Epileptic Seizure Classification Using Battle Royale Search and Rescue Optimization-Based Deep LSTM

Epilepsy is a severe threat to society due to the treatment time, cost, and unpredictable nature of the disease, thereby imposing an urgent need for intelligent analysis. Electroencephalogram (EEG) is a commonly deployed test for detecting epilepsy that analyses the electrical activity of an individual's brain. This work proposes an optimized deep sequential model to improve the seizure classification performance based on a hybrid feature set derived from EEG signals. A novel hybridized Battle Royale Search and Rescue optimization (BRRO) algorithm is proposed for optimizing a deep learning (DL) model. Also, the proposed hybrid feature set utilizes empirical mode decomposition, variational mode decomposition, and empirical wavelet transform to capture the temporal property of the data set. The proposed method is validated using publicly available data sets. The results manifest that the proposed optimized algorithm provides better results than the other alternatives.

Automated summary

Epilepsy poses a severe threat to society due to the long treatment time, high cost, and unpredictable nature of the disease. This study proposes an optimized deep sequential model to improve the classification performance of seizure based on a hybrid feature set derived from EEG signals.