Real-Time Classification of Healthy and Apnea Subjects using ECG Signals with Variational Mode Decomposition

Abstract– In the first place, introduces a novel method for classi-fication of healthy and apnea subjects using variational mode decomposition. At the same time, method distinguishes the apnea and normal subjects with the help of an Electrocardiogram(ECG) signal. Polysomnogram is the gold standard used for identification of apnea subjects. Although, process is complex, expensive and time consuming. In this paper both online and offline based feature extraction and classification methods are explored. while, proper extraction of suitable features from the signal is done by applying variational mode decomposition. In spite of, Two features are extracted from the variational mode functions (VMFs) 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. As a result, accuracy obtained for both online and offline processes are 97.5% and 95% respectively.