Robust Optimization of electroencephalograph (EEG) Signals for Epilepsy Seizure Prediction by utilizing VSPO Genetic Algorithms with SVM and Machine Learning Methods

Abstract

Objectives: To optimize the EEG signals in order to predict the epileptic seizures at early stage and to improve the accuracy level by employing genetic algorithm and machine learning methods. Methods: Virus Swarm Particle Optimization Technique (VSPO) based Genetic algorithm is utilized for the purpose of feature selection and Machine Learning SVM technique is utilized for classification of EEG signals to determine seizure or non-seizure. The Discrete Wavelet Transform (DWT) is utilized for factor extraction to assess the recurrence range of EEG signals associated with seizures, to partition them into separate spaces using DWT of EEG symbols, and to consider the variations between seizure and normal functionality. VPSO-GA with SVM extracts the features from the Andrzejak R G dataset and then selects the relevant function to perform classification and prediction in order to optimize the EEG signals for early ES prediction and to improve the accuracy level. To demonstrate the effectiveness of the proposed algorithm, MATLAB is used for implementation. The performance results are compared to the existing baseline versions FCM-MPSO, EDMLC and K-MODE. Findings: EEG signals are optimized and early ES prediction is done with 98.13% accuracy level, 98.03% sensitivity, 98.01% specificity, 98.90% Precision, 97.96% Recall, 191 True Positive, 104 True Negative and 98.46% F-Score to predict the seizure in an optimized manner which is high compared to the existing versions. Novelty: According to the findings of the comprehensive study, the proposed algorithm VPSO-SVM outperforms FCM-MPSO, EDMLC and K-MODE in terms of accuracy level of epileptic seizure prediction at early stage by optimizing the EEG signals in a robust manner.

Epileptic seizure prediction based on Convolutional neural networks and optimization techniques

“…Pinto et al [33] proposed ML-based evolutionary algorithm for prediction of seizures. Banupriya et al [34] optimized EEG signals with Virus Swarm Particle Optimization Technique (VSPO) and achieved qualitative results. Despite the promising seizure detection results obtained using the aforementioned CNN models, there are still a number of enhancements that can be made.…”

An automated detection of epileptic seizures EEG using CNN classifier based on feature fusion with high accuracy

“…However, if too many epileptic EEG features are extracted and fused, it may lead to lower computational efficiency and information redundancy, and there are also some bad features that interfere with the classification results. Therefore, a small number of studies have performed the selection of hybrid features, such as features selection by use of genetic algorithms based on the Viral Swarm Particle Optimization (VSPO) technique [ 20 ], but the classification accuracy obtained by this method is not high. In addition, according to the EEG characteristics of epilepsy, selecting an effective classification model is very critical for the automatic detection of epilepsy.…”

“…With the development of artificial intelligence, machine learning models were widely used in automatic epilepsy detection, such as Artificial Neural Networks (ANN) [ 5 ], Random Forests (RF) [ 21 ], and Support Vector Machines (SVM). Although the traditional machine learning algorithms such as SVM are widely used, the method is more suitable for single channel and small sample datasets [ 13 , 20 , 22 – 24 ]. However, when larger data with multiple features for EEG signals is analyzed, deep learning algorithms such as Convolutional Neural Network (CNN) have obvious advantages compared to traditional machine learning algorithms [ 8 , 19 , 25 – 28 ].…”

generic heart diseases prediction and application of genetic algorithms in healthcare systems

“…Researchers have developed and constructed many metaheuristic algorithms to optimize solution that exist and are inspired by natural biological behaviour and patterns. Some of these algorithms include the following: ant colony inspired by ants' behaviour [8], artificial bee colony inspired by bees behaviour [9], Grey Wolf optimizer inspired by grey wolves behaviour [10], artificial neural networks emanated from the neural systems [11], simulated annealing [12], river formation dynamics inspired on the process of river formation [13], artificial immune systems inspired on immune system functions [14], genetic algorithm inspired by genetic mechanisms [15], and many other algorithms. To solve complex problems or to find an optimal decision, metaheuristic approaches have been rapidly utilized in other field of science for decision making process.…”