Rule-Based Mamdani-Type Fuzzy Modeling of Perceived Stress, And Cortisol Responses to Awakening

In this paper, Two Mamdani type fuzzy models (four inputs–one output and two inputs–one output) were developed to test the hypothesis that high job demands and low job control (job strain) are associated with elevated free cortisol levels early in the working day and with reduced variability across the day and to evaluate the contribution of anger expression to this pattern. The models were derived from multiple data sources including One hundred five school teachers (41 men and 64 women) classified 12 months earlier as high (N = 48) or low (N = 57) in job strain according to the demand/control model sampled saliva at 2-hour intervals from 8:00 to 8:30 hours to 22:00 to 22:30 hours on a working day. The quality of the model was determined by comparing predicted and actual fuzzy classification and defuzzification of the predicted outputs to get crisp values for correlating estimates with published values. A modified form of the Hamming distance measure is proposed to compare predicted and actual fuzzy classification. An entropy measure is used to describe the ambiguity associated with the predicted fuzzy outputs. The four input model predicted over 70% of the test data within one-half of a fuzzy class of the published data. The two input model predicted over 40% of the test data within one-half of a fuzzy class of the published data. Comparison of the models show that the four input model exhibited less entropy than the two input model.