HengNet: An Ultra-lightweight Model with Two-level Reuse Algorithm for Seizure Detection and Prediction

IEEE International Symposium on Circuits and Systems proceedings, pp. 1–5

Abstract

Traditional models based on electroencephalographic (EEG) signals for seizure monitoring encounter difficulties in simultaneously optimizing accuracy, response latency, and computational load. These challenges hinder their deployment in edge computing environments, where real-time local inference is critical. To address these issues, we introduce a novel network architecture, designated as HengNet. This architecture integrates a Two-level Reuse Algorithm (TRA), which strategically reutilizes outputs from intermediate layers, considerably reducing the average computational load per inference—vital for scenarios requiring frequent inferences. When tested on the CHB-MIT dataset, this patient-specific model attains classification accuracies of 95.67% and 99.60% for seizure prediction and detection, respectively. Notably, it maintains an average computational load of merely 0.05 million multiply-accumulate operations (MACs) per inference and has a compact model size of 6.87 K parameters. These results represent a significant advancement compared with existing methods. Operating at a rate of 32 inferences per second, the computational load of the model for seizure prediction has been reduced by more than 19.4 times, and for seizure detection, by more than 6.4 times.

Authors 5

1. Heng Zhang

   Nanjing University

   Affiliation as printed

   Nanjing University,School of Electronic Science and Engineering,Nanjing,China

2. Wenjie Fan

   Nanjing University

   Affiliation as printed

   Nanjing University,School of Electronic Science and Engineering,Nanjing,China

3. Xingjie Zou

   Nanjing University

   Affiliation as printed

   Nanjing University,School of Electronic Science and Engineering,Nanjing,China

4. Qinyu Chen Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden University,The Leiden Institute of Advanced Computer Science,Leiden,Netherlands

5. Yuxiang Fu

   Nanjing University

   Affiliation as printed

   Nanjing University,School of Integrated Circuits,Suzhou,China