FUZZY EXPERT SYSTEM.pptx

Description of fuzzy expert system

1. SUBMITTED BY-BISWARUP DAS SEMESTER-10 TH ROLL NO-04 PRESENTATION ON FUZZY EXPERT SYSTEM

2. CONTENTS INTRODUCTION OVERVIEW OF EXPERT SYSTEM COMPONENTS OF FUZZY EXPERT SYSTEM FUZZY RULES LINGUISTIC VARIABLES FUZZY EXPERT SYSTEM CONSTRUCTION OF FUZZY EXPERT SYSTEM DESIGN PROCEDURE APPLICATIONS CONCLUSION REFERENCES

3. INTRODUCTION According to Webster an EXPERT is – “ One with special skill or knowledge representing mastery of particular subject ”. In every domain, there exist someone who has adequate knowledge about certain parts of that domain. However it is not possible for every person to master every knowledge of that domain. Experts is being defined as per their capabilities to solve particular task of that domain.

4. OVERVIEW OF AN EXPERT SYSTEM Problems that are often tackled by human experts are handled by expert systems. It requires the following:- - a substantial knowledge base - a good inference engine - an effective user interface that can engage with consumers to address issues related to the specific area for which it was created. It acquires knowledge from human experts through the knowledge acquisition process.

5. Architecture of an expert system

6. Architecture of fuzzy Expert

7. COMPONENTS OF FUZZY EXPERT SYSTEM Knowledge base:- It contains the fuzzy production rules(e.g.-if A then B). Inference Engine:- In this, it uses two approaches to make fuzzy inferences based on a set of production rules:- - Data driven - Goal driven Meta knowledge base:- Basically, it includes guidelines for using production rules in the knowledge base. Explanatory Interface:- It creates a channel of communication between the user and the system and outlines how the system will provide the user with a solution to their problem. Knowledge Acquisition Module:- It obtains relevant knowledge from human experts in order to update the knowledge and meta knowledge base.

8. FUZZY RULES A fuzzy rule is a conditional statement in the form of: - IF x is A - THEN y is B x and y are linguistic variables . A and B are linguistic values determined by fuzzy sets on the universe of discourses X and Y respectively.

9. Linguistic Variables A linguistic variable is fuzzy variable -e.g. the fact “Jack is tall” implies linguistic variable “Jack” takes the linguistic value “tall”. Use linguistic variables to form fuzzy rules: - If ‘project duration’ is long THEN ‘risk’ is high - If risk is very high THEN ‘project funding’ is very low

10. Fuzzy Expert System A fuzzy expert system is an expert system that uses fuzzy rules, fuzzy logic, and fuzzy sets. A fuzzy logic system will occasionally activate many rules - If the antecedent is true to some degree of membership, then the consequent is true to same degree.

11. Fuzzy Expert System Two distinct fuzzy sets describing tall and heavy:

12. Fuzzy Expert Systems IF height is tall THEN weight is heavy

13. Fuzzy Expert Systems Other Examples (multiple antecedents) -e.g. IF ‘Project duration’ is long AND ‘Project staffing’ is large AND ‘Project funding’ is inadequate THEN risk is high e.g. IF service is excellent OR food is delicious THEN tip is generous

14. Construction O f Fuzzy E xpert System Knowledge Representation:- -- knowledge can be represented by three ways- 1. Rules: If PREMISE then CONCLUSION 2. SEMANTIC NET: Class of knowledge representation formalism using nodes and arcs. 3.Frame: U sing slots and values, a data structure can represent typical scenarios . Inference Engine:- Uses knowledge in a specific representation to reach an expert conclusion or provide expert advice. -- Operates on two basic ways- 1) Forward Chaining: Data Driven(e.g. XCON) 2) Backward Chaining: Goal Driven(e.g. MYCIN)

15. Design Procedure Starting with some level of preparation and pre-processing is necessary to identify the issue. Next, inference method has to be determined. Basically there are two methods- 1) Mamdani Method 2) Takegi- sugeno- kang Method The choice of inference method is entirely dependent on the choice of defuzzification method. The process of enumerating linguistic variable is to be carried out after these selections have been made. Next stage is to determine membership functions and the fuzzy rules that maps fuzzy facts to fuzzy conclusions. After creating the rules, they are tested against some desired outputs in order to do optimization and accuracy.

16. Applications Agricultural Field:- - VARIEX:- It enables selection of best cultivators for diverse agricultural situations . Sports:- -Goalkeeper quality recognition( Bazmara , jafari ). Computer Engineering:- - Fuzzy Controllers. Mechanical Engineering:- - Emulation of complex production system.

17. Conclusion Fuzzy expert system are one of the most significant game changers in the field of computation. However, it has a number of drawbacks and difficulties. To design a system that overcomes these drawbacks and provides an efficient solution regarding its task domain is a very important and challenging task. If we can able to do so, then it will provide an unmatched power to the problem solving domain.

18. References Rich, Elain ; Knight, kevin ; Artificial Intelligence, Third edition. Klir , George J,; Yuan, Bo; fuzzy sets and Fuzzy Logic –Theory and applications. Garibaldi, Jonathan M.; Fuzzy Expert Systems. Kandel , Abraham ; Fuzzy Expert Systems; CRC press. Web References https://www.merriam-webster.com/dictionary/expert

19. THANK YOU