Cognitive Load Assessment in Motor Learning Tasks by Near‐Infrared Spectroscopy Using Type‐2 Fuzzy Sets

This chapter addresses a novel approach to assess and classify, by near‐Infrared spectroscopy, the cognitive load of subjects from their hemodynamic response while engaged in motor learning tasks such as vehicle driving. Classification of cognitive load includes five main steps: acquisition and normalization of the fNIRs signals, pre‐processing and artifact removal, feature extraction, feature selection, and classification. A set of complex motor‐activity‐learning stimuli for braking, steering control, and acceleration is prepared to experimentally measure and classify the cognitive load of car drivers in three distinct classes: high, medium, and low. The chapter proposes new models of general and interval type‐2 fuzzy classifiers to reduce the scope of uncertainty in cognitive load classification due to the fluctuation of the hemodynamic features within and across sessions. It discusses the design issues and biological implications of the type‐2 fuzzy classifiers. The chapter also provides experimental basis for performance analysis and comparison of the proposed classifiers with traditional/existing ones.