R-Peaks and Wavelet-Based Feature Extraction on K-Nearest Neighbor for ECG Arrhythmia Classification

The aim of this research is to classify 17 types of arrhythmias by applying the algorithm developed from combining the morphological and the wavelet-based statistical features. The proposed arrhythmia classification algorithm consists of four stages: pre-processing, detection of R-peaks, feature extraction, and classification. Seven morphological features (MF) that were retrieved from the R-peak locations. Following this, another nine wavelet-based statistical features (SF) were gathered by decomposing wavelets in level 4 from the Daubechies 1 wavelet (Db1). These 16 features are then applied to the k-nearest neighbor (k-NN) algorithm. The accuracy (ACC) of the suggested classification algorithm was assessed by using the MIT-BIH arrhythmia benchmark database (MIT-BIHADB). The experimental results of this work attained an average accuracy (ACC) of 99.00%.