Next Article in Journal
Pioneering Soundscapes: Investigating Commercial Fused Deposition Modelling Filament’s Potential for Ultrasound Technology in Bone Tissue Scaffolds
Previous Article in Journal
Transforming Bone Tunnel Evaluation in Anterior Cruciate Ligament Reconstruction: Introducing a Novel Deep Learning System and the TB-Seg Dataset
Previous Article in Special Issue
MRI-Driven Alzheimer’s Disease Diagnosis Using Deep Network Fusion and Optimal Selection of Feature
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Bioengineering
Volume 12
Issue 5
10.3390/bioengineering12050528
bioengineering-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Cross-Subject Emotion Recognition with CT-ELCAN: Leveraging Cross-Modal Transformer and Enhanced Learning-Classify Adversarial Network †

by
Ping Li
1,‡,§,
Ao Li
1,‡,
Xinhui Li
1,‡ and
Zhao Lv
1,2,*
1
School of Computer Science and Technology, Anhui University, Hefei 230601, China
2
The Key Laboratory of Flight Techniques and Flight Safety, Civil Aviation Flight University of China, Deyang 618307, China
*
Author to whom correspondence should be addressed.
†
This article is a revised and expanded version of a paper entitled “CAT-LCAN: A Multimodal Physiological Signal Fusion Framework for Emotion Recognition”, which was presented at BICS 2024 (The 14th International Conference on Advances in Brain Inspired Cognitive Systems, Heifei, Anhui, China, 6 December 2024–28 January 2025).
‡
These authors contributed equally to this work.
§
Current address: Chingyuan Campus, Anhui University, 111 Jiulong Road, Shushan District, Hefei 231200, China.
Bioengineering 2025, 12(5), 528; https://doi.org/10.3390/bioengineering12050528
Submission received: 16 April 2025 / Revised: 8 May 2025 / Accepted: 12 May 2025 / Published: 15 May 2025
(This article belongs to the Special Issue Biomedical Applications of Multimodal Imaging Combined with Artificial Intelligence)
Browse Figures
Review Reports Versions Notes

Abstract

Multimodal physiological emotion recognition is challenged by modality heterogeneity and inter-subject variability, which hinder model generalization and robustness. To address these issues, this paper proposes a new framework, Cross-modal Transformer with Enhanced Learning-Classifying Adversarial Network (CT-ELCAN). The core idea of CT-ELCAN is to shift the focus from conventional signal fusion to the alignment of modality- and subject-invariant emotional representations. By combining a cross-modal Transformer with ELCAN, a feature alignment module using adversarial training, CT-ELCAN learns modality- and subject-invariant emotional representations. Experimental results on the public datasets DEAP and WESAD demonstrate that CT-ELCAN achieves accuracy improvements of approximately 7% and 5%, respectively, compared to state-of-the-art models, while also exhibiting enhanced robustness.
Keywords: multimodal emotion recognition; cross-modal transformer; adversarial learning; cross-subject generalization; physiological signals multimodal emotion recognition; cross-modal transformer; adversarial learning; cross-subject generalization; physiological signals

Share and Cite

MDPI and ACS Style

Li, P.; Li, A.; Li, X.; Lv, Z. Cross-Subject Emotion Recognition with CT-ELCAN: Leveraging Cross-Modal Transformer and Enhanced Learning-Classify Adversarial Network. Bioengineering 2025, 12, 528. https://doi.org/10.3390/bioengineering12050528

AMA Style

Li P, Li A, Li X, Lv Z. Cross-Subject Emotion Recognition with CT-ELCAN: Leveraging Cross-Modal Transformer and Enhanced Learning-Classify Adversarial Network. Bioengineering. 2025; 12(5):528. https://doi.org/10.3390/bioengineering12050528

Chicago/Turabian Style

Li, Ping, Ao Li, Xinhui Li, and Zhao Lv. 2025. "Cross-Subject Emotion Recognition with CT-ELCAN: Leveraging Cross-Modal Transformer and Enhanced Learning-Classify Adversarial Network" Bioengineering 12, no. 5: 528. https://doi.org/10.3390/bioengineering12050528

APA Style

Li, P., Li, A., Li, X., & Lv, Z. (2025). Cross-Subject Emotion Recognition with CT-ELCAN: Leveraging Cross-Modal Transformer and Enhanced Learning-Classify Adversarial Network. Bioengineering, 12(5), 528. https://doi.org/10.3390/bioengineering12050528

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop