Occupational safety and health management expense (OSHE) in construction industry is a statutory expense used for the purpose of preventing occupational accident and health disorders for construction workers, and the detailed usage standard is stipulated in the law and regulations governed by the Ministry of Employment and Labor in Korea. Previous studies focused on improvement of the accounting rate of OSHE and institutional improvement to secure usage transparency, but analysis showed that the review of improvement directions for usage items was insufficient. Considering recent trends, such as the increase in industrial demand to improve existing usage items and the introduction of various smart safety products incorporating the Fourth Industrial Revolution technology, it is expected that it will be necessary to review ways to improve the usage items to enhance the operational efficiency of OSHE. Accordingly, this study collected opinions from various stakeholders, and presented a roadmap to improve usage items of OSHE through importance-performance analysis (IPA) based on the data. This study is expected to meet the needs demanded by industry, and to be utilized as a reference for policy preparation to enhance the safety of construction sites.

Construction supervision is a key task that can confirm and inspect the project execution and support the creation of successful results. For the efficient performance of construction supervision, collecting various information necessary for the supervisor’s decision-making is a prerequisite, and the use of digital technology has recently been proposed as an alternative. Accordingly, the purpose of this study is to present a roadmap for the step-by-step use of digital technology to improve the efficiency of construction supervision. This study was limited to the supervision of construction projects, which have a high proportion of contract volumes in the Korean construction industry and can directly affect people’s lives. This study reclassified Korea’s construction supervision works, collected data on the urgency and effectiveness of detailed works from various stakeholders, and derived a final roadmap using importance–performance analysis. The results of this study are expected to serve as basic guidelines that can be used when reviewing digital technologies that can be applied step by step to improve the efficiency of construction supervision work.

Recently, the application of 3D printing in the production of curved panels has increased due to the irregular shape of free-form buildings. In general, 3D printing based on additive manufacturing (AM) methods requires various supports that cause a waste of printing materials and an increase in production time. In this study, we proposed a method for printing a pair of panels that can hold each other through the minimal support connected between each panel. However, this printing method causes an additional non-productivity factor called the non-printing path for the nozzle to move between the pair of panels. Therefore, we also developed an optimal layout model that can minimize non-printing paths and used the genetic algorithm (GA) for its calculation. As a result of applying the optimization model proposed in this study through the case study, the non-printing path was reduced by 18.54% compared with that from the existing method, and the non-printing time was reduced by 34.41 h. The total production time, including non-printing time and printing time, was reduced by 3.89%, and the productivity was improved by 4.04%. The model proposed in this study is expected to minimize unproductive factors that occur in the process of manufacturing curved panels and reduce the energy consumption.

Cost is a key performance indicator for evaluating the success of architectural construction projects. While previous studies have relied on quantitative data and statistical models to evaluate cost performance, recent advancements in methods have enabled analysis using unstructured data. Unstructured data, particularly in construction supervision reports, can be considered the significant variables for performance evaluation, as they represent independent third-party monitoring of the construction project’s execution. This study aims to present a framework that supports cost performance evaluation using unstructured data and random forests (RFs), a representative method of machine learning. Specifically, association rule analysis and social network analysis were used to identify the main keywords, and an RF model was applied to these data to evaluate cost performance. The tuning of hyper-parameters in the RF was implemented by the Bayesian optimization technique with the augmentation of the original dataset. The accuracy of cost performance evaluation was 59% for the traditional logistic regression (LR), 74% for the regularization-based logistic regression (BLR) designed to prevent overfitting, and 76% for the RF model utilizing augmented data. The complementary utility of the models consisting of the proposed framework can be useful for deriving various evaluation explanations about cost performance. The applicability is expected to increase as more data become available in the future.