MAK-Net: A Multi-Scale Attentive Kolmogorov–Arnold Network with BiGRU for Imbalanced ECG Arrhythmia Classification
Sensors · 2025
DOI: 10.3390/s25133928 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Cong Zhao und 4 weiteren Autor:innen. Beteiligte Einrichtung: Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen 518107, China. Hauptthemen laut MEDLINE: Electrocardiography, Arrhythmias, Cardiac. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shenzhen Science and the Technology Program.
Abstract (Originalsprache)
Accurate classification of electrocardiogram (ECG) signals is vital for reliable arrhythmia diagnosis and informed clinical decision-making, yet real-world datasets often suffer severe class imbalance that degrades recall and F1-score. To address these limitations, we introduce MAK-Net, a hybrid deep learning framework that combines: (1) a four-branch multiscale convolutional module for comprehensive feature extraction across diverse waveform morphologies; (2) an efficient channel attention mechanism for adaptive weighting of clinically salient segments; (3) bidirectional gated recurrent units (BiGRU) to capture long-range temporal dependencies; and (4) Kolmogorov–Arnold Network (KAN) layers with learnable spline activations for enhanced nonlinear representation and interpretability. We further mitigate imbalance by synergistically applying focal loss and the Synthetic Minority Oversampling Technique (SMOTE). On the MIT-BIH arrhythmia database, MAK-Net attains state-of-the-art performance—0.9980 accuracy, 0.9888 F1-score, 0.9871 recall, 0.9905 precision, and 0.9991 specificity—demonstrating superior robustness to imbalanced classes compared with existing methods. These findings validate the efficacy of multiscale feature fusion, attention-guided learning, and KAN-based nonlinear mapping for automated, clinically reliable arrhythmia detection.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen 518107, China.
- Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province, College of Physics and Optoelectronic Engineering, Shenzhen University, Shenzhen 518060, China.
- Shenzhen Key Laboratory of Photonic Devices and Sensing Systems for Internet of Things, Guangdong and Hong Kong Joint Research Centre for Optical Fiber Sensors, Shenzhen University, Shenzhen 518060, China.
- Individualized Interdisciplinary Program, The Hong Kong University of Science and Technology, Hong Kong, China.
- System Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511400, China.
ORCID-Profile: Yiping Wang
Förderung
- National Natural Science Foundation of China
- Shenzhen Science and the Technology Program
Zitieren
APA
Zhao, C., Lai, B., Xu, Y., Wang, Y., & Dong, H. (2025). MAK-Net: A Multi-Scale Attentive Kolmogorov–Arnold Network with BiGRU for Imbalanced ECG Arrhythmia Classification. Sensors. https://doi.org/10.3390/s25133928
Vancouver
Zhao C, Lai B, Xu Y, Wang Y, Dong H. MAK-Net: A Multi-Scale Attentive Kolmogorov–Arnold Network with BiGRU for Imbalanced ECG Arrhythmia Classification. Sensors. 2025. doi:10.3390/s25133928
BibTeX
@article{Zhao2025,
author = {Zhao, Cong and Lai, Bingwei and Xu, Yongzheng and Wang, Yiping and Dong, Haorong},
title = {MAK-Net: A Multi-Scale Attentive Kolmogorov–Arnold Network with BiGRU for Imbalanced ECG Arrhythmia Classification},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25133928}
}
EUVIMED