Seizure-Sentry: A Wearable Multi-Channel EEG Monitoring System with Deep Wave Net-Based Seizure Prediction

DOI

10.2991/978-94-6239-727-9_11How to use a DOI?

Keywords

Epilepsy; EEG; Seizure Prediction; Deep Learning; Wearable Health Devices; LSTM

Abstract

Epileptic seizures occur unpredictably and can severely impact patient safety and quality of life. Accurate seizure prediction from EEG signals enables timely intervention and improves clinical decision-making. This paper presents Deep Wave Net, a compact hybrid convolutional–recurrent neural network designed for EEG-based seizure prediction. EEG signals are preprocessed via bandpass filtering and artefact suppression. Spatial–temporal features are then extracted through stacked Conv1D and LSTM layers. Deep Wave Net is evaluated on the CHB-MIT Scalp EEG Database and achieves a prediction accuracy of 95.98% (94.1–97.4%), an F1-score of 0.989, and a false alarm rate of 0.23 false alarms per hour. Deep Wave Net extends prior CNN–LSTM designs through three targeted contributions: (i) a temporally-calibrated max-pooling formulation that preserves ictal spike-wave morphology; (ii) a compact architecture explicitly designed for quantised on-device deployment on ARM Cortex-M4 microcontrollers; and (iii) system-level co-design with the Seizure-Sentry wearable acquisition hardware. These results demonstrate that Deep Wave Net effectively captures neural dynamics associated with preictal progression and offers a promising, deployment-ready direction for continuous seizure monitoring in wearable and clinical applications.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ramji Gupta
AU  - Madhur Raiyani
AU  - Alpana Pandey
AU  - Richa Mishra
AU  - Mukul Jain
AU  - Priyansh Dwivedi
PY  - 2026
DA  - 2026/07/22
TI  - Seizure-Sentry: A Wearable Multi-Channel EEG Monitoring System with Deep Wave Net-Based Seizure Prediction
BT  - Proceedings of the International Conference on Sustainable Micro-Nano Materials & Innovative Technology (ICSUMMIT 2026)
PB  - Atlantis Press
SP  - 138
EP  - 154
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6239-727-9_11
DO  - 10.2991/978-94-6239-727-9_11
ID  - Gupta2026
ER  -