Paper Info
Title
Novel methodology of cardiac health recognition based on ECG signals and evolutionary-neural system.
Abstract
•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.
Year
DOI
Venue
2018
10.1016/j.eswa.2017.09.022
Expert Systems with Applications
Keywords
Field
DocType
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
Signal processing,Data mining,Normalization (statistics),Computer science,Artificial intelligence,Artificial neural network,Genetic algorithm,Pattern recognition,Support vector machine,Feature extraction,Discrete Fourier transform,Machine learning,Computational complexity theory
Journal
Volume
Issue
ISSN
92
C
0957-4174
Citations 
PageRank 
References 
29
0.85
66
Authors
1
Name
Order
Citations
PageRank
Pawel Plawiak1998.84