ECG classification using ICA features and support vector machines

Authors:
Yang Wu;Liqing Zhang
Affiliations:
Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai, China;Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai, China
Venue:
ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I
Year:
2011

Citing 8
Cited 0

A fast fixed-point algorithm for independent component analysis

Neural Computation
Pairwise classification and support vector machines

Advances in kernel methods
Probability Estimates for Multi-class Classification by Pairwise Coupling

The Journal of Machine Learning Research
Feature Selection Based on Mutual Information: Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy

IEEE Transactions on Pattern Analysis and Machine Intelligence
Active learning methods for electrocardiographic signal classification

IEEE Transactions on Information Technology in Biomedicine
Preprocessing and analysis of ECG signals - A self-organizing maps approach

Expert Systems with Applications: An International Journal
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)
Self-adaptive blind source separation based on activation functions adaptation

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Classification accuracy is vital in practical application of automatic ECG diagnostics. This paper aims at enhancing accuracy of ECG signals classification. We propose a statistical method to segment heartbeats from ECG signal as precisely as possible, and use the combination of independent component analysis (ICA) features and temporal feature to describe multi-lead ECG signals. To obtain the most discriminant features of different class, we introduce the minimal-redundancy-maximal-relevance feature selection method. Finally, we designed a vote strategy to make the decision from different classifiers. We test our method on the MIT-BIT Arrhythmia Database, achieving a high accuracy.