Wavelet analysis for detection of phasic electromyographic activity in sleep: Influence of mother wavelet and dimensionality reduction

• Type of Material: Article
• Authors: Jacqueline A. Fairley, Emory University; George Georgoulas, Technological Educational Institution of Epirus; Otis L. Smart, Emory University; George Dimakopoulos, University of Aegean; Petros Karvelis, Technological Educational Institution of Epirus; Chrysostomos D. Stylios, Technological Educational Institution of Epirus; David Rye, Emory University; Donald Bliwise, Emory University
• Language: English
• Date: 2014-05-01
• Publisher: Elsevier: 12 months
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2014.Published by Elsevier Ltd.
• License: Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1016/j.compbiomed.2013.12.011
• Title of Journal or Parent Work: Computers in Biology and Medicine
• ISSN: 0010-4825
• Volume: 48
• Issue: 1
• Start Page: 77
• End Page: 84
• Grant/Funding Information: This work was supported in part by the National Institute for Neurological Disorders and Stroke (NINDS) under Grant Nos. 1 R01 NS-050595; 1 R01 NS-055015; 1 F32 NS-070572, 3 R01 NS-079268-02W1; and the “Action support post-doctoral fellows of the Operational Programme Education and Lifelong Learning” of the Greek Ministry of Education; Lifelong Learning and Religious Affairs; co-financed by the European Union; along with the National Science Foundation sponsored program Facilitating Academic Careers in Engineering and Science (FACES) at the Georgia Institute of Technology (GaTech) and Emory University.
• Keywords: Life Sciences & Biomedicine - Other Topics; Science & Technology; Technology; Electromyogram; Principal component analysis; Feature selection; Rapid eye movement sleep behavior disorder (RBD); Life Sciences & Biomedicine; Feature extraction; Mathematical & Computational Biology; Engineering, Biomedical; Wavelets; BEHAVIOR DISORDER; Engineering; Computer Science, Interdisciplinary Applications; Biology; Computer Science
• Research Categories: Engineering, Biomedical; Biology, Neuroscience

Abstract

Phasic electromyographic (EMG) activity during sleep is characterized by brief muscle twitches (duration 100-500. ms, amplitude four times background activity). High rates of such activity may have clinical relevance. This paper presents wavelet (WT) analyses to detect phasic EMG, examining both Symlet and Daubechies approaches. Feature extraction included 1. s epoch processing with 24 WT-based features and dimensionality reduction involved comparing two techniques: principal component analysis and a feature/variable selection algorithm. Classification was conducted using a linear classifier. Valid automated detection was obtained in comparison to expert human judgment with high (>90%) classification performance for 11/12 datasets.