Abstract
This paper presents a new approach for the optimization of a dictionary used in ECG signal compression and reconstruction systems, based on Compressed Sensing (CS). Alternatively to fully data driven methods, which learn the dictionary from the training data, the proposed approach uses an over complete wavelet dictionary, which is then reduced by means of a training phase. Moreover, the alignment of the frames according to the position of the R-peak is proposed, such that the dictionary optimization can exploit the different scaling features of the ECG waves. Therefore, at first, a training phase is performed in order to optimize the overcomplete dictionary matrix by reducing its number of columns. Then, the optimized matrix is used in combination with a dynamic sensing matrix to compress and reconstruct the ECG waveform. In this paper, the mathematical formulation of the patient-specific optimization is presented and three optimization algorithms have been evaluated. For each of them, an experimental tuning of the convergence parameter is carried out, in order to ensure that the algorithm can work in its most suitable conditions. The performance of each considered algorithm is evaluated by assessing the Percentage of Root-mean-squared Difference (PRD) and compared with the state of the art techniques. The obtained experimental results demonstrate that: (i) the utilization of an optimized dictionary matrix allows a better performance to be reached in the reconstruction quality of the ECG signals when compared with other methods, (ii) the regularization parameters of the optimization algorithms should be properly tuned to achieve the best reconstruction results, and (iii) the Multiple Orthogonal Matching Pursuit (M-OMP) algorithm is the better suited algorithm among those examined.
Highlights
In recent decades, technological advancements have led to the implementation and diffusion of Wearable Health Devices (WHDs)
The compression of ECG signals is based on Domain Transform Methods (DTMs) [2,3,4], which ensure almost no information loss of the clinical information of the patient, but these methods require a high computational loads at the WHD nodes, which translates to a higher power consumption
The proposed approach is an alternative to fully data driven dictionary optimization methods, where the dictionary is constructed from the training data, and utilizes an overcomplete wavelet dictionary that is reduced by means of dictionary optimization algorithm, in order to leave only the highest impact columns for the purpose of the reconstruction of the ECG signals
Summary
Technological advancements have led to the implementation and diffusion of Wearable Health Devices (WHDs). Digital CS methods require low computational loads in the compression step of ECG signals, and a higher one in the reconstruction step For these reasons, the compression step can be performed directly on WHD by means of CS, while the latter can be achieved by the receiving node that has enough computation power, without energy consumption constraints (e.g., PC, server). The authors present results which demonstrate that, even if the reconstruction quality of CS-based compression is lower than the classical DWT methods, it ensures a much higher energy efficiency and a lower computational load at the sink node, making it suitable for real-time ECG compression and decompression for remote healthcare services. The performance of CS is lower when compared to SPIHT, but the CS-based method proposed in [6] exhibits lower distortion on the reconstructed ECG signal and lower power consumption, making it very appealing for applications with tight constraints such as those required for WHDs
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
