EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

YOLOv11-Safe: An Explainable AI Framework for Data-Driven Building Safety Evaluation and Design Optimization in University Campuses

Jing Hou, Yanfeng Hu, Bingchun Jiang, Zhoulin Chang, Mingjie Cao, Beili Wang

Buildings · 16.11.2025 · 15 (22) · 4125

DOI: 10.3390/buildings15224125 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Buildings, online erschienen am 16.11.2025. Verfasst von Jing Hou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: School of Mechanical and Electrical Engineering, Guangdong University of Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Campus buildings often present hidden safety risks such as falls and wheelchair instabilities, which are closely related to architectural layout, material selection, and accessibility design. This study develops YOLOv11-Safe, an attention-enhanced and geometry-aware framework that functions as both a detection model and a spatial diagnostic tool for building safety assessment. The framework integrates a modified SimAM attention mechanism and a normalized Wasserstein distance (NWD) loss to improve detection accuracy in complex indoor environments, trained on a dataset of 1000 annotated images covering fall and wheelchair accident scenarios. To interpret spatial risk patterns, a Random Forest classifier combined with SHAP analysis was applied to quantify the contribution of five architectural–behavioral variables: body–ground contact ratio (BGCR), accessibility index (AI), event duration (D), body posture angle (PA), and spatial density (SD). Results show that BGCR and AI dominate the risk-level prediction, while D, PA, and SD refine boundary conditions. Scene-based verification further demonstrated that the framework accurately localized unsafe features—such as uneven drainage edges and discontinuous handrails—and translated them into actionable design feedback. The proposed approach thus links deep-learning detection with interpretable spatial analysis, offering a quantitative foundation for evidence-based architectural safety optimization in university campuses.

Förderung

  • School of Mechanical and Electrical Engineering, Guangdong University of Science and Technology

Zitieren

APA

Hou, J., Hu, Y., Jiang, B., Chang, Z., Cao, M., & Wang, B. (2025). YOLOv11-Safe: An Explainable AI Framework for Data-Driven Building Safety Evaluation and Design Optimization in University Campuses. Buildings, 15(22), 4125. https://doi.org/10.3390/buildings15224125

Vancouver

Hou J, Hu Y, Jiang B, Chang Z, Cao M, Wang B. YOLOv11-Safe: An Explainable AI Framework for Data-Driven Building Safety Evaluation and Design Optimization in University Campuses. Buildings. 2025;15(22):4125. doi:10.3390/buildings15224125

BibTeX
@article{Hou2025,
  author = {Hou, Jing and Hu, Yanfeng and Jiang, Bingchun and Chang, Zhoulin and Cao, Mingjie and Wang, Beili},
  title = {YOLOv11-Safe: An Explainable AI Framework for Data-Driven Building Safety Evaluation and Design Optimization in University Campuses},
  journal = {Buildings},
  year = {2025},
  volume = {15},
  number = {22},
  pages = {4125},
  doi = {10.3390/buildings15224125}
}
Kostenlos starten →