An efficient automated technique for CAD diagnosis using flexible analytic wavelet transform and entropy features extracted from HRV signals
作者:
Highlights:
• Classification of normal and CAD subjects is proposed using HRV signals.
• FAWT is used to decompose the HRV signal.
• K-NN entropy estimator and fuzzy entropy are used for feature extraction.
• Obtained classification accuracy of 100%.
摘要
•Classification of normal and CAD subjects is proposed using HRV signals.•FAWT is used to decompose the HRV signal.•K-NN entropy estimator and fuzzy entropy are used for feature extraction.•Obtained classification accuracy of 100%.
论文关键词:HRV,CAD,FAWT,Nonlinear features,LS-SVM
论文评审过程:Received 4 December 2015, Revised 17 May 2016, Accepted 16 June 2016, Available online 27 June 2016, Version of Record 7 July 2016.
论文官网地址:https://doi.org/10.1016/j.eswa.2016.06.038