Orthogonal Matching Pursuit Based Classifier for Premature Ventricular Contraction Detection

Premature Ventricular Contractions (PVCs) are a common topic of discussion among cardiologists as this type of heart arrhythmia is very frequent among the general population, often endangering people’s health. In this paper, a software system is proposed that differentiates PVCs from normal, healthy heartbeats collected in the MIT-BIH Arrhythmia Database. During classification, training data were recorded from subjects different than those from which testing data were measured, making the classifiers attempt to recognize patterns they were not trained for. A modification of the Orthogonal Matching Pursuit (OMP) based classifier is described and used for comparison with other, well-established classifiers. The absolute accuracy of the described algorithm is 87.58%. More elaboration on the results based on cross-reference is also given.

[1]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[2]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[3]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[4]  John D. Storey,et al.  Optimality Driven Nearest Centroid Classification from Genomic Data , 2007, PloS one.

[5]  Roger G. Mark,et al.  The MIT-BIH Arrhythmia Database on CD-ROM and software for use with it , 1990, [1990] Proceedings Computers in Cardiology.

[6]  Qi Haibing,et al.  A Method of Continuous Wavelet Transform for QRS Wave Detection in ECG Signal , 2010, 2010 International Conference on Intelligent Computation Technology and Automation.

[7]  D. Lavanya,et al.  Performance Evaluation of Decision Tree Classifiers on Medical Datasets , 2011 .

[8]  Václav Snásel,et al.  Preprocessing methods for SVD-based iris recognition , 2010, 2010 International Conference on Computer Information Systems and Industrial Management Applications (CISIM).

[9]  T. Blumensath,et al.  On the Difference Between Orthogonal Matching Pursuit and Orthogonal Least Squares , 2007 .

[10]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  M. Teshnelab,et al.  Comparison of neural network, ANFIS, and SVM classifiers for PVC arrhythmia detection , 2008, 2008 International Conference on Machine Learning and Cybernetics.

[12]  Lenka Lhotska,et al.  Proposal of Feature Extraction from Wavelet Packets Decomposition of QRS Complex for Normal and Ventricular ECG Beats Classification , 2009 .

[13]  G. Bortolan,et al.  Comparison of four methods for premature ventricular contraction and normal beat clustering , 2005, Computers in Cardiology, 2005.

[14]  G.B. Moody,et al.  The impact of the MIT-BIH Arrhythmia Database , 2001, IEEE Engineering in Medicine and Biology Magazine.

[15]  Pavel Bobrov,et al.  Brain-Computer Interface: Common Tensor Discriminant Analysis classifier evaluation , 2011, 2011 Third World Congress on Nature and Biologically Inspired Computing.

[16]  Gregory T. A. Kovacs,et al.  Robust Neural-Network-Based Classification of Premature Ventricular Contractions Using Wavelet Transform and Timing Interval Features , 2006, IEEE Transactions on Biomedical Engineering.