Feature-Based Machine Learning Ensemble for the Classification of Harmful Brain Activities

Single-channel EEG-based sleep state detection using spectral features and machine learning

DPML: Derivative-Based EEG Preprocessing for Enhanced Epileptic Seizure Detection Using Machine Learning

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.

An Efficient EEG-based System for Multi-Class Neurological Disorder Diagnosis using EMPA Optimized Bi-LSTM

Neurological illness detection using electroencephalograms (EEGs) is not an easy task due to the nature of brain signals, which are not stationary and noisy. In order to obtain the correct multi-class classification, the paper develops a hybrid deep learning framework that includes pre-processing, graph-based feature generation and efficient time modelling. The initial step of cleaning the data is to eliminate any missing data, or artefacts in EEG signals to obtain higher resulting output. A Graph Convoluted Network (GCN) is then used to approximate the functional connectivity between the EEG electrodes and each of the channels is represented as a node in a modelled graph. The GCN models spatial relationships and gets trained on features that are of relevance to the neurological patterns. The Bidirectional Long Short-Term Memory (BiLSTM) network receives features to acquire forward and backward statistical relationships. To enhance the convergence and speed of the weight selection process, the Enhanced Marine Predators Algorithm (EMPA) is applied to avoid falling into the local minima. Proposed model is more effective with higher accuracy of precision ,recall value and F1-score value. The experimental results demonstrating a sufficient recall of spatio-temporal behaviour and classification performance make the proposed model useful to be used in clinical decision support systems.

Towards Low-resource Deep Learning for Biomedical Signal Classification: An ECG and EEG Based Approach

This study presents two lightweight deep learning pipelines for ECG arrhythmia and EEG emotion classification. These pipelines are designed for resource-constrained environments and can be executed on standard CPU hardware. The proposed framework combines self-supervised representation learning, hybrid neural architectures and GAN-based data augmentation into a single workflow to address limited labelled data and class imbalance. Class-wise GANs are used to balance ECG beats from the MIT-BIH Arrhythmia Database. A ViT–TFN classifier receives the robust latent representations that the SimCLR and MoCo models learn from the enhanced data. This model covers long-range temporal dependencies as well as fine-grained morphological characteristics. The emotion dataset follows the same augmentation and self-supervised learning pipeline before being processed by a GCN–GAT classifier that makes use of attention-based weighting and channel-wise spatial correlations. The EEG model achieves 94.15% accuracy across negative, neutral and positive emotions, the ECG model obtains 92.14% accuracy, with good performance for normal and supraventricular beats. The observed class separability is supported by Principal Component Analysis and tDistributed Stochastic Neighbour Embedding visualizations, which show distinct clusters in the learned feature space. Overall, the findings show that hybrid architectures, augmentation and self-supervised learning can provide competitive performance in real world low-resource settings.

Deep Hybrid Neural Network for Automated Epileptic Seizure Detection from EEG Signals using MAT-LAB

A Deep Hybrid Neural Network framework that combines Convolutional Neural Networks (CNN) with the Aquila Optimizer (AO) for the automatic detection of epileptic seizures utilizing EEG data in MATLAB is introduced.

Attention-Based Fusion of EEG Spectrograms and Scalograms for Schizophrenia Detection Using Vision Transformers

Abstract Schizophrenia is a neuropsychiatric disorder that affects brain activity, making timely and reliable diagnosis challenging. Although electroencephalography (EEG) provides a non-invasive and cost-effective diagnostic modality, its non-stationary nature and complex temporal–spectral characteristics limit the effectiveness of conventional machine learning and deep learning approaches, which often rely on a single time–frequency representation or simple feature fusion strategies. To address these limitations, this study proposes an attention-based fusion framework that integrates complementary time–frequency representations for EEG-based schizophrenia detection. Spectrograms and scalograms generated using the Short-Time Fourier Transform (STFT) and Continuous Wavelet Transform (CWT) capture global spectral information and localized temporal–frequency characteristics, respectively. These representations are processed by a Vision Transformer (ViT), while a bidirectional cross-attention module enables effective interaction and fusion of complementary features before global feature learning. The proposed framework achieved average classification accuracies of 98.34 ± 0.21% and 98.68 ± 0.15% on Dataset 1 and Dataset 2, respectively. Comparative experiments demonstrate that the proposed framework consistently improves classification performance over methods based on individual time–frequency representations and conventional feature fusion approaches, indicating that the proposed attention-guided fusion strategy effectively exploits complementary EEG information for schizophrenia detection.