In-Ear EEG Based Attention State Classification Using Echo State Network

Abstract

It is important to maintain attention when carrying out significant daily-life tasks that require high levels of safety and efficiency. Since degradation of attention can sometimes have dire consequences, various brain activity measurement devices such as electroencephalography (EEG) systems have been used to monitor attention states in individuals. However, conventional EEG instruments have limited utility in daily life because they are uncomfortable to wear. Thus, this study was designed to investigate the possibility of discriminating between the attentive and resting states using in-ear EEG signals for potential application via portable, convenient earphone-shaped EEG instruments. We recorded both on-scalp and in-ear EEG signals from 6 subjects in a state of attentiveness during the performance of a visual vigilance task. We have designed and developed in-ear EEG electrodes customized by modelling both the left and right ear canals of the subjects. We use an echo state network (ESN), a powerful type of machine learning algorithm, to discriminate attention states on the basis of in-ear EEGs. We have found that the maximum average accuracy of the ESN method in discriminating between attentive and resting states is approximately 81.16% with optimal network parameters. This study suggests that portable in-ear EEG devices and an ESN can be used to monitor attention states during significant tasks to enhance safety and efficiency.

Frontal EEG-Based Multi-Level Attention States Recognition Using Dynamical Complexity and Extreme Gradient Boosting

“…Compared with the performance of previous studies on the EEG application of attention state monitoring (Chen et al, 2017;Hu et al, 2018;Gaume et al, 2019;Jeong and Jeong, 2020), we dealt with the recognition up to four levels of attention states and our performance is higher than them using Complexity-XGBoost (see Table 3). The Complexity-XGBoost achieved the accuracy of 81.39 ± 1.47% for four-level attention states (HA, MA, LA, and RS), 80.42 ± 0.84% for three-level attention states (HA, MA, and LA), and 95.36 ± 2.31% for two-level attention states (AS and RS) when using 5-fold cross-validation.…”

A simplified design of a cEEGrid ear-electrode adapter for the OpenBCI biosensing platform

“…Before this project, OpenBCI ear-based sensing systems had to be individually conceived and assembled with substantial engineering efforts (see, e.g. [11] , [12] , [13] ). Also, the cEEGrid sensors were only usable by designing adapters for expensive EEG amplifiers or purchasing a more expensive commercial analog (e.g., the MBT Smarting Mobi).…”

Transcranial Auricular Vagus Nerve Stimulation (taVNS) and Ear-EEG: Potential for Closed-Loop Portable Non-invasive Brain Stimulation

“…The EEG signal provides reliable markers of attention states; such as fluctuations in the cortical alpha rhythm that mirror attentional fluctuations ( Fiedler et al, 2017 ; Jeong and Jeong, 2020 ). The ear-EEG system gives subjects the opportunity to move freely and wear the device for long periods of time.…”