• Journal of the Korea Institute of Building Construction
• /
• v.23 no.6
• /
• pp.831-839
• /
• 2023

This study aims to develop a framework for an accident prediction model leveraging a deep neural network algorithm, specifically tailored for small-scale construction sites. Notably, the incidence of accidents in the construction sector is markedly higher compared to other industries, with a significant contribution from small-scale sites. The challenging nature of construction in urban settings, coupled with the increasing frequency of adverse weather conditions, is likely to escalate accident risks at these sites. Anticipating and mitigating accidents at small-scale construction sites is therefore crucial to decrease the overall industry accident rate. Consequently, this research introduces a Deep Neural Network-based model for forecasting accidents at small-scale construction sites. The framework and findings of this study are poised to serve as a guideline for the safety management of small-scale construction projects, ultimately aiding in the realization of safer, more sustainable construction practices at these sites.

• Journal of the Korea Institute of Building Construction
• /
• v.21 no.5
• /
• pp.397-408
• /
• 2021

The construction industry has the highest occupational accidents/injuries and has experienced the most fatalities among entire industries. Korean government installed surveillance camera systems at construction sites to reduce occupational accident rates. Construction safety managers are monitoring potential hazards at the sites through surveillance system; however, the human capability of monitoring surveillance system with their own eyes has critical issues. A long-time monitoring surveillance system causes high physical fatigue and has limitations in grasping all accidents in real-time. Therefore, this study aims to build a deep learning-based safety monitoring system that can obtain information on the recognition, location, identification of workers and heavy equipment in the construction sites by applying multiple object tracking with instance segmentation. To evaluate the system's performance, we utilized the Microsoft common objects in context and the multiple object tracking challenge metrics. These results prove that it is optimal for efficiently automating monitoring surveillance system task at construction sites.

• Journal of the Korea Institute of Construction Safety
• /
• v.2 no.2
• /
• pp.50-55
• /
• 2019

Currently, safety management is becoming important at domestic construction sites. Despite the importance of safety management, accidents at construction sites are steadily increasing. Fire accidents among safety accidents cause not only negative effects on schedule delay or work plans at construction sites, but also huge casualties. Therefore, the purpose of this research is to extract the causes of fire at the construction site through the case of fire at the construction site, and to prioritize prevention through the analysis of the factors to contribute to the prevention of fire. As a research method, we select fire factors through case, conduct surveys through expert group, and analyze survey through AHP technique. The results of the AHP analysis of the survey of expert groups showed that the workers and their sub-item ranked high. Therefore, the priority for fire prevention was given, and this research is believed to help prevent fire.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.361-369
• /
• 2022

Unsafe actions and behaviors of workers cause most accidents at construction sites. Nowadays, occupational safety is a top priority at construction sites. However, this problem often requires money and effort from investors or construction owners. Therefore, decreasing the accidents rates of workers and saving monitoring costs for contractors is necessary at construction sites. This study proposes an unsafe behavior detection method based on a skeleton model to classify three common unsafe behaviors on the scaffold: climbing, jumping, and running. First, the OpenPose method is used to obtain the workers' key points. Second, all skeleton datasets are aggregated from the temporary size. Third, the key point dataset becomes the input of the action classification model. The method is effective, with an accuracy rate of 89.6% precision and 90.5% recall of unsafe actions correctly detected in the experiment.

• Journal of the Society of Disaster Information
• /
• v.20 no.1
• /
• pp.106-116
• /
• 2024

Purpose: This paper conducts IoT and CCTV-based safety monitoring to analyze accidents and potential risks occurring at construction sites, and detect and analyze risks such as falls and collisions or abnormalities and to establish a system for early warning using devices like a walkie-talkie and chatbot service. Method: A safety management service model is presented through smart construction technology case studies at the construction site and review a relevant literature analysis. Result: According to 'Construction Accident Statistics,' in 2021, there were 26,888 casualties in the construction industry, accounting for 26.3% of all reported accidents. Fatalities in construction-related accidents amounted to 417 individuals, representing 50.5% of all industrial accident-related deaths. This study suggests implementing AI chatbot services for construction site safety management utilizing IoT-based health monitoring technologies in smart construction practices. Construction sites where stakeholders such as workers participate were demonstrated by implementing an artificial intelligence chatbot system by selecting major risk areas within the workplace, such as scaffolding processes, openings, and access to hazardous machinery. Conclusion: The possibility of commercialization was confirmed by receiving more than 90 points in the satisfaction survey of participating workers regarding the empirical results of the artificial intelligence chatbot service at construction sites.

• Korean Journal of Construction Engineering and Management
• /
• v.25 no.4
• /
• pp.15-23
• /
• 2024

Recently, quality problems, such as the collapse of apartment structures under construction, has emerged as a social issue. Although there are various causes of quality problem and the impact of each problem may be different, the problems from the perspective of construction engineer of construction company are investigated. Therefore, this study aim to investigate the adequacy of construction engineer's experience, number of field engineer, timing of engineer deployment at construction sites, etc. in order to resolve quality and safety problems. In this study, a questionnaire survey was conducted targeting construction managers to obtain objective opinions. The results showed that the number of construction engineers in construction companies should be increased and that intermediate construction engineers should be increased to enable practical site management for resolving quality and safety problems. In addition, it was found that there was a need to reduce the number of non-regular employed field construction engineers in construction site and at the same time systematically regulate the number of on-site construction engineers, similar to safety managers and quality managers.

• Journal of the Korea Safety Management & Science
• /
• v.20 no.2
• /
• pp.21-35
• /
• 2018

The purpose of this study is to reduce the accident rate by introducing a safety system for small construction sites belonging to local governments. In the case of a small construction site, permission is granted through the building permission department and the construction management of the building safety management of 1,000 square meters of floor area less than 3 stories is not properly performed in the Enforcement Decree of the Building Act of Korea. In the current state of industrial accidents in 2016, 81.8% of all accident victims are found to be vulnerable to accident such as those occurring at work places with less than 50 employees. Considering the fact that the construction work with less than 5 billion KRW of the construction cost in Korea generates the most deaths, it is time to introduce the safety and health system of local governments.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2019.11a
• /
• pp.197-198
• /
• 2019

In this study, the study was conducted to derive the utility of the safety management system applying block chain technology and big data technology to improve the problems of construction sites where concealment and operation of safety accidents occur. If block chain technology and big data technology are applied to construction safety management, transparent data can be collected, and based on the collected data, it is possible to predict accidents that can occur at the construction site and establish countermeasures. It can also be an opportunity to strengthen the safety awareness of construction workers and managers, and can clearly identify the responsibility in the event of a safety accident. This study suggests that the application of the 4th Industrial Revolution technology could be a great opportunity to innovate the construction industry which is less than other industries.

• Journal of Construction Engineering and Project Management
• /
• v.9 no.4
• /
• pp.16-33
• /
• 2019

The increasing size and complexity of modern construction projects demands mature capabilities of onsite personnel with regard to recognizing unsafe situations. Construction safety training is paper or computer-based and suffers from a distinct gap between the classroom training environment and real-world construction sites; even trained personnel can find it difficult to recognize many of the potential safety hazards at their jobsites even after receiving construction safety training. Immersive technologies can overcome the current limitations in construction safety training by reducing the gap between the classroom and a real construction environment. This research developed and tested a new Augmented Reality (AR)-based assessment tool to evaluate the hazard recognition skills of students majoring in construction management as part of a construction safety course. The quantitative and qualitative results of this research confirmed that AR-based assessment can become a very effective assessment tool to evaluate safety knowledge and skills in a construction safety course, outperforming both paper and computer-based assessment methods. The students preferred AR-based assessment because it provides a realistic visual context for real world safety hazards.

• Journal of Construction Engineering and Project Management
• /
• v.6 no.2
• /
• pp.1-7
• /
• 2016

Construction in the UK is the second most dangerous industry in terms of fatal and minor injuries according to the 2014 report of HSE. The use of mobile devices such as iPad, Tablets and Smart phones on the live construction projects is also on the increase in the UK due to the 2016 - Level 2 BIM (Building Information Modelling) implementation target, set by the UK Government. Hence, the use of such devices may become a distraction from work activities on the construction sites and will cause a major risk to the end users. The subject of improving safety of BIM use is widely researched, but there is a gap in knowledge about the actual use of the mobile devices and perception of 'Site BIM', on the construction site activities. The main gap identified in the 'Site BIM' is the health and safety aspect of using such devices on the construction sites. A safer way of working with such devices needs to be identified to avoid any potential site hazards and fatalities before the widespread use of the devices are found on the construction projects. In that context, the paper is aimed to highlight the safety issues that are required to address for the successful implementation of the mobile devices for safer use of the 'Site BIM'. Questionnaire survey was used to collect the site information among construction professionals in the UK. The survey findings suggested that a proactive approach may be helpful to stop potential hazards and risks causing by the use of mobile devices and potential measures need to be identified before any injuries and incidents occur. The paper concludes that training, changing size of mobile devices and ensuring a separate induction training for 'Site BIM' tools will improve the health and safety of the end users of the mobile devices at the live construction sites.