{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:46:03Z","timestamp":1757609163904,"version":"3.44.0"},"reference-count":45,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T00:00:00Z","timestamp":1756857600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"S&T Program of Hebei","award":["22370701D"],"award-info":[{"award-number":["22370701D"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Detecting unsafe human behaviors is crucial for enhancing safety in industrial production environments. Current models face limitations in multi-scale target detection within such settings. This study introduces a novel model, Sec-YOLO, which is specifically designed for detecting unsafe behaviors. Firstly, the model incorporates a receptive-field attention convolution (RFAConv) module to better focus on the key features of unsafe behaviors. Secondly, a deformable convolution network v2 (DCNv2) is integrated into the C2f module to enhance the model\u2019s adaptability to the continually changing feature structures of unsafe behaviors. Additionally, inspired by the multi-branch auxiliary feature pyramid network (MAFPN) structure, the neck architecture of the model has been restructured. Importantly, to improve feature extraction and fusion, feature-enhanced hybrid attention (FEHA) is introduced and integrated with DCNv2 and MAFPN. Experimental results demonstrate that Sec-YOLO achieves a mean average precision (mAP) at 0.5 of 92.6% and mAP at 0.5:0.95 of 63.6% on a custom dataset comprising four common unsafe behaviors: falling, sleeping at the post, using mobile phones, and not wearing safety helmets. These results represent a 2.0% and 2.5% improvement over the YOLOv8n model. Sec-YOLO exhibits excellent performance in practical applications, focusing more precisely on feature handling and detection.<\/jats:p>","DOI":"10.7717\/peerj-cs.3151","type":"journal-article","created":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T08:38:31Z","timestamp":1756888711000},"page":"e3151","source":"Crossref","is-referenced-by-count":0,"title":["Detection of unsafe workplace behaviors: Sec-YOLO model with FEHA attention"],"prefix":"10.7717","volume":"11","author":[{"given":"Yang","family":"Liu","sequence":"first","affiliation":[]},{"given":"Shuaixian","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Tao","family":"Song","sequence":"additional","affiliation":[]},{"given":"Wenyu","family":"Dong","sequence":"additional","affiliation":[]}],"member":"4443","published-online":{"date-parts":[[2025,9,3]]},"reference":[{"article-title":"Multiple cameras fall dataset","year":"2010","author":"Auvinet","key":"10.7717\/peerj-cs.3151\/ref-1"},{"key":"10.7717\/peerj-cs.3151\/ref-2","first-page":"11027","article-title":"Dynamic convolution: attention over convolution kernels","author":"Chen","year":"2020"},{"issue":"1","key":"10.7717\/peerj-cs.3151\/ref-3","doi-asserted-by":"publisher","first-page":"1002","DOI":"10.1109\/TIP.2024.3354108","article-title":"DEA-Net: single image dehazing based on detail-enhanced convolution and content-guided attention","volume":"33","author":"Chen","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"issue":"1","key":"10.7717\/peerj-cs.3151\/ref-4","doi-asserted-by":"publisher","first-page":"107917","DOI":"10.1016\/j.compbiomed.2024.107917","article-title":"Accurate leukocyte detection based on deformable-DETR and multi-level feature fusion for aiding diagnosis of blood diseases","volume":"170","author":"Chen","year":"2024","journal-title":"Computers in Biology and Medicine"},{"issue":"20","key":"10.7717\/peerj-cs.3151\/ref-5","doi-asserted-by":"publisher","first-page":"8385","DOI":"10.3390\/s23208385","article-title":"Student behavior detection in the classroom based on improved YOLOv8","volume":"23","author":"Chen","year":"2023","journal-title":"Sensors"},{"key":"10.7717\/peerj-cs.3151\/ref-6","first-page":"764","article-title":"Deformable convolutional networks","author":"Dai","year":"2017"},{"key":"10.7717\/peerj-cs.3151\/ref-7","first-page":"11953","article-title":"Scaling up your kernels to 31\u00d731: revisiting large kernel design in CNNs","author":"Ding","year":"2022"},{"key":"10.7717\/peerj-cs.3151\/ref-8","first-page":"576","article-title":"Human detection based Yolo backbones-transformer in UAVs","author":"Do","year":"2023"},{"key":"10.7717\/peerj-cs.3151\/ref-9","doi-asserted-by":"publisher","DOI":"10.17632\/7w7fccy7ky.4","article-title":"Dataset CAUCAFall","author":"Eraso","year":"2022"},{"issue":"7","key":"10.7717\/peerj-cs.3151\/ref-10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.autcon.2017.09.018","article-title":"Detecting non-hardhat-use by a deep learning method from far-field surveillance videos","volume":"85","author":"Fang","year":"2018","journal-title":"Automation in Construction"},{"issue":"1","key":"10.7717\/peerj-cs.3151\/ref-11","doi-asserted-by":"publisher","first-page":"106530","DOI":"10.1016\/j.ssci.2024.106530","article-title":"Investigating the relationship between human and organisational factors, maintenance, and accidents. The case of chemical process industry in South Africa","volume":"176","author":"Gonyora","year":"2024","journal-title":"Safety Science"},{"key":"10.7717\/peerj-cs.3151\/ref-12","first-page":"13708","article-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021"},{"key":"10.7717\/peerj-cs.3151\/ref-13","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"issue":"4","key":"10.7717\/peerj-cs.3151\/ref-14","doi-asserted-by":"publisher","first-page":"104580","DOI":"10.1016\/j.ssci.2019.104580","article-title":"Analysis of severe industrial accidents caused by hazardous chemicals in South Korea from January 2008 to June 2018","volume":"124","author":"Jung","year":"2020","journal-title":"Safety Science"},{"issue":"4","key":"10.7717\/peerj-cs.3151\/ref-15","doi-asserted-by":"publisher","first-page":"105057","DOI":"10.1016\/j.imavis.2024.105057","article-title":"ASF-YOLO: a novel YOLO model with attentional scale sequence fusion for cell instance segmentation","volume":"147","author":"Kang","year":"2024","journal-title":"Image and Vision Computing"},{"key":"10.7717\/peerj-cs.3151\/ref-16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.14458","article-title":"YOLOv11: an overview of the key architectural enhancements","author":"Khanam","year":"2024"},{"issue":"4","key":"10.7717\/peerj-cs.3151\/ref-17","doi-asserted-by":"publisher","first-page":"101400","DOI":"10.1016\/j.aei.2021.101400","article-title":"Computer vision and long short-term memory: learning to predict unsafe behaviour in construction","volume":"50","author":"Kong","year":"2021","journal-title":"Advanced Engineering Informatics"},{"issue":"1\u20133","key":"10.7717\/peerj-cs.3151\/ref-18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jhazmat.2005.10.059","article-title":"Statistical analysis of incidents reported in the Greek Petrochemical Industry for the period 1997\u20132003","volume":"135","author":"Konstandinidou","year":"2006","journal-title":"Journal of Hazardous Materials"},{"issue":"3","key":"10.7717\/peerj-cs.3151\/ref-19","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.cmpb.2014.09.005","article-title":"Human fall detection on embedded platform using depth maps and wireless accelerometer","volume":"117","author":"Kwolek","year":"2014","journal-title":"Computer Methods and Programs in Biomedicine"},{"issue":"11","key":"10.7717\/peerj-cs.3151\/ref-20","doi-asserted-by":"publisher","first-page":"108785","DOI":"10.1016\/j.patcog.2022.108785","article-title":"HAM: hybrid attention module in deep convolutional neural networks for image classification","volume":"129","author":"Li","year":"2022","journal-title":"Pattern Recognition"},{"key":"10.7717\/peerj-cs.3151\/ref-21","first-page":"936","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"10.7717\/peerj-cs.3151\/ref-22","first-page":"11966","article-title":"A ConvNet for the 2020s","author":"Liu","year":"2022"},{"issue":"9","key":"10.7717\/peerj-cs.3151\/ref-23","doi-asserted-by":"publisher","first-page":"409","DOI":"10.3390\/buildings11090409","article-title":"Applications of computer vision in monitoring the unsafe behavior of construction workers: current status and challenges","volume":"11","author":"Liu","year":"2021","journal-title":"Buildings"},{"key":"10.7717\/peerj-cs.3151\/ref-24","first-page":"8759","article-title":"Path aggregation network for instance segmentation","author":"Liu","year":"2018"},{"issue":"8","key":"10.7717\/peerj-cs.3151\/ref-25","doi-asserted-by":"publisher","first-page":"105135","DOI":"10.1016\/j.ssci.2020.105135","article-title":"Implementing the theoretical domains framework in occupational safety: Development of the safety behaviour change questionnaire","volume":"136","author":"Morgan","year":"2021","journal-title":"Safety Science"},{"article-title":"Safety-helmet-wearing-dataset (SHWD)","year":"2019","author":"njvisionpower","key":"10.7717\/peerj-cs.3151\/ref-26"},{"article-title":"Helmet detection","year":"2022a","author":"PaddlePaddle","key":"10.7717\/peerj-cs.3151\/ref-27"},{"article-title":"Mobile phone usage detection","year":"2022b","author":"PaddlePaddle","key":"10.7717\/peerj-cs.3151\/ref-28"},{"issue":"7","key":"10.7717\/peerj-cs.3151\/ref-29","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1016\/j.jsr.2023.08.018","article-title":"Real-time monitoring unsafe behaviors of portable multi-position ladder worker using deep learning based on vision data","volume":"87","author":"Park","year":"2023","journal-title":"Journal of Safety Research"},{"key":"10.7717\/peerj-cs.3151\/ref-30","first-page":"10778","article-title":"EfficientDet: scalable and efficient object detection","author":"Tan","year":"2020"},{"key":"10.7717\/peerj-cs.3151\/ref-31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.12524","article-title":"YOLOv12: attention-centric real-time object detectors","author":"Tian","year":"2025"},{"issue":"3","key":"10.7717\/peerj-cs.3151\/ref-32","doi-asserted-by":"publisher","first-page":"102709","DOI":"10.1016\/j.aei.2024.102709","article-title":"YOLO-MIF: improved YOLOv8 with multi-information fusion for object detection in gray-scale images","volume":"62","author":"Wan","year":"2024","journal-title":"Advanced Engineering Informatics"},{"issue":"1","key":"10.7717\/peerj-cs.3151\/ref-33","doi-asserted-by":"publisher","first-page":"106442","DOI":"10.1016\/j.engappai.2023.106442","article-title":"Mixed local channel attention for object detection","volume":"123","author":"Wan","year":"2023","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.7717\/peerj-cs.3151\/ref-34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.14458","article-title":"YOLOv10: real-time end-to-end object detection","author":"Wang","year":"2024"},{"key":"10.7717\/peerj-cs.3151\/ref-35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2309.11331","article-title":"Gold-YOLO: efficient object detector via gather-and-distribute mechanism","author":"Wang","year":"2023"},{"key":"10.7717\/peerj-cs.3151\/ref-36","first-page":"1","article-title":"YOLOv9: learning what you want to learn using programmable gradient information","author":"Wang","year":"2024"},{"key":"10.7717\/peerj-cs.3151\/ref-37","doi-asserted-by":"publisher","first-page":"2126","DOI":"10.1016\/j.proeng.2011.11.2415","article-title":"Analysis and control of human error","volume":"26","author":"Wenwen","year":"2011","journal-title":"Procedia Engineering"},{"key":"10.7717\/peerj-cs.3151\/ref-38","first-page":"3","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"issue":"2","key":"10.7717\/peerj-cs.3151\/ref-39","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1016\/j.psep.2017.11.018","article-title":"Human factors risk assessment and management: process safety in engineering","volume":"113","author":"Xie","year":"2018","journal-title":"Process Safety and Environmental Protection"},{"article-title":"Multi-branch auxiliary fusion YOLO with re-parameterization heterogeneous convolutional for accurate object detection","year":"2024","author":"Yang","key":"10.7717\/peerj-cs.3151\/ref-40"},{"issue":"5439","key":"10.7717\/peerj-cs.3151\/ref-41","doi-asserted-by":"publisher","first-page":"105061","DOI":"10.1016\/j.jlp.2023.105061","article-title":"Analysis on causes of chemical industry accident from 2015 to 2020 in Chinese mainland: a complex network theory approach","volume":"83","author":"Yang","year":"2023","journal-title":"Journal of Loss Prevention in the Process Industries"},{"key":"10.7717\/peerj-cs.3151\/ref-42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.03198","article-title":"RFAConv: innovating spatial attention and standard convolutional operation","author":"Zhang","year":"2023"},{"issue":"3","key":"10.7717\/peerj-cs.3151\/ref-43","doi-asserted-by":"publisher","first-page":"26137","DOI":"10.1109\/ACCESS.2024.3362958","article-title":"YOLO-Fall: a novel convolutional neural network model for fall detection in open spaces","volume":"12","author":"Zhao","year":"2024","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3151\/ref-44","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3443146","article-title":"Helmet-YOLO: a new method for real-time, high-precision helmet wearing detection","author":"Zhou","year":"2024","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3151\/ref-45","first-page":"9300","article-title":"Deformable ConvNets V2: more deformable, better results","author":"Zhu","year":"2019"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3151.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3151.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3151.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3151.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T08:38:34Z","timestamp":1756888714000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3151"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,3]]},"references-count":45,"alternative-id":["10.7717\/peerj-cs.3151"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3151","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"type":"electronic","value":"2376-5992"}],"subject":[],"published":{"date-parts":[[2025,9,3]]},"article-number":"e3151"}}