An Efficient Hybrid Model for Patient-Independent Seizure Prediction Using Deep Learning

Recently, many researchers have deployed different deep learning techniques to predict epileptic seizure, using electroencephalogram signals. However, most of this research requires very large amounts memory and complicated feature extraction algorithms. In addition, they could not precisely examine EEG signal characteristics, which led poor prediction performance. research, a non-patient-specific seizure approach is proposed. The proposed model integrates Wavelet-based processing with architectures for efficient pre-ictal inter-ictal system uses models one-dimensional convolutional neural networks discriminate between signals in order enhance Experiments been carried out on benchmark dataset validate the robustness model. experimental results showed that achieved 93.4% 16 patients 97.87% 6 patients. can seizures effectively, remarkable potential clinical applications.