An intelligent learning approach for improving ECG signal classification and arrhythmia analysis

作者：

Highlights：

• The proposed work is to analyze an ECG signal for arrhythmia analysis.

• Noise removal of ECG signal, feature extraction, feature selection, and classification of ECG signal into five types of arrhythmia.

• HMM classifier has an average accuracy of 99.8% in classifying the samples into five types of arrhythmia.

• The proposed model has an overall accuracy of 99.7%, the sensitivity of 99.7%, and the positive predictive value of 100% and a detection error rate of 0.0004.

摘要

•The proposed work is to analyze an ECG signal for arrhythmia analysis.•Noise removal of ECG signal, feature extraction, feature selection, and classification of ECG signal into five types of arrhythmia.•HMM classifier has an average accuracy of 99.8% in classifying the samples into five types of arrhythmia.•The proposed model has an overall accuracy of 99.7%, the sensitivity of 99.7%, and the positive predictive value of 100% and a detection error rate of 0.0004.

论文关键词：ECG,Noise suppression,Baseline wander (BW),Power line interference (PLI),Electromyography (EMG),Signal to noise ratio (SNR),Devoted wavelet,Feature extraction,HMM (Hidden Markov Model),Cardiac arrhythmia

论文评审过程：Received 16 May 2019, Revised 19 September 2019, Accepted 30 December 2019, Available online 31 December 2019, Version of Record 7 January 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2019.101788