EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Event-Driven Neuromorphic Architecture for Energy-Efficient Driver Distraction Detection

Wei Song

INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL · 07.07.2026 · 21 (4)

DOI: 10.15837/ijccc.2026.4.7221 ↗

Kurz gefasst

Fachartikel in der Zeitschrift INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, online erschienen am 07.07.2026. Verfasst von Wei Song. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study proposes an energy-efficient framework for embedded driver distraction detection based on brain-inspired computing. The framework integrates a dynamic vision sensor (DVS) with a spiking neural network (SNN) and incorporates dissipative wave dynamics to achieve efficient feature propagation. The experimental results demonstrated that the system maintained high detection accuracy and energy efficiency across various driving scenarios. The proposed system achieved over 99% accuracy in complex scenarios while reducing power consumption by more than 85% compared to the GPU-CNN baseline. These improvements demonstrate the feasibility of event-driven neuromorphic computing for sustainable embedded driver monitoring. The research provides new insights for the practical deployment of low-power automotive safety systems.

Zitieren

APA

Song, W. (2026). Event-Driven Neuromorphic Architecture for Energy-Efficient Driver Distraction Detection. INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, 21(4). https://doi.org/10.15837/ijccc.2026.4.7221

Vancouver

Song W. Event-Driven Neuromorphic Architecture for Energy-Efficient Driver Distraction Detection. INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL. 2026;21(4). doi:10.15837/ijccc.2026.4.7221

BibTeX
@article{Song2026,
  author = {Song, Wei},
  title = {Event-Driven Neuromorphic Architecture for Energy-Efficient Driver Distraction Detection},
  journal = {INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL},
  year = {2026},
  volume = {21},
  number = {4},
  doi = {10.15837/ijccc.2026.4.7221}
}
Kostenlos starten →