An ECG denoising method based on adversarial denoising convolutional neural network

Hou, Yanrong; Liu, Ruixia; Shu, Minglei; Chen, Changfang

doi:10.1016/j.bspc.2023.104964

Cited by 12 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The evaluation metrics applied to assess the proposed algorithm's performance in this research are consistent with those employed by Hou, et al [8]. The evaluation metrics considers two main aspects: reconstruction quality and compression efficiency, gauged through various metrics.…”

Section: Metricsmentioning

confidence: 94%

“…ECG signals are highly susceptible to noise, and the accuracy of arrhythmia analysis is compromised when noise is present [8,9]. Numerous studies [9][10][11][12] have explored the use of deep autoencoder-based ECG signal denoising to enhance arrhythmia detection, but they face challenges, and the obtained results often fall short of optimal.…”

Section: Introductionmentioning

confidence: 99%

“…This clarity is crucial for ensuring that the analyzed ECG signals for arrhythmia detection are easily interpretable and provide precise diagnostic information. Conversely, a low RMSE signifies that the Deep Autoencoder model effectively removes noise and variability, resulting in a reconstructed signal that closely aligns with the original signal with minimal error [8]. The pursuit of optimal SNR and RMSE values involves experiments with various Deep Autoencoder configurations, including the exploration of the number of layers, the number of units in each layer, and different training methods in those studies.…”

Section: Introductionmentioning

confidence: 99%

“…Deevi, et al [12] achieved noteworthy results in their denoising research, obtaining SNR values of 22.4501%, 13.8266%, and 17.0403%, with the highest accuracy reaching 99.53%. Hou, et al [8] applied a denoising autoencoder to an arrhythmia dataset, resulting in a substantial increase in SNR by 88.57%. Meanwhile, Shi, et al [13] contributed to the field by conducting research on arrhythmia classification using a denoising autoencoder, achieving an average SNR of 17.48dB.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning Autoencoder Study on ECG Signals

Mochamad Reza,

Satria Mandala,

Zaki

et al. 2023

JNTE

View full text Add to dashboard Cite

Arrhythmia refers to an irregular heart rhythm resulting from disruptions in the heart's electrical activity. To identify arrhythmias, an electrocardiogram (ECG) is commonly employed, as it can record the heart's electrical signals. However, ECGs may encounter interference from sources like electromagnetic waves and electrode motion. Several researchers have investigated the denoising of electrocardiogram signals for arrhythmia detection using deep autoencoder models. Unfortunately, these studies have yielded suboptimal results, indicated by low Signal-to-Noise Ratio (SNR) values and relatively large Root Mean Square Error (RMSE). This study addresses these limitations by proposing the utilization of a Deep LSTM Autoencoder to effectively denoise ECG signals for arrhythmia detection. The model's denoising performance is evaluated based on achieved SNR and RMSE values. The results of the denoising evaluations using the Deep LSTM Autoencoder on the AFDB dataset show SNR and RMSE values of 56.16 and 0.00037, respectively. Meanwhile, for the MITDB dataset, the corresponding values are 65.22 and 0.00018. These findings demonstrate significant improvement compared to previous research. However, it's important to note a limitation in this study—the restricted availability of arrhythmia datasets from MITDB and AFDB. Future researchers are encouraged to explore and acquire a more extensive collection of arrhythmia data to further enhance denoising performance.

show abstract

Section: Metricsmentioning

confidence: 94%