Article: Impact of feature extraction techniques on cardiac arrhythmia classification: experimental approach Journal: International Journal of Computer Applications in Technology (IJCAT) 2021 Vol.66 No.2 pp.132 - 144 Abstract: This paper provides comparative analysis of state-of-the-art feature extraction techniques in context of ECG arrhythmia classification. In addition, the authors examine a linear heuristic function LW-index as an indirect measure for separability of feature sets. Seven feature sets are extracted using state-of-the-art feature extraction techniques. These include Temporal features, Morphological features, EMD-based features, Wavelet Transform-based features, DCT features, Hjorth Parameters and Convolutional features, respectively. The feature sets' performance is evaluated using SVM classifier. The experimental set up is designed to classify ECG signals into four types of arrhythmic beats which are normal (N), Ventricular Ectopic Beat (VEB), Supraventricular Ectopic Beat (SVEB) and fusion beat (F). A PSO-based feature selection method is used for dimensionality reduction utilising LW-index as cost function. The results validate the hypothesis that convolutional features have better discrimination capability as compared to other state-of-the-art features. This paper can resolve the hassles for new researchers related to performance efficacy of individual feature extraction techniques. The work offers an inexpensive methodology and measure to indirectly evaluate and compare the performance of feature sets. Inderscience Publishers - linking academia, business and industry through research

Title: Impact of feature extraction techniques on cardiac arrhythmia classification: experimental approach

Authors: Manisha Jangra; Sanjeev Kumar Dhull; Krishna Kant Singh

Addresses: Department of ECE, Guru Jambheshwar University of Science & Technology, Hisar, Haryana, India ' Department of ECE, Guru Jambheshwar University of Science & Technology, Hisar, Haryana, India ' Faculty of Engineering and Technology, Jain (Deemed-to-be University), Bengaluru, Karnataka, India

Abstract: This paper provides comparative analysis of state-of-the-art feature extraction techniques in context of ECG arrhythmia classification. In addition, the authors examine a linear heuristic function LW-index as an indirect measure for separability of feature sets. Seven feature sets are extracted using state-of-the-art feature extraction techniques. These include Temporal features, Morphological features, EMD-based features, Wavelet Transform-based features, DCT features, Hjorth Parameters and Convolutional features, respectively. The feature sets' performance is evaluated using SVM classifier. The experimental set up is designed to classify ECG signals into four types of arrhythmic beats which are normal (N), Ventricular Ectopic Beat (VEB), Supraventricular Ectopic Beat (SVEB) and fusion beat (F). A PSO-based feature selection method is used for dimensionality reduction utilising LW-index as cost function. The results validate the hypothesis that convolutional features have better discrimination capability as compared to other state-of-the-art features. This paper can resolve the hassles for new researchers related to performance efficacy of individual feature extraction techniques. The work offers an inexpensive methodology and measure to indirectly evaluate and compare the performance of feature sets.

Keywords: ECG; feature extraction; validity index; feature selection; CNN; PSO; DWT; DCT; Hjorth parameters; EMD; temporal features; MIT-BIH database; SVM.

DOI: 10.1504/IJCAT.2021.119766

International Journal of Computer Applications in Technology, 2021 Vol.66 No.2, pp.132 - 144

Received: 19 Jul 2020
Accepted: 26 Sep 2020
Published online: 20 Dec 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Impact of feature extraction techniques on cardiac arrhythmia classification: experimental approach

Keep up-to-date