Novel methodology of cardiac health recognition based on ECG signals and evolutionary-neural system
作者：
Highlights：
• New methodology based on single lead and analysis of longer (10-s) ECG signal fragments is proposed.
• New training based on genetic algorithm coupled with 10-fold cross-validation is employed.
• 17 classes: normal sinus rhythm + pacemaker rhythm + 15 cardiac disorders are recognized.
• New feature extraction and selection based on PSD, DFT and GA are employed.
• Recognition sensitivity at a level of 90.20% (98 errors per 1000 classifications) is promising.
摘要
•New methodology based on single lead and analysis of longer (10-s) ECG signal fragments is proposed.•New training based on genetic algorithm coupled with 10-fold cross-validation is employed.•17 classes: normal sinus rhythm + pacemaker rhythm + 15 cardiac disorders are recognized.•New feature extraction and selection based on PSD, DFT and GA are employed.•Recognition sensitivity at a level of 90.20% (98 errors per 1000 classifications) is promising.
论文关键词：ECG,Biomedical signal processing and analysis,Classification,Machine learning algorithms,Neural networks,Support vector machine,K-nearest neighbor algorithm,Evolutionary-neural system,Genetic algorithm,Feature extraction and selection,Discrete Fourier transform
论文评审过程：Received 14 June 2017, Revised 9 August 2017, Accepted 9 September 2017, Available online 13 September 2017, Version of Record 4 October 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.09.022
