TY - GEN
T1 - TWEN
T2 - 15th International Conference on Information and Communication Technology Convergence, ICTC 2024
AU - Kim, Taewan
AU - Jin, Chang Gyun
AU - Kim, Seong Eun
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Emotions significantly influence human cognition, behavior, and social interactions, making accurate recognition essential in Human-Computer Interaction (HCI) applications. This study addresses challenges in EEG-based emotion recognition, particularly inter-subject variability and label noise, which hinder the development of robust and generalized models. We propose a robust Two-phase Weakly Supervised Emotion Network (TWEN), a novel deep learning model designed to enhance emotion recognition. TWEN incorporates a Two-phase Multitask Autoencoder to mitigate inter-subject variability and a Top-k Selection method to reduce label noise. The model captures both local and global temporal features of EEG signals through an innovative fusion of attention mechanisms, ensuring accurate classification of emotions over varying durations. Evaluations on the THU-EP dataset demonstrate that TWEN outperforms state-of-the-art models, achieving a classification accuracy of 60.8%, with a standard deviation of 4.07%.
AB - Emotions significantly influence human cognition, behavior, and social interactions, making accurate recognition essential in Human-Computer Interaction (HCI) applications. This study addresses challenges in EEG-based emotion recognition, particularly inter-subject variability and label noise, which hinder the development of robust and generalized models. We propose a robust Two-phase Weakly Supervised Emotion Network (TWEN), a novel deep learning model designed to enhance emotion recognition. TWEN incorporates a Two-phase Multitask Autoencoder to mitigate inter-subject variability and a Top-k Selection method to reduce label noise. The model captures both local and global temporal features of EEG signals through an innovative fusion of attention mechanisms, ensuring accurate classification of emotions over varying durations. Evaluations on the THU-EP dataset demonstrate that TWEN outperforms state-of-the-art models, achieving a classification accuracy of 60.8%, with a standard deviation of 4.07%.
KW - EEG
KW - Emotion recognition
KW - THU-EP
KW - Two-phase Multitask Autoencoder
KW - Weakly supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85217679778&partnerID=8YFLogxK
U2 - 10.1109/ICTC62082.2024.10827151
DO - 10.1109/ICTC62082.2024.10827151
M3 - Conference contribution
AN - SCOPUS:85217679778
T3 - International Conference on ICT Convergence
SP - 1494
EP - 1498
BT - ICTC 2024 - 15th International Conference on ICT Convergence
PB - IEEE Computer Society
Y2 - 16 October 2024 through 18 October 2024
ER -