Online MECG Compression based on Incremental Tensor Decomposition for Wearable Devices.

Lightweight and real-time multi-lead electrocardiogram (MECG) compression on wearable devices is important and challenging for long-term health monitoring. To make use all three kinds of correlations of MECG data simultaneouly, we construct 3-order incremental tensor and formulate data compression problem as tensor decomposition. However, the conventional tensor decomposition algorithms for large-scale tensor are usually too computationally expensive to apply to wearable devices. To reduce the computation complexity, we develop online compression approach by incrimental tracking the CANDECOMP/PARAFAC (CP) decomposition of dynamic incremental tensors, which can efficiently utilize the tensor compression result based on the previous MECG data to derive the tensor compression upon arriving of new data. We evaluate the performance of our method with the Physikalisch-Technische Bundesanstalt MECG diagnostic dataset. Our method can achieve the averaged percentage root-mean-square difference (PRD) of 8.35 2.28% and the compression ratio (CR) of 43.05 2.01, which is better than five state-of-the-art of methods. Additionally, it can also well preserve the information of R-peak. Our method is suitable for near real-time MECG compression on wearable devices.

[1]  A. G. Ramakrishnan,et al.  ECG coding by wavelet-based linear prediction , 1997, IEEE Transactions on Biomedical Engineering.

[2]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[3]  Michele Rossi,et al.  Boosting the Battery Life of Wearables for Health Monitoring Through the Compression of Biosignals , 2017, IEEE Internet of Things Journal.

[4]  Wisnu Jatmiko,et al.  3D SPIHT for multi-lead ECG compression , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[5]  H A Fozzard,et al.  AZTEC, a preprocessing program for real-time ECG rhythm analysis. , 1968, IEEE transactions on bio-medical engineering.

[6]  Jieping Ye,et al.  Tensor Completion for Estimating Missing Values in Visual Data , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  K.M. Buckley,et al.  ECG data compression using cut and align beats approach and 2-D transforms , 1999, IEEE Transactions on Biomedical Engineering.

[8]  Willis J. Tompkins,et al.  A Real-Time QRS Detection Algorithm , 1985, IEEE Transactions on Biomedical Engineering.

[9]  Samarendra Dandapat,et al.  Block sparsity-based joint compressed sensing recovery of multi-channel ECG signals , 2017, Healthcare technology letters.

[10]  Nai-Kuan Chou,et al.  ECG data compression using truncated singular value decomposition , 2001, IEEE Trans. Inf. Technol. Biomed..

[11]  Arnon D. Cohen,et al.  ECG signal compression using analysis by synthesis coding , 2000, IEEE Transactions on Biomedical Engineering.

[12]  Jiannong Cao,et al.  Accurate Recovery of Internet Traffic Data: A Sequential Tensor Completion Approach , 2018, IEEE/ACM Transactions on Networking.

[13]  Girish Kumar Singh,et al.  Efficient compression technique based on temporal modelling of ECG signal using principle component analysis , 2017 .

[14]  A. Cohen,et al.  Compression of multichannel ECG through multichannel long-term prediction , 1998, IEEE Engineering in Medicine and Biology Magazine.

[15]  Shen-Chuan Tai,et al.  Beat-based ECG compression using gain-shape vector quantization , 2005, IEEE Trans. Biomed. Eng..

[16]  H. Koymen,et al.  Multichannel ECG data compression by multirate signal processing and transform domain coding techniques , 1993, IEEE Transactions on Biomedical Engineering.

[17]  Tsung-Han Tsai,et al.  An Efficient ECG Lossless Compression System for Embedded Platforms With Telemedicine Applications , 2018, IEEE Access.

[18]  W. A. Coberly,et al.  ECG data compression techniques-a unified approach , 1990, IEEE Transactions on Biomedical Engineering.

[19]  Kun Xie,et al.  Missing Data Recovery Based on Tensor-CUR Decomposition , 2018, IEEE Access.

[20]  James Bailey,et al.  Accelerating Online CP Decompositions for Higher Order Tensors , 2016, KDD.

[21]  A. Cohen,et al.  ECG compression using long-term prediction , 1993, IEEE Transactions on Biomedical Engineering.

[22]  Joos Vandewalle,et al.  A Multilinear Singular Value Decomposition , 2000, SIAM J. Matrix Anal. Appl..

[23]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[24]  Xingyuan Wang,et al.  A 2-D ECG compression algorithm based on wavelet transform and vector quantization , 2008, Digit. Signal Process..

[25]  Johan Håstad,et al.  Tensor Rank is NP-Complete , 1989, ICALP.

[26]  Felix J. Herrmann,et al.  Massive 3D seismic data compression and inversion with hierarchical Tucker , 2017 .

[27]  Chih-Lung Lin,et al.  A quality-on-demand algorithm for wavelet-based compression of electrocardiogram signals , 2002, IEEE Transactions on Biomedical Engineering.

[28]  Samarendra Dandapat,et al.  Exploiting multi-lead electrocardiogram correlations using robust third-order tensor decomposition. , 2015, Healthcare technology letters.

[29]  Wen-Shiung Chen,et al.  High performance data compression method with pattern matching for biomedical ECG and arterial pulse waveforms , 2004, Comput. Methods Programs Biomed..

[30]  Philip S. Yu,et al.  Incremental tensor analysis: Theory and applications , 2008, TKDD.

[31]  Rajiv Kumar,et al.  Massive 3 D seismic data compression and inversion with hierarchical , 2017 .

[32]  W. Mueller.  Arrhythmia detection program for an ambulatory ECG monitor. , 1978, Biomedical sciences instrumentation.