Jul 2026· Journal of Intelligent Systems and Computer Applications· 0 citations· 38 references
TL;DR
Comparative analysis indicates that advanced feature selection methods combined with machine learning classifiers consistently improve EEG classification performance, while clustering techniques effectively enhance data representation and classification accuracy.
Abstract
Electroencephalography (EEG) has become one of the most widely used non-invasive techniques for monitoring brain activity and supporting the diagnosis of neurological disorders, particularly epilepsy. However, the high dimensionality and complexity of EEG signals present significant challenges for developing accurate and computationally efficient machine learning models. Feature selection and clustering techniques have therefore emerged as essential preprocessing approaches for reducing data dimensionality, eliminating redundant information, and improving classification performance. This paper presents a comprehensive review of recent machine learning approaches that integrate feature selection and clustering methods for EEG signal classification. The reviewed studies are categorized into three classification groups, namely Support Vector Machine (SVM), Random Forest (RF), and other classification algorithms including hybrid multi-classifier approaches, together with K-means and other clustering techniques. Each study is critically analyzed in terms of the datasets employed, feature selection strategy, clustering algorithm, classification method, evaluation metrics, and reported performance. Furthermore, the strengths, limitations, and research gaps of existing approaches are discussed to provide a comprehensive understanding of current developments in the field. Comparative analysis indicates that advanced feature selection methods combined with machine learning classifiers consistently improve EEG classification performance, while clustering techniques effectively enhance data representation and classification accuracy. The review also highlights that many existing studies primarily emphasize classification accuracy while overlooking important performance indicators such as computational complexity, execution time, robustness, and model generalizability. Finally, potential research directions are identified to support the development of more reliable, efficient, and clinically applicable EEG classification systems.
This paper presents a new feature selection technique mainly based on the Kullback-Leibler (KL) divergence to diagnose epileptic seizures in the EEG dataset. Utilizing high-dimensional medical datasets necessitates implementing feature selection as a crucial procedure for the early detection of diseases to safeguard public health. Furthermore, high-dimensional data significantly impacts the predictive accuracy of machine learning algorithms and amplifies system complexity, thereby diminishing the efficiency of outcomes. Furthermore, after feature selection, some features do not play any significant role in effective classification. Thus, EEG classification followed by the selection of optimal features can produce better results. From a mathematical perspective, the proposed model undertakes the computation of signal similarities, selects optimal features characterized by high similarity, and eliminates redundant features. The evaluation of the system's performance was conducted using the EEG Bonn University dataset. Furthermore, metrics such as accuracy, precision, and recall were employed for assessment, with comparative analysis against existing methodologies. The experimental findings substantiated the efficacy of the proposed model as a valuable instrument for optimal feature selection in EEG data analysis. Notably, the suggested model achieved a 100% accuracy.
Abdulkareem A. Al-Hamzawi, Ekram Hakem· Journal of Intelligent Syste...· 0 citations
Epilepsy and migraine are prone to clinical misdiagnosis due to overlapping clinical manifestations, while the limited availability of electroencephalogram (EEG) data further complicates accurate differential diagnosis. To address this challenge, this study proposes a three-class classification framework for epilepsy, migraine, and healthy controls based on EEG signals collected from 36 participants. After preprocessing the raw EEG data with a 0.5–60 Hz bandpass filter, 15 features were extracted, including 12 statistical features and three nonlinear dynamical features. Four machine learning models, namely support vector machine (SVM), random forest (RF), LightGBM, and XGBoost, were systematically evaluated for classification performance. Among them, XGBoost achieved the best overall results, with a test accuracy of 0.90 and superior performance across all major evaluation metrics. Feature importance analysis based on the gain metric of XGBoost identified the Hurst exponent as the most influential feature. Notably, its inter-group distribution differences were highly consistent with the pathological characteristics of epilepsy and migraine. These findings suggest that EEG-based feature fusion combined with machine learning provides an effective strategy for multi-class neurological disease classification, and that the Hurst exponent may serve as a promising biomarker for the differential diagnosis of epilepsy and migraine.
Shiqi Li, Yao Miao· 2026 IEEE International Conf...· 0 citations
This paper presents a comparative study for epilepsy monitoring using EEG signals along two main axes. The first axis consists of comparing the performance of the differentiation technique, which is known to be very important for the study of non-stationarity, with wavelet transform, which is widely used for detecting different brain rhythms. The second part aims to compare the performance of different machine learning algorithms, including k-Nearest Neighbors (k-NN), Decision Trees, Random Forest, and Support Vector Machines (SVM). Used features are statistical and higher order statistics characteristics such as mean, standard deviation, median, Min-Max, Kurtosis and Skewness. We tested our approach on publicly available and widely used datasets in the literature, namely the University of Bonn dataset and the Bern-Barcelona dataset. The experimental results demonstrate the effectiveness of the differentiation method as an important tool for EEG preprocessing, leading to very high performance.
Ines Bouzouita, Zayneb Brari, S. Belghith· International Conference on...· 0 citations
Schizophrenia is a chronic psychiatric disorder where the perception, cognition and behaviors are disturbed, which requires a proper and timely diagnosis to give an effective clinical intervention. EEG has been a recently viable non invasive technique for identifying neurophysiological markers related to schizophrenia. EEG-derived features, however, are usually very high dimensional and include redundant features and reduce classification performance. We propose a novel explainable machine learning approach for automated schizophrenia detection using EEG features. A publicly available EEG Psychiatric Disorders dataset was used to extract 1,144 features from both the demographic information and the EEG. To minimize feature redundancy, Analysis of Variance (ANOVA) based SelectKBest feature-selection was used to select 50 most discriminative-features. The hyperparameters of the Extra Trees classifier were then optimized by grid search and the selected features were classified using this optimized Extra Trees classifier. The model performance was assessed by an independent hold-out test set and Stratified-5-Fold Cross-Validation. The optimized model attained 95.35%, 95.29%, 95.83%, and 96.27% for hold-out test accuracy, balanced accuracy, F1-score and ROC-AUC, respectively. Moreover, the Stratified-5-Fold Cross-Validation provided a mean accuracy of 85.37 ± 5.01% and a mean ROC-AUC of 93.14 ± 2.51%, showing good generalization across the different data folds. Additionally, SHapley Additive exPlanations (SHAP) analysis revealed the most important demographic and EEG biomarkers for classification, improving the model interpretability. The results show that integrating ANOVA-based feature-selection with an optimized Extra Trees classifier, significantly improves classification performance while providing clinically interpretable predictions.
R. N. Panda, Anubhav Kumar· Genetics and Molecular Resea...· 0 citations
OBJECTIVE
This work proposes an automated system for the detection of epileptic seizures based on electroencephalogram (EEG) signals, integrating numerous metaheuristic optimization algorithms. This study aims to improve classification accuracy and computational efficiency by optimizing feature selection and classification in a machine learning-based detection system.
METHODS
The four feature extraction strategies were employed:(i) the Discrete Wavelet Transform (DWT), (ii) the DWT with the Hjorth parameters, (iii) the DWT with the statistical features, and (iv) the DWT with the statistical and Hjorth parameters. The metaheuristic- based optimization methods, Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Bee Algorithm (BA), and Genetic Algorithm (GA) were used to select the optimal feature from each feature set. Optimized features were then classified using a Support Vector Machine (SVM) classifier.
RESULTS
DWT + PSO + SVM model showed the highest level of classification of 97.8%, which is significantly higher compared to the other combinations of feature extraction and optimization. The feature optimization using Genetic Algorithms showed better computational efficiency, whereas ACO and BA yielded performance improvement within a given feature configuration.
DISCUSSION
The better performance of the meta-heuristic-optimized models, especially the DWT-PSO hybrid, demonstrates the effectiveness and robustness of the proposed model for automated seizure detection. These findings demonstrate the appropriateness of meta-heuristic optimization for dealing with the complex feature space of EEG and enhancing detection reliability. The results are particularly meaningful to real-time seizure monitoring systems in resource-limited systems, e.g., Healthcare Internet of Medical Things (IoMT) systems.
CONCLUSION
The findings indicate the high potential of meta-heuristic optimization tools for improving the accuracy of epileptic seizure detection and the overall performance of the system. The suggested architecture provides a clear pathway for developing effective, reliable, and real- time EEG-based seizure-detection systems.
Naresh Rana, Shruti Jain· Current Medicinal Chemistry· 0 citations
EEG based Emotion recognition has gained a lot of interest in the domain of Affective Computing, Healthcare and Human-Computer Interaction. Emotion classification in EEG signals remains difficult, though, because of their nonlinearity, noise and dependence on the specific person. In this paper, we suggest an Adaptive Multi-Domain EEG Feature Fusion Framework for four-class emotion recognition. The proposed method is a hybrid technique composed of frequency-specific band-pass filtering, denoising using wavelet, multi-domain feature extraction, data augmentation and dimensionality reduction using PCA. Three types of features are extracted: time domain, Fast Fourier Transform (FFT) domain and Power Spectral Density (PSD) domain features, and these features are combined to create a feature representation. Gaussian noise injection, temporal shifting and amplitude scaling are used as augmentation strategies to obtain a better generalization. Optimized feature set is classified with Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest (RF), Decision Tree (DT), Naïve Bayes (NB) classifiers. The effectiveness of the proposed framework for robust emotion recognition using EEG data has been demonstrated through experiments. The classifiers evaluated and found that the highest classification accuracy was for the Random Forest model with 99.6%, followed by KNN model with 99.5%, SVM model with 99.2%, and Decision Tree model with 99.1%. Naïve Bayes had a relatively poor accuracy rate of 92.0%, however. The findings demonstrate that the proposed multi-domain EEG feature fusion framework is more effective to recognize emotions accurately by four classes.
Prasanna Mula, V. Malathy, Mohammad Farukh Hashmi et al.· 2026 7th International Confe...· 0 citations