Cognitive load detection using adaptive/fixed-frequency empirical wavelet transform and multi-domain feature optimization

Neuronal activity is stimulated by cognitive load, which is crucial for comprehending the brain’s response to mental strain or stress-inducing stimuli. This study aims to look into the feasibility of extracting and classifying features from adaptive and traditional (rhythms) subbands of electroencephalogram (EEG) signals to assess cognitive load. Each EEG channel data (4-second duration) was decomposed into five subband signals (SBSs) using the empirical wavelet transform (EWT)-based multi-resolution analysis with adaptive and fixed spectral boundary frequencies. In fixed-frequency EWT (FF-EWT), the filter bank was designed with specific boundary frequencies for EEG rhythm extraction. In contrast to FF-EWT, the spectral boundaries of adaptive frequency EWT (AF-EWT) were adaptively found using the scale-space method. In the next step, multi-domain features (time-domain, frequency-domain, and non-linear features) were extracted from each EEG rhythm or SBS. The feature space dimension was reduced using binary atom search optimization (BASO) and binary equilibrium optimization (BEO) algorithms for improved classification performance. We have carried out a comprehensive study that includes feature-wise, rhythm/SBS-wise, and overall feature classification using seven machine learning techniques and their variants. Our proposed method combining FF-EWT-based multi-domain features with BASO and ensemble learning (EL) classifiers achieved the highest classification accuracy of 97.9%, 94.7%, and 99.1% in detecting cognitive loads using the mental arithmetic task (MAT), simultaneous workload (STEW), and mental load recognition (MLR) EEG datasets, respectively. Among rhythms and SBSs, the gamma rhythm appeared to play a significant role in analyzing a variety of cognitive tasks and achieved the highest classification accuracy. The proposed method outperformed the existing state-of-the-art techniques in the literature for cognitive load detection.