Title: The estimation of statistical features from VMD levels for automated sleep apnoea classification

Authors: M. Suchetha; A. Smruthy; D. Edwin Dhas; S. Sehastrajit; Said Ziani

Addresses: Centre for Healthcare Advancement, Innovation and Research, Vellore Institute of Technology, Chennai Campus, India ' Centre for Healthcare Advancement, Innovation and Research, Vellore Institute of Technology, Chennai Campus, India ' Centre for Healthcare Advancement, Innovation and Research, Vellore Institute of Technology, Chennai Campus, India ' Centre for Healthcare Advancement, Innovation and Research, Vellore Institute of Technology, Chennai Campus, India ' ENSAM, Mohammed V University, Rabat, Morocco

Abstract: Sleep-related diseases are common nowadays. It is affecting around 30% of the total population all over the world. The main reasons for sleep apnoea syndrome are the lack of exercise and obesity. It is important to screen the sleep apnoea because it indirectly affects the cardiovascular and intelligence quotient (IQ) functions. In this proposed work, we are introducing a novel classification of apnoea and healthy subjects by using the variational mode decomposition (VMD) algorithm. The main intention of this work is to extract the different statistical features from the decomposed electrocardiogram (ECG) modes and classify the features that are extracted from the decomposed modes using the support vector machine (SVM) classifier model. Our proposed work attained an accuracy of 97.56% in the classification of sleep apnoea.

Keywords: variational mode decomposition; VMD; sleep apnoea; electro cardiogram; support vector machine; SVM; intelligent quotient.

DOI: 10.1504/IJBRA.2024.141381

International Journal of Bioinformatics Research and Applications, 2024 Vol.20 No.4, pp.357 - 369

Received: 06 Oct 2023
Accepted: 04 Mar 2024
Published online: 10 Sep 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article