Automated Epileptic Seizure Detection using Improved Crystal Structure Algorithm with Stacked Autoencoder

Epilepsy can be referred to as a neurological disorder, categorized by intractable seizures with serious consequences. To forecast such seizures, Electroencephalogram (EEG) datasets should gathered continuously. EEG signals were recorded using numerous electrodes fixed on the scalp that cannot worn patients Neurostimulators intervene in advance and ignore seizure rate. Its productivity is increased heuristics advanced prediction. In recent times, several authors have deployed various deep learning approaches for predicting epileptic utilizing signals. this work, an Automated Epileptic Seizure Detection Improved Crystal Structure Algorithm Stacked Auto encoder (AESD-ICSASAE) technique has been developed. The presented AESD-ICSASAE executes three-stage process. At initial level, applies min-max normalization approach normalize input data. Next, uses ICSA based feature selection method optimal choice of features. Finally, SAE classification process takes place hyperparameter performed Arithmetic Optimization (AOA). depict enhanced outcomes technique, series experiments was made. Furthermore, proposed method's results tested CHB-MIT database, indicating accuracy 98.9%. These validate highest level across all analyzed A full set validated enhancements.