A PVC Identification Method of ECG Signal Based on Improved BPNN

Abstract:

Computer-aided diagnosis of Premature Ventricular Contraction (PVC) plays an important role in timely detection and treatment of arrhythmias. Conventional identification methods based on back propagation neural network (BPNN) get problems of overlong training time and local optimum. This paper proposes an application of improved BPNN on PVC identification and the improvements of BPNN are based on self-adaptive learning rate and momentum in training. Denoising and feature extraction of ECG signal obtained from MIT-BIH arrhythmia database are processed first. A comparison between standard BPNN and improved BPNN shows that the latter gets less training time and better accuracy.

• Periodical: Applied Mechanics and Materials (Volumes 738-739)
• Pages: 578-581
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.738-739.578
• Online since: March 2015
• Authors: Xiong Yang*, Xin Yu Jin, Jian Feng Shen
• Keywords: BPNN, ECG Signal, Momentum, PVC Identification, Self-Adaptive Learning Rate

References

[1] Qu Xiao; Cai Wei Jian; Ge Ding Fei, ECG signal classification based on BPNN, Electric Information and Control Engineering (ICEICE), 2011 International Conference on , vol., no., p.1362, 1364, 15-17 April (2011).

DOI: 10.1109/iceice.2011.5777902

[2] Wang Zhiqiong; Liu Hongyan; Xiao Jing, The ELM-based Algorithm on the Detection of Premature Ventricular Contraction, Journal of Computer Research and Development, vol 50, pp.196-204; (2013).

[3] YuemeiXu; Hong Zhang; Study on the Improved BP Algorithm and Application, Information Processing, 2009. APCIP 2009. Asia-Pacific Conference on , vol. 1, no., p.7, 10, 18-19 July (2009).

DOI: 10.1109/apcip.2009.9

[4] Cheng-Yi Chiang; Hong-Hui Chen; Tung-Chien Chen; Chien-Sheng Liu; Yu-Jie Huang; Shey-Shi Lu; Chii-Wann Lin; Liang-Gee Chen, Analysis and design of on-sensor ECG processors for realtime detection of VF, VT, and PVC, Signal Processing Systems (SIPS), 2010 IEEE Workshop on , vol., no., p.42, 45, 6-8 Oct. (2010).

DOI: 10.1109/sips.2010.5624762

[5] Li Song; Liu Li-jun; Xie Yong-le; Chaotic prediction for short-term traffic flow of optimized BP neuralnetwork based on genetic algorithm,; Control and Decision , vol 26, no 10, p.1581, 1585, Oct (2011).

[6] Hui Zhang; Yongqi Wang; Chen Deng, Application of gesture recognition based on simulated annealing BP neural network, Electronic and Mechanical Engineering and Information Technology (EMEIT), 2011 International Conference on , vol. 1, no., p.178, 181, 12-14 Aug. (2011).

DOI: 10.1109/emeit.2011.6022891

[7] RongXie; Xinmin Wang; Yan Li; Kairui Zhao, Research and application on improved BP neural network algorithm, Industrial Electronics and Applications (ICIEA), 2010 the 5th IEEE Conference on , vol., no., p.1462, 1466, 15-17 June (2010).

DOI: 10.1109/iciea.2010.5514820