Search

There is a growing interest in exploring the use of wearable Augmented Reality (AR) devices to improve the task performance of construction workers. However, user interaction with AR has not been well understood in the current literature, which may result in poor usability, occupational hazards, and low acceptance. To bridge this gap, this study introduced cognitive ergonomics theory to design and develop an AR application for improving the kinaesthetic performance of construction workers conducting onsite assembly tasks. The methodology of this study is three-fold. First, articles in relation to cognitive ergonomics were reviewed to propose a unique cognitive model that reveals the cognitive mechanisms of construction workers, including human information processing, selective attention, and attention resources. Second, the characteristics of existing AR application functions were synthesised to develop a customised and user-friendly wearable AR application that aligns with the identified cognitive mechanisms. Third, a rebar-tying experiment was conducted to validate the developed AR application. The results indicate that the experimenters instructed by the application can complete the task independently without the need to seek after expert assistance; the application has a potential to foster the skill development of construction workers and enhance their kinaesthetic performance; and the proposed cognitive model and the AR development principles are well aligned from the perspective of cognitive ergonomics, which could promote the uptake of wearable AR in the construction industry. • Cognitive ergonomics theories were introduced to design and develop the AR application. • A cognitive model was proposed to reveal the impact of the application on construction worker performance. • The development assisted the workers in assembling rebars more independently. • The kinaesthetic performance of workers significantly increased as well. [ABSTRACT FROM AUTHOR]

Spatial locations of personnel, equipment, and materials are constantly changing as construction projects progress. The dynamic nature of the construction industry affects workers' performance of identifying hazards. Even though a great deal of effort has been made to improve construction safety, the construction industry still witnesses a high accident rate. In order to complement the existing body of knowledge relating to construction safety, this paper integrates Digital Twin (DT), Deep Learning (DL), and Mixed Reality (MR) technologies into a newly developed real-time visual warning system, which enables construction workers to proactively determine their safety status and avoid accidents. Next, system tests were conducted under three quasi-on-site scenarios, and the feasibility was proven in terms of synchronising construction activities over a large area and visually representing hazard information to its users. These evidenced merits of the development testing scenarios can improve workers' risk assessment accuracy, reinforce workers' safety behaviour, and provide a new perspective for construction safety managers to analyse construction safety status. • The proposed system generates simulated virtual construction sites based on the digital twin concept. • The virtual construction sites integrate BIM models and live video data for hazard identification. • Wearable mixed reality devices can present real-time hazard information to individual workers intuitively. • Three preliminary experiments have demonstrated the feasibility of the proposed system. [ABSTRACT FROM AUTHOR]

Low situational awareness contributes to safety incidents in construction. Existing Deep Learning (DL)-based applications lack the capability to provide context-specific and interactive feedback that is essential for workers to fully understand their surrounding environments. This paper proposes the Visual Construction Safety Query (VCSQ) system. The system encompasses real-time Image Captioning (IC), safety-centric Visual Question Answering (VQA), and keyword-based Image-Text Retrieval (ITR), integrated with head-mounted Augmented Reality (AR) devices. System validation includes benchmarks and real-world images. The ITR module posted high recall rates of 0.801 and 0.835 for Recall@5 and @10. The VQA module achieved an 89.7% accuracy rate, and the IC module had a SPICE score of 0.449. Feasibility tests and surveys confirmed the system's practical advantages in different construction scenarios. This study establishes an integration roadmap adaptable to future advancements in interactive DL and immersive AR. • A vision-language system is developed for real-time captions and safety queries. • A dataset is created containing 7 safety considerations for unsafe situation query. • An intuitive AR application is incorporated for an immersive user experience. • The system achieves 89.7% accuracy and 83.5% recall rates against benchmark datasets. [ABSTRACT FROM AUTHOR]

Abdominal aortic aneurysm (AAA) is a fatal disease, and exposure to 3,4-benzopyrene (Bap) is closely related to the development of AAA. We have found that Bap could impair the biological function of endothelial progenitor cells (EPCs), which are associated with the occurrence of AAA. We have also demonstrated that macrophage activation plays a key role in Bap-induced AAA, but the mechanism is unknown. Here, we used a mouse lncRNA array to investigate the expression signatures of lncRNAs and mRNAs in Bap-activated macrophage. A total of 457 lncRNAs and 219 mRNAs were found to be differentially expressed. The function of differential mRNAs was determined by pathway and Gene Ontology analysis. Eight pathways associated with inflammation were upregulated, and seven pathways including cell apoptosis were downregulated. It was worth noting that AGE-RAGE pathway, which was involved in Bap-induced EPC dysfunction, was significantly upregulated in Bap-activated macrophage and may contribute to AAA formation. Thus, lncRNAs may exert a key role in activated macrophages and intervene the core lncRNAs and may inhibit the occurrence of a series of cascade reactions in the macrophages, which may provide potential targets for AAA caused by smoking. [ABSTRACT FROM AUTHOR]

• A novel data augmentation method is proposed for enhancing DL model performance under occlusion. • A lightweight DL model is formulated for real-time worker and machinery detection. • A real-time proximity detection application was developed by integrating DL and image post-processing techniques. • The developed application manifests significant merits in risk mitigation. Automated recognition of image patterns in surveillance cameras is beneficial for safety monitoring. A representative application is visual proximity detection for accident prevention. However, existing deep learning (DL)-based proximity detection methods are likely to be inaccurate due to congestion, background clutter, and occlusion in construction sites. Another problem is that most of these methods cannot suffice computing capability, network training efficiency, and performance accuracy at the same time. This study first presents a novel context-guided data augmentation method that addresses the performance loss issue due to object occlusion. This method places new instances on images based on contextual image information rather than randomly erasing images to simulate occlusion circumstances. Next, a light-weight and less-costly DL model named YOLOv4-EFNB0 is formulated for multi-class construction resource detection in real-time. Moreover, this study presents a proactive proximity detection application by integrating YOLOv4-EFNB0 with homography transformation. Based on the experiment, YOLOv4-EFNB0 demonstrates a better object detection outcome when trained on the augmented dataset over the Moving Objects in Construction Sites (MOCS) baseline dataset. This study also conducts a feasibility test for the visual proximity detection application. The results indicate the application has a high accuracy rate and a fast speed, namely, 96.76% in 25 Frames Per Second (FPS), which can facilitate the automation of safety monitoring and inspection. [ABSTRACT FROM AUTHOR]