An Evaluation of the EEG Alpha-to-Theta and Theta-to-Alpha Band Ratios as Indexes of Mental Workload

Abstract

Many research works indicate that EEG bands, specifically the alpha and theta bands, have been potentially helpful cognitive load indicators. However, minimal research exists to validate this claim. This study aims to assess and analyze the impact of the alpha-to-theta and the theta-to-alpha band ratios on supporting the creation of models capable of discriminating self-reported perceptions of mental workload. A dataset of raw EEG data was utilized in which 48 subjects performed a resting activity and an induced task demanding exercise in the form of a multitasking SIMKAP test. Band ratios were devised from frontal and parietal electrode clusters. Building and model testing was done with high-level independent features from the frequency and temporal domains extracted from the computed ratios over time. Target features for model training were extracted from the subjective ratings collected after resting and task demand activities. Models were built by employing Logistic Regression, Support Vector Machines and Decision Trees and were evaluated with performance measures including accuracy, recall, precision and f1-score. The results indicate high classification accuracy of those models trained with the high-level features extracted from the alpha-to-theta ratios and theta-to-alpha ratios. Preliminary results also show that models trained with logistic regression and support vector machines can accurately classify self-reported perceptions of mental workload. This research contributes to the body of knowledge by demonstrating the richness of the information in the temporal, spectral and statistical domains extracted from the alpha-to-theta and theta-to-alpha EEG band ratios for the discrimination of self-reported perceptions of mental workload.

Human Mental Workload: A Survey and a Novel Inclusive Definition

“…In detail, theta EEG power spectrum in the frontal, temporal, and occipital areas was higher during the most complex task conditions. An evaluation of the alpha-to-theta and the theta-to-alpha band rations were investigated as indexes of mental workload (Raufi and Longo, 2022 ). In details, authors demonstrated the richness of the information in the temporal, spectral and statistical domains extracted from these indexes for the discrimination of self-reported perceptions of mental workload over two task load conditions.…”

Modeling Cognitive Load as a Self-Supervised Brain Rate with Electroencephalography and Deep Learning

“…It will also serve as a layer of explainability, providing analysts with tools for explaining spatial and temporal dynamic of cognitive activation. The inferences of these models of cognitive load can be compared against other indexes such as the theta-to-alpha or alpha-to-theta band ratios [ 54 ], increasing their meaningfulness and validity. Eventually, studies can be devoted to the development of additional recurrent neural networks for understanding the temporal aspects of the high-level representations of cognitive activation, and establishing if there exist sequences, and their lengths, that are repetitive and recurrent over time.…”

“…State-of-the-art models manipulating EEG data often rely on frequency bands, such as the alpha or theta rhythms, deemed the alphabet for brain functions and mental state extraction. These have been individually used as cognitive load indicators [ 50 , 51 ], or aggregated together [ 21 , 52 , 53 , 54 ] because they have been shown to be sensitive to task difficulty manipulation, task engagement or memory load [ 55 , 56 ]. However, these approaches often discard some EEG bands in favour of other bands.…”

Schizo-Net: A novel Schizophrenia Diagnosis Framework Using Late Fusion Multimodal Deep Learning on Electroencephalogram-Based Brain Connectivity Indices

“…In recent years, deep learning methods have been developed to detect various neurological disorders that utilize EEG signals [15], [75] and solve various classification tasks [76], [77], [78]. Although these methods work well in finding hidden features and patterns from the nonlinear data, they struggle to attain higher-classification accuracy on EEG due to the data being highly complex and the frequent non-cerebral contamination that accompanies it [61], [62].…”