Construction risk assessment (RA) based on expert knowledge and experience incorporates uncertainties that reduce its accuracy and effectiveness in implementing countermeasures. To support the construction of RA procedures and enhance associated decision-making processes, machine learning (ML) approaches have recently been investigated in the literature. Most ML approaches have difficulty processing dependency information from real-life construction datasets. This study developed a novel RA model that incorporates a graph convolutional network (GCN) to account for dependency information between construction accidents. For this purpose, the construction accident dataset was restructured into an accident network, wherein the accidents were connected based on the shared project type. The GCN decodes the construction accident network information to predict each construction activity’s severity outcome, resulting in a prediction accuracy of 94%. Compared with the benchmark feedforward network (FFN) model, the GCN demonstrated a higher prediction accuracy and better generalization ability. The developed GCN severity predictor allows construction professionals to identify high-risk construction accident scenarios while considering dependency based on the shared project type. Ultimately, understanding the relational information between construction accidents increases the representativeness of RA severity predictors, enriches ML models’ comprehension, and results in a more reliable safety model for construction professionals.

Construction companies are under pressure to enhance their site safety condition, being constantly challenged by rapid technological advancements, growing public concern, and fierce competition. To enhance construction site safety, literature investigated Machine Learning (ML) approaches as risk assessment (RA) tools. However, their deployment requires knowledge for selecting, training, testing, and employing the most appropriate ML predictor. While different ML approaches are recommended by literature, their practicality at construction sites is constrained by the availability, knowledge, and experience of data scientists familiar with the construction sector. This study develops an automated ML system that automatically trains and evaluates different ML to select the most accurate ML-based construction accident severity predictors for the use of construction professionals with limited data science knowledge. A real-life accident dataset is evaluated through automated ML approaches: Auto-Sklearn, AutoKeras, and customized AutoML. The investigated AutoML approaches offer higher scalability, accuracy, and result-oriented severity insight due to their simple input requirements and automated procedures.

High dimensionality and skewness are two intrinsic characteristics of real estate dataset that affects the price prediction accuracy of deep neural network (DNN). The objective of this study is to investigate the effect of skewness in prediction accuracy of combined principal component analysis (PCA) with DNN (PCA-DNN) model. This research follows a threefold approach over a high dimensional and positively skewed real estate price dataset. Firstly, data distribution is to conform with normality using three conventional skewness reduction techniques, namely as square root transformation (SRT), cube root transformation (CRT), and logarithmic transformation (LT) methods. Secondly, the high dimensionality of original, SRT, CRT and LT skewed datasets are to be reduced using PCA. Thirdly, price prediction accuracy of PCA-DNN model over datasets with different skewness levels are to be compared by observing their error values. The results suggest that CRT method can considerably improve both prediction accuracy and computational time of PCA-DNN model, while displaying a good generalization ability. Despite CRT method, SRT and LT methods resulted in high error values and overfitting issues, respectively.

No abstract

No abstract