Analysis And Comparison Of Ventricular Cardiac Arrhythmia Classification Using Sodium Channel Parameters With ANN And KNN Classifier
Aim: Aim of this research is to analyze and compare ventricular Cardiac Arrhythmia (CA) classification using Sodium Channel (Na+) parameters with Artificial Neural Network (ANN) and K-Nearest Neighbour (KNN) classifiers. Materials and Methods: Ten Tusscher Human Ventricular Cell Model (THVCM) (data) is used for arrhythmias classification. THVCM has well defined sodium (Na+) channel dynamics. Sample size was calculated by keeping threshold 0.05, G Power 80%, confidence interval 95% and enrolment ratio as 1. Number of samples considered is 20 for each analysis and will be imported to the classifier, K-Nearest Neighbour (KNN) and Artificial Neural Network (ANN) classifier to find better accuracy. Finally, the results (accuracy) will be validated by using Statistical Package for the Social Science (SPSS) software. Result: Ventricular normal, tachycardia and bradycardia data are fed into novel ANN and KNN classifiers. The results obtained from classifiers for 20 samples are fed to SPSS. In that ANN shows accuracy of 35.6% with standard deviation (3.17822) and Standard error mean (0.71067). Similarly KNN produces an accuracy value of 18.05% with standard deviation (1.19593) and Standard error mean (0.26739). Conclusion: As per the results, it clearly shows that the novel ANN has better accuracy for classification than KNN.
Mahanya.G.B, Nithyaselvakumari S. Analysis And Comparison Of Ventricular Cardiac Arrhythmia Classification Using Sodium Channel Parameters With ANN And KNN Classifier. Cardiometry; Issue 25; December 2022; p.911-918; DOI: 10.18137/cardiometry.2022.25.911918; Available from: https://www.cardiometry.net/issues/no25-december-2022/analysis-comparison-ventricular-cardiac