Hsiang-Chin Chien

Hsiang-Chin Chien

Auto-generated profile, based on publicly available information

Hsiang-Chin Chien

National yang Ming Chiao Tung University

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 October 2018
Verified
Conference Paper
Open access
CHChih-Chung Hsu
Chih-Chung Hsu
CLChia-Yen Lee
Chia-Yen Lee
TLTing-Xuan Liao
Ting-Xuan Liao
JLJun-Yi Lee
Jun-Yi Lee
THTsai-Yne Hou
Tsai-Yne Hou
HCHsiang-Chin Chien
Hsiang-Chin Chien


28 March 2025
Verified
Book Chapter
Closed access
PDF file
CWChing-Ping Wang
Ching-Ping Wang
HCHsiang-Chin Chien
Hsiang-Chin Chien
XCXin-Yu Chen
Xin-Yu Chen
HLHong-Kun Lin
Hong-Kun Lin
CCChi-Sheng Chang
Chi-Sheng Chang
JCJung-Chih Chen
Jung-Chih Chen

19 May 2026 in IEEE Access
Verified
Journal Article
Open access
HCHsiang-Chin Chien
Hsiang-Chin Chien
CLChia-Yen Lee
Chia-Yen Lee
JCJung-Chih Chen
Jung-Chih Chen
Emotion emerges from the coordinated interplay between central neural activity and peripheral autonomic responses; however, many existing deep learning approaches model these modalities independently, limiting their ability to capture complementary affective information and to remain robust under small-dataset and partially missing-data conditions. To address this issue, this study presents EmoRecog-Net, a unified multimodal framework for video-induced emotion categorization and recognition using functional magnetic resonance imaging (fMRI) and physiological signals. The proposed architecture integrates convolutional neural networks to learn spatial representations, gated recurrent units to model temporal dynamics, and a multilayer perceptron to perform nonlinear cross-modal fusion. Experiments were conducted on the ICBHI 2024 multimodal benchmark, which includes synchronized fMRI, photoplethysmography (PPG), and respiration (R) signals. Model performance was evaluated using F1-score, area under the curve (AUC), accuracy, and the official Finalscore metric. The proposed method achieved the lowest Finalscore of 0.2815 among the compared methods on the benchmark, outperforming representative CNN-LSTM, attention-based, graph-based, and autoencoder-based baselines. In addition, ablation studies demonstrated that GRU-based temporal modeling and MLP-based multimodal fusion consistently improved performance under limited-data and class-imbalanced conditions. These results indicate that jointly modeling coupled brain-autonomic dynamics provides a robust and effective strategy for multimodal affective computing. Overall, EmoRecog-Net offers a compact yet effective design for emotion decoding in small-scale multimodal settings.