NeuroWave-Net: Enhancing Epileptic Seizure Detection from EEG Brain Signals via Advanced Convolutional and Long Short-Term Memory Networks

This study introduces a novel approach to seizure classification through the utilization of electroencephalogram (EEG) data. The NeuroWave-Net, a hybrid model amalgamating convolutional neural networks (CNN) and long short-term memory (LSTM) architectures, is proposed. Diverging from conventional methodologies, our model capitalizes on CNN’s adeptness in feature extraction and LSTM’s proficiency in seizure classification. The pivotal strength of the NeuroWave-Net resides in its seamless integration of these disparate architectures, harnessing their synergistic capabilities to enhance accuracy in identifying seizure conditions within EEG data. Demonstrating exceptional performance, our proposed model attains a classification accuracy of 99.48%. This study contributes

to the advancement of seizure classification models, offering a robust and streamlined 

methodology for precise categorization within EEG datasets. The NeuroWave-Net underscores the potential of hybrid neural network architectures in the realm of neurological diagnostics.

• Supervision