Expert System Using Fuzzy Logic Computer Science Essay

Published: Last Edited:

This essay has been submitted by a student. This is not an example of the work written by our professional essay writers.

This paper describes the suitability of application of expert system using Fuzzy Logic (FL) technology in agriculture and proposes the development of a rule-based expert system, named SITAPAL( It is Hindi Language Word and it means Custard Apple), for the efficient management of the custard apple. The proposed system uses the knowledge of visual deficiency symptoms, evident in the plants, to diagnose the nutrients deficiency/excess in the custard apple crop. This system has been developed in the Microsoft VB.Net environment. The visual deficiency symptoms of all the essential elements have been included in the knowledge base of the expert system. The system first finds out the deficiency/excess of nutrients in the soil and then recommends the name of suitable fertilizer taking in consideration some chemical properties of the soil. The results given by the system have been found to be consistent and sound. However, the diagnosis result has been found to be more accurate in the case of sever deficiencies.

Keywords: expert system; knowledge base; Fuzzy Logic; Visual Basic.Net


Expert Systems is one of the important application oriented branches of Artificial Intelligence in last two decades, a great deal of expert systems had been developed and applied to many fields such as office automation, science, medicine and agriculture. All of us directly or indirectly depend on agriculture from where come commodities to feed the living beings. In the developing countries like India, Pakistan, Bangladesh, Israel, Egypt and African countries, agriculture is the occupation of major portion of population. However, agricultural practices are more manual and technically non-advanced in comparison to developed countries. The potential benefits of applying expert systems to agriculture management have been identified for several years. The days of printed notes are gone and computer based solutions are welcomed. The production of crop depends on so many factors like fertility of the soil, type of seed, climatic condition, water logging, application of fertilizers, pest and disease control etc. For better yields every factor requires proper planning and management that in turn needs correct decision making from farmers based on information and knowledge obtained from different related areas. Fuzzy systems are an alternative to traditional notions of set membership and logic that has its origins in ancient Greek philosophy, and applications at the leading edge of Artificial Intelligence. Yet, despite its long-standing origins, it is a relatively new field, and as such leaves much room for development.


Expert system evolved as first commercial product of Artificial Intelligence and is now available in large number of areas specially related with decision-making. The appropriateness of this technology has also been recognized and realized in the field of agriculture and several successful systems have been developed. The modern time agriculture requires information and application of knowledge from different interacting fields of science and engineering to do appropriate decision-making that in turn depends on interplay of this information and knowledge.



Rule based programming is one of the commonly used techniques to develop expert system and the same has been used in the present work too. A typical rule-based expert system integrates a problem domain specific knowledge base, an inference engine and the user interface. The system is capable in using its internal knowledge and rules to formulate its own solution procedure based on problem definition. The proposed system has the following four functional modules:

(i) Knowledge base

(ii) Inference engine

(iii) Intelligent User's interface

(iv) Explanation module

The interconnection and arrangement of these modules is shown in Fig.1. The present system has been developed in the visual basic environment, which works as an inference engine in backward chaining. The development process of the expert system is very systematic and can be carried out in different stages The whole process followed has been presented in the flow chart diagram shown in the Fig.2. The Knowledge Base of the present system consists of two modules. First module of the knowledge base for identification pest and other is for recommending appropriate pesticide.

Figure 1: Interconnection between modules


We defined the control objectives and criteria

Determine the input and output relationships and choose a minimum number of variables for input to the FL engine (typically error and rate-of-change-of-error).

Using the rule-based structure of FL, break the control problem down into a series of IF X AND Y THEN Z rules that define the desired system output response for given system input conditions. The number and complexity of rules depends on the number of input parameters that are to be processed and the number fuzzy variables associated with each parameter. If possible, use at least one variable and its time derivative. Although it is possible to use a single, instantaneous error parameter without knowing its rate of change, this cripples the system's ability to minimize overshoot for a step inputs.

Create FL membership functions that define the meaning (values) of Input/Output terms used in the rules.

Test the system, evaluate the results, tune the rules and membership functions, and retest until satisfactory results are obtained.


The knowledge acquisition is most important part of this project. It done for the proposed system from two sources namely human expert and by gleaning the useful knowledge from the standard references. Efforts have been made to collect more and more heuristic knowledge to identify the pests based on deficiency symptoms. The deficiency symptoms related crop have been included.

The following information is collected from a domain knowledge person.

Custard Apple (Annona Squamosa), Popularly known as "Sitaphal" in southern side of India. The ripe fruit is very delicious and nutritionally valuable with 20-22% sugars. It is tropical origin and cannot stand frost or prolonged cold periods. Fruits become hard and do not ripen in severe cold weather. It grows well in low to medium altitudes with warm winters and moderate summers. The custard apple is generally propagated by seed. But the plants obtained by seed propagation differ markedly in fruit size, yield and quality. Pits of 0.5 X0.5 X0.5 m are dug at 2-4m apart depending upon the soil fertility. Two baskets or 20kg FYM and 300g super phosphate are incorporated at the time of filling the pit.


Fig 2.0 : Welcome screen to the expert system

Fig 3.0 : Main Menu

The above is main entry screen. The user can select the option to navigate the expert system. The screen shows the various modules of the system. The modules are Planting, Climatic and soil requirements, Pests and Diseases, Harvesting, Yield and Ripening, About Custard Apple, and Marketing Opportunities.

Fig 4.0 : Planting Information System

The above screen is showing the module planting. When the user chooses the present season is Autumn and asking the result to start the plantation the system is responding with answer "NO". If the user asks the question why? It shows as "THE CUSTARD APPLE PLANATION IS NOT POSSIBLE IN AUTUMN SEASON.

Fig 5.0 : Expert Advices about the Sitapal

All the above all modules are prepared. Because of the lack of space here, we are not showing the results. This software is free software. It will be kept on the web. The web portal is Select the downloads and you can find the complete information.


Integrating Fuzzy logic and Expert Systems under a unified framework in agriculture domain is very important task specially in scheduling system like Agriculture This paper presents an Expert system using fuzzy logic. This system provides a hierarchical representation of the problem solving methods, tasks and primitive problem solving methods (inference step). It also contains generic domain knowledge, i.e. the part of the domain knowledge that can be reused in other similar agriculture scheduling systems without modification. This system also helps the knowledge engineer to build a new simpler, quicker and more effective system, and reusing the already existing components in similar systems. The developers can generate or update their systems to include the growing expertise and techniques. The system is in beta testing and many farmers expressed their views. We are welcoming your views to improve the sustainability of agriculture in developing countries. The future scope of this system is to develop system with local languages of India like Telugu, Hindi and other.