EEG signal classification using PSO trained RBF neural network for epilepsy identification

Ensemble Fusion Models Using Various Strategies and Machine Learning for EEG Classification

Electroencephalography (EEG) helps to assess the electrical activities of the brain so that the neuronal activities of the brain are captured effectively. EEG is used to analyze many neurological disorders, as it serves as a low-cost equipment. To diagnose and treat every neurological disorder, lengthy EEG signals are needed, and different machine learning and deep learning techniques have been developed so that the EEG signals could be classified automatically. In this work, five ensemble models are proposed for EEG signal classification, and the main neurological disorder analyzed in this paper is epilepsy. The first proposed ensemble technique utilizes an equidistant assessment and ranking determination mode with the proposed Enhance the Sum of Connection and Distance (ESCD)-based feature selection technique for the classification of EEG signals; the second proposed ensemble technique utilizes the concept of Infinite Independent Component Analysis (I-ICA) and multiple classifiers with majority voting concept; the third proposed ensemble technique utilizes the concept of Genetic Algorithm (GA)-based feature selection technique and bagging Support Vector Machine (SVM)-based classification model. The fourth proposed ensemble technique utilizes the concept of Hilbert Huang Transform (HHT) and multiple classifiers with GA-based multiparameter optimization, and the fifth proposed ensemble technique utilizes the concept of Factor analysis with Ensemble layer K nearest neighbor (KNN) classifier. The best results are obtained when the Ensemble hybrid model using the equidistant assessment and ranking determination method with the proposed ESCD-based feature selection technique and Support Vector Machine (SVM) classifier is utilized, achieving a classification accuracy of 89.98%.

Detection of Anxiety-Based Epileptic Seizures in EEG Signals Using Fuzzy Features and Parrot Optimization-Tuned LSTM

In humans, epilepsy is diagnosed through electroencephalography (EEG) signals. Epileptic seizures (ESs) arise due to anxiety. The detection of anxiety-based seizures is challenging for radiologists, and there is a limited availability of anxiety-based EEG signals. Data augmentation methods are required to increase the number of novel samples. An epileptic seizure arises due to anxiety, which manifests as variations in EEG signal patterns consisting of changes in the size and shape of the signal. In this study, anxiety EEG signals were synthesized by applying data augmentation methods such as random data augmentation (RDA) to existing epileptic seizure signals from the Bonn EEG dataset. The data-augmented anxiety seizure signals were processed using three algorithms-(i) fuzzy C-means-particle swarm optimization-long short-term memory (FCM-PS-LSTM), (ii) particle swarm optimization-long short-term memory (PS-LSTM), and (iii) parrot optimization LSTM (PO-LSTM)-for the detection of anxiety ESs via EEG signals. The predicted accuracies of detecting ESs through EEG signals using the proposed algorithms-namely, (i) FCM-PS-LSTM, (ii) PS-LSTM, and (iii) PO-LSTM-were about 98%, 98.5%, and 96%, respectively.

A machine learning approach for differentiating bipolar disorder type II and borderline personality disorder using electroencephalography and cognitive abnormalities

This study addresses the challenge of differentiating between bipolar disorder II (BD II) and borderline personality disorder (BPD), which is complicated by overlapping symptoms. To overcome this, a multimodal machine learning approach was employed, incorporating both electroencephalography (EEG) patterns and cognitive abnormalities for enhanced classification. Data were collected from 45 participants, including 20 with BD II and 25 with BPD. Analysis involved utilizing EEG signals and cognitive tests, specifically the Wisconsin Card Sorting Test and Integrated Cognitive Assessment. The k-nearest neighbors (KNN) algorithm achieved a balanced accuracy of 93%, with EEG features proving to be crucial, while cognitive features had a lesser impact. Despite the strengths, such as diverse model usage, it's important to note limitations, including a small sample size and reliance on DSM diagnoses. The study suggests that future research should explore multimodal data integration and employ advanced techniques to improve classification accuracy and gain a better understanding of the neurobiological distinctions between BD II and BPD.

Classification of self-limited epilepsy with centrotemporal spikes by classical machine learning and deep learning based on electroencephalogram data

Electroencephalogram (EEG) has been widely utilized as a valuable assessment tool for diagnosing epilepsy in hospital settings. However, clinical diagnosis of patients with self-limited epilepsy with centrotemporal spikes (SeLECTS) is challenging due to the presence of similar abnormal discharges in EEG displays compared to other types of epilepsy (non-SeLECTS) patients. To assist the diagnostic process of epilepsy, a comprehensive classification study utilizing machine learning or deep learning techniques is proposed. In this study, clinical EEG was collected from 33 patients diagnosed with either SeLECTS or non-SeLECTS, aged between 3 and 11 years. In the realm of classical machine learning, sharp wave features (including upslope, downslope, and width at half maximum) were extracted from the EEG data. These features were then combined with the random forest (RF) and extreme random forest (ERF) classifiers to differentiate between SeLECTS and non-SeLECTS. Additionally, deep learning was employed by directly inputting the EEG data into a deep residual network (ResNet) for classification. The classification results were evaluated based on accuracy, F1-score, area under the curve (AUC), and area under the precision-recall curve (AUPRC). Following a 10-fold cross-validation, the ERF classifier achieved an accuracy of 73.15 % when utilizing sharp wave feature extraction for classification. The F1-score obtained was 0.72, while the AUC and AUPRC values were 0.75 and 0.63, respectively. On the other hand, the ResNet model achieved a classification accuracy of 90.49 %, with an F1-score of 0.90. The AUC and AUPRC values for ResNet were found to be 0.96 and 0.92, respectively. These results highlighted the significant potential of deep learning methods in SeLECTS classification research, owing to their high accuracy. Moreover, feature extraction-based methods demonstrated good reliability and could assist in identifying relevant biological features of SeLECTS within EEG data.

Novel ML-Based Algorithm for Detecting Seizures from Single-Channel EEG

There is a need for seizure classification based on EEG signals that can be implemented with a portable device for in-home continuous minoring of epilepsy. In this study, we developed a novel machine learning algorithm for seizure detection suitable for wearable systems. Extreme gradient boosting (XGBoost) was implemented to classify seizures from single-channel EEG obtained from an open-source CHB-MIT database. The results of classifying 1-s EEG segments are shown to be sufficient to obtain the information needed for seizure detection and achieve a high seizure sensitivity of up to 89% with low computational cost. This algorithm can be impeded in single-channel EEG systems that use in- or around-the-ear electrodes for continuous seizure monitoring at home.

Information-Theoretic Approaches in EEG Correlates of Auditory Perceptual Awareness under Informational Masking

In informational masking paradigms, the successful segregation between the target and masker creates auditory perceptual awareness. The dynamics of the build-up of auditory perception is based on a set of interactions between bottom-up and top-down processes that generate neuronal modifications within the brain network activity. These neural changes are studied here using event-related potentials (ERPs), entropy, and integrated information, leading to several measures applied to electroencephalogram signals. The main findings show that the auditory perceptual awareness stimulated functional activation in the fronto-temporo-parietal brain network through (i) negative temporal and positive centro-parietal ERP components; (ii) an enhanced processing of multi-information in the temporal cortex; and (iii) an increase in informational content in the fronto-central cortex. These different results provide information-based experimental evidence about the functional activation of the fronto-temporo-parietal brain network during auditory perceptual awareness.

High-Performance Computational Recognition of Communication Signals Based on Bispectral Quadratic Feature Model

In response to the problems in the signal identification of radiation sources during the communication process, the bispectral quadratic feature model is applied to the identification algorithm for communication signals. According to the signal eigenvalues obtained from the bispectrum of the diagonal slices in the radiation source signals, the eigenvalues of the bispectrum diagonal slices can be extended from the frequency domain to the complex plane through the chirp-z operation in this paper, and the relevant data are obtained based on the bispectrum quadratic feature model of the signals by using the separation rules corresponding to the extended Babbitt distance. The bispectral quadratic feature model method is used to establish a sparse observation model, and the communication signal processing problem can be transformed into an estimation problem of signal motion parameters through the construction of a parametric database. At the same time, the high-resolution distance of communication signals is tested, and the communication signals are estimated by using the variational inference method. Finally, practical cases are analyzed, and the results indicate that the algorithm proposed in this paper can be used to identify different types of communication signals in accordance with simulated and measured data in the processing of communication signals in various environments, which has the certain anti-interference capacity to noise, can improve the identification rate of communication signals, and has verified the effectiveness and practicality of the algorithm proposed in this paper.

A hybrid PSO-parallel fuzzy brain emotional learning classifier for medical diseases diagnosis

This study presents a fuzzy brain emotional learning classifier (FBELC), combined with a modified particle swarm optimization (PSO) algorithm, that allows a network to automatically determine the optimum values for a reward signal and a classification threshold. The designed FBELC model imitates the brain decision process including the emotion information. To verify the predictive performance, a novel fitness function based on the accuracy of the training and cross-validation datasets is used for a PSO algorithm. This PSO-FBELC model is used to diagnose breast tumors and heart diseases. A comparison of simulations using the proposed PSO-FBELC with other processes shows that the proposed model performs better in terms of recognition accuracy.

Data classification based on fractional order gradient descent with momentum for RBF neural network

The weight-updating methods have played an important role in improving the performance of neural networks. To ameliorate the oscillating phenomenon in training radial basis function (RBF) neural network, a fractional order gradient descent with momentum method for updating the weights of RBF neural network (FOGDM-RBF) is proposed for data classification. Its convergence is proved. In order to speed up the convergence process, an adaptive learning rate is used to adjust the training process. The Iris data set and MNIST data set are used to test the proposed algorithm. The results verify the theoretical results of the proposed algorithm such as its monotonicity and convergence. Some non-parametric statistical tests such as Friedman test and Quade test are taken for the comparison of the proposed algorithm with other algorithms. The influence of fractional order, learning rate and batch size is analysed and compared. Error analysis shows that the algorithm can effectively accelerate the convergence speed of gradient descent method and improve its performance with high accuracy and validity.

PSR-based research of feature extraction from one-second EEG signals: a neural network study

The speed and accuracy of signal classification are the most valuable parameters to create real-time systems for interaction between the brain and the computer system. In this work, we propose a schema of the extraction of features from one-second electroencephalographic (EEG) signals generated by facial muscle stress. We have tested here three sorts of EEG signals. The signals originate from different facial expressions. The phase-space reconstruction (PSR) method has been used to convert EEG signals from these three classes of facial muscle tension. For further processing, the data has been converted into a two-dimensional (2D) matrix and saved in the form of color images. The 2D convolutional neural network (CNN) served to determine the accuracy of the classifications of the previously unknown PSR generated images from the EEG signals. We have witnessed an improvement in the accuracy of the signal classification in the phase-space representation. We have found that the CNN network better classifies colored trajectories in the 2D phase-space graph. At the end of this work, we compared our results with the results obtained by a one-dimensional convolution neural network.

Transductive Joint-Knowledge-Transfer TSK FS for Recognition of Epileptic EEG Signals

Intelligent recognition of electroencephalogram (EEG) signals is an important means to detect seizure. Traditional methods for recognizing epileptic EEG signals are usually based on two assumptions: 1) adequate training examples are available for model training and 2) the training set and the test set are sampled from data sets with the same distribution. Since seizures occur sporadically, training examples of seizures could be limited. Besides, the training and test sets are usually not sampled from the same distribution for generic non-patient-specific recognition of EEG signals. Hence, the two assumptions in traditional recognition methods could hardly be satisfied in practice, which results in degradation of model performance. Transfer learning is a feasible approach to tackle this issue attributed to its ability to effectively learn the knowledge from the related scenes (source domains) for model training in the current scene (target domain). Among the existing transfer learning methods for epileptic EEG recognition, transductive transfer learning fuzzy systems (TTL-FSs) exhibit distinctive advantages-the interpretability that is important for medical diagnosis and the transfer learning ability that is absent from traditional fuzzy systems. Nevertheless, the transfer learning ability of TTL-FSs is restricted to a certain extent since only the discrepancy in marginal distribution between the training data and test data is considered. In this paper, the enhanced transductive transfer learning Takagi-Sugeno-Kang fuzzy system construction method is proposed to overcome the challenge by introducing two novel transfer learning mechanisms: 1) joint knowledge is adopted to reduce the discrepancy between the two domains and 2) an iterative transfer learning procedure is introduced to enhance transfer learning ability. Extensive experiments have been carried out to evaluate the effectiveness of the proposed method in recognizing epileptic EEG signals on the Bonn and CHB-MIT EEG data sets. The results show that the method is superior to or at least competitive with some of the existing state-of-art methods under the scenario of transfer learning.

Training radial basis function networks for wind speed prediction using PSO enhanced differential search optimizer

This paper presents an integrated hybrid optimization algorithm for training the radial basis function neural network (RBF NN). Training of neural networks is still a challenging exercise in machine learning domain. Traditional training algorithms in general suffer and trap in local optima and lead to premature convergence, which makes them ineffective when applied for datasets with diverse features. Training algorithms based on evolutionary computations are becoming popular due to their robust nature in overcoming the drawbacks of the traditional algorithms. Accordingly, this paper proposes a hybrid training procedure with differential search (DS) algorithm functionally integrated with the particle swarm optimization (PSO). To surmount the local trapping of the search procedure, a new population initialization scheme is proposed using Logistic chaotic sequence, which enhances the population diversity and aid the search capability. To demonstrate the effectiveness of the proposed RBF hybrid training algorithm, experimental analysis on publicly available 7 benchmark datasets are performed. Subsequently, experiments were conducted on a practical application case for wind speed prediction to expound the superiority of the proposed RBF training algorithm in terms of prediction accuracy.