Fuzzy Expert System in Agriculture Domain

Fuzzy Expert System in Agriculture Domain

M. Kalpana (Tamil Nadu Agricultural University, India) and A. V. Senthil Kumar (Hindusthan College of Arts and Science, India)
Copyright: © 2020 |Pages: 15
DOI: 10.4018/978-1-5225-9175-7.ch001


Agriculture is an important source of livelihood and economy of a country. Decision making plays an important role in various fields. Farmers are the backbone of agriculture. They need expert systems to make decisions during land preparation, sowing, fertilizer management, irrigation management, etc. for farming. Expert systems may suggest precisely suitable solutions to farmers for all the activities. Uncertainty deals with various situations during sowing, weed management, diagnosis of disease, insect, storage, marketing of product, etc. Uncertainty is compounded by many facts that many decision-making activities in agriculture are often vague or based on perception. Imprecision, vagueness, and insufficient knowledge are handled using the concept of fuzzy logic. Fuzzy logic with expert systems helps find uncertain data. Fuzzy expert systems are oriented with numerical processing.
Chapter Preview

Fuzzy Logic

Fuzzy logic acts in the way as that of human. It helps to model our sense of word and from that, the decision are made. As it thinks like a human, it is termed as intelligent system. Fuzzy logic follows many value logic in which truth values of each variable shape is real numbers between 0 and 1. In computer science, fuzzy logic handles imprecise and vague, ideas may be represented as “low”, “medium” or “high”. Fuzzy logic used in the field of agriculture for decision making.

Key Terms in this Chapter

Fuzzy Rule: Fuzzy rule is a conditional statement. The form of fuzzy rules is given by IF THEN statements. If y is B THEN x is A, where x and y are linguistic variables, and A and B are linguistic values determined by fuzzy sets.

Heuristic Knowledge: Knowledge regarding practice, accurate judgment, one’s ability of evaluation, and guessing.

Expert System: Expert system is a computer-based program which performs like a human expert in a narrow domain. The components of the expert system are the knowledge base, the database, the inference engine, the explanation facilities and the user interface.

Factual Knowledge: Information widely accepted by the knowledge engineers and scholars in the task domain.

Artificial Intelligence (AI): Artificial intelligence is branch of computer science; the machine behaves in the way as a human thinks and is considered an intelligent system.

Production Rule: A statement expressed in the IF (antecedent) THEN (consequent) form. If the antecedent is true, then the consequent is also true.

Aggregation: Aggregation is the third step in fuzzy inference. It is the process of combining clipped or scaled consequent membership functions of all fuzzy rules into a single fuzzy set for each output variable.

Fuzzy Logic: Fuzzy logic is multi-valued and handles the concept of partial truth. A system of logic developed for representing conditions that cannot be easily described by the binary terms “true” and “false.” The concept was introduced by Lotfi Zadeh in 1965.

Knowledge: Knowledge is to understand the subject theoretically or practically. Knowledge helps us to make a correct decision.

Knowledge Representation: Method used to organize and formalize the knowledge in the knowledge base. It is in the form of IF-THEN-ELSE rules.

Fuzzy Inference: Fuzzy inference process is based on fuzzy logic. The steps in fuzzy inference are fuzzification of the input variables, rule evaluation, aggregation of the rule outputs and defuzzification.

Fuzzy Variable: A quantity that can take on linguistic values. For example, the fuzzy variable “disease” might have values such as “low,” “medium,” or “high.”

Defuzzification: Defuzzification is the last step in fuzzy inference mechanism. The process of converting fuzzy values from the combined output of fuzzy rules in crisp values (numerical values). The input to the defuzzification process is an aggregate set and the output from this process is a single number.

Fuzzy Expert System: A fuzzy expert system is the combination of expert system and fuzzy logic. In expert system fuzzy logic is used instead of Boolean logic. A fuzzy expert system is a collection of fuzzy rules and membership functions that are used to reason data. In conventional expert system uses symbolic reasoning, fuzzy expert system is toward numerical processing.

Antecedent: Antecedent is a part of IF rule. It is a conditional statement.

Inference Engine: Inference engine is one of the basic components of an expert system that carries out reasoning whereby the expert system reaches a solution. It matches the rules provided in the rule base with the facts contained in the database.

Information: Available resources like survey on experimental data, literature maps, digital form of photographs.

Forward Chaining: Forward chaining is the strategy of working forward for conclusion/solution of a problem.

Fuzzy Set: Fuzzy set is expressed as a function and the elements of the set are mapped into their degree of membership. A set with the fuzzy boundaries are “hot,” “medium,” or “cold” for temperature.

Membership Function: Membership function is a mathematical function that defines a fuzzy set on the universe of discourse. Membership functions used in fuzzy expert systems are triangles, trapezoid and Gaussian function.

Fuzzification: Fuzzification is the first step in the fuzzy inference mechanism. The process of mapping the crisp (numerical) value into its degrees to which the inputs belong to the respective fuzzy sets.

Intersection: In set theory, an intersection between two sets contains elements shared by all sets. For example, the intersection of short men and tall men contains all men who are short and tall. In fuzzy set theory, an element may partly belong to both sets, and the intersection is the lowest membership value of the element in both sets.

Certainty Factor: A number assigned to a fact or a rule to indicate the certainty or confidence, with this value fact or rules are validated.

Fact: Fact is a statement has the property of being either true or false.

Linguistic Variable: A Linguistic variable has values that are language elements, such as words and phrases. In fuzzy logic, terms linguistic variable and fuzzy variable are synonyms.

Degree of Membership: A numerical value between 0 and 1 that represents the degree to which an element belongs to a particular set.

Knowledge Engineers: The knowledge engineer is a person with the qualities of empathy, quick learning, and case analyzing skills.

Knowledge Base: Knowledge base is a basic component of an expert system that contains knowledge about a particular domain.

Complete Chapter List

Search this Book: