Comparative Analysis of Mamdani, Sugeno and Tsukamoto Fuzzy Inference Systems to Support Decisions on Selecting Outstanding Employees

Abstract

The awarding of exceptional employees is founded on legality, objectivity, and transparency, as determined by authorized officials following a rigorous assessment process. However, it has been observed that during the assessment procedure, there are instances where the established principles of objectivity may be compromised. To address this challenge, the utilization of the Fuzzy Logic Method is proposed as a means to enhance the decision-making process in evaluating outstanding employees. This method involves the comparison of three distinct Fuzzy Inference Systems (FIS): the Mamdani, Sugeno, and Tsukamoto Methods. The employment of these methods ensures the attainment of precise calculation outcomes. The proposed approach involves the incorporation of attendance, performance, and behavior data as input variables, with employee assessments serving as the output variables. The study was conducted using input data from three employees in the form of attendance, performance, and behavior data, as well as a set of rules (rule sets) determined by experts. The results of the study indicate that the Tsukamoto fuzzy inference system provides accurate and appropriate assessments for the decision-making process involving various sets of rules.