Fuzzy Modeling of Subjective Workload Score
This project was concerned with the development of a computer model to estimate the subjective workload score of individuals by evaluating the heart rate signals. The identification of a model to estimate subjective workload score of individuals under different workload situations is a too ambitious task since different individuals (due to different body conditions, emotional states, age, gender, etc.) show different physiological response (assessed by evaluating heart rate signal) under different workload situations. This is equivalent to say that the mathematical mappings between physiological parameters and workload score are uncertain. Our approach to deal with the uncertainties in workload modeling problem consists of following steps: 1) The uncertainties, arising due the individual variations in identifying a common model valid for all the individuals, are filtered out using a fuzzy filter. 2) Stochastic modeling of the uncertainties (provided by the fuzzy filter) using finite mixture models and utilizing this information regarding uncertainties for identifying the structure and initial parameters of a workload model. 3) Finally, the workload model parameters, for an individual, are identified in an online scenario using machine learning algorithms. The contribution of the study was to propose, with a mathematical analysis, a fuzzy based modeling technique that first filters out the uncertainties from the modeling problem, analyzes the uncertainties statistically using finite mixture modeling, and finally the information about uncertainties is utilized for adapting the workload model to an individual's physiological conditions. This approach, demonstrated with the real-world medical data of 11 subjects, provided a fuzzy based tool useful for modeling in presence of uncertainties.