A Two-Layer LSTM Deep Learning Model for Epileptic Seizure Prediction

Abstract

We propose an efficient seizure prediction model based on a two-layer LSTM using the Swish activation function. The proposed structure performs feature extraction based on the time and frequency domains and uses the minimum distance algorithm as a post-processing step. The proposed model is evaluated on the Melbourne dataset and achieves the highest Area Under Curve (AUC) score of 0.92 and the lowest False Positive Rate (FPR) of 0.147 compared to previous work while having sensitivity and accuracy of 86.8 and 85.1, respectively. The proposed system has a low number of trainable parameters, and thus reducing the complexity of resource-constrained applications.