Convolutional channel modulator for transformer and LSTM networks in EEG-based emotion recognition
Biomedical Engineering Letters · 2025-07 · 15 (4) · 749-761
DOI: 10.1007/s13534-025-00475-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomedical Engineering Letters, online erschienen am 21.04.2025. Verfasst von Hyunwook Kang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, Inha University, Inha-ro, Incheon, 22212 Republic of Korea. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government, National Research Foundation of Korea (NRF) grant funded by the Korea government.
Abstract (Originalsprache)
Electroencephalogram (EEG) signal is receiving much attention from recent studies since it is highly associated with intrinsic emotion. However, EEG signals contain underlying factors of variations across different sessions of the same subject, which make it difficult to learn temporal relationships between successive time steps. To disentangle invariant features, we propose a feature re-weighting mechanism on the extracted EEG features for temporal sequence modeling. Based on this method, our proposed model, called Convolutional Channel Modulator for Transformer and LSTM networks (CCMTL), extracts emotion-related inter-channel correlations using convolution operations and emphasizes important features by generating a channel attention map. This attention map is then used to perform matrix multiplication on the extracted features, which helps the subsequent Transformer to focus on important affective features. Furthermore, the sequential temporal modeling enhances the overall model's capability to understand temporal relationships both in global and sequential contexts. Experimental settings on public EEG emotion datasets demonstrate the superiority of the proposed CCMTL, surpassing six state-of-the-art models. Our code is publicly available at https://github.com/affctivai/CCMTL.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical and Computer Engineering, Inha University, Inha-ro, Incheon, 22212 Republic of Korea.
- Department of Neurology and Neurological Sciences, Stanford University School of Medicine, 453 Quarry Road, Stanford, CA 94305 USA.
- Department of Artificial Intelligence, Inha University, Inha-ro, Incheon, 22212 Republic of Korea.
ORCID-Profile: Byung Hyung Kim
Förderung
- Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government
- National Research Foundation of Korea (NRF) grant funded by the Korea government
Zitieren
APA
Kang, H., Choi, J. W., & Kim, B. H. (2025). Convolutional channel modulator for transformer and LSTM networks in EEG-based emotion recognition. Biomedical Engineering Letters, 15(4), 749-761. https://doi.org/10.1007/s13534-025-00475-7
Vancouver
Kang H, Choi JW, Kim BH. Convolutional channel modulator for transformer and LSTM networks in EEG-based emotion recognition. Biomedical Engineering Letters. 2025;15(4):749-761. doi:10.1007/s13534-025-00475-7
BibTeX
@article{Kang2025,
author = {Kang, Hyunwook and Choi, Jin Woo and Kim, Byung Hyung},
title = {Convolutional channel modulator for transformer and LSTM networks in EEG-based emotion recognition},
journal = {Biomedical Engineering Letters},
year = {2025},
volume = {15},
number = {4},
pages = {749--761},
doi = {10.1007/s13534-025-00475-7}
}
EUVIMED