# EpiDeNet: An Energy-Efficient Approach to Seizure Detection for Embedded Systems

arXiv: https://arxiv.org/abs/2309.07135 · HTML: https://mlsanity.com/paper/2309.07135/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 25 references that are in the map.
- First posted on arXiv 28 Aug 2023.

## Builds on (most cited first, 6 of 6)

- [DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUs](https://mlsanity.com/paper/2008.07127/) (2020)
- [ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal Convolutional Network](https://mlsanity.com/paper/2103.13740/) (2021)
- [Robust tracking of respiratory rate in high-dynamic range scenes using mobile thermal imaging](https://mlsanity.com/paper/1705.06628/) (2017)
- [Towards Long-term Non-invasive Monitoring for Epilepsy via Wearable EEG Devices](https://mlsanity.com/paper/2106.08008/) (2021)
- [Energy-Efficient Tree-Based EEG Artifact Detection](https://mlsanity.com/paper/2204.09577/) (2022)
- [Edge Deep Learning for Neural Implants](https://mlsanity.com/paper/2012.00307/) (2020)

## Built on by (most cited first, 1 of 1)

- [BISeizuRe: BERT-Inspired Seizure Data Representation to Improve Epilepsy Monitoring](https://mlsanity.com/paper/2406.19189/) (2024)

## Abstract (arXiv)

Epilepsy is a prevalent neurological disorder that affects millions of individuals globally, and continuous monitoring coupled with automated seizure detection appears as a necessity for effective patient treatment. To enable long-term care in daily-life conditions, comfortable and smart wearable devices with long battery life are required, which in turn set the demand for resource-constrained and energy-efficient computing solutions. In this context, the development of machine learning algorithms for seizure detection faces the challenge of heavily imbalanced datasets. This paper introduces EpiDeNet, a new lightweight seizure detection network, and Sensitivity-Specificity Weighted Cross-Entropy (SSWCE), a new loss function that incorporates sensitivity and specificity, to address the challenge of heavily unbalanced datasets. The proposed EpiDeNet-SSWCE approach demonstrates the successful detection of 91.16% and 92.00% seizure events on two different datasets (CHB-MIT and PEDESITE, respectively), with only four EEG channels. A three-window majority voting-based smoothing scheme combined with the SSWCE loss achieves 3x reduction of false positives to 1.18 FP/h. EpiDeNet is well suited for implementation on low-power embedded platforms, and we evaluate its performance on two ARM Cortex-based platforms (M4F/M7) and two parallel ultra-low power (PULP) systems (GAP8, GAP9). The most efficient implementation (GAP9) achieves an energy efficiency of 40 GMAC/s/W, with an energy consumption per inference of only 0.051 mJ at high performance (726.46 MMAC/s), outperforming the best ARM Cortex-based solutions by approximately 160x in energy efficiency. The EpiDeNet-SSWCE method demonstrates effective and accurate seizure detection performance on heavily imbalanced datasets, while being suited for implementation on energy-constrained platforms.