Abstract
ABSTRACT This manuscript proposes a multi-class recognition system with improved classification accuracy using machine-learning techniques by considering electroencephalogram (EEG) and speech signal analysis to classify and detect patients affected by Alzheimer’s disease (AD) and Parkinson’s disease (PD) in its initial stages. Acquired raw EEG and speech signal are pre-processed utilising wavelet filters to eliminate noises, then the features impedivity, phase angle, higher frequency slope of phase angle, standard deviation, minimal pitch, maximal pitch, count of voice breaks are extracted from EEG and speech signal using bag of deep reduced features. Optimal features mean absolute values, enhanced wavelength, wavelength, zeros crossing are selected using an improved chaotic multi-verse Harris Hawks optimisation (CMVHHO) algorithm. Finally, Random Forest (RF) classifier is employed to classify patients suffered by AD with PD. Experimental results show 95.17%, 96.31% and 97.48% higher accuracy for AD compared with existing methods, like MCR-AD-PD-SPWVD-CNN, MCR-AD-PD-ICA-DSCHN and MCR-AD-DWT-KNN-RLDA, respectively.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.