Share Email Print

Proceedings Paper

Adaptive EMG noise reduction in ECG signals using noise level approximation
Author(s): Mohamed Marouf; Lazar Saranovac
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper the usage of noise level approximation for adaptive Electromyogram (EMG) noise reduction in the Electrocardiogram (ECG) signals is introduced. To achieve the adequate adaptiveness, a translation-invariant noise level approximation is employed. The approximation is done in the form of a guiding signal extracted as an estimation of the signal quality vs. EMG noise. The noise reduction framework is based on a bank of low pass filters. So, the adaptive noise reduction is achieved by selecting the appropriate filter with respect to the guiding signal aiming to obtain the best trade-off between the signal distortion caused by filtering and the signal readability. For the evaluation purposes; both real EMG and artificial noises are used. The tested ECG signals are from the MIT-BIH Arrhythmia Database Directory, while both real and artificial records of EMG noise are added and used in the evaluation process. Firstly, comparison with state of the art methods is conducted to verify the performance of the proposed approach in terms of noise cancellation while preserving the QRS complex waves. Additionally, the signal to noise ratio improvement after the adaptive noise reduction is computed and presented for the proposed method. Finally, the impact of adaptive noise reduction method on QRS complexes detection was studied. The tested signals are delineated using a state of the art method, and the QRS detection improvement for different SNR is presented.

Paper Details

Date Published: 19 December 2017
PDF: 9 pages
Proc. SPIE 10613, 2017 International Conference on Robotics and Machine Vision, 106130E (19 December 2017); doi: 10.1117/12.2299841
Show Author Affiliations
Mohamed Marouf, Univ. of Belgrade (Serbia)
Lazar Saranovac, Univ. of Belgrade (Serbia)

Published in SPIE Proceedings Vol. 10613:
2017 International Conference on Robotics and Machine Vision
Chiharu Ishii; Genci Capi; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top