EUVIMEDEUVIMED entdecken
Crossref

Real-Time Driver Cognitive Workload Recognition: Attention-Enabled Learning With Multimodal Information Fusion

Haohan Yang, Jingda Wu, Zhongxu Hu, Chen Lv

IEEE Transactions on Industrial Electronics · 2024-05 · 71 (5) · 4999-5009

DOI: 10.1109/tie.2023.3288182 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Industrial Electronics, 2024-05. Verfasst von Haohan Yang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 89-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: Start-Up Grant, Nanyang Technological University, Agency for Science, Technology and Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Driver workload inference is significant for the design of intelligent human–machine cooperative driving schemes since it allows the systems to alert drivers before potentially dangerous maneuvers and achieve a safer control transition. However, pattern variations among individual drivers and sensor artifacts pose great challenges to the existing cognitive workload recognition approaches. In this article, we develop an attention-enabled recognition network with a decision-level fusion architecture to further improve the workload estimation performance. Specifically, the cross-attention mechanism can enhance useful feature representations learned by hyper long-short-term-memory-based modules from time-series multimodal information, i.e., electroencephalogram signals, eye movements, and vehicle states. A novel dataset containing multiple driving scenarios is constructed to evaluate the model performance across different historical horizons and decision thresholds, and test results demonstrate the superior performance of the proposed model to other existing methods. Furthermore, robustness tests and driver-in-the-loop experiments are conducted to verify the effectiveness of the developed model in real-time workload levels inference. The code and supplementary materials are available athttps://yanghh.io/Driver-Workload-Recognition.

Förderung

  • Start-Up Grant
  • Nanyang Technological University
  • Agency for Science, Technology and Research
  • ANR-NRF joint
  • MTC Individual Research

Zitieren

APA

Yang, H., Wu, J., Hu, Z., & Lv, C. (2024). Real-Time Driver Cognitive Workload Recognition: Attention-Enabled Learning With Multimodal Information Fusion. IEEE Transactions on Industrial Electronics, 71(5), 4999-5009. https://doi.org/10.1109/tie.2023.3288182

Vancouver

Yang H, Wu J, Hu Z, Lv C. Real-Time Driver Cognitive Workload Recognition: Attention-Enabled Learning With Multimodal Information Fusion. IEEE Transactions on Industrial Electronics. 2024;71(5):4999-5009. doi:10.1109/tie.2023.3288182

BibTeX
@article{Yang2024,
  author = {Yang, Haohan and Wu, Jingda and Hu, Zhongxu and Lv, Chen},
  title = {Real-Time Driver Cognitive Workload Recognition: Attention-Enabled Learning With Multimodal Information Fusion},
  journal = {IEEE Transactions on Industrial Electronics},
  year = {2024},
  volume = {71},
  number = {5},
  pages = {4999--5009},
  doi = {10.1109/tie.2023.3288182}
}
Kostenlos starten →