N. Kosmyna, K. El Adl and M. Kim, "Wearable Pair of EEG, EOG and fNIRS Glasses for Cognitive Workload Detection," 2024 IEEE 20th International Conference on Body Sensor Networks (BSN), Chicago, IL, USA, 2024, pp. 1-4, doi: 10.1109/BSN63547.2024.10780518.

Abstract

 A rapidly growing number of studies demonstrate the potential benefits of Brain-Computer Interfaces (BCIs) in a wide range of use cases including education, workplace safety, and mental health. Recent technological advances have allowed a growing number of wearable BCIs appear both as research prototypes and on the market. The goal of this project was to develop and evaluate a BCI platform that integrates both electrical and metabolic sensing in a wearable glasses form-factor. Our system combines data from three different physiological modalities: four channels of functional Near-Infrared Spectroscopy (fNIRS), three Electroencephalography (EEG) channels and two Electrooculography (EOG) channels. We compared different preprocessing and cognitive load classification strategies using data collected in a 14 subject mental arithmetic study. An SVM produced an average accuracy of 79% using EEG+EOG+fNIRS features compared with 62% and 63% for EEG and fNIRS respectively.