An intelligent optimized deep learning model to achieve early prediction of epileptic seizures

Seizure prediction from electroencephalogram (EEG) time series data and a sequential deep learning (DL) predictor substantially boosts epileptic patients' quality of life. However, a significant challenge is a variation in seizure characteristics with time and individuals along with a need for more data. Also, considerable dissimilarity is noticed in the duration between various seizure stages. Thus, a patient-generic approach is required to mitigate the problem. As a result, multiple feature augmentation procedures are used to create a hybrid feature space to capture the non-linearity of epileptic seizures. This elaborate feature space helps the predictor learn better to enhance the seizure prediction. Additionally, the predictor is optimized using a novel hybrid Forensic-based-Search-and-Rescue Optimization (FB-SARO) to improve the seizure prediction. In addition, an optimal seizure prediction horizon (SPH) is also determined through the classifier's learning. The SPH helps attain early prediction while preserving accuracy and achieving a minimum False Prediction Rate (FPR). It also helps raise the alarm to provide the patients with ample preparation time for medical assistance. The proposed approach is testified through publicly available datasets and compared with existing state-of-the-art techniques.