Prediction of arrhythmia from MIT-BIH database using random forest (RF) and voted perceptron (VP) classifiers.

The main purpose of the study is to predict arrhythmia from the MIT-BIH database using Random Forest (RF) and Voted Perceptron (VP) classifiers. Materials and Methods: The proposed study uses the RF and VP Machine learning Algorithms to predict the arrhythmia using MIT-BIH dataset with healthy (n=65) and Arrhythmia (n=65) ECG signals collected from IEEE data port in.XLSX format for our study with alpha value as 0.05, 95% as CI, power as 80% and enrolment ratio as 1. The classification of arrhythmia and healthy subjects was performed using WEKA 3.8.5, a data mining tool. The statistical analysis was performed on IBM SPSS software version 21. RESULTS: The statistical significant difference (p<.000) was observed between RF and VP classifiers. Conclusion: The classifiers have been trained, tested, validated using 10 fold cross-validation in WEKA software, the innovative voted perceptron classifier has achieved a higher classification accuracy rate (88.86)% than RF classifier (87.06)%. [ABSTRACT FROM AUTHOR]