EEG/fNIRS Based Workload Classification Using Functional Brain Connectivity and Machine Learning

Abstract

There is high demand for techniques to estimate human mental workload during some activities for productivity enhancement or accident prevention. Most studies focus on a single physiological sensing modality and use univariate methods to analyse multi-channel electroencephalography (EEG) data. This paper proposes a new framework that relies on the features of hybrid EEG–functional near-infrared spectroscopy (EEG–fNIRS), supported by machine-learning features to deal with multi-level mental workload classification. Furthermore, instead of the well-used univariate power spectral density (PSD) for EEG recording, we propose using bivariate functional brain connectivity (FBC) features in the time and frequency domains of three bands: delta (0.5–4 Hz), theta (4–7 Hz) and alpha (8–15 Hz). With the assistance of the fNIRS oxyhemoglobin and deoxyhemoglobin (HbO and HbR) indicators, the FBC technique significantly improved classification performance at a 77% accuracy for 0-back vs. 2-back and 83% for 0-back vs. 3-back using a public dataset. Moreover, topographic and heat-map visualisation indicated that the distinguishing regions for EEG and fNIRS showed a difference among the 0-back, 2-back and 3-back test results. It was determined that the best region to assist the discrimination of the mental workload for EEG and fNIRS is different. Specifically, the posterior area performed the best for the posterior midline occipital (POz) EEG in the alpha band and fNIRS had superiority in the right frontal region (AF8).

Altered Functional Brain Network Structure between Patients with High and Low Generalized Anxiety Disorder

“…Our analysis showed that connections have a significant correlation with the prefrontal brain regions, distributed mostly between the frontal and other regions of the brain. A similar result has been reported by Shen et al [ 4 ] and Song et al [ 46 ]. Research has shown that people with generalized anxiety disorder (GAD) may have abnormal FC [ 47 , 48 ].…”

Neurovascular Coupling Analysis Based on Multivariate Variational Gaussian Process Convergent Cross-Mapping

“…To the best of our knowledge, it is worth mentioning, our experimental results provide the first causal analysisbased explanation for the significant differences in EEG-fNIRS coupling between the 0-back condition and the 2back and 3-back conditions, while no significant differences were observed between the 2-back and 3-back conditions. This viewpoint has been partially reflected in previous WM classification studies based on EEG-fNIRS [54]. However, it does not explain the underlying reasons for this phenomenon.…”

From local counterfactuals to global feature importance: efficient, robust, and model-agnostic explanations for brain connectivity networks

“…All subject-wise regions of interest (ROI) time-series were averaged within each ROI and preprocessed into subject-wise, ROI-to-ROI adjacency matrices, which has been proven to be successful in previous studies [49] , [50] , [51] , [52] , [53] , [54] , calculated as Pearson’s correlation coefficient for each possible pair of the 246 ROIs. This approach generates a database with 30135 columns and more than a thousand rows ( )., which constituted our final dataset to be used for classification.…”