Classification of ECG signals of normal and abnormal subjects using common spatial pattern

Abstract

In this paper, an ECG signal classification method is presented to classify multi-lead ECG signals into normal and abnormal classes using Common Spatial Pattern (CSP) as the feature extraction algorithm. The method consists of two main stages: CSP-based feature extraction and classification. After segmenting the signal into non-overlapping segments, each segment is projected onto a CSP projection matrix to extract the training and testing feature vectors. These vectors are used in the classification stage. In this study, three classifiers — linear discriminant analysis (LDA), naive Bayes (NB), and support vector machine (SVM)—were used. The proposed approach was evaluated using 104 subjects' recordings (52 normal and 52 abnormal) from the Physikalisch-Technische Bundesanstalt (PTB) dataset. The three classifiers achieved accuracy rates of 80.65%, 84%, and 100%, respectively.