Imagen de Portada

FastKAN-DDD: A novel fast Kolmogorov-Arnold network-based approach for driver drowsiness detection optimized for TinyML deployment

Guardado en:
Publicado en:PLoS One vol. 20, no. 11 (Nov 2025), p. e0332577
Autor principal: Essahraui, Siham
Otros Autores: Ismail Lamaakal, Maleh, Yassine, Khalid El Makkaoui, Mouncef Filali Bouami, Ouahbi, Ibrahim, Elmannai, Hela, Abd El-Latif, Ahmed A
Publicado:
Public Library of Science
Materias:
Physiology
Microcontrollers
Traffic accidents
Accuracy
Deep learning
Datasets
Sleepiness
Real time
Machine learning
Driver fatigue
Vehicles
Fatigue
Embedded systems
Radial basis function
Failure analysis
Neural networks
Classification
Inference
Network latency
Traffic accidents & safety
Drowsiness
Latency
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:Driver drowsiness is a leading cause of traffic accidents and fatalities, highlighting the urgent need for intelligent systems capable of real-time fatigue detection. Although recent advancements in machine learning (ML) and deep learning (DL) have significantly improved detection accuracy, most existing models are computationally demanding and not well-suited for deployment in resource-limited environments such as microcontrollers. While the emerging domain of TinyML presents promising avenues for such applications, there remains a substantial gap in the development of lightweight, interpretable, and high-performance models specifically tailored for embedded automotive systems. This paper introduces FastKAN-DDD, an innovative driver drowsiness detection model grounded in the Fast Kolmogorov-Arnold Network (FastKAN) architecture. The model incorporates learnable nonlinear activation functions based on radial basis functions (RBFs), facilitating efficient function approximation with a minimal number of parameters. To enhance suitability for TinyML deployment, the model is further optimized through post-training quantization techniques, including dynamic range, float-16, and weight-only quantization. Comprehensive experiments were conducted using the UTA-RLDD dataset—a real-world benchmark for driver drowsiness detection—evaluating the model across various input resolutions and quantization schemes. The FastKAN-DDD model achieved a test accuracy of 99.94%, with inference latency as low as 0.04 ms and a total memory footprint of merely 35 KB, rendering it exceptionally well-suited for real-time inference on microcontroller-based systems. Comparative evaluations further confirm that FastKAN surpasses several state-of-the-art TinyML models in terms of accuracy, computational efficiency, and model compactness. Our code’s are publicly available at: https://github.com/sihamess/driver_drowsiness_detection_TinyML.
ISSN:1932-6203
DOI:10.1371/journal.pone.0332577
Fuente:Health & Medical Collection