EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EFIB-Net: Information Bottleneck-Guided Multi-Resolution Attention Network for Robust ECG Denoising

Minghao Ma, Chen Liu, Yulin Mu, Jingqiu Chen, Li Zhu

Applied Sciences · 26.06.2026 · 16 (13) · 6401

DOI: 10.3390/app16136401 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 26.06.2026. Verfasst von Minghao Ma und 4 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wearable electrocardiogram (ECG) monitoring enables continuous cardiovascular assessment, yet signals acquired in ambulatory environments are inevitably corrupted by baseline wander, electrode motion artifacts, and muscle interference, which obscure diagnostically critical waveform features. Existing deep learning denoisers rely on heuristic attention mechanisms and time-domain-only losses, lacking principled control over what information the network retains or discards. To address this limitation, we propose EFIB-Net, an information bottleneck-guided multi-resolution network for robust ECG denoising. The framework introduces two complementary components: an efficient frequency-guided attention module that derives temporal attention weights directly from the energy distribution of parallel multi-resolution convolutional branches, requiring only four learnable parameters while providing physically interpretable feature selection that naturally highlights QRS complexes, and a variational information bottleneck constraint at the encoder–decoder bottleneck that forces the latent representation to retain only reconstruction-relevant information and discard noise, guided by a spectral–temporal composite loss. To the best of our knowledge, we are among the first to explicitly introduce the information bottleneck principle into deep-learning-based ECG signal denoising. Experiments on the MIT-BIH Arrhythmia Database show that EFIB-Net outperforms ten traditional and deep learning baselines across four standard metrics—signal-to-noise ratio (SNR), root mean square error, percentage root-mean-square difference, and correlation coefficient; at an input SNR of −5 dB it reaches 8.12 dB output SNR, surpassing the strongest attention-based competitor by 1.77 dB (p

Zitieren

APA

Ma, M., Liu, C., Mu, Y., Chen, J., & Zhu, L. (2026). EFIB-Net: Information Bottleneck-Guided Multi-Resolution Attention Network for Robust ECG Denoising. Applied Sciences, 16(13), 6401. https://doi.org/10.3390/app16136401

Vancouver

Ma M, Liu C, Mu Y, Chen J, Zhu L. EFIB-Net: Information Bottleneck-Guided Multi-Resolution Attention Network for Robust ECG Denoising. Applied Sciences. 2026;16(13):6401. doi:10.3390/app16136401

BibTeX
@article{Ma2026,
  author = {Ma, Minghao and Liu, Chen and Mu, Yulin and Chen, Jingqiu and Zhu, Li},
  title = {EFIB-Net: Information Bottleneck-Guided Multi-Resolution Attention Network for Robust ECG Denoising},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {13},
  pages = {6401},
  doi = {10.3390/app16136401}
}
Kostenlos starten →