Adaptive Dictionary Reconstruction for Compressed Sensing of ECG Signals

Abstract

This paper proposes a novel adaptive dictionary (AD) reconstruction scheme to improve the performance of compressed sensing (CS) with electrocardiogram signals (ECG). The method is based on the use of multiple dictionaries, created using dictionary learning (DL) techniques for CS signal reconstruction. The modified reconstruction framework is a two-stage process that leverages information about the signal from an initial signal reconstruction stage. By identifying whether a QRS complex is present and if so, determining a location estimate of the QRS, the most appropriate dictionary is selected and a second stage more refined signal reconstruction can be obtained. The performance of the proposed algorithm is compared with state-of-the-art CS implementations in the literature, as well as the set partitioning in hierarchical trees (SPIHT) wavelet-based lossy compression algorithm. The results indicate that the proposed reconstruction scheme outperforms all existing CS implementations in terms of signal fidelity at each compression ratio tested. The performance of the proposed approach also compares favorably with SPIHT in terms of signal reconstruction quality. Furthermore, an analysis of the overall power consumption of the proposed ECG compression framework as would be used in a body area network (BAN) demonstrates positive results for the proposed CS approach when compared with existing CS techniques and SPIHT.

A Novel Blaschke Unwinding Adaptive-Fourier-Decomposition-Based Signal Compression Algorithm With Application on ECG Signals

“…The principle is evaluating the coefficients of the original signal associated with a pre-designed basis so that the signal can be represented by few parameters. For example, the wavelet transform [10,13,14,15], the discrete cosine transform (DCT) [16,17], the Hermite transform [18,19], the nonlinear transform [20], the compressed sensing [21,22,23], and the singular value decomposition (SVD) [24,25]. While the wavelet transform is popular, however, the compression performance is largely dependent on the chosen mother wavelet, number of decomposition levels and different optimization schemes [26].…”

“…Note that we do not compare our results with that reported in [25], since only 14 cases out of the whole database were reported in it. We also do not make comparison with the compressed sensing [21,22,23], because the algorithm of set partitioning in hierarchical tree (SPIHT) [15] performs better than the compressed sensing presently, and our performance results outperform SPTHI as shown in Table 3. Table 4 lists a comparison for records no.…”

Compressed sensing for electrocardiogram acquisition in wireless body sensor network: A comparative analysis

“…36 Besides, Engan et al 37 adopted a series of iterative least square-based DL algorithms while multi-scale DL is exploited by Polania and Barner 38 to evacuate the correlation within each wavelet sub-band. Multiple overcomplete dictionaries are used by Craven et al, 39 and furthermore, two-stage reconstruction was creatively developed at the same time. The ECG signal was first recovered using the standard K-SVD dictionary, and then QRS detection was performed to decide whether there is a QRS complex and location of the QRS in this reconstructed signal piece.…”

“…Experimental results revealed the superiority of the proposed approach. 39 Besides the application in ECG acquisition which is the primary concern of this article, CS is also applicable for compressed and lowcost acquisition of EEG, 40,41 EMG, 30,42 and PPG (photoplethysmogram) 43 in WBSN. For example, Baheti and Garudadri 43 developed a CS-based hardware system for noninvasive monitoring of pulse oximeter.…”

“…There are other 30 original ECG recordings introduced for training of standard K-SVD, 35,36 and relative overcomplete dictionaries of a state-of-the-art algorithm. 39 2. Performance indicators.…”