Purpose: The purpose of this study is to systematically identify, assess, and categorize the barriers to digital transformation (DT) in the engineering and construction sectors, and thus to better understand the impact and how these sectors might be overcome.Design/methodology/approach: This study adopted a sequential mixed qualitative and quantitative data collection and analysis approach. DT barriers were first identified from relevant literature and verified by an expert panel. Then, a questionnaire survey assessing the impacts of the identified DT barriers was distributed to construction professionals in China, and 192 valid responses were retrieved. Further, the data obtained were analyzed using ranking analysis, exploratory factor analysis (EFA), and partial least squares-structural equation modeling (PLS-SEM).Findings: Based on the ranking analysis, the top three barriers are “lack of industry-specific standards and laws,” “lack of clear vision, strategy and direction for DT,” and “lack of support from top management for DT.” EFA enabled the grouping of the 26 barriers into 3 categories: (1) lack of laws and regulations (LLR), (2) lack of support and leadership (LSL), and (3) lack of resources and professionals (LRP). The PLS-SEM analysis revealed that LLR, LSL, and LRP were found to have significant negative impacts on DT.Originality/value: These findings contribute to the body of knowledge on DT in the construction industry and help construction firms and government bodies improve the understanding of these barriers to DT and put forward relevant policies and incentives, thus seizing the DT benefits as a way to enhance construction project management.

As one of the emerging digital technologies, building information modeling (BIM) has been increasingly used in the architecture, engineering, and construction (AEC) industry of many countries. One of the core benefits associated with BIM is facilitating collaboration among project teams, thereby improving information sharing and project performance by providing BIM-based construction networks (BbCNs). Nevertheless, it is still challenging to ensure an effective collaboration process in BIM-enabled projects. Several studies have investigated the factors that influence collaboration in BIM-enabled projects; however, most of these studies focus on technical matters of BIM, while the perspectives of socio-organization and processes have received less attention and are still in the conceptual stage, especially for the role of people management. Thus, an exploratory study was proposed to explore how key factors influence the professionals’ willingness to collaborate in BIM-enabled projects. A total of 10 hypotheses were established based on literature review and expert verification. Following that, a questionnaire survey was administered in China to solicit the opinions of 273 BIM professionals for data collection. The hypotheses were then examined on the basis of the predictive capacity of regression analysis (binary logistic regression), with the findings validated using neural network analysis (multilayer perceptron). It was found that seven independent variables have a statistically significant influence on professionals’ willingness to collaborate in BIM-enabled projects, namely, professional knowledge, skill, training, investment, BIM tools, BIM ownership, and standards and regulations. Among them, the variable of professional knowledge was ranked as the most influential factor. While extending the existing knowledge of literature, the findings of this study also deliver insights for stakeholders by enhancing their understanding of the BIM collaboration process and its influence factors.

Over the last decade, a 3D reconstruction technique has been developed to present the latest as-is information for various objects and build the city information models. Meanwhile, deep learning based approaches are employed to add semantic information to the models. Studies have proved that the accuracy of the model could be improved by combining multiple data channels (e.g., XYZ, Intensity, D, and RGB). Nevertheless, the redundant data channels in large-scale datasets may cause high computation cost and time during data processing. Few researchers have addressed the question of which combination of channels is optimal in terms of overall accuracy (OA) and mean intersection over union (mIoU). Therefore, a framework is proposed to explore an efficient data fusion approach for semantic segmentation by selecting an optimal combination of data channels. In the framework, a total of 13 channel combinations are investigated to pre-process data and the encoder-to-decoder structure is utilized for network permutations. A case study is carried out to investigate the efficiency of the proposed approach by adopting a city-level benchmark dataset and applying nine networks. It is found that the combination of IRGB channels provide the best OA performance, while IRGBD channels provide the best mIoU performance.

In the era of the first Industrial Revolution, many buildings were built with red bricks, and the heritage buildings built at that time are more than 100 years old. In these old heritage buildings, damage is bound to occur due to chemical and physical effects. Technologies such as automatic damage detection can effectively manage damage, but they can be affected by other categories present in heritage buildings. Therefore, this paper proposes a CNN algorithm that can automatically detect cracks and damage that occur in heritage buildings, as well as multi-label classification, such as doors, windows, arches, artwork, brick walls, stonewalls, and vents. A total of 2400 thermal infrared images are collected for 8 categories and automatic classification was performed using the CNN algorithm. The average precision and average sensitivity for the eight categories of heritage buildings are 97.72% and 97.43%, respectively. This paper defines the causes of misclassification as the following two causes: misclassification by multiple objects and misclassification by the perception of the CNN algorithm.

Water quality monitoring of medium-sized inland water is important for water environment protection given the large number of small-to-medium size water bodies in China. A case study was conducted on Yuandang Lake in the Yangtze Delta region, with a surface area of 13 km². This study proposed utilising a multispectral uncrewed aerial vehicle (UAV) to collect large-scale data and retrieve multiple water quality parameters using machine learning algorithms. An alternate processing method is proposed to process large and repetitive lake surface images for mapping the water quality data to the image. Machine learning regression methods (Random Forest, Gradient Boosting, Backpropagation Neural Network, and Convolutional Neural Network) were used to construct separate water quality inversion models for ten water parameters. The results showed that several water quality parameters (COD_Mn, temperature, pH, DO, and NC) can be retrieved with reasonable accuracy (R² = 0.77, 0.75, 0.73, 0.67, and 0.64, respectively), although others (NH₃-N, BGA, TP, Turbidity, and Chl-a) have a determination coefficient (R²) less than 0.6. This work demonstrated the tremendous potential of employing multispectral data in conjunction with machine learning algorithms to retrieve multiple water quality parameters for monitoring medium-sized bodies of water.

Infrastructure industry is a significant contributor to a country's economy, but it is beset by cost overruns and delays. Therefore, project monitoring is essential to determine project performance by comparing the site progress to the schedule baseline. However, manual tracking lacks the precision and efficiency. The ability to quickly and accurately identify differences is important to implement essential measures to reduce the impact of delays. This paper aims to build a technology-assisted progress monitoring framework for road base course construction. A case study is carried out on a road construction site using an Unmanned Aerial Vehicle to capture as-built data in a timely manner. Photogrammetry is used to generate point cloud model as the 3 D geometrical representative of the site. Percentage of Completion is computed as an indication for the progress of the construction along with the location of the work performed and the quantity of the material used. The framework produced a detailed and accurate construction progress report with evidence support from point cloud data which allows the visualization of the actual construction site in three dimensions. The findings reveal that the framework enables accurate and efficient tracking of road base course construction progress as well as schedule comparison.