IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

DSR-YOLOv8: A Dangerous Behavior Detection Algorithm for Electric Power Construction Workers Based on Depthwise Separable Residual Improved YOLOv8

DSR-YOLOv8: A Dangerous Behavior Detection Algorithm for Electric Power Construction Workers Based on Depthwise Separable Residual Improved YOLOv8
View Sample PDF
Author(s): Lingwen Meng (Electric Power Research Institute of Guizhou Power Grid Co. Ltd., China), Shasha Luo (Electric Power Research Institute of Guizhou Power Grid Co. Ltd., China), Jiangang Liu (Electric Power Research Institute of Guizhou Power Grid Co. Ltd., China), Bangming Zhang (Electric Power Research Institute of Guizhou Power Grid Co. Ltd., China)and Zhonghai Ruan (GuangZhou Power Electrical Technology Co., Ltd., China)
Copyright: 2026
Volume: 17
Issue: 1
Pages: 15
Source title: International Journal of Ambient Computing and Intelligence (IJACI)
Editor(s)-in-Chief: Nilanjan Dey (Techno International New Town, Kolkata, India)
DOI: 10.4018/IJACI.404000

Purchase


Abstract

The power construction industry's growth demands efficient monitoring of high-risk worker behaviors, yet traditional methods are inefficient and existing models face false alarms in complex scenes. This study proposes DSR-YOLOv8, an improved YOLOv8 algorithm integrating three modules: (1) DSRAB using deep separable convolution and global pooling to enhance subtle action features and denoising; (2) SD_SPPF with multi-scale dilated kernels to expand the receptive field while reducing computational costs; (3) dynamic region-processing with partial convolutional heads to focus on critical areas and suppress interference. Evaluated on a self-built Dangerous Behavior Dataset (DBD) containing “helmet-wearing,” “no helmet,” and “smoking” scenarios, DSR-YOLOv8 achieved 91.2% accuracy (+3.5%) and 89.7% mAP (+3.6%) over baselines, demonstrating efficient hazardous behavior detection for enhanced safety in power construction.

Related Content

Arjun Kaarat, Venkata Jaipal Reddy Batthula, Richard S. Segall. © 2026. 31 pages.
QingLe Zheng. © 2026. 22 pages.
Prasanna Rajbhandari, Richard S. Segall. © 2026. 33 pages.
Catherine Camiguing Gabia, Dwight Gabia, Samuel C. Villa Jr., Blesie M. Villa, Nelson F. Nolon, Irene Mamites, Melanie M. Himang. © 2026. 27 pages.
Lingwen Meng, Shasha Luo, Jiangang Liu, Bangming Zhang, Zhonghai Ruan. © 2026. 15 pages.
Dong Liang, Peilin Chen. © 2026. 18 pages.
Marine M. Milad. © 2026. 24 pages.
Body Bottom