Hybrid Reptile-Snake Optimizer Based Channel Selection for Enhancing Alzheimer’s Disease Detection  

作　　者：Digambar Puri Pramod Kachare Smith Khare Ibrahim Al-Shourbaji Abdoh Jabbari Abdalla Alameen 

机构地区：[1]Department of Electronics and Telecommunication,Ramrao Adik Institute of Technology,D.Y.Patil Campus,Navi-Mumbai,Maharashtra,400706,India [2]Maersk Mc-Kinney Moller Institute,Faculty of Engineering,University of Southern Denmark,Odense,Denmark [3]Department of Electrical and Electronics Engineering,Jazan University,Jazan,45142,Saudi Arabia [4]Department of Computer Science,University of Hertfordshire,Hatfield,UK [5]Department of Computer Engineering and Information,College of Engineering in Wadi Alddawasir,Prince Sattam Bin Abdulaziz University,Wadi Alddawasir,11991,Saudi Arabia

出　　处：《Journal of Bionic Engineering》2025年第2期884-900,共17页仿生工程学报(英文版)

摘　　要：The global incidence of Alzheimer's Disease(AD)is on a swift rise.The Electroencephalogram(EEG)signals is an effective tool for the identification of AD and its initial Mild Cognitive Impairment(MCI)stage using machine learning models.Analysis of AD using EEG involves multi-channel analysis.However,the use of multiple channels may impact the classification performance due to data redundancy and complexity.In this work,a hybrid EEG channel selection is proposed using a combination of Reptile Search Algorithm and Snake Optimizer(RSO)for AD and MCI detection based on decomposition methods.Empirical Mode Decomposition(EMD),Low-Complexity Orthogonal Wavelet Filter Banks(LCOWFB),Variational Mode Decomposition,and discrete-wavelet transform decomposition techniques have been employed for subbands-based EEG analysis.We extracted thirty-four features from each subband of EEG signals.Finally,a hybrid RSO optimizer is compared with five individual metaheuristic algorithms for effective channel selection.The effectiveness of this model is assessed by two publicly accessible AD EEG datasets.An accuracy of 99.22% was achieved for binary classification from RSO with EMD using 4(out of 16)EEG channels.Moreover,the RSO with LCOWFBs obtained 89.68%the average accuracy for three-class classification using 7(out of 19)channels.The performance reveals that RSO performs better than individual Metaheuristic algorithms with 60%fewer channels and improved accuracy of 4%than existing AD detection techniques.

关 键 词：Alzheimer's Disease Brain disorder ELECTROENCEPHALOGRAM Reptile Search Algorithm Snake Optimizer Optimization 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]