Article Preview
TopLiterature Review
Sunindijo et al. (2017) identified four areas that are essential for improving security performance in the construction industry: 1) quantitative research for skilled construction personnel; 2) learning-in-practice and interactions with the people and equipment at work; 3) skill enhancement methodologies to enhance employees' safety awareness; and 4) university participation to increase safety knowledge. While basic security education satisfies the legislative minimums, these researchers believe that additional procedures, like the exchange of information, are equally critical to improving security knowledge and understanding (Roy et al., 2023). They created a novel safety framework that is Internet-of-Things (IoT)-dependent and that allows for real-time surveillance of development locations, humans, and settings (Chung et al., 2020). The proposed framework not only detects real-time employee security issues, such as near misses, in order to minimize injury rates, but also saves digitized information to enhance future training and its own future surveillance (Aljarf et al., 2023). The approach we suggest in this study offers users a cost-effective alternative for improved construction security. However, this method is still in the planning stages (Singh et al., 2022). More advantages will become apparent after the system has been executed throughout the actual project (Tang et al., 2020).
A detailed assessment of the applications of wearable technology for security surveillance tailored to construction sites was published by Awolusi et al. in 2018. Wearable device features and security regulations that are believed to impact security performance and management strategies were investigated. According to the current study, current wearable technologies that have been employed in various companies could be employed to observe and evaluate a broad range of security performance metrics in the development industry (Yang et al., 2020). Different wearable sensors may be mixed depending on various attributes for multiparameter security analysis (Zheng et al., 2019). Regarding the outcome of this study, further investigation could include creating models of construction-specific wearable components as well as evaluating their usefulness(Sun et al., 2020). To create the groundwork for precise dynamic analysis, smart extensive forecast, and thorough and reliable project tracking, it is necessary to delve deeply into the possibilities of project monitoring and administration, as well as enhance the surveillance system. Sun,W et al. (2020), presented a power grid construction safety early warning framework. The classic support vector machine (SVM) security early warning technique's mathematical approach has limits in parameter tuning. Since it cannot acquire a stronger early warning impact, the Particle Swarm Optimization technique is preferable to the previous technique in parameter tuning. It searches for improved parameter combinations and achieves an improved early warning impact by combining information from the entire group and mutual collaboration between people. Still, the detection speed is low in this method.