Reducing the Complexity of Deep Learning Models for EEG Analysis on Wearable Devices
Quick Answer
This paper explores the deployment of deep neural networks (DNNs) for EEG analysis on wearable devices, focusing on reducing complexity through parameter quantization and electrode reduction.
Quick Take
The findings indicate that these methods can significantly lower DNN complexity with minimal accuracy loss, facilitating the use of advanced models for detecting epileptic seizures in resource-constrained environments.
Key Points
- Wearable healthcare devices are rapidly growing in the IoT sector.
- DNNs face energy and computational constraints in wearable applications.
- Parameter quantization and electrode reduction can reduce DNN complexity.
- Minimal accuracy loss is observed when applying these techniques.
- The study focuses on EEG analysis for detecting epileptic seizures.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Wearable healthcare devices are the fastest-growing Internet of Things (IoT) sector. Many automated healthcare services rely on two crucial biological signals, namely ECG and EEG, which reflect the activity of the heart and brain, respectively. Although deep neural networks are considered the primary way to process and analyze these signals, the very tight energy and computational power constraints in wearable devices are far below the computational, energy, and memory bandwidth demands of DNN models, thereby impeding the deployment of deep learning in many practical wearable services. This paper investigates the feasibility of deploying state-of-the-art DNN models in resource-constrained wearable devices. Notably, we explore the trade-off between accuracy and computational complexity of DNNs when parameter quantization and electrode reduction methods are used. Our investigation centers on several state-of-the-art DNN models designed for EEG signal analysis, specifically for detecting epileptic seizures. Our findings demonstrate that, when applied judiciously, these techniques can significantly reduce the complexity of the DNNs under consideration with minimal adverse effects on accuracy. These results reveal the explicit trade-offs between accuracy and complexity reduction encountered when adapting DNN-based online EEG analysis for wearable devices.
| Subjects: | Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR) |
| Cite as: | arXiv:2606.12742 [cs.AI] |
| (or arXiv:2606.12742v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.12742 arXiv-issued DOI via DataCite |
Submission history
From: Mehdi Modarressi [view email]
[v1]
Wed, 10 Jun 2026 23:08:12 UTC (82 KB)
[v2]
Mon, 15 Jun 2026 18:39:59 UTC (85 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.