A novel QRS complex detection on ECG with motion artifact during exercise

We present a novel QRS complex detection scheme from ECG with motion artifact. The algorithm relies on subspace learning and template matching. QRS complex detection during exercise is a challenging problem because multiple artifacts affect the ECG measurement. Motion artifact is considered to be the main disturbance added to the measurement during exercise. To deal with the problem, we train a dictionary to represent motion artifact using information from a tri-axis accelerometer, and then remove the artifact contribution from noisy ECG measurements. We select the GCC-PHAT filter for efficient QRS detection on the denoised ECG measurements. We show that the proposed algorithm has appreciably higher motion artifact reduction capability and lower computational complexity than competing algorithms. It is therefore a preferred alternative for implementation in mobile health monitoring systems.

[1]  David A. Tong,et al.  Adaptive reduction of motion artifact in the electrocardiogram , 2002, Proceedings of the Second Joint 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society] [Engineering in Medicine and Biology.

[2]  Pablo Laguna,et al.  A wavelet-based ECG delineator: evaluation on standard databases , 2004, IEEE Transactions on Biomedical Engineering.

[3]  Ahmed H. Tewfik,et al.  Learning Sparse Representation Using Iterative Subspace Identification , 2010, IEEE Transactions on Signal Processing.

[4]  S Odman.  Changes in skin potentials induced by skin compression. , 1989, Medical & biological engineering & computing.

[5]  A. Bruckstein,et al.  K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation , 2005 .

[6]  N.V. Thakor,et al.  Applications of adaptive filtering to ECG analysis: noise cancellation and arrhythmia detection , 1991, IEEE Transactions on Biomedical Engineering.

[7]  Chih-Yu Hsu,et al.  A Novel Personal Identity Verification Approach Using a Discrete Wavelet Transform of the ECG Signal , 2008, 2008 International Conference on Multimedia and Ubiquitous Engineering (mue 2008).

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

[9]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[10]  D. Hertz,et al.  Time delay estimation by generalized cross correlation methods , 1984 .

[11]  J. Webster,et al.  The origin of skin-stretch-caused motion artifacts under electrodes. , 1996, Physiological measurement.

[12]  G. Carter,et al.  The generalized correlation method for estimation of time delay , 1976 .

[13]  Michael S. Brandstein,et al.  A robust method for speech signal time-delay estimation in reverberant rooms , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[14]  Sunyoung Kim,et al.  Correlation Between Electrode-Tissue Impedance and Motion Artifact in Biopotential Recordings , 2012, IEEE Sensors Journal.

[15]  Rik Vullings,et al.  Using an injection signal to reduce motion artifacts in capacitive ECG measurements , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).