# Efficient and Accurate Epilepsy Seizure Prediction and Detection Based on Multi-Teacher Knowledge Distillation RGF-Model

## TL;DR

This paper introduces a lightweight model for predicting and detecting epileptic seizures in real-time using wearable devices, achieving high accuracy with low computational cost.

## Contribution

The RGF-Model combines a novel Ring-GRU and FiLM with multi-teacher knowledge distillation for efficient seizure prediction and detection.

## Key findings

- The RGF-Model achieves 99.54% AUC and 0.01 FPR/h for seizure prediction on the CHB-MIT dataset.
- It maintains 98.78% accuracy for seizure detection with only 0.082 million parameters.
- The model outperforms existing teacher models in efficiency while preserving accuracy.

## Abstract

Background: Epileptic seizures are unpredictable, and while existing deep learning models achieve high accuracy, their deployment on wearable devices is constrained by high computational costs and latency. To address this, this work proposes the RGF-Model, a lightweight network that unifies seizure prediction and detection within a single causal framework. Methods: By integrating Feature-wise Linear Modulation (FiLM) with a Ring-Buffer Gated Recurrent Unit (Ring-GRU), the model achieves adaptive task-specific feature conditioning while strictly enforcing causal consistency for real-time inference. A multi-teacher knowledge distillation strategy is employed to transfer complementary knowledge from complex teacher ensembles to the lightweight student, significantly reducing complexity without sacrificing accuracy. Results: Evaluations on the CHB-MIT and Siena datasets demonstrate that the RGF-Model outperforms state-of-the-art teacher models in terms of efficiency while maintaining comparable accuracy. Specifically, on CHB-MIT, it achieves 99.54% Area Under the Curve (AUC) and 0.01 False Prediction Rate per hour (FPR/h) for prediction, and 98.78% Accuracy (Acc) for detection, with only 0.082 million parameters. Statistical significance was assessed using a random predictor baseline (p < 0.05). Conclusions: The results indicate that the RGF-Model provides a highly efficient solution for real-time wearable epilepsy monitoring.