Comparative analysis of Mamdani, Larsen and Tsukamoto methods of fuzzy inference system for students’ academic performance evaluation

Abstract

Over the last few years, the use of the fuzzy logic technique for evaluating performance in the teaching-learning process is growing rapidly. In this research work, three different fuzzy inference methods: Mamdani fuzzy inference method, Larsen fuzzy inference method and Tsukamoto fuzzy inference method have been proposed for students' academic performance appraisal for multi-input variables. To obtain a degree of satisfaction, the Triangular membership function is used. The results of experiments showed the best fuzzy inference method among Mamdani, Larsen and Tsukamoto. We have also compared the results with the existing statistical method.