Etudiant : BOUKHADA OMAYMA

Filière : Master Informatique Décisionnelle et Vision Intelligente (MIDVI)

Encadrant : Pr. RIFFI JAMAL

Annèe : 2021

Résumé : Brain is a significant part of human which controls entire parts of human body. Brain can be viewed as collection of interconnected neurons which decides human behavior. Electroencephalography (EEG) is a modality which helps to analyze brain and its behaviors based on respective frequency of a signal. In this work, a prediction of Epileptic Seizures and a classification of emotion dataset was done using several deep learning models. It was shown that the Long Short-Term Memory (LSTM) with 98% Accuracy has the best performance compared to Multilayer Perceptron (MLP), Convolutional Neural Network (CNN1D), Bidirectional LSTM (BiLSTM) and Gated Recurrent Unit (GRU) both on the seizures prediction and emotion recognition.