Electroencephalography based detection of cognitive state during learning tasks: An extensive approach

Abstract

Detecting cognitive states during learning tasks is an essential component in neurocognitive experiments for assessing and enhancing the cognitive performance of individuals. Studies have demonstrated that mental state recognition systems utilizing brain signals are proficient in the automated monitoring of learners’ cognitive states. The current study focuses on developing an efficient individualized and cross-subject cognitive state assessment model based on Electroencephalography (EEG) patterns during learning tasks. For this study, EEGs of 20 healthy subjects were recorded during a resting state followed by a learning task and examined EEG activations patterns in a wide perspective of feature types and rhythms. The extracted features included time-domain features such as Hjorth parameters, Wavelet-based features, and Spectral entropy. Three classifiers, Support Vector Machine, k-Nearest Neighbor, and Linear Discriminant Analysis were employed to recognize the mental state. A new EEG-based attention index using band ratios is proposed and is demonstrated as an effective predictor for recognizing attentive reading. The proposed model can yield recognition performance with an accuracy of 92.9% in the subject-dependent approach and 77.2% in the subject-independent approach with the Support Vector Machine Classifier. The findings are useful for the design and development of neurofeedback systems that monitor and enhance the cognitive performance in healthy individuals, as well as in individuals with cognitive deficits.