Kwon, Jangho Ha, Jihyeon Kim, Da-Hye Choi, Jun Won Kim, Laehyun 2024-01-19T13:34:02Z 2024-01-19T13:34:02Z 2022-01-10 2021-10 2169-3536 https://pubs.kist.re.kr/handle/201004/116340 We present a glasses-type wearable device to detect emotions from a human face in an unobtrusive manner. The device is designed to gather multi-channel responses from the user's face naturally and continuously while he/she is wearing it. The multi-channel facial responses consist of local facial images and biosignals including electrodermal activity (EDA) and photoplethysmogram (PPG). We had conducted experiments to determine the optimal positions of EDA sensors on the wearable device because EDA signal quality is very sensitive to the sensing position. In addition to the physiological data, the device can capture the image region representing local facial expressions around the left eye via a built-in camera. In this study, we developed and validated an algorithm to recognize emotions using multi-channel responses obtained from the device. The results show that the emotion recognition algorithm using only local facial images has an accuracy of 76.09% at classifying emotions. Using multi-channel data including EDA and PPG, this accuracy was increased by 8.46% compared to using the local facial expression alone. This glasses-type wearable system measuring multi-channel facial responses in a natural manner is very useful for monitoring a user's emotions in daily life, which has a huge potential for use in the healthcare industry. English IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC HEART-RATE-VARIABILITY SENSOR Emotion Recognition Using a Glasses-Type Wearable Device via Multi-Channel Facial Responses Article 10.1109/ACCESS.2021.3121543 1 IEEE ACCESS, v.9, pp.146392 - 146403 IEEE ACCESS 9 146392 146403 scie scopus 000714706800001 2-s2.0-85118246850 Computer Science, Information Systems Engineering, Electrical & Electronic Telecommunications Computer Science Engineering Telecommunications Article HEART-RATE-VARIABILITY SENSOR Wearable computers Emotion recognition Sensors Cameras Biomedical monitoring Glass Motion pictures Wearable device emotion recognition affective computing facial expression biosignal physiological responses