Knowledge management for construction accident cases can identify dangerous conditions and prevent accidents by controlling risks on-site. However, because accident cases are recorded as unstructured text data, significant time and effort are required to retrieve and analyze the knowledge a user wants. To overcome these limitations, this research proposes a knowledge management system for construction accident cases using natural language processing. For this purpose, two models were developed that can retrieve appropriate cases according to user intentions and automatically analyze tacit knowledge from construction accident cases. In the retrieval model, the query is expanded using a construction accident case thesaurus. Ranking is calculated using Okapi BM25 and weighting according to the thesaurus. In the analysis model, knowledge is automatically extracted using rule-based and conditional random field (CRF) methods. The proposed system can retrieve results that are 97% relevant to the accident cases the user intended and can automatically analyze knowledge with accuracies of 93.75% and 84.13% for the rule-based and CRF models, respectively. The results demonstrate the potential of knowledge discovery from accident reports for more-effective safety management.

Fall accidents constitute a crucial type of accident in the construction industry. This study investigates fall accidents that occurred in the United States between 1997 and 2012. Using the 20,997 construction industry accidents recorded in the Occupational Safety and Health Administration (OSHA) database, this study examines the frequency and trend of fall accidents. Additionally, by using data from 9,141 fall accidents, this study investigates various dimensions of fall accidents, such as fall height, fall location, and fall protection, and types of industry and projects where fall accidents occurred. The analyses and subsequent findings are discussed as follows: First, the percentage of fall accidents from four major accident types (fall, struck by, caught in or between, and electrocution) has been increased substantially. Second, in terms of project type, residential housing projects experienced a higher portion of fall accidents. Third, more than 80% of fall accidents occurred from a height of less than 9.1 m (30 ft), and only 11% of fall accident victims were properly equipped with fall protection. These findings serve to alert safety agencies of the need to diagnose the current state of fall accidents and to revise the policies and regulations to reduce these figures.

Unsafe acts of workers (e.g., misjudgment or inappropriate operation) become the major root causes of construction accidents when they are combined with unsafe working conditions (e.g., work surface conditions or weather) on a construction site. The overarching goal of the research presented in this paper is to explore ways to prevent unsafe acts of workers and reduce the likelihood of construction accidents occurring. The study specifically aims to (1) understand the relationships between human behavior related and working condition related risk factors, (2) identify the significant behavior and condition factors and their impacts on accident types (e.g., struck by/against, caught in/between, falling, shock, inhalation/ingestion/absorption, or respiratory failure) and injury severity (e.g., fatality, hospitalized, or nonhospitalized), and (3) analyze the fundamental accident-injury relationship on how each accident type contributes to the injury severity. The study reviewed 9,358 accidents that o...

When bidding on construction projects, contractors need to understand the specifications properly to manage project risks. However, specifications are mainly analyzed based on human cognitive abilities, which can take considerable time and can lead to errors due to misunderstanding. While efforts have been made to automate this process, that the existing academic efforts to automate the process have limitations. To develop an automated specification reviewing model applicable to various kinds of specifications, the authors propose information extraction frameworks consisting of five categories. In addition, a named entity recognition (NER) model was developed based on bidirectional long short-term memory architecture to extract information from text data automatically. The data set for model development comprised 56 construction specifications, which included a total of 4,659 sentences labeled according to five categories of information. Word2Vec was utilized to aconvert labeled text data to the form of numeric vectors to be input into the NER model. The NER model successfully assigned every word in the testing data to an appropriate category with a satisfactory performance of 0.919 precision and 0.914 recall. These results contribute to the automation of the construction specification review process. Although this research focused on road construction projects, the proposed information extraction framework can be applied to other types of construction projects.

Recently, an increasing number of green residential buildings have been developed worldwide owing to active promotion from the authorities and increasing interest from customers. However, in the same way as traditional residential buildings, the construction of green residential buildings faces various risks. The aims of this study are to identify and assess the diverse risks in green residential building construction projects, compare their risk criticalities with those in traditional counterparts, and propose helpful risk mitigation measures. To achieve these goals, a comprehensive literature review was first conducted, and a questionnaire was then administered to 30 construction companies in Singapore. Survey results showed that “complex procedures to obtain approvals”, “overlooked high initial cost”, “unclear requirements of owners”, “employment constraint”, and “lack of availability of green materials and equipment” were the top five critical risks in green residential building construction projects. Survey results also showed that green residential building projects were facing risks at a more critical level than those traditional residential building projects. Additionally, this study proposed fourteen risk mitigation measures to tackle the risks in green residential building construction projects. This study has contributed to the body of knowledge by identifying and evaluating the critical risks and mitigation measures in green residential building construction projects. Meanwhile, the findings from this study can also provide an in-depth understanding of risk management in green residential building construction projects to practitioners and thus benefit the practice.

This study was conducted to investigate how the work environment and psychological state influence construction workers’ perceptions and safety behaviors. Structural equation modeling was developed with five factors on the working environment (i.e., job demand, job control, job support, rewards, organizational justice, lack of reward), two factors on workers’ psychological condition (i.e., depression and trait anxiety), and four factors on safety perception (i.e., safety motivation, safety knowledge, and safety compliance and participation behaviors). Sample data were collected from 399 construction workers working at 29 construction sites in South Korea and analyzed the direct and indirect effects between those factors. The results showed that construction workers’ safety compliance and participation behavior are related to their safety knowledge and motivation, and depression and trait anxiety were found to lower safety motivation, knowledge, and, eventually, safety behavior. Job demands, lack of job control, lack of reward, and lack of organizational justice negatively impacted safety behavior. In contrast, job support did not show a significant relationship with safety behavior.