A generic and patient-specific classification system designed for robust and accurate detection of electrocardiogram (ECG) heartbeat patterns is presented. The proposed feature extraction process utilizes morphological wavelet transform features, which are projected onto a lower dimensional feature space using principal component analysis, and temporal features from the ECG data. Due to its time–frequency localization properties, the wavelet transform is an efficient tool for analyzing nonstationary ECG signals which can be used to decompose an ECG signal according to scale, thus allowing separation of the relevant ECG waveform morphology descriptors from the noise, interference, baseline drift, and amplitude variation of the original signal. For the pattern recognition unit, feedforward and fully connected artificial neural networks (ANNs), which are optimally designed for each patient by the multidimensional particle swarm optimization (MD PSO) technique, are employed. Despite many promising ANN-based techniques have been applied to ECG signal classification, these classifier systems have not performed well in practice and their results have generally been limited to relatively small datasets mainly because such systems have in general static (fixed) network structures for classifiers. On the other hand, the proposed algorithm based on patient-adaptive architecture by means of an evolutionary classifier design has demonstrated significant performance improvement over such conventional global classifier systems. By using relatively small common and patient-specific training data, the proposed classification system can adapt to significant interpatient variations in ECG patterns by training the optimal network structure, and thus, achieves higher accuracy over larger datasets. The classification experiments over a benchmark database demonstrate that the proposed system achieves such average accuracies and sensitivities better than most of the current state-of-the-art algorithms for detection of ventricular ectopic beats (VEBs) and supra-VEBs (SVEBs). Finally, due to its parameter-invariant nature, the proposed system is highly generic, and thus, applicable to any ECG dataset.
Particle Swarm Optimization Architecture Space Particle Swarm Optimization Parameter Propose Feature Extraction Hash Index
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.
Recommended practice for testing and reporting performance results of ventricular arrhythmia detection algorithms. Association for the Advancement of Medical Instrumentation, Arlington (1987)Google Scholar
Shyu, L.Y., Wu, Y.H., Hu, W.C.: Using wavelet transform and fuzzy neural network for VPC detection from the holter ECG. IEEE Trans. Biomed. Eng. 51(7), 1269–1273 (2004)CrossRefGoogle Scholar
Silipo, R., Marchesi, C.: Artificial neural networks for automatic ECG analysis. IEEE Trans. Signal Process. 46(5), 1417–1425 (1998)CrossRefGoogle Scholar
Silipo, R., Laguna, P., Marchesi, C., Mark, R.G.: ST-T segment change recognition using artificial neural networks and principal component analysis. Computers in Cardiology, 213–216 (1995)Google Scholar
Talmon, J.L.: Pattern Recognition of the ECG. Akademisch Proefscrift, Berlin (1983)Google Scholar
Thakor, N.V., Webster, J.G., Tompkins, W.J.: Estimation of QRS complex power spectra for design of a QRS filter. IEEE Trans. Biomed. Eng. 31, 702–705 (1984)CrossRefGoogle Scholar
Van den Bergh, F.: An analysis of particle swarm optimizers. Ph.D. thesis, Department of Computer Science, University of Pretoria, Pretoria (2002)Google Scholar
Willems, J.L., Lesaffre, E.: Comparison of multigroup logisitic and linear discriminant ECG and VCG classification. J. Electrocardiol. 20, 83–92 (1987)CrossRefGoogle Scholar
Yao, X., Liu, Y.: A new evolutionary system for evolving artificial neural networks. IEEE Trans. Neural Netw. 8(3), 694–713 (1997)MathSciNetCrossRefGoogle Scholar