A lightweight deep learning framework achieved higher ECG compression efficiency and reconstruction accuracy than conventional methods, enabling real-time monitoring on low-power microcontrollers.
Does a deep learning-based framework with adaptive sensing and binary thresholding improve ECG signal compression and reconstruction compared to conventional compressed sensing?
A novel deep learning-based framework for ECG compression and reconstruction outperforms conventional methods and enables efficient, real-time monitoring on low-power edge devices.
Absolute Event Rate: 0% vs 0%
This paper presents an efficient deep learning–based framework for ECG signal compression and reconstruction within the Compressed Sensing (CS) paradigm. Conventional CS techniques often suffer from computational inefficiency and strict sparsity requirements, limiting their suitability for real-time biomedical applications. To overcome these challenges, we propose a lightweight neural architecture that jointly learns an adaptive sensing mechanism and an accurate reconstruction process. The proposed framework introduces two key innovations: (1) a Data-Driven Sensing Matrix (DSM) that dynamically captures the intrinsic structure of ECG signals to achieve superior compression performance, and (2) a Binary Thresholding Matrix (BTM) that converts the learned sensing matrix into a hardware-efficient binary representation. Furthermore, an autoencoder-based end-to-end model is designed to seamlessly integrate sensing and reconstruction. Experimental validation on the MIT-BIH Arrhythmia Database demonstrates that the proposed methods achieve markedly higher reconstruction accuracy and compression efficiency compared to conventional CS approaches. Deployment on an STM32 microcontroller further verifies the potential of the proposed framework for real-time, low-power ECG monitoring in edge and wearable healthcare systems. • Introduces a data-driven sensing matrix for efficient ECG compression. • Proposes a binary threshold matrix enabling hardware-efficient implementation. • Develops a lightweight autoencoder for joint ECG sensing and reconstruction. • Demonstrates real-time, low-power ECG monitoring on STM32 microcontroller.
Lal et al. (Sat,) reported a other. A lightweight deep learning framework achieved higher ECG compression efficiency and reconstruction accuracy than conventional methods, enabling real-time monitoring on low-power microcontrollers.