Real-Time Classification of Healthy and Apnea Subjects Using ECG Signals With Variational Mode Decomposition

This paper introduces a novel method for the classification of healthy and apnea subjects using variational mode decomposition. The proposed method distinguishes the apnea and normal subjects with the help of an electrocardiogram (ECG) signal. Polysomnogram is the gold standard used for the identification of apnea subjects. This process is complex, expensive, and time-consuming. In this paper, both online and off-line-based feature extraction and classification methods are explored. The proper extraction of suitable features from the signal is done by applying variational mode decomposition. Two features are extracted from the variational mode functions, namely, energy and RR interval of ECG signal. These features are fed in to a support vector machine classifier, where they are classified as healthy and apnea. The accuracy obtained for both online and off-line processes are 97.5% and 95%, respectively.