Classification of Cognitive Load based on Oculometric Features

• Published in: 2021 44th International Convention on Information, Communication and Electronic Technology (MIPRO) pp. 377 - 382
• Main Authors: Gambiraza, Mate, Kesedzic, Ivan, Sarlija, Marko, Popovic, Sinisa, Cosic, Kresimir
• Format: Conference Proceeding
• Language: English
• Published: Croatian Society MIPRO 27.09.2021
• Subjects: classification; cognitive load; eye tracking; Feature extraction; Physiology; Protocols; pupillometry; Recurrent neural networks; Reliability; Support vector machines; SVM; Visual systems
• ISSN: 2623-8764
• DOI: 10.23919/MIPRO52101.2021.9597067

Cognitive load is related to the amount of working memory resources used in the execution of various mental tasks. Different multimodal features extracted from peripheral physiology, brain activity, and oculometric reactions have been used as non-intrusive, reliable, and objective measures of cognitive load. In this paper, we use data from 38 participants performing a four-level difficulty n-back task (0-, 1-, 2-, and 3-back task), with their oculometric reactions simultaneously recorded. Based on the neuroanatomic structure and function of the visual system, 26 oculometric features are extracted and organized into 3 groups related to: pupil dilation (PD), blinking, and fixation. The discriminative power of each group of features was evaluated in four-level cognitive load classification using a support vector machine (SVM) model and feature selection, and the achieved classification accuracies were: 33.33% using only pupil dilation features, 30.90% using only blink-related features, 30.21% using only fixations-related features. Finally, a 36.11% classification accuracy was achieved using a combination of all extracted oculometric features. The presented results show that various groups of oculometric features provide complementary information about the subject's cognitive load. The comparison of the extracted groups of features is given, and the most important features in terms of classification performance are discussed.