Heart arrhythmia diagnosis based on the combination of morphological, frequency and nonlinear features of ECG signals and metaheuristic feature selection algorithm
作者：
Highlights：
• A new method for discrimination of seven types of ECG beats is proposed.
• This method employs a combination of morphology, frequency, and nonlinear indices.
• Application of feature selection (include GA, PSO, DE, and NSGA-II) is discussed.
• KNN, RBFNN, FF-net, Fit-net, and Pat-net are employed for classification.
• High classification accuracy 98.75% is obtained based on the proposed method.
摘要
•A new method for discrimination of seven types of ECG beats is proposed.•This method employs a combination of morphology, frequency, and nonlinear indices.•Application of feature selection (include GA, PSO, DE, and NSGA-II) is discussed.•KNN, RBFNN, FF-net, Fit-net, and Pat-net are employed for classification.•High classification accuracy 98.75% is obtained based on the proposed method.
论文关键词：ECG signal,Cardiac arrhythmia recognition,Nonlinear indices,Meta-heuristic optimization algorithm,FF net classifier
论文评审过程：Received 8 February 2020, Revised 18 May 2020, Accepted 25 June 2020, Available online 1 July 2020, Version of Record 8 July 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.113697
