Detection of Cardiac Arrhythmia based on feature fusion and Machine Learning algorithms

Automated analysis of Electrocardiogram(ECG) signal has a great importance for early diagnosis of cardiovascular arrhythmia. This work deals with the governing process for the detection of arrhythmic and normal ECG signals which are collected from MIT-BIH database. Collected raw ECG signals are used for preprocessing to remove the noise from the signal. From the preprocessed ECG signal different morphological and nonlinear parameters are extracted as features for the detection process. Adaptive weight factor of individual feature is evaluated for the development of fused feature sets for better classification accuracy. Machine learning algorithms like Decision tree, Random Forest, Support Vector Machine have been employed for the classification process. The best classification result with 99.08% accuracy has been obtained using the Random Forest classifier.