A novel framework of MOPSO-GDM in recognition of Alzheimer's EEG-based functional network

Background Most patients with Alzheimer's disease (AD) have an insidious onset and frequently atypical clinical symptoms, which are considered a normal consequence of aging, making it difficult to diagnose AD medically. But then again, accurate diagnosis is critical prevent degeneration provide early treatment for patients. Objective This study aims establish novel EEG-based classification framework deep learning methods recognition. Methods First, considering the network interactions in different frequency bands (δ, θ, α, β, γ), multiplex networks reconstructed by phase synchronization index (PSI) method, fourteen topology features extracted subsequently, forming high-dimensional feature vector. However, combination, not all can effective information Moreover, combining manual selection time-consuming laborious. Thus, optimization algorithm called MOPSO-GDM was proposed multi-objective particle swarm (MOPSO) Gaussian differential mutation (GDM) algorithm. In addition error rates support vector machine, naive bayes, discriminant analysis classifiers, our also considers distance measure as objective. Results Finally, this method achieves excellent rate 0.0531 (5.31%) size 8, ten-fold cross-validation strategy. Conclusion These findings show that adaptively combine best brain explore synchronization, functional interactions, characterize abnormalities, improve recognition efficiency diseases. While improving accuracy application algorithms, we aim expand understanding function neurological disorders through networks.