Quantifying the Third-Party Loss in Building Construction Sites Utilizing Claims Payouts: A Case Study in South Korea

A deep neural network algorithm-based approach for predicting recovery period of accidents according to construction scale

Despite ongoing safety efforts, construction sites experience a concerningly high accident rate. Notwithstanding that policies and research to reduce the risk of accidents in the construction industry have been active for a long time, the accident rate in the construction industry is considerably higher than in other industries. This trend may likely be further exacerbated by the rapid growth of large-scale construction projects driven by urban population expansion. Consequently, accurately predicting recovery periods of accidents at construction sites in advance and proactively investing in measures to mitigate them is critical for efficiently managing construction projects. Therefore, the purpose of this study is to propose a framework for developing accident prediction models based on the Deep Neural Network (DNN) algorithm according to the scale of the construction site. This study suggests DNN models and applies the DNN for each construction site scale to predict accident recovery periods. The model performance and accuracy were evaluated using mean absolute error (MAE) and root-mean-square error (RMSE) and compared with the widely used multiple regression analysis model. As a result of model comparison, the DNN models showed a lower prediction error rate than the regression analysis models for both small-to-medium and large construction sites. The findings and framework of this study can be applied as the opening stage of accident risk assessment using deep learning techniques, and the introduction of deep learning technology to safety management according to the scale of the construction site is provided as a guideline.

Work-Related Injuries among Insured Construction Workers Presenting to a Swiss Adult Emergency Department: A Retrospective Study (2016-2020)

Occupational injuries are one of the main causes of Emergency Department visits and represent a substantial source of disability or even death. However, the published studies and reports on construction-occupational accidents in Switzerland are limited. We aimed to investigate the epidemiology of fatal and non-fatal injuries among construction workers older than 16 years of age over a 5-year period. Data were gathered from the emergency department (ED) of Bern University Hospital. A retrospective design was chosen to allow analysis of changes in construction accidents between 2016-2020. A total of 397 patients were enrolled. Compared to studies in other countries, we also showed that the upper extremity and falling from height is the most common injured body part and mechanism of injury. Furthermore, we were able to show that the most common age group representing was 26-35 years and the second common body part injured was the head, which is a difference from studies in other countries. Wound lacerations were the most common type of injury, followed by joint distortions. By stratifying according to the season, occupational injuries among construction workers were found to be significant higher during summer and autumn. As work-related injuries among construction workers are becoming more common, prevention strategies and safety instructions must be optimized.

Predicting financial losses due to apartment construction accidents utilizing deep learning techniques

This study aims to generate a deep learning algorithm-based model for quantitative prediction of financial losses due to accidents occurring at apartment construction sites. Recently, the construction of apartment buildings is rapidly increasing to solve housing shortage caused by increasing urban density. However, high-rise and large-scale construction projects are increasing the frequency and severity of accidents occurring inside and outside of construction sites, leading to increases of financial losses. In particular, the increase in severe weather and the surge in abnormal weather events due to climate change are aggravating the risk of financial losses associated with accidents occurring at construction sites. Therefore, for sustainable and efficient management of construction projects, a loss prediction model that prevents and reduces the risk of financial loss is essential. This study collected and analyzed insurance claim payout data from a main insurance company in South Korea regarding accidents occurring inside and outside of construction sites. Deep learning algorithms were applied to develop predictive models reflecting scientific and recent technologies. Results and framework of this study provide critical guidance on financial loss management necessary for sustainable and efficacious construction project management. They can be used as a reference for various other construction project management studies.

A Deep Learning Model Development to Predict Safety Accidents for Sustainable Construction: A Case Study of Fall Accidents in South Korea

So far, studies for predicting construction safety accidents have mostly been conducted by statistical analysis methods that assume linear models, such as regression and time series analysis. However, it is difficult for this statistical analysis method to reflect the nonlinear characteristics of construction safety accidents determined by complex influencing factors. In general, deep learning techniques are used to analyze the nonlinear characteristics of complex influencing factors. Therefore, the purpose of this study is to propose a framework for developing a deep learning model for predicting safety accidents for sustainable construction. For this study, 1766 cases of actual accidents were collected by the Korea Occupational Safety Authority (KOSHA) over the 10-year period from 2010 to 2019. Eight factors influencing accident prediction such as medical day, progress rate, and construction scale were selected. Subsequently, the predictive power between deep learning models and conventional multi-regression models was compared using actual accident data at construction sites. As a result, a deep neural network (DNN) improved predictive power by 9.3% in mean absolute error (MAE) and 10.6% in root mean square error (RMSE) compared to a conventional multi-regression model. The results of this study provide guidelines for the introduction of deep learning technology to construction safety management.

Harnessing Machine Learning for Classifying Economic Damage Trends in Transportation Infrastructure Projects

Given the highly visible nature, transportation infrastructure construction projects are often exposed to numerous unexpected events, compared to other types of construction projects. Despite the importance of predicting financial losses caused by risk, it is still difficult to determine which risk factors are generally critical and when these risks tend to occur, without benchmarkable references. Most of existing methods are prediction-focused, project type-specific, while ignoring the timing aspect of risk. This study filled these knowledge gaps by developing a neural network-driven machine-learning classification model that can categorize causes of financial losses depending on insurance claim payout proportions and risk occurrence timing, drawing on 625 transportation infrastructure construction projects including bridges, roads, and tunnels. The developed network model showed acceptable classification accuracy of 74.1%, 69.4%, and 71.8% in training, cross-validation, and test sets, respectively. This study is the first of its kind by providing benchmarkable classification references of economic damage trends in transportation infrastructure projects. The proposed holistic approach will help construction practitioners consider the uncertainty of project management and the potential impact of natural hazards proactively, with the risk occurrence timing trends. This study will also assist insurance companies with developing sustainable financial management plans for transportation infrastructure projects.

Development of Model to Predict Natural Disaster-Induced Financial Losses for Construction Projects Using Deep Learning Techniques

This study goals to develop a model for predicting financial loss at construction sites using a deep learning algorithm to reduce and prevent the risk of financial loss at construction sites. Lately, as the construction of high-rise buildings and complex buildings increases and the scale of construction sites surges, the severity and frequency of accidents occurring at construction sites are swelling, and financial losses are also snowballing. Singularly, as natural disasters rise and construction projects in urban areas increase, the risk of financial loss for construction sites is mounting. Thus, a financial loss prediction model is desired to mitigate and manage the risk of such financial loss for maintainable and effective construction project management. This study reflects the financial loss incurred at the actual construction sites by collecting claim payout data from a major South Korean insurance company. A deep learning algorithm was presented in order to develop an objective and scientific prediction model. The results and framework of this study provide critical guidance on financial loss management necessary for sustainable and successful construction project management and can be used as a reference for various other construction project management studies.

Modeling Deep Neural Networks to Learn Maintenance and Repair Costs of Educational Facilities

Educational facilities hold a higher degree of uncertainty in predicting maintenance and repair costs than other types of facilities. Moreover, achieving accurate and reliable maintenance and repair costs is essential, yet very little is known about a holistic approach to learning them by incorporating multi-contextual factors that affect maintenance and repair costs. This study fills this knowledge gap by modeling and validating deep neural networks to efficiently and accurately learn maintenance and repair costs, drawing on 1213 high-confidence data points. The developed model learns and generalizes claim payout records on the maintenance and repair costs from sets of facility asset information, geographic profiles, natural hazard records, and other causes of financial losses. The robustness of the developed model was tested and validated by measuring the root mean square error and mean absolute error values. This study attempted to propose an analytical modeling framework that can accurately learn various factors, significantly affecting the maintenance and repair costs of educational facilities. The proposed approach can contribute to the existing body of knowledge, serving as a reference for the facilities management of other functional types of facilities.