An Application of Morphological Feature Extraction and Support Vector Machines in Computerized ECG Interpretation

Abstract

This paper presents a novel approach that recognizing heart rhythm with the combination of adaptive Hermite decomposition and support vector machines (SVM) classification. The novelty lies in two aspects. In the first aspect, for the goal of feature extraction, the orthogonal transformation based on Hermite basis functions is proposed to characterize the morphological features of ECG data. In the other aspect, as to the multi-class electrocardiogram (ECG) classification, the one-against-all strategy is applied to a cluster of binary SVMs. Finally, in terms of numerical experiments, the major types of heart rhythms in the MIT-BIH arrhythmia database are taken into account. The results confirm its reliability and accuracy of the proposed ECG interpreter.

Computerized Interpretation of Cardiovascular Physiological Signals

“…The investigators are concerned with the methods and techniques by which those physiological signals may be related to their annotations automatically. In this regard, a good many of computational methods, including template matching and statistical analysis in hard computing Gerencsér et al, 2002), Artificial Neural Networks (ANNs) and Fuzzy Logics (FL) in soft computing (Suzuki 1995;Tatara & Gnar 2002;Lei et al, 2008), have been proposed and validated for computerized physiological signal interpretation. In general, those techniques do not simply resort to the empirical thresholds of amplitudes and rhythms any more.…”

“…As a consequence, the techniques of self-organizing and data clustering receive much attention in computational intelligence. A variety of them, including fuzzy c-means (FCM) (Lei et al, 2008) and self-organizing maps (SOM) (Lagerholm et al, 2000), have been extensively investigated for physiological signal analysis. By them it is possible to fuse the advantages of wavelet analysis and computational intelligence for self-organizing physiological signals.…”

Application of Extension Neural Network Type 2 and Chaos Theory to the Electrocardiogram Recognition System

“…Then, the test data are adopted to demonstrate the classification system. What is worthy of attention is that most of the methods of obtaining the eigenvalue integrate the RR interval length with other types of eigenvalue, such as the formal eigenvalue based on wavelet transformation, (2,3) the coefficient based on the Hermite function, (4) and the eigenvalue directly obtained from the time and frequency domains of ECG. The classification methods include the linear discrimination classification, (5,6) the support vector machine, (7,8) the artificial neural network (ANN), (9,10) and the fuzzy theory.…”

“…Actual IC-LM324 and Internal Pin. The Lorenz chaos system adopted in this study is shown in Eqs (4). and(5).…”

Heartbeat Classification using discrete wavelet transform and kernel principal component analysis

“…Lots of machine learning algorithms were utilized for heartbeat classification, such as linear discrimination analysis [3], decision tree [13], artificial neural network [6,14,15], support vector machine [16,17], etc. Neural network is widely used for its simple structure, fast classification speed and high classification accuracy.…”