Mental Workload: Physiological Assessment and Validation Using Visual Stimuli

ABSTRACT This paper provides a notion for the use of electroencephalography (EEG) in the field of cognitive science. In particular, we investigated the brain activity of operators while spotting the differences in similar‐looking pictures at three levels of difficulty. As many practical loads are fundamentally intrinsic, the task was designed to specifically induce intrinsic workload (the productive load as per Cognitive Load Theory (CLT)). The experiment used the task: Spot the Difference to create a workload scenario comprising three difficulty levels: spotting five differences, three more differences, and two more differences (along with retaining the previous differences from working memory). The task was designed intrinsically as the operators are generally occupied with tasks involving working memory and requiring attention towards the varying number of resources. By utilising the brain signatures a mental workload model was developed employing a Support Vector Machine (SVM) as the classifier. The workload levels were classified within an accuracy range of 84% to 98% ( p < 0.05). Moreover, using subjective ratings about the workload on NASA's Task Load Index (NASA‐TLX) rating scale, workload scores were obtained for validation corresponding to the difficulty levels. Finally, a correlation study showed the association of different EEG features with the workload score within a correlation coefficient range of 0.306 to 0.748 ( p < 0.05 2‐tailed). The reported results can also provide new insights into the cognitive workload assessment of the operators at various phases of task loads. Findings of this type may lead to the industrial and professional measurement and improvement of cognitive aptitude soon.