English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Electroencephalography (EEG) analysis exploits computer technologies and mathematical signal analysis techniques to derive useful information from EEG signals. EEG analysis aims to help scientists better understand the brain, help physicians make better decisions about patient diagnoses and treatment choices and advance the Brain-Computer Interface (BCI) technology. Over the last years, machine learning has been very much used in EEG analysis. Artificial neural networks (ANNs) are among the most effective machine learning algorithms that perform computing tasks similar to biological neurons in the human brain. Nevertheless, the neural network model's performance might significantly degrade and overfit due to some irrelevant features that negatively influence the model performance. Therefore, feature selection should be the first step of the model design. Furthermore, neural networks performance relies heavily on the algorithm that is employed to train them. Backpropagation is a common technique for training neural networks; however, backpropagation might get stuck into a set of sub-optimal weights and biases from which it cannot escape. Both feature selection and training can be formulated as optimization problems. Thus, proper optimization techniques to use for feature selection and training will contribute to performance improvement. Swarm optimization algorithms are robust and powerful techniques that can be employed to find high-quality solutions to such problems. In this paper, Grey Wolf Optimizer (GWO) and Particle Swarm Optimization (PSO) algorithms are applied for the feature selection and the training of a Feed-forward Neural Network (FFNN) to classify the state of the eye as closed or open based on brain wave data (EEG). The aim is to enhance the FFNN's ability to detect the eye state with high accuracy. The performance of the FFNN in terms of test accuracy, precision, recall, and F1_score is investigated. To better estimate the ability and effectiveness of the proposed model, five classical machine learning classifiers are used: (1) Support Vector Machine; (2) k-Nearest Neighbors; (3) Decision Tree; (4) Gaussian Naive Bayes; (5) Logistic Regression. Experimental results proved that the FFNN model outperforms all other classifiers, particularly when feature selection and training are performed with the GWO algorithm.

High Performance Implementation of Neural Networks Learning Using Swarm Optimization Algorithms for EEG Classification Based on Brain Wave Data