Affiliation:
1. Tamil Nadu Agricultural University, India
2. Hindusthan College of Arts and Science, India
Abstract
Fuzzy expert systems are designed based on fuzzy logic and deal with fuzzy sets. Many fuzzy expert systems have been developed for diagnosis. Fuzzy expert systems are developed using fuzzification interface, enhanced fuzzy assessment methodology, and defuzzification interface. Fuzzification helps to convert crisp values into fuzzy values. By applying the enhanced fuzzy assessment methodology for rice, the yield parameters of rice can be diagnosed with number of tillers per hill, number of grains per panicle, and 1000 grain weight. Pest and disease incidence becomes simple for scientists. Enhanced fuzzy assessment methodology for rice uses triangular membership function with Mamdani's inference and K Ratio. Defuzzification interface is adopted to convert the fuzzy values into crisp values. Performance of the system can be evaluated using the accuracy level. Accuracy is the proportion of the total number of predictions that are correct. The proposed algorithm was implemented using MATLAB fuzzy logic tool box to construct fuzzy expert system for rice.
Reference20 articles.
1. Sarma, Singh, & Singh. (2010). An Expert System for diagnosis of diseases in Rice Plant. International Journal of Artificial Intelligence, 1(1), 26–31.
2. Brar, D. S., & Khush, G. S. (2002). Article. In M. S. Kang (Ed.), Transferring genes from wild species into rice, in Quantitative Genetics, Genomics and Plant Breeding (pp. 1–41). Oxford, UK: CABI.
3. A fuzzy expert system for fault detection in statistical process control of industrial processes
4. Induction of fuzzy rules and membership functions from training examples
5. Development of project cost contingency estimation model using risk analysis and fuzzy expert system