Epilepsy is a neurological disorder characterized by unpredictable seizures that can severely affect patients’ quality of life. Diagnosis primarily relies on the analysis of the electroencephalogram (EEG), a complex, noisy, and nonstationary signal representing the summation of various brain rhythms (delta, theta, alpha, beta, and gamma). Since manual EEG analysis is difficult and time-consuming, automatic approaches are necessary to efficiently detect seizures and diagnose the disease. In this work, we propose a novel framework that integrates wavelets for brain rhythms estimation with Chaos-Embedding and the Higuchi fractal dimension to extract highly discriminative features. These features are then used in a robust representation space and classified using K-Nearest Neighbors is employed to differentiate between healthy patients, epileptic patients, and epileptic patients during seizures. Experimental results show that the proposed approach achieves near-perfect performance, outperforming existing methods and providing a promising tool for the automatic diagnosis of epilepsy based on brain rhythms.
Zayneb Brari, Ines Bouzouita, S. Belghith· International Conference on...· 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