Skip to content
Open access

Real-Time Epileptic Seizure Detection from Raw EEG Using Classical Machine Learning and Time-Domain Feature

Aug 2026 · Machine Learning and Knowledge Extraction · 0 citations · 69 references

TL;DR

This study systematically introduces and evaluates 25 less-explored time-domain features, 13 of which have no documented precedent as classification features in scalp EEG seizure detection, against 25 classical features and their 50-feature combination.

Abstract

Automated detection of epileptic seizures from electroencephalogram (EEG) recordings is essential for timely clinical intervention and long-term patient monitoring. Deep learning achieves high accuracy, but its limited interpretability and computational demands restrict deployment in resource-constrained, real-time clinical environments; furthermore, classical machine learning studies have concentrated on a narrow group of well-known temporal features. This study systematically introduces and evaluates 25 less-explored time-domain features, 13 of which have no documented precedent as classification features in scalp EEG seizure detection, against 25 classical features and their 50-feature combination. Raw, unfiltered recordings from the CHB-MIT database were segmented into 10-second windows, and seven classical classifiers were optimized with GridSearchCV under subject-wise StratifiedGroupKFold cross-validation, with the data partitioned at the patient level such that no patient appeared in both the training and test sets. The multilayer perceptron trained on the combined 50-feature set performed best (accuracy 86.59%, F1-score 86.35%), exceeding the classical features alone by 5.1 and 4.6 percentage points, respectively; the less-explored features alone remained competitive (84.63%, 84.67%). SHAP analysis identified the exponent of the detrended fluctuation analysis (DFA)—a long-range, nonlinear measure of temporal correlation—as the most influential predictor. The curated feature set, its rigorous subject-level validation, and its interpretability provide a reproducible and computationally efficient foundation for future clinical deployment.

Read PDF

Similar papers

Open access Jun 2026

Epileptic Seizure Detection from EEG Signal Using Progressive Channel Selection and Deep Learning

This study investigates a novel Progressive Channel Selection (PCS) framework designed to identify and retain only the most informative EEG channels across patients, which provides a more effective trade-off between detection accuracy and channel efficiency.

Suraiya Akter Mumu, Shupta Das, M. A. Akhand et al. · 0 citations
Aug 2026

An Optimized Deep Learning Framework for Robust Epileptic Seizure Detection Using EEG Signals

A proposed method for detecting epileptic seizures from electroencephalogram data involves creating an optimal deep learning architecture that incorporates deep learning architectures, feature optimisation, and wavelet-based preprocessing.

M. Nanditha, A. S. Kumar, Saravanakumar Selvaraj et al. · 0 citations
Conference Jul 2026

Next-Generation Deep Learning Approaches for Accurate Epilepsy Detection from EEG Signals

Epilepsy is neurological disorder which is a result of abnormal brain activity which causes repetitive seizures. The analysis of electroencephalogram (EEG) is vital in determining the pattern of epileptic and facilitating clinical diagnosis. Manual interpretation of EEG signals is very cumbersome and time consuming however, because of the high-dimensional and time varying nature of the brain signals. An automated epilepsy detection (EEG) framework is trained based on deep learning. It is a signal preprocessing, time frequency transformation, hierarchical feature extraction based on a hybrid neural architecture that encodes spatial and temporal EEG features. This is followed by the classification of the learned representations with the aim of obtaining the epileptic and non-epileptic brain activity patterns. The experimental assessment shows a better performance than the traditional procedures. The currently proposed model is significantly more accurate (96.7%), sensitive (96.0%), and specific (96.2%), as compared to classical machine learning models like support vector machines (91.2% accuracy) and random forest models (92.6% accuracy). Such results suggest that the improvement in performance of these techniques will be about 4-5 percent compared to the use of conventional techniques. The framework has a high potential of aiding in stable and automatic diagnosis of epilepsy in clinical settings.

Ritu Nagila, Kalaiyarasan R., M. S. et al. · 0 citations
Open access Jul 2026

Patient-independent automated pediatric seizure monitoring based on expert-labeled electrographic ictal data as core reference knowledge

Background Automated seizure detection using scalp electroencephalography (EEG) is essential to the efficient monitoring of seizures in patients with epilepsy. However, patient-independent seizure detection remains challenging, primarily because of the inherent intersubject variability in EEG characteristics. Purpose We proposed a patient-independent seizure detection approach based on 1,604 single-channel electrographic focal-onset ictal EEG segments verified by epileptologists in patients with focal epilepsy. Methods We constructed deep learning models trained on these segments and applied them to individual EEG channels to identify seizure occurrences. To evaluate patient-independent detection performance, we conducted internal validation using the 2 datasets employed for segment acquisition, followed by external validation with an independent unseen dataset obtained from a tertiary medical institution. Results In the internal validation using a leave-one-patient-out scenario, overall sensitivity, false alarm rate, and latency were 80.1%–100%, 0.64–1.13/hr, and 8.0–21.4 seconds, respectively. In the external validation using the final seizure detection model, the corresponding values were 100%, 0.38–0.67/hr, and 10.0–10.2 seconds, respectively, according to detection length. This technique outperformed those of previous patient-independent studies that employed relatively simple deep learning tasks. Conclusion A curated set of expert-labeled ictal EEG segments served as the core reference knowledge for the proposed seizure detector in recognizing seizure occurrence in unseen patients. Because the proposed approach analyzes individual channels in parallel, it may be clinically applicable to continuous seizure monitoring, particularly in wearable seizure detection systems with a limited number of channels.

Yoon Gi Chung, Jaeso Cho, Anna Cho et al. · 0 citations