New ECG Compression Method for Portable ECG Monitoring System Merged with Binary Convolutional Auto-Encoder and Residual Error Compensation

Abstract

In the past few years, deep learning-based electrocardiogram (ECG) compression methods have achieved high-ratio compression by reducing hidden nodes. However, this reduction can result in severe information loss, which will lead to poor quality of the reconstructed signal. To overcome this problem, a novel quality-guaranteed ECG compression method based on a binary convolutional auto-encoder (BCAE) equipped with residual error compensation (REC) was proposed. In traditional compression methods, ECG signals are compressed into floating-point numbers. BCAE directly compresses the ECG signal into binary codes rather than floating-point numbers, whereas binary codes take up fewer bits than floating-point numbers. Compared with the traditional floating-point number compression method, the hidden nodes of the BCAE network can be artificially increased without reducing the compression ratio, and as many hidden nodes as possible can ensure the quality of the reconstructed signal. Furthermore, a novel optimization method named REC was developed. It was used to compensate for the residual between the ECG signal output by BCAE and the original signal. Complemented with the residual error, the restoration of the compression signal was improved, so the reconstructed signal was closer to the original signal. Control experiments were conducted to verify the effectiveness of this novel method. Validated by the MIT-BIH database, the compression ratio was 117.33 and the root mean square difference (PRD) was 7.76%. Furthermore, a portable compression device was designed based on the proposed algorithm using Raspberry Pi. It indicated that this method has attractive prospects in telemedicine and portable ECG monitoring systems.

Compression of Bio-Signals Using Block-Based Haar Wavelet Transform and COVIDOA for IoMT Systems

“…Shi et al [ 29 ] proposed a new ECG compression method based on a binary convolutional auto-encoder (BCAE) equipped with residual error compensation (REC). The proposed method aimed to achieve efficient ECG compression through deep learning while ensuring high signal quality.…”

Deep Learning Autoencoder Study on ECG Signals

“…The evaluation metrics considers two main aspects: reconstruction quality and compression efficiency, gauged through various metrics. Key performance criteria are defined by SNR and RMSE [13]. Furthermore, equations ( 1) and (2) present the formulas for both SNR and RMSE:…”

“…In this context, let the original signal be denoted as Do, the reconstructed signal as Dr, and the average value of the original signal as Dm, with the signal length represented by L. Root mean square (RMS) serves as a metric quantifying the disparity between the original signal and its reconstructed counterpart. Additionally, the SNR is employed to assess the relative magnitude of the true signal against the background noise [13].…”

“…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. These collective findings showcase advancements in autoencoder-based denoising techniques for improving the analysis and detection of arrhythmia signals.…”

The increasing instance of negative emotion reduce the performance of emotion recognition

“…Due to its capability to capture neural electrical activity, EEG is highly valuable in comprehending human cognitive processes, attention, emotional responses (Li et al, 2020;Schlumpf et al, 2022). ECG is capable of providing crucial insights into the heart's functioning (Shi et al, 2022). Features extracted from ECG signals can be utilized to analyze variations in heart rate resulting from emotional changes (Chen P. et al, 2022;Rabbani and Khan, 2022).…”