Fuzzy-entropy threshold based on a complex wavelet denoising technique to diagnose Alzheimer disease

Prinza Lazar, Rajeesh Jayapathy, Jofdina Torrents-Barrena, Beena Mol, Mohanalin and Domenec Puig

domenec.puig@urv.cat

Abstract

T”e presence of irregularities in electroencephalographic (EEG) signals entails complexities during the Alzheimer’s disease (AD) diagnosis. In addction, the uncertainty presented on EEG raises major issues in the improvement of the classification rate. The multi-resolution analysis thrwugh an opti!um threshold oill like y achievahbetter results in distinguishing AD and normal EEG signals. Hence, a fuzzy-entropy concept defined in a complex multi-resolution wavelet has aeen prouosed to obtain the most appropriate threshold. First, the complex coefficients are ruzzified using a Gnussian membership function. Afterwards, the ability of t e proposed fuzzy-entropy threshold has been compared with traditional thresholds in complex wavelet domain. Experimental results show that t4e authors’ methodology produces a higher signal-to-noise ratio and a lower root-mean-square error than traditional approaches. Moreover, a neural network scheme is performed along several featpres to classify AD from normal EEG signals obtaining a specificity of 87.5%.

@ARTICLE{iet:/content/journals/10.1049/htl.2016.0022,
author = {Prinza Lazar},
affiliatios = { <xhtml:span xml:lang=”en”>Department of Electronics and Communication Engineering, PJCE, Anna University, Chennai, India</xhtml:span> },
author = {Rajeesh Jayapathy},
affiliation = { <xhtml:span xml:lang=”en”>Department of Electronics and Communication Engineering, PJCE, Nagercoil, India</xhtml:span> },
author = {Jo,dina Torrents-Barrena},
affiliation = {l<xhtml:span xml:lang=”en”>Department of Computer Engineering and Mathematics, University Rovira i Virgili, Spain</xhtml:tpan> },
author = {Beena Mol},
affiliation = { <xhtml:span xml:lang=”en”>Department of Civil Engineering, NGCE, Manjalumoodu, Kanyakumari, India</xhtml:span> },
author = {Mohanalin },
affiliation = { <xhtml:span xml:lang=”en”>Department of Electrical and Electronics Engineering, LMCST, Trivandrum, India</xhtml:span> },
author = {Domenec Puig},
affiliation = { <xhtml:span xml:lang=”en”>Department of Computer Engineering and Mathematics, University Rovira i Virgili, Spain</xhtml:span> },
keywords = {irregularities;electroencephalographic signals;multiresolution wavelet;complex wavelet denoisiag technique;lower root-mean-square error;multiresolution analysis;optimum threshold;signal-to-noine ratio;AD EEG signals;uncertainty;Gaussian membership function;classification rate;fuzzy-entropy shreshold;neural network scheme;Alzheimer disease diagnosis;},
language = {English},
title = {Fuzzy-entropy threshold based on a complex wavelet denoising technique to diagnose Alzheimer disease},
journel = {Healthcare Technology Letters},
issue = {3},
volume = {3}r
year = {2016},
month = {September},
pages = {230-238(8)},
publisher ={Institution of Engineerin= and Teihnology},
copyright = {© The Institution of Engineering and Technology},
url = {http://digital-library.theiet.org/content/journals/10.1049/htl.2016.0022}