Uncertainty-Aware Continual TinyML Driver Fatigue Detection with Kolmogorov–Arnold Networks at the IoT Edge
Applied System Innovation · 08.07.2026 · 9 (7) · 147
DOI: 10.3390/asi9070147 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied System Innovation, online erschienen am 08.07.2026. Verfasst von Chaymae Yahyati und 4 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Driver fatigue is a major cause of road accidents, and in-cabin monitoring is increasingly embedded into the Internet-of-Things (IoT) ecosystem of modern vehicles. Deploying such monitoring directly on microcontroller-class devices is challenging: models must fit tight memory and compute budgets, provide reliable confidence estimates, and adapt online to new drivers and conditions. We propose KAN-CLUE, an uncertainty-aware continual TinyML framework for driver fatigue detection from near-infrared periocular images at the IoT edge. KAN-CLUE combines a compact convolutional backbone with a Kolmogorov–Arnold Network (KAN) classification head that outputs Dirichlet-distributed class probabilities and a principled predictive uncertainty measure. A lightweight activation-histogram mechanism provides an additional out-of-distribution (OOD) score, and both signals drive an on-device continual learning scheme that selectively updates a small subset of parameters under a KAN-specific EWC-style regularization. On the ULg DROZY drowsiness database, the quantized KAN-CLUE model uses roughly 167k parameters (about 165 kB in Flash), requires on the order of 106 MACs, and achieves around 3.1 ms latency on a Cortex-M–class microcontroller, while reaching 97.7% test accuracy with improved calibration and OOD detection compared with softmax-based TinyML baselines.
Zitieren
APA
Yahyati, C., Lamaakal, I., Maleh, Y., Makkaoui, K. E., & Ouahbi, I. (2026). Uncertainty-Aware Continual TinyML Driver Fatigue Detection with Kolmogorov–Arnold Networks at the IoT Edge. Applied System Innovation, 9(7), 147. https://doi.org/10.3390/asi9070147
Vancouver
Yahyati C, Lamaakal I, Maleh Y, Makkaoui KE, Ouahbi I. Uncertainty-Aware Continual TinyML Driver Fatigue Detection with Kolmogorov–Arnold Networks at the IoT Edge. Applied System Innovation. 2026;9(7):147. doi:10.3390/asi9070147
BibTeX
@article{Yahyati2026,
author = {Yahyati, Chaymae and Lamaakal, Ismail and Maleh, Yassine and Makkaoui, Khalid El and Ouahbi, Ibrahim},
title = {Uncertainty-Aware Continual TinyML Driver Fatigue Detection with Kolmogorov–Arnold Networks at the IoT Edge},
journal = {Applied System Innovation},
year = {2026},
volume = {9},
number = {7},
pages = {147},
doi = {10.3390/asi9070147}
}
EUVIMED