An improved classification method for arrhythmia electrocardiogram dataset

Making a correct diagnosis of the type of arrhythmia is conducive to the prevention and treatment of heart disease, abnormal heart rhythm may be caused by underlying heart disease, and in some circumstances can even give rise to life-threatening. In today's era, the computer technology develops by leaps and bounds, which provides technical conditions for identifying types of arrhythmia. For instance, when determining the type of arrhythmia, electrocardiogram (ECG) data can be automatically classified according to machine learning algorithms. Usually the number of samples under each data set is not necessarily balanced. In this paper Difference-Weighted k-nearest neighbor (DF-WKNN) classifier is presented to recognize unbalanced UCI cardiac arrhythmia data from the UCI arrhythmia data set. This method incorporates the correlation of K neighbors into the classification. Experiments have found that the classification accuracy of DF-WKNN algorithm is 70.80%, which has better effects than other KNN-based algorithms when classifying unbalanced ECG data sets.

[1]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[2]  R. Ganesh Kumar,et al.  A Neural Network Approach for Cardiac Arrhythmia Classification , 2013 .

[3]  Yedukondalu Kamatham,et al.  MSVM-based classifier for cardiac arrhythmia detection , 2016, 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[4]  Saurabh Singh,et al.  ECG Arrhythmia Classification Using Spearman Rank Correlation and Support Vector Machine , 2011, SocProS.

[5]  N.V. Thakor,et al.  Applications of adaptive filtering to ECG analysis: noise cancellation and arrhythmia detection , 1991, IEEE Transactions on Biomedical Engineering.

[6]  G.G. Cano,et al.  An approach to cardiac arrhythmia analysis using hidden Markov models , 1990, IEEE Transactions on Biomedical Engineering.

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

[8]  Henggui Zhang,et al.  3D virtual human atria: A computational platform for studying clinical atrial fibrillation. , 2011, Progress in biophysics and molecular biology.

[9]  Lei Zhang,et al.  GPU-based fusion method for 3D electrophysiological data visualization , 2012, 2012 International Conference on Computerized Healthcare (ICCH).

[10]  A V Holden,et al.  Dynamical and cellular electrophysiological mechanisms of ECG changes during ischaemia. , 2005, Journal of theoretical biology.

[11]  Lei Zhang,et al.  G-Heart: A GPU-based System for Electrophysiological Simulation and Multi-modality Cardiac Visualization , 2014, J. Comput..

[12]  João Luiz Dihl Comba,et al.  Visualizing intracardiac atrial fibrillation electrograms using spectral analysis , 2013, Computing in Science & Engineering.

[13]  Fei Yang,et al.  Fusion visualization for cardiac anatomical and ischemic models with depth weighted optic radiation function , 2015, 2015 Computing in Cardiology Conference (CinC).

[14]  Sahibsingh A. Dudani.  The Distance-Weighted k-Nearest-Neighbor Rule , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[15]  Bai Jie.  Potential Pathogenesis Discovery of Arrhythmia Based on Cardiac Electrophysiological Models:Research Progress , 2016 .

[16]  Henggui Zhang,et al.  A composite visualization method for electrophysiology-morphous merging of human heart , 2017, Biomedical engineering online.

[17]  Kuanquan Wang,et al.  Coupling Ray Radiation Function Based Biophysical Detailed Dual Pattern Cardiac Visualization , 2017 .

[18]  Shweta H. Jambukia,et al.  Classification of ECG signals using machine learning techniques: A survey , 2015, 2015 International Conference on Advances in Computer Engineering and Applications.