An Energy-Efficient Edge-AI Framework for Continuous EEG-Based Cognitive Screening
IEEE Open Journal of Engineering in Medicine and Biology · 2026 · 7 · 392-399
DOI: 10.1109/ojemb.2026.3743417 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Open Journal of Engineering in Medicine and Biology, 2026. Verfasst von Ashutosh Kumar Sinha und 4 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: I-DAPT HUB Foundation.
Abstract (Originalsprache)
Goal: Continuous health monitoring using wearables is increasingly important for the early detection of neurodegenerative disorders such as Alzheimer's disease. However, most EEG-based diagnostic systems rely on cloud processing and high-power hardware, making them unsuitable for long-term wearable deployment. Achieving continuous cognitive screening on resource-constrained sensing platforms requires energy-efficient signal processing, compact models, and minimal wireless communication.
Methods
This paper presents an energy-efficient Edge-AI framework designed for microcontroller-class wearable devices. The system combines on-device preprocessing with a TinyML-optimized multi-scale Inception neural network to perform real-time inference directly on the sensing node. The pipeline incorporates an energy-aware Artifact Variance Gate to reject high-variance corrupted signal windows before inference while conserving computational energy. The variance gate serves as a hardware fail-fast mechanism that discards corrupted signal windows before inference. Next, we employ exponential moving standardization for adaptive signal normalization. Further, we introduce a variance-aware, learnable step-size quantization strategy that compresses the model to INT8 precision via quantization-aware training, enabling deployment within strict memory budgets. The model performs binary classification of EEG recordings from subjects with clinically diagnosed Alzheimer's disease (AD) and cognitively normal (CN) controls.
Results
Evaluation on the OpenNeuro ds004504 dataset using Leave-One-Subject-Out (LOSO) Cross-Validation achieves 86.2% classification accuracy while reducing model memory requirements by $\sim 4\times$ compared with the original FP32 model.
Conclusions
Finally, we developed a helmet prototype with a deployed quantized model embedded with edge hardware and evaluated it on an independent cohort of 20 subjects using a 19-channel wet-electrode.
Förderung
- I-DAPT HUB Foundation
Zitieren
APA
Sinha, A. K., Sinha, A., Shukla, P., Mishra, R., & Gupta, H. P. (2026). An Energy-Efficient Edge-AI Framework for Continuous EEG-Based Cognitive Screening. IEEE Open Journal of Engineering in Medicine and Biology, 7, 392-399. https://doi.org/10.1109/ojemb.2026.3743417
Vancouver
Sinha AK, Sinha A, Shukla P, Mishra R, Gupta HP. An Energy-Efficient Edge-AI Framework for Continuous EEG-Based Cognitive Screening. IEEE Open Journal of Engineering in Medicine and Biology. 2026;7:392-399. doi:10.1109/ojemb.2026.3743417
BibTeX
@article{Sinha2026,
author = {Sinha, Ashutosh Kumar and Sinha, Akash and Shukla, Prakhar and Mishra, Rahul and Gupta, Hari Prabhat},
title = {An Energy-Efficient Edge-AI Framework for Continuous EEG-Based Cognitive Screening},
journal = {IEEE Open Journal of Engineering in Medicine and Biology},
year = {2026},
volume = {7},
pages = {392--399},
doi = {10.1109/ojemb.2026.3743417}
}
EUVIMED