Teacher discipline assessment with Mamdani Fuzzy Logic decision support system on attendance data at Phatnawitya School Yala

Abstract

Teacher discipline is a crucial factor in maintaining the quality of the learning process in schools; however, discipline assessment is often conducted subjectively and relies on rigid threshold values. This study aims to develop a decision support system based on Mamdani Fuzzy Logic to evaluate teacher discipline using attendance data. The research method includes fuzzification, Mamdani fuzzy inference, and defuzzification using the centroid method, with two input variables attendance and absence without permission (alpha) and one output variable in the form of a discipline score. The results indicate that teachers with attendance ≥90% and alpha ≤3 days are classified as “Very Good”, those with attendance between 80-89% fall into the “Good” to “Fair” categories, while attendance below 75% or alpha above 12 days is categorized as “Poor”. The fuzzy system produces consistent, stable, and flexible assessments through gradual value transitions. In conclusion, Mamdani Fuzzy Logic is effective as a more objective and realistic tool for evaluating teacher discipline compared to conventional threshold-based methods.