Using independent component analysis to obtain feature space for reliable ECG Arrhythmia classification

Abstract

Electrocardiogram (ECG) reflects the activities of the human heart and reveals hidden information on its structure and behaviour. The information is extracted to gain insights that assist explanation and identification of diverse pathological conditions. This was traditionally done by an expert through visual inspection of ECGs. The complexity and tediousness of this onus hinder long-term monitoring and rapid diagnosis, computerised and automated ECG signal processing are therefore sought after. In this paper an algorithm that uses independent component analysis (ICA) to improve the performance of ECG pattern recognition is proposed. The algorithm deploys the basis functions obtained via the ICA of typical ECG to extract ICA features of ECG signals for further pattern recognition, with the hypothesis that components of an ECG signal generated by different parts of the heart during normal and arrhythmic cardiac cycles might be independent. The features obtained via the ICA together with the R-R interval and QRS segment power are jointly used as the input to a machine learning classifier, an artificial neural network in this case. Results from training and validation of the MIT-BIH Arrhythmia database shows significantly improved performance in terms of recognition accuracy. This new method also allows for the reduction of the number of inputs to the classifier, simplifying the system and increasing the real-time performance. The paper presents the algorithm, discusses the principle algorithm and presents the validation results.

ECG-based heartbeat classification for arrhythmia detection: A survey

“…Aiming at reducing the dimension of the feature vector, various techniques have been applied directly on the samples that represent the heartbeat (in the neighborhood of the R peak) as principal component analysis (PCA) [75,76,77], or independent component analysis (ICA) [78,79,80], in which new coefficients are extracted to represent the heartbeat. Chawla [81] presents a comparative study between the use of PCA and ICA to reduce the noise and artifacts of the ECG signal and showed that PCA is a better technique to reduce noise, while ICA is better one to extract features.…”

An Efficient Algorithm for Cardiac Arrhythmia Classification Using Ensemble of Depthwise Separable Convolutional Neural Networks

“…In terms of accuracy, refs. [46] and [47] have the closest but still a lower accuracy than our proposed algorithm, i.e., 99.61% and 99.80%, respectively. Note that, ref.…”

“…Note that, ref. [46] only performs classification for eight classes, while [47] only performs classification for four classes, while we perform classification for sixteen classes. Hence, it is evident that our proposed algorithm with the [256 256 256] ensemble of CNNs outperforms the other algorithms.…”

ECG Arrhythmia Classification Algorithms

“…Using large feature vector can make slow classification algorithm. The dimension of feature vector can be reduced using various techniques like principle component analysis (PCA) [40], [41], [42] or Independent component analysis (ICA) [43],[39], [25]. Some other different techniques are also introduced by authors, like Hermite transform [44], clustering [45], [46], [47], random projection [48], Lyapunov exponent [49], [50], projected and dynamic [38].…”