Exploiting multi-scale signal information in joint compressed sensing recovery of multi-channel ECG signals

Computational complexity and power consumption are prominent issues in wireless telemonitoring applications involving physiological signals. Compressed sensing (CS) has emerged as a promising framework to address these challenges because of its energy-efficient data reduction procedure. In this work, a CS-based approach is studied for joint compression/reconstruction of multi-channel electrocardiogram (MECG) signals. The MECG signals share spatially correlated cardiac information across the channels, which is exploited in a joint CS framework for improved signal recovery. Weighted mixed-norm minimization (WMNM)-based joint sparse recovery algorithms are proposed, which can successfully recover the signals from all the channels simultaneously by utilizing the joint sparsity of MECG signals in wavelet domain. The proposed algorithms exploit multi-scale signal information through a multi-scale weighting approach. Under this strategy, weights are designed based.on the diagnostic information contents of each wavelet subband/scale. In particular, clinically relevant information is captured in the form of subband energy, entropy, and amplitude decay, and based on this weighting rules are defined at each wavelet scale. Such a weighting approach emphasizes nonzero wavelet coefficients having high diagnostic importance during joint CS reconstruction. Insignificant coefficients are deemphasized simultaneously, resulting in a sparser solution. Simulation results using Physikalisch-Technische Bundesanstalt (PTB), Common Standards for Electrocardiography (CSE) and Massachusetts Institute of Technology-Boston's Beth Israel Hospital (MIT-BIH) MECG databases show that the proposed methods can achieve superior reconstruction quality with a lower number of measurements compared to their non-weighted counterpart and other existing CS-based methods. Reduction in the required number of measurements reduces computational burden and directly translates into higher compression efficiency, resulting in low energy consumption in CS-based telemonitoring systems. The diagnostic reconstruction quality of the algorithm is validated using diagnostic distortion measures like wavelet energy-based diagnostic distortion (WEDD) and with a post-reconstruction classification task. It achieves a classification accuracy of 73.2% even when MECG signals are jointly reconstructed using only about 10% of compressed measurements, validating the diagnosability of the reconstructed signals even at very low data rates. (C) 2016 Elsevier Ltd. All rights reserved.