally reddish mango panicle.

Infected young fruits may have a purplish haze.

Panicles have a whitish-gray haze; killed flowers turn brown and gray
Young infected fruit turn brown and fall.
Severe infection of young leaves results in premature leaf drop. On mature leaves, the spots turn purplish brown, as the white fungal mass eventually disappears
Stem-end rotmsThe infected fruit has initially violet lesion at the stem-end, turning light-brown, and finally becoming black.

The inner tissues of the fruit become soft and watery.

Affected fruit appear dark brown and water soaked
Post-harvest treatment of fruit with hot water or fungicides can reduce the development of this disease.

Hot water treatment (refer to p. 17, Anthracnose, prevention and control)
DIEBACK
Drying of twigs and branches followed by complete defoliation, which gives the tree an appearance of scorching by fire.

The affected leaf turns brown and its margins roll upwards.

The twig or branch dies, shrivels and falls.

At this stage, the twig or branch dies, shrivels and falls. This may be accompanied by exudation of gum.

In old branches, brown streaking of vascular tissue is seen on splitting it longitudinally.

The areas of cambium and phloem show brown discolouration and yellow gum like substance is found in some of the cells.

BACTERIAL CANKER
Bacterial leaf spot is noticed on the leaves as angular water soaked spots or lesions, surrounded by clear holes.

Longitudinal cracks also develop on the petioles.

Cankerous lesions appear on petioles, twigs and young fruits.

The water soaked lesions also develop on fruits which later turn dark brown to black.

ROOT ROT
Withering and drying of the plant from top to bottom and whole plant die up
Domain experts usually recognize mango diseases by the appearance of at least the above first three basic listed symptoms under each diseases.
This concept is the most useful concept in order to conclude whether the mango is infected by the disease or not, and which diseases is affected this plant.
To summarize, the decision tree based on conceptual model depicted in figure 10 shows the symptoms and levels of decisions that domain experts use during diagnosis and treatment of mango diseases.

Figure SEQ Figure * ARABIC 10 Decision trees for diagnosis and treatment of Mango DiseaseAs shown in the above figure 10, the decision tree structure shows the flow of knowledge in the diagnosis and treatment of mango diseases. First it checks the appearance of the basic symptoms of mango diseases on the plant leaves, roots, stem, fruits, petioles and panicles and etc. In general, the necessary knowledge was extracted from domain experts and relevant documents analysis was made for building the decision tree model of concepts in the diagnosis and treatment of mango diseases. This is used for building the knowledge-based system that can provide advice for farmers and experts.

KNOWLEDGE REPRESENTATIONKnowledge representation is the last phase of the knowledge base development. In the representation of knowledge into knowledge base, the knowledge acquired from knowledge acquisition process is represented into structured form 91. There are many approaches for representing knowledge into the knowledge base. Such representation in KBS is the rule based representation in logical paradigm of simple if-then rules in backward or forward chaining. We have chosen here the backward chaining for knowledge representation with simple if-do pair in place of if-then rules. It contains the logical rules that direct the expert system how to solve problem, actions to perform such as giving advice, going to other sections, calling to routines etc. The first section in the system is always named as start section 91. The advice is given when condition(s) in the section is (are) fulfilled 91.
Once the knowledge has been acquired and modeled, the next step is knowledge representation using appropriate format that is both understandable by end-users, experts and inference engine 71. Knowledge representation is a means of encoding the human expert’s knowledge in an appropriate medium. It is the dedication to a vocabulary, data structures, and programs that let domain knowledge usable. There are several commonly used techniques for knowledge representation in the development of knowledge-based systems. These are logic, production rules, semantic nets, frames and cases 71. In this study a rule-based knowledge representation and reasoning is followed. They are one of the most commonly used techniques for the development of knowledge-based systems. Knowledge is represented in the form of condition-action pairs: IF this condition (or antecedent condition or premise) occurs, THEN some action (or conclusion or consequence) will occur. The following rules in the knowledge base of the prototype are expressed with natural language rules IF … THEN …
Rule 1:
If the symptom of mango diseases is Leaf spots
And there is flower, twig, and blossom blight
And Fruit rot
And “Tear staining” is that develops when spore-laden water droplets from infected twigs and panicles wash over and infects the fruit.

And the panicles (flower clusters) start to show as a small black or dark-brown spots
Then Anthracnose is diagnosis
Rule 2:
If the symptom of mango diseases is Leaf spots
And there is flower, twig, and blossom blight
And there is a profusion of rust-colored microscopic “spores” on the leaf surface
And Rust-red “spore” masses will also develop on infected stems
And Altitude is high
Then the Alga Spot (Red Rust, Green Scurf) is diagnosis
Rule 3:
If the symptom of mango diseases is Leaf spots
And there is flower, twig, and blossom blight
And Fruit rot
And “Tear staining” is that develops when spore-laden water droplets from infected twigs and panicles wash over and infects the fruit.

And the panicles (flower clusters) start to show as a small black or dark-brown spots
And the rot produces dark streaking of the water-conducting tissue
Then stem-end rot is diagnosis
Rule 4:
If the symptom of mango diseases is Leaf spots
And there is flower, twig, and blossom blight
And Bacterial leaf spot is noticed on the leaves as angular water soaked spots or lesions, surrounded by clear holes.

And longitudinal cracks also develop on the petioles.

And Cankerous lesions appear on petioles, twigs and young fruits.

Then the Bacterial Canker is diagnosis
Rule 5:
If the symptom of mango diseases is white superficial powdery fungal growth on leaves, stalks of panicles, flowers and young fruits
And the affected flowers and fruits drop pre-maturely
And the dead flowers can easily crumble in one’s hand
And whitish-gray haze covers a normally reddish mango panicle
Then Mango powdery Mildew is diagnosis
Rule 6:
If the symptom of mango diseases is sudden dropping of leaves after the emergence of seedling from the soil
And Withering and drying of the plant from top to bottom and whole plant die up
And appear during prolonged rain and humid weather at or below the ground level with circular to irregular water soaked patches
Then Root rot and Damping off is diagnosis
Rule 7:
If the symptom of mango diseases is drying of twigs and branches followed by complete defoliation, which gives the tree an appearance of scorching by fire
And Internal browning in wood tissue is observed when it is slit open along with the long axis.
And cracks appear on branches and gum exudes before they die out.

And affected leaf turns brown and its margins roll upwards.

And In old branches, brown streaking of vascular tissue is seen on splitting it longitudinally.

Then Die Back is diagnosis
These rules are added to the knowledge base using prolog programming language. These rules capture common evidence of problems associated with the criteria for mango disease diagnosis. The detail is presented in appendix 3.

CHAPTER FOURIMPLEMENTATION AND EXPERMENTATIONIn the following sections, the implementation includes the real construction of the prototype system for diagnosis and treatment of mango diseases. After the necessary knowledge was represented using a rule-based knowledge representation technique, the next step is coding the represented knowledge using Prolog programming language into a suitable format that is understandable by the inference engine. The system performance testing and user acceptance were included in this chapter.

ARCHITECTURE OF THE PROTOTYPE SYSTEMArchitecture defines how the system is constructed, describes what the critical components were and how they fit together. A KBS tool is a software development environment containing the basic components of KBSs. The core components of developed KBS are shown in figure 11.

Figure SEQ Figure * ARABIC 11 Architecture of the developed prototype systemGiven users query through the user interface the system reasons for diagnosis and treatment of mango diseases using reference engine. Back ward chaining is used in study. During reasoning knowledge base is constructed. In this prototype there are two main categories of knowledge bases, signs and symptoms knowledge base and treatment knowledge base.

In addition, the system is capable of proving explanation for sign and symptoms of diseases of mango.

But, the KBS not learns and update its fact base when new facts were generated during reasoning.
DIAGNOSIS AND TREATMENTDeveloping a prototype KBS for diagnosis and treatment of mango diseases is one of the specific objectives of the study. The developed system has the capability of providing diagnosing and treatments of Anthracnose, powdery mildew, Root rot and Bactria cancer. Even though mango diseases have some similar signs and symptoms, there is also difference in sign and symptoms observed from one species from other. It is possible to diagnosis mango diseases by combining different signs and symptoms. The prototype system integrates tacit and explicit knowledge acquired from domain knowledge experts concerning the sign and symptoms of different mango diseases. Figure 4.3 below shows sample of how the prototype system accepts user response and provide the final advice as a solution for diagnosis and treatment.

Figure SEQ Figure * ARABIC 12 How prototype system diagnosis and treatmentEXPLANATION FACILITY BY PROTOTYPE SYSTEMA prototype system can provide facility of what signs and symptoms mean which is used during diagnosis and why it is selected as the signs and symptoms of mango diseases for diagnosis and treatments. Figure 4.6 show how a prototype system provides explanation facility for the signs and symptoms.

Figure SEQ Figure * ARABIC 13 How prototype system gives explanation facilityTESTING AND EVALUATION OF THE PROTOTYPE SYSTEMSYSTEM PERFORMANCE EVALUATIONTo evaluate the performance of the system cases were collected from Ambo Plant protection research center and Assosa Agricultural research center. The numbers of collected cases were fifteen (15). Classifying the test cases into negative or positive is required to evaluate the performance of the system in assigning the cases in to the correct category: positive or negative, this is done by domain experts. The good performing system decides not (none) mango diseases cases as negative and positive (infected) mango diseases cases as decided by the plant pathologist. The evaluators were domain expert selected from Ambo Plant Protection research center.

In this research, system performance testing confusion matrix techniques was used and the performance of the system was calculated using recall, precision and F measure were used for measure effectiveness.

The confusion matrix has four categories: True positive, False positive, False negative and True negative. True positive (TP) is cases that were identified by the domain expert as correctly diagnosis and also diagnosis by the prototype system as correctly. False positive occur when incorrect data inserted into the system and the system is give result diagnosis correct. That means some irrelevant documents may be retrieved by the system as relevant. True negative (TN) is incorrect cases diagnosis incorrectly by the prototype system and expert domain. This is the case when incorrect (negative) cases were inserted and the proposed system produce negative decision i.e. non mango diseases. For instance when the evaluators input the cases that domain expert decided as incorrect and the system also decide it as incorrect.

False negative (False drop or Errors of commission) is the situation when incorrect cases were inserted in the system for testing and the prototype system produce positive result. Put differently, when case which is not indicate some disease of mango by the domain expert is decided as disease for mango by the prototype system.
Actual Positive Actual Negative
Predicted Positive TP FP
Predicted Negative FN TN
Table SEQ Table * ARABIC 1 Confusion matrix conceptIn the process of testing the performance of the prototype system, the domain experts classify correctly and incorrectly diagnosed mango diseases cases by comparing the judgments reached by the prototype system with that of the domain experts judgments reached on the same mango disease test cases. The result was presented by confusion matrix in table 2 below.

Actual correctly diagnosis cases Actual incorrectly diagnosis cases
Predicted correct by the prototype system 8 1
Predicted incorrect by the prototype system 2 4
Total 10 5
Table SEQ Table * ARABIC 2 Confusion matrix of the prototype systemFrom the above table the correct diagnosis by prototype system is 12 and incorrect diagnosis is 3. This indicated the system performance is 80%. The recall, precision and F measure were calculated depending on the above data in the confusion matrix.

TP Rate FP Rate Precision Recall F-Measure
Results 0.777 0.166 0.875 0.777 0.823
Table SEQ Table * ARABIC 3 Accuracy of the prototype systemKnowledge based system evaluation plays an important role in judging the efficiency and effectiveness of it. Recall and precision are the common performance measure of the system. As it showed in table 4.2 the value of recall is 0.875 and precision is 0.777. F measure is a derived effectiveness measurement. The resultant value was interpreted as a weighted average of the precision and recall. The best value is 1 and the worst is 0. As it showed in the above table 3 the F measure of the prototype system is 0.823 which indicate that the prototype has a very good performance.

The challenges behind evaluation performance of prototype system are some of the cases have no contain enough information of signs and symptoms of mango diseases except the commons one. The knowledge variation among the profession of mango diseases diagnosis and treatment is the other challenge.

USER ACCEPTANCE TESTING (UAT)User acceptance testing is a form of testing to verify if the system can support day-to-day business and user scenarios to validate rules, various workflows, data correctness, and overall fit for use and ensure the system is sufficient and correct for business usage (Vince, 2010).It is a process of evaluating a new or revised system undertaken by domain experts, knowledge engineer and end-users of the system to make sure it meets the objectives of its development (John, 2001). User aacceptances testing is independent of the system development process and performed by end-users and stakeholders before formally produced. Performingg system acceptance testing depends on different user acceptance criteria like functionality, correctness, validation, verification, easy of use and user interface. Solomon 71 selected visual interaction techniques to check acceptance of their system.
Eight (8) domain experts were selected from Assosa Agriculture research center. Since, the procedure requires visual interaction with all selected domain experts, it difficult to take a lot of respondents. The prototype system was showed to the domain experts what is the prototype system can do including its user interface.Then the researcher distributed the questionnaire for those domain experts and data was collected. Lastly the user acceptance of the prototype system was analyzed. Table 4.3 below shows the analyzed data about user acceptance of the system which was collected from the respondents.No.
Criteria of evaluation Poor Fair Good Very good Excellent Average
1 Is the prototype easy to use and interact with it? 0 0 2 2 4 4.25
2 Is MKBS attractive? 0 0 2 2 4 3.875
3 Is the system more efficient in time? 0 0 1 2 5 4.5
4 How accurately does the system reach a decision about diagnosis of mango diseases? 1 0 1 2 4 4.25
5 Does the system incorporate sufficient knowledge about how to diagnoses and treatment of mango? 0 0 3 3 2 3.875
6 Is the system giving the right conclusions and the right recommendations? 0 0 1 3 4 4.375
7 How do you rate the significance of the system in the domain area? 0 0 2 4 2 4
Average 4.16
Table SEQ Table * ARABIC 4 Performance evaluations by domain expertsAs shown in the above table 4, 50% of the users evaluated the prototype as excellent, 25% as very good, 25% as good. This shows that the system is ease of use and interacts.

The second evaluation criteria are attractiveness of the prototype system which showed a greater rate of attractiveness by the evaluators. The majority 50% was scored as excellent, 25% as very good, and 25% as good. In the efficiency of the prototype system with respect to time criteria of evaluation, 62.5% of the evaluators scored as excellent, 25% as very good, and the rest 12.5% as good. Moreover, 50% of the evaluators gave the prototype system an excellent score with regard to the accuracy of the prototype system in diagnosis of mango diseases, 25% as very good, 12.5 as good and 12.5% as fair. And when asked if the prototype system included adequate knowledge about diagnosis and treatment of mango disease, 37.5% of the evaluators rated the prototype system as very good and as good, and 25.5 as excellent. The ability of the prototype system in making right conclusions and recommendations criteria was scored 50% of the evaluators as excellent while 37.5% and 12.5% of the evaluators scored it with very good and good respectively.
To this end, the significance of the system in the domain area criteria indicate, 50% of the evaluators gave the prototype system very good, 25.5% rated the prototype system as excellent and 25% as good. Finally, the average performance of the prototype system according to the evaluation results filled by the domain experts is 4.16 out of 5 or 83.21% which is very good.
The user acceptance of the prototype system is not registered 100% because of unawareness of domain experts about KBS importance in their domain area. In addition, misunderstanding some of them considered if the prototype system is implemented it can be reduce number of workers.
CHAPTER FIVECONCLUSION AND RECOMMENDATIONSCONCLUSION
Today many agriculture facilities are supported by IT applications resulting in increase agricultural sector services by reducing time and cost of providing agricultural sector services. KBS have been found to be very useful in our today’s world driven by technology. KBS is currently attracting a great deal of interest in the business community including agriculture. Almost all the business contemporary depends on knowledge. So it’s always a good idea to find a way to keep and preserve knowledge. In Ethiopia most of the peoples are farmers, it’s believed that more than 80% of the population depends on agriculture; therefore it’s logical to assume that there exists shortage of agricultural experts in the country. KBS can be used as an additional or source of information when experts are not available. It gets attention on diagnosis and treatment of diseases Mango diseases are problematic plant diseases all over the word. It causes the destruction of mango plant in many countries especially in tropical area and developing countries where there is scarcity of agronomy experts and tools for diagnosis and treatments. So, Rule based reasoning was used for the development of a prototype KBS and the developed prototype correctly assists agricultural experts (agronomists) for diagnosis and treatment of mango diseases. The user acceptance testing of the system indicated 83.21% which show that the prototype system is acceptable by the professionals and necessity to implement in agriculture sectors. In addition, as the performance results indicate the system registers 82.3% accuracy. But the purpose of KBS is not to replace human experts, but to assist agronomists and make their knowledge and experience more widely available and permit general practioners to work better.
5.2 RECOMMENDATIONS
This study achieved its objectives and answered its research questions with a hopeful performance and user acceptance results. And the following recommendations were given based on the observed opportunities and uncover areas by this research to fully implement the KBS for diagnosis and treatment of mango infection and related diseases.

Tacit knowledge about the diagnosis and treatment of mango disease is extracted from the domain experts using interviewing method in order to have detail understanding of the domain knowledge. However, it was a difficult task to extract the necessary knowledge due to the personal nature of tacit knowledge. Therefore, it is important to apply data mining techniques to extract the hidden knowledge about the disease and more research work must be done to integrate the application of data mining techniques with knowledge-based systems.

During the discussion with domain experts, domain experts noted that KBS system has promising prospect for Ethiopian agriculture, especially if it’s developed using local languages like Amharic, Afan Oromo and Tigrigna. So, future work on this area should consider using local languages.

The domain Experts and the researcher also suggests that KBS would be more applicable if the system is deployed on smart phones since its handy and most of the farmers will eventually use one.

As this rule based knowledge base system is not self learning, in the future learning component should be integrated that reasons and remembers when new circumstances and unknown facts are asked by users to suggest solutions.
Due to the knowledge was modeled using Boolean decision tree with only yes or no classification the expert’s rules might not be clearly understood or expressed, and the user might be unsure of the answers to the questions. So the researcher recommend for the future works on this area to use some probabilistic technique to deal with uncertainty.
The knowledge was collected from limited experts and might not be enough so future work should consider adding to the knowledge to make it complete and could also work on insects pest management.

To develop these KBSs, SWI-prolog editor environment was used, but to make this system more interactive and make life easy for potential users, other visual user interface tools should be used, such as Java and C#.

Reference
ICARDA, “Ethiopia and ICARDA”,Ties that Bind. No. 29. ISBN: 92-9127-245-0 ICARDA, Aleppo, Syria, iv+20 pp. En, 2010.

Mellor, J. and Dorosh, “Agriculture and the Economic Transformation of Ethiopia Development Strategy and Governance Division: Ethiopia Strategy Support Program 2.”International Food Policy Research Institute, 2010.

National Bank of Ethiopia (NBE), Annual Report. Addis Ababa, Ethiopia, 2006.

CSA, “Area and Production of Major Crops”. Sample Enumeration Survey. Addis Ababa, Ethiopia, 2009.

K. Berhe, Y. Dessalegn, Y. Baredo, W. Teka, and A. Tegegne, “Smallholder-based fruit seedling supply system for sustainable fruit production in Ethiopia”, Improving Productivity and Market Success (IPMS) of Ethiopia Farmers Project, Addis Ababa, Ethiopia, 2007.

CSA, “Area and Production of Major Crops”. Sample Enumeration Survey. Addis Ababa, Ethiopia, 2012.

Lakshmi, B.K.M., P.N. Reddy and R.D. Prasad, “Cross-infection Potential of Colletotrichum gloeosporioides Penz. isolates causing Anthracnose in subtropical fruit”, Tropical Agriculture Research, 22(2): 183-193, 2011.

Central Intelligence Agency (CIA).: Banana in Southern Region of Ethiopia, pp: 119-134, 2010.

Edward A. Evans, “Recent Trends in World and U.S. Mango Production, Trade, and Consumption”,University of Florida, United state of America. Pp 4, 2005.

E. Etisa, L. Ayele and D. Tadesse, “Review on the status of some tropical fruits in Ethiopia”, Proceeding of the inaugural and first Ethiopian Horticultural Society conference. Addis Ababa, Ethiopia. Pp39-44, 2006.

C.S.A (Central Statistics Authority), Addis Ababa, Ethiopia, 2012/2013
M. Dawd, B. H/Gabriel and Seyoum Hailemariam, “White mango scale: A new insect pest of mango in western Ethiopia”,. Addis Ababa. Ethiopia. 257-267pp. 2012.

Borchsenius, N. S. “A catalogue of the armoured scale insects (Diaspidoidea) of the World”. In Russian.) Nauka, Moscow, Leningrad, Russia. 449 pp, 1966.

Daneel, M. S. and S. Dreyer , “Biological control of the mango scale, Aulacaspis tubercularis,in South Africa”Yearbook-South African Mango Growers’ Association. 18: 52-55. 4 ref, 1998.

T. H. Terefe, S. Tsegaye, and T. Wakuma, “Alert White Mango Scale Insect ‘ s Infestations and Its Implications in Guto Gida and Diga Distrcts of East Wellega Zone by,” vol. 2, no. 2, 2014.

A. Kumar Gupta and D.M, “Bireshwar Computational Model for Agricultural Decision Support System,” International Journal of Computer Applications (0975 – 8887), vol. 66, No.15, pp. 1-2, 2013
S. Dubey, R. Pandey and S. Gautam, “Literature Review on Fuzzy Expert System in Agriculture”, International Journal of Soft Computing and Engineering (IJSCE), vol. 2, pp. 289-290, 2013
S. Marwaha, “AGRIDAKSH—A TOOL FOR DEVELOPING ONLINE EXPERT SYSTEM,” Division of Computer Applications, Indian Agricultural Statistics Research Institute, pp.17, 2012.

J. H. Frenster, “Expert systems and open systems in medical artificial intelligence. Proc. Am. Assoc. Medical Systems and Informatics, Congress 89 (7). 118-120. San Francisco, California, 1989.

Dudam, RO and Shortliffe, EH, “Expert system research”, Journal of American Society of Information Science 220(4594), 1983.

Turban, E. and Aronson, J.E, “Decision Support and Intelligent Systems”. New Jersey:Prentice Hall International,Inc, 1990.

Russell, S. and P. Norvig, “Artificial Intelligence: A Modern Approach. 2nd Edn”, Prentice Hall, Englewood Cliffs, NJ, 2004.

Ranjan Y, “Farm Advisory System for Farmers of Northeastern states of India,” international journal of innovations in Engineering and Technology (IJIET), vol. 5, pp. 169-172, 2015.

S.N. Islam, “Expert System on Wheat Crop Management,” Development of Expert System through AGRIdaksh, New Delhi, 2004.

Diao et al, “Agricultural growth linkages in Ethiopia: Estimates using Fixed and Flexible Price Models” IFPRI Discussion Paper No. 00695. pp. 1- 41, 2007.

MoARD (Ministry of Agriculture and Rural Development), “Improved technologies and resource management for Ethiopian agriculture”, A Training Manual. RCBP-MoARD, Addis Ababa, Ethiopia, 2009.

J. Griesbach, “Mango growing in Kenya”. World Agro forestry Centre (ICRAF). Nairobi, Kenya, 2003.

Lakshmi, B.K.M., P.N. Reddy and R.D. Prasad, “Cross-infection Potential of Colletotrichum gloeosporioides Penz. isolates causing Anthracnose in subtropical fruit”, Tropical Agriculture Research, 22(2): 183-193, 2011.

CIA (Central Intelligence Agency). World Fact book, accessed on July, Daniel : Banana in Southern Region of Ethiopia, pp: 119-134, 2017
S.S. Abu-Naser, K.A. Kashkash and M. Fayyad,”developing an expert system for plant disease diagnosis” Journal of Arteficial Intelligence, faculty of Engineering and Information Technology, Al- Azhar University, Gaza, Palestine, 2008.

T. Bezu, “Production Scenarios of Mango (Mangifera indica L.) in Harari Regional State, Eastern Ethiopia”, science, Technology and Arts Research Journal, Haramaya University, Dire Dawa, Ethiopia, 2014.

Blackmore, B, “Developing the principles of precision farming”, Proceedings of Agrotech 99, Barretos, Novemeber 15-19, Barretos Institute of Technology, Brazil, pp: 133-250, 1999.

Blackmore, B, “Using Information technology to improve crop management”, Proceedings of AgMet Millennium Conference, Feb. 29, Institut for Jordbrugsvidenskab, Dublin, pp: 30-38, 2000.

Satrio Dewanto and Jonathan Lukas ,”Experet system for diagnosis pest and disease in fruit plants”, EPJ Web of Conferences, Universitas Bina Nusantara, Computer Engineering Department, Jakarta, Indonesia, 2014.

P. Mercy and N. Rani1 ,” Expert Systems in Agriculture: A Review”, Journal of Computer Science and Applications, Volume 3, Number 1 , pp. 59-71, India, 2011.

T. Singh, “Prototype Expert System for Diagnosis and Treatment of Diabetes”, Graduate Project, USA, 2001.

T. Aboneh, “Knowledge based system for pre-medical triage treatment at Adama University Asella Hospital”. Master’s Thesis, Addis Ababa University, Ethiopia, 2013.
A. Salem, “Case Based Reasoning Technology for Medical Diagnosis”, World Academy of Science, Engineering and Technology, 2007.

B. Henok, “A case based reasoning knowledge based system for hypertension management”, Msc. Thesis, Addis Ababa University, Ethiopia, 2011.

Dipanwita, B, S Bairagi, N Panse and N Shinde, “Disease diagnosis system”, Journal of Computer Science & Informatics, 1(2), 48–51, 2011.

“Growth and Transformation Plan (GTP) 2010/11-2014/15,” Ministry of Finance and Economic Development (MOFED), Addis Ababa, Nov 2010.
B. Ambachew, ” Knowledge Based System for Oilseed Crop Disease Diagnosis and Treatment,” vol. 1, no. A thesis submitted in partial fulfillment of the requirements for the degree of Master of Information science, 2015.

E. Tefera, “Developing Knowledge Based System For Cereal Crop Diagnosis And Treatment: The Case Of Kulumsa Agriculture Research Center,” vol. 1, no. A thesis submitted in partial fulfillment of the requirements for the degree of Master in Information science , 2012.
B. Asferi, “Exploring Pest Management Practices and Development of Knowledge Base System for Pepper Disease Diagnosis,” no. Master thesis Addis Ababa University, 2010.
S. Hussen and Z. Yimer, “A s s e s s m e n t o f P r o d u c t i o n P o t e n t i a l s a n d C o n s t r a i n t s o f M a n g o ( M a n g i f e r a i n d i c a ) a t B a t i , O r o m i y a Z o n e , E t h i o p i a,” pp. 1–9.

H. Takele, “Review of mango value chain in Ethiopia.” Journal of biology, agriculture and health care, vol. 4, no. 25, pp. 230–240, 2014
CSA, “Agricultural sample survey report on area and production of major crops in 2013/14”. Statistical Bulletin 532, Addis Ababa, Ethiopia, 2014.

Y. Dessalegn, H. Assefa, T. Derso, and M. Tefera, “Mango Production Knowledge and Technological Gaps of Smallholder Farmers in Amhara Region , Ethiopia,” pp. 28–39.

W. M. Haggag, “Mango diseases in Egypt”, Department of Plant Pathology National Research Center, Dokki, Cairo, Egypt. ISSN Print: 2151-7517, ISSN Online: 2151-7525, Agric. Biol. J. N. Am., 2010.

U. Nations and C. On, “United Nations Conference On Trade And Development,” 2016.

Dr. G. Thiribhuvanamal, “Major Diseases of Horticultural Crops and this Management”, Department of Plant Pathology Centre for Plant Protection Studies, Tamil Nadu Agricultural University, pp. 294-302.

A. Gultie and S. Sahile, “Assessment of Fruit Management in Gondar town Markets of North Western Ethiopia,” vol. 2, no. 4, pp. 4–8, 2013.

WHO, “Reducing risks, promoting health”, The World Health Report, Geneva, 2002.

Spackman A. and P. Connelly, “Knowledge based systems in laboratory medicine and pathology: A review and survey of the field.”, Arch Path Lab Med, 78(3): 271–282, 1987.

Tutorials Point, “Artificial Intelligence for Beginners,” vol. 1, 2015.

R. A. Priti Srinivas Sajja, “Advanced Knowledge Based Systems: Model, Applications & Research,” vol. 1, pp. 1-11, 2010.

G. Dagnew, “Designing A Knowledge Based System For Blood Transfusion,” 2012.

K. D. Pradipta and R. D. Chandrasekhar , “Rtificial Intelligencelecture Notes for Bachelor of Technology in Computer Science and Engineering & Information Technology”.
A. Pannu, “Artificial Intelligence and its Application in Different Areas,” vol. 4, no. 10, 2015.
G. Avram, “Empirical Study on Knowledge Based Systems,” vol. 8, no. 1, pp. 11-20, 2005.
E. Feigenbaum, “Knowledge-Based Systems In Japan,” 1993.
Yelapure, Jadhav and Babar, “Knowledge based System for Tomato Crop with SpecialReference to Pesticides,” 2011.

B. Ambisa, “develop a knowledge based system for coffee diseases and pests diagnosis and treatment ” vol. 1, no. A thesis submitted in partial fulfillment of the requirements for the degree of Master of Information science, 2012.

S. Esseynew, “Prototype Knowledge Based System for Anxiety Mental Disorder Diagnosis,” 2011.

S. D. Seifu, “The Potential For Applying Knowledge Base System for Diagnosis of Acute Respiratory Tract Infections,” 2010.

H. Bekele, “A Case Based Reasoning Knowledge Based System for Hypertension Management,” 2011
D. Jones And . B. J.R., “Building Expert Systems,” 1989.

D. Lake, “Web-Based Expert System For Cattle Diseases Diagnose,” 2013.
T. A. Alemu, “Application Of Case Based Recommender System In The Tourism Sector For The Selection Of Tourist Attraction Areas In Ethiopia,” 2014.

A. Mohammed, “Towards Integrating Data Mining with Knowledge Based System: The Case of Network Intrusion detection,” 2013.

S. Gebremariam, “A Self-Learning Knowledge Based System for Diagnosis And Treatment of Diabetes,” 2013.

T. Mulugeta, “Integrating Data Mining Results With The Knowledge Based System for Diagnosis And Treatment of Visceral Leishmaniasis,” 2015.

D. A. Abetwe, “Application Of Knowledge Based System For Woody Plant Species Identification,” 2009.
Online. Available: http://intelligence.worldofcomputing.net/knowledge-representation/frames.html#.V39aV_lTLIU.

Online. Available: http://intelligence.worldofcomputing.net/knowledge-representation/frames.html#.V39aV_lTLIU.

D. K. BASHA, “DESIGNING A KNOWLEDGEBASE SYSTEM FOR VAT ADMINISTRATION,” 2009.

Online. Available: http://cis-linux1.temple.edu/~pwang/3203-AI/Lecture/KBS.htm.

(. t. A. Intelligence. Online. Available: http://cis-linux1.temple.edu/~pwang/3203-AI/Lecture/KBS.htm.
T. Kelela, “Knowledge Based Reasoning for Agricultural Crop Management Decisions,” vol. I, no. An Experiment Using Rule Based and Artificial Neural Network, Master thesis Addis Ababa University, 2009.
R. Jain, “Expert Systems with Applications PulsExpert?: An expert system for the diagnosis and control of diseases in pulse crops,” Expert Syst. Appl., vol. 38, no. 9, pp. 11463–11471, 2011.

V. Lo and O. Lo, “JAPIEST?: An integral intelligent system for the diagnosis and control of tomatoes diseases and pests in hydroponic greenhouses,” vol. 35, pp. 1506–1512, 2008.

Yelapure,S. J., Jadhav, S. K. and Babar, V. M.. Knowledge based System for Tomato Crop with Special Reference to Pesticides. International Journal of Computer Applications (IJCA) 25, 2011.

F. A. Gobena,” Web Based Agronomy Advisory System: the Case of Cereal Crops”, Addis Ababa University, 2014.

Pearson Education, “Chapter 18 – Knowledge Acquisition, Representation, and Reasoning”, Available at: http://wps.prenhall.com/wps/media/objects/3778/3869053/Turban_Online_Chapter_W18.pdf, Accessed date: June 02, 2017.

Y. Erdania and Indonesien, “Acquisition of Human Expert Knowledge for Rule-based Knowledge-based Systems using Ternary Grid”, 2005.

P.H. Jones, “Knowledge Acquistion: Knowledge Engineering in Agriculture”, Available at: https://engineering.purdue.edu/~engelb/abe565/knowacq.htm, Accessed date: October 17, 2017.

From paper Mango Diseases and Pests_ Mango Resources Information System, Available at: htm1 , Accessed date: October 17, 2017.

G. Sefu, N. Satheesh, and G. Berecha, “Effect of Essential Oils Treatment on Anthracnose ( Colletotrichum gloeosporioides ) Disease Development , Quality and Shelf Life of Mango Fruits ( Mangifera indica L ),” vol. 15, no. 11, pp. 2160–2169, 2015.

T. Savolainen, D. Beeckmann, P. Groumpos, and H. Jagdev, “Positioning of Modeling Approaches, Methods and Tools”, Computers in Industry, Vol.25, pp.255-262, 1995.

G. Booch, J. Rumbaugh, and I. Jacobson, “The Unified Modelling Language User Guide”, Addison Wesley, Reading, Massachusetts, 1999.

S. K. Sarma and K. R. Singh, “An Expert System for diagnosis of diseases in Rice Plant This paper presents an architectural framework of an Expert System in the area of agriculture and describes the design and development of the rule based expert system is intended for the diagnosis o,” no. 1, pp. 26–31.

R. Gashaw, “A Web based Expert System for Diagnosis of Disease and Pest in Ethiopian Coffee,” 2011.

Kassa Belay, Degnet Abebaw , “Challenges Facing Agricultural Extension Agents Case Study from South-western Ethiopia,” Blackwell Publishing Ltd., United Kingdom , 2004.
J. F. Dirou and D. Horticulturist, “Blight diseases in mangoes,” pp. 1–3, 2004.

K. Pernezny, R. Ploetz, P. Pathology, and E. Re-, “Some Common Diseases of Mango in Florida,” 2000.

S. C. Nelson, “Mango Powdery Mildew,” 2008.