EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ECG Signal Compression and Reconstruction Based on CNN-LSTM-Attention Model

Wenyan Liu, Dongzhi Chen iD, Ze Zhang, Yajie Cao, Yi Liu, Zhiguo Gui iD, Lili Liu

Sensors · 23.06.2026 · 26 (13) · 3983

DOI: 10.3390/s26133983 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.06.2026. Verfasst von Wenyan Liu und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Information and Communication Engineering, North University of China, Taiyuan 030051, China. Hauptthemen laut MEDLINE: Electrocardiography, Signal Processing, Computer-Assisted, Data Compression. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Strategic Priority Science and Technology Project of Inner Mongolia University of Technology, the National Natural Science Foundation of China Youth Project, the Applied Basic Research Programs of Shanxi Province in China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The high prevalence of cardiovascular diseases and the extensive application wearable electrocardiogram (ECG) devices for long-term monitoring have posed significant challenges for the transmission, storage, and real-time processing of massive amounts of ECG data. Consequently, efficient ECG compression and reconstruction have become a research priority in remote ECG monitoring. Traditional compressed sensing is complex and has high computational overhead, while single deep learning models cannot simultaneously extract local waveforms and model temporal dependencies. To address these shortcomings in the reconstruction process, this paper presents a CNN-LSTM-Attention hybrid model. This model utilizes a convolutional neural network (CNN) to capture local ECG waveform features, employs a long short-term memory (LSTM) network to learn long-term temporal dependencies, and introduces an attention mechanism to weight and fuse key diagnostic features, enabling accurate focus on key components including the QRS complex and ST segment. Experimental results on the MIT-BIH Arrhythmia dataset demonstrate that across the full compression range of 0.1–0.9, the proposed model achieves favorable comprehensive performance. Its PRD is stabilized at 10–12%, the SNR stays above 20 dB, and the RMSE is mostly lower than 0.25 mV. In terms of reconstruction accuracy and stability, our model outperforms the single CNN and CNN-LSTM models by a large margin.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectrocardiographySignal Processing, Computer-AssistedData CompressionConvolutional Neural NetworksLong Short Term MemoryHumansCompression AlgorithmsArrhythmias, CardiacNeural Networks, ComputerAlgorithms

Stichwörter der Autor:innen

ECG signalattention mechanismcompressive sensingconvolutional neural networklong short-term memory network

Autor:innen und Institutionen

  • School of Information and Communication Engineering, North University of China, Taiyuan 030051, China.
  • School of New Energy, Inner Mongolia University of Technology, Ordos 017010, China.

ORCID-Profile: Dongzhi Chen, Zhiguo Gui

Förderung

  • the Strategic Priority Science and Technology Project of Inner Mongolia University of Technology
  • the National Natural Science Foundation of China Youth Project
  • the Applied Basic Research Programs of Shanxi Province in China

Zitieren

APA

Liu, W., Chen, D., Zhang, Z., Cao, Y., Liu, Y., Gui, Z., & Liu, L. (2026). ECG Signal Compression and Reconstruction Based on CNN-LSTM-Attention Model. Sensors, 26(13), 3983. https://doi.org/10.3390/s26133983

Vancouver

Liu W, Chen D, Zhang Z, Cao Y, Liu Y, Gui Z, et al. ECG Signal Compression and Reconstruction Based on CNN-LSTM-Attention Model. Sensors. 2026;26(13):3983. doi:10.3390/s26133983

BibTeX
@article{Liu2026,
  author = {Liu, Wenyan and Chen, Dongzhi and Zhang, Ze and Cao, Yajie and Liu, Yi and Gui, Zhiguo and Liu, Lili},
  title = {ECG Signal Compression and Reconstruction Based on CNN-LSTM-Attention Model},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {13},
  pages = {3983},
  doi = {10.3390/s26133983}
}
Kostenlos starten →