Title: EEG and speech signal based multi-class recognition manoeuvre by exploiting a Hyb-SGTS and a dual stage deep CNN architecture for an early diagnosis of HC, AD and PD neurological diseases

Authors: Chetan Balaji; D.S. Suresh

Addresses: Department of Electronics and Communication, Channabasaveshwara Institute of Technology, Gubbi, Visvesvaraya Technological University-Belagavi, India ' Department of Electronics and Communication, Channabasaveshwara Institute of Technology, Gubbi, Visvesvaraya Technological University-Belagavi, India

Abstract: Alzheimer's disease (AD) and Parkinson's disease (PD) are the neurodegenerative illness of the brain that affects the nerve system of brain. The early detection and diagnosis of these disorders are essential in customising patient's treatment plans to better manage the development and progression, this helps to achieve maximum treatment benefit before mental deterioration occurs. In this paper, the early detection of AD with PD diseases utilising hybrid seagull and tunicate swarm (Hyb-SGTS) optimisation based feature selection technique with dual stage deep convolutional neural network (DSDCNN) are proposed. The experimental results obtained from the employed optimisation method yields a better performance and provide maximal classification accuracy with improved efficiency when compared with the existing methods, such as support vector machines (SVMs), Naïve Bayes (NB), K-nearest neighbour (KNN), and random forest (RF). The proposed method will yield in increased accuracy and will produce low computational complexity.

Keywords: neurodegenerative diseases; NDDs; Alzheimer's disease; Parkinson's disease; healthy controls; hybrid seagull and tunicate swarm optimisation algorithm; dual stage deep convolutional neural network; DSDCNN.

DOI: 10.1504/IJBET.2024.138064

International Journal of Biomedical Engineering and Technology, 2024 Vol.44 No.4, pp.348 - 366

Received: 23 Aug 2022
Accepted: 18 Mar 2023
Published online: 18 Apr 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article