Hongjin Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hongjin Kim has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Chang-Hwan Im
Department of Electronic Engineering, Hanyang University, Seoul 04763, Republic of Korea
1 shared publication - Hyeji Yu
School of Electrical Engineering, Kookmin University, Seoul 02707, Republic of Korea
1 shared publication - Jonggyun Kim
School of Electrical Engineering, Kookmin University, Seoul 02707, Republic of Korea
1 shared publication - Ki-Young Jung
Department of Neurology, Seoul National University Hospital, Seoul National University College of Medicine, Seoul 03080, Republic of Korea
1 shared publication - Kyeonggu Lee
Department of Electronic Engineering, Hanyang University, Seoul 04763, Republic of Korea
1 shared publication - Minsu Kim
Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by MDPI AG in Biosensors
- Vol. 16 (11) , 641
Monitoring Reduced Vigilance Using an Eyeglass-Type EEG System
An eyeglass-type electroencephalography (EEG) device has emerged as a promising platform for continuous cognitive state monitoring owing to its seamless integration into daily life and greater usability compared with conventional headset-style EEG systems. However, the feasibility of EEG-based reduced-vigilance monitoring using this form factor remains insufficiently examined. To address this issue, we conducted a two-phase experiment involving 21 participants to establish a mental fatigue-sensitive index and validate a monitoring algorithm for reduced vigilance associated with drowsiness or mental fatigue using a custom-made eyeglass-type EEG device. In the first phase, a long-term sustained attention task (d2 test) was employed to induce mental fatigue, and the ratio of low-alpha to high-beta power was identified as a potential biomarker of mental-fatigue-related vigilance decline. In the second phase, system performance was evaluated through a prolonged, monotonous video-watching experiment designed to elicit reduced vigilance. The algorithm combined the drowsiness detection index (theta-plus-alpha power) from the TP9 and TP10 channels with the candidate fatigue-sensitive index from the differential channel. Subject-specific calibration-based thresholds were used to generate index-specific segment-level decisions, which were combined using a logical OR rule. In the pseudo-real-time evaluation of 16 participants, the final fusion model achieved a mean accuracy of 70.31%, a false-positive rate of 10.40%, a recall of 49.67%, and a precision of 81.80%, calculated from participant-level metrics. Detection performance depended partly on the inclusion of segments with prolonged eye closure, with lower recall after their exclusion. Nevertheless, these findings provide preliminary evidence for the feasibility of detecting behaviorally defined reduced vigilance using an eyeglass-type EEG device.
- 9 November 2026
- Published by MDPI AG in Biosensors
- Vol. 16 (11) , 641
Open AccessMonitoring Reduced Vigilance Using an Eyeglass-Type EEG System
An eyeglass-type electroencephalography (EEG) device has emerged as a promising platform for continuous cognitive state monitoring owing to its seamless integration into daily life and greater usability compared with conventional headset-style EEG systems. However, the feasibility of EEG-based reduced-vigilance monitoring using this form factor remains insufficiently examined. To address this issue, we conducted a two-phase experiment involving 21 participants to establish a mental fatigue-sensitive index and validate a monitoring algorithm for reduced vigilance associated with drowsiness or mental fatigue using a custom-made eyeglass-type EEG device. In the first phase, a long-term sustained attention task (d2 test) was employed to induce mental fatigue, and the ratio of low-alpha to high-beta power was identified as a potential biomarker of mental-fatigue-related vigilance decline. In the second phase, system performance was evaluated through a prolonged, monotonous video-watching experiment designed to elicit reduced vigilance. The algorithm combined the drowsiness detection index (theta-plus-alpha power) from the TP9 and TP10 channels with the candidate fatigue-sensitive index from the differential channel. Subject-specific calibration-based thresholds were used to generate index-specific segment-level decisions, which were combined using a logical OR rule. In the pseudo-real-time evaluation of 16 participants, the final fusion model achieved a mean accuracy of 70.31%, a false-positive rate of 10.40%, a recall of 49.67%, and a precision of 81.80%, calculated from participant-level metrics. Detection performance depended partly on the inclusion of segments with prolonged eye closure, with lower recall after their exclusion. Nevertheless, these findings provide preliminary evidence for the feasibility of detecting behaviorally defined reduced vigilance using an eyeglass-type EEG device.