Comparative Analysis of Deep Learning Methods Using Multiple Modal Data for Driver Fatigue Identification

DOI

10.2991/978-94-6463-512-6_57How to use a DOI?

Keywords

Driver Fatigue; Deep Learning; Image-based Fatigue Identification; Physiological Signal-based Fatigue Identification

Abstract

Driver fatigue is a critical safety concern that significantly increases the risk of accidents on roads. By analyzing patterns and behaviors through sophisticated algorithms, deep learning can predict fatigue states and alert drivers, thereby enhancing safety. Its predictive capabilities can also inform the development of systems that promote driver safety and reduce the likelihood of fatigue-related incidents. This paper examines various machine learning-based approaches to detecting driver fatigue, focusing primarily on image-based and physiological signal-based fatigue identification. Image-based techniques utilize facial recognition and behavioral analysis to detect fatigue signs, such as frequent blinking and yawning, while physiological methods analyze data from sensors that measure heart rate variability, brain waves, and other bodily signals indicative of fatigue. The review highlights the strengths and limitations of each method, emphasizing the potential of integrating these approaches in multimodal systems. Challenges such as variable environmental conditions, system reliability, and data privacy are discussed, along with suggestions for future research aimed at improving the accuracy and practicality of fatigue detection systems.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yian Wang
PY  - 2024
DA  - 2024/09/23
TI  - Comparative Analysis of Deep Learning Methods Using Multiple Modal Data for Driver Fatigue Identification
BT  - Proceedings of the 2024 International Conference on Artificial Intelligence and Communication (ICAIC 2024)
PB  - Atlantis Press
SP  - 542
EP  - 552
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-512-6_57
DO  - 10.2991/978-94-6463-512-6_57
ID  - Wang2024
ER  -