Psychophysiologically Based Real-Time Adaptive General Type 2 Fuzzy Modeling and Self-Organizing Control of Operator's Performance Undertaking a Cognitive Task

This paper presents a new modeling and control fuzzy-based framework validated with real-time experiments on human participants experiencing stress via mental arithmetic cognitive tasks identified through psychophysiological markers. The ultimate aim of the modeling/control framework is to prevent performance breakdown in human–computer interactive systems with a special focus on human performance. Two designed modeling/control experiments which consist of carrying-out arithmetic operations of varying difficulty levels were performed by ten participants (operators) in the study. With this new technique, modeling is achieved through a new adaptive, self-organizing, and interpretable modeling framework based on general Type-2 fuzzy sets. This framework is able to learn in real time through the implementation of a restructured performance learning algorithm that identifies important features in the data without the need for prior training. The information learnt by the model is later exploited via an energy model based controller that infers adequate control actions by changing the difficulty level of the arithmetic operations in the human–computer interaction system; these actions being based on the most current psychophysiological state of the subject under study. The real-time implementation of the proposed modeling and control configurations for the human–machine interaction under study shows superior performance as compared to other forms of modeling and control, with minimal intervention in terms of model retraining or parameter retuning to deal with uncertainties, disturbances, and inter/intrasubject parameter variability.