Fuzzy‐entropy threshold based on a complex wavelet denoising technique to diagnose Alzheimer disease. Issue 3 (1st July 2016)

• Record Type: Journal Article
• Authors: Lazar, Prinza; Jayapathy, Rajeesh; Torrents‐Barrena, Jordina; Mol, Beena; Mohanalin, ; Puig, Domenec
• Is Part Of: Healthcare technology letters. Volume 3:Issue 3(2016)
• Page Start: 230
• Page End: 238
• Publication Date: 2016-07-01
• Subjects: fuzzy systems -- diseases -- electroencephalography -- medical signal processing -- signal classification -- signal denoising -- wavelet transforms -- wavelet neural nets -- entropy -- mean square error methods; fuzzy‐entropy threshold -- complex wavelet denoising technique -- Alzheimer disease diagnosis -- irregularities -- electroencephalographic signals -- uncertainty -- classification rate -- multiresolution analysis -- optimum threshold -- AD EEG signals -- multiresolution wavelet -- Gaussian membership function -- signal‐to‐noise ratio -- lower root‐mean‐square error -- neural network scheme; Biomedical engineering -- Periodicals; Medical technology -- Periodicals; 610.28
• DOI: 10.1049/htl.2016.0022
• Languages: English
• ISSNs: 2053-3713

Abstract

Abstract : The presence of irregularities in electroencephalographic (EEG) signals entails complexities during the Alzheimer's disease (AD) diagnosis. In addition, the uncertainty presented on EEG raises major issues in the improvement of the classification rate. The multi‐resolution analysis through an optimum threshold will likely achieve better results in distinguishing AD and normal EEG signals. Hence, a fuzzy‐entropy concept defined in a complex multi‐resolution wavelet has been proposed to obtain the most appropriate threshold. First, the complex coefficients are fuzzified using a Gaussian membership function. Afterwards, the ability of the proposed fuzzy‐entropy threshold has been compared with traditional thresholds in complex wavelet domain. Experimental results show that the 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 features to classify AD from normal EEG signals obtaining a specificity of 87.5%.