Abstract Robust performance evaluation is critical for optimizing the sequential workflows of prefabricated building (PB) projects. However, traditional data envelopment analysis (DEA) frequently overlooks interstage dependencies and structural inefficiencies. To address this, a three-stage superefficient network epsilon-based measure (SE-NEBM) model is proposed. By synthesizing network constraints with radial and non-radial adjustments, this framework simultaneously resolves the black-box limitation and captures structural inefficiencies often missed by purely proportional measures. The model was applied to 31 shear-wall PB projects in China, benchmarking prefabricated concrete (PC) against prefabricated concrete masonry (PCM) systems. Results indicate that PCM projects outperform PC projects by 42.86%, a disparity driven primarily by a 48.12% efficiency advantage in the construction stage. To determine the drivers of this performance variation, Tobit regression identified installation tolerance as a pivotal factor, and sensitivity analyses confirmed the robustness of the proposed framework. This study fills a critical methodological gap by providing a quantitative, stage-sensitive tool for benchmarking PB projects, offering actionable insights for technology selection and process optimization in industrialized construction.
Abstract With the advancement of modular integrated construction (MiC), transportation has emerged as a critical link in the construction supply chain, directly impacting project cost, schedule, and safety. While design for manufacture and assembly (DfMA) prioritizes factory production and on-site assembly efficiency, it often overlooks the transportability of components, leading to a disconnect between architectural design and downstream logistics. To address this gap, this study proposes a quantitative evaluation framework for the design for transportability (DFT) of volumetric modular buildings. The framework encompasses 12 key design factors across 4 dimensions: geometry, weight, structure, and construction details. By employing the fuzzy analytic hierarchy process (Fuzzy AHP), the study identifies component dimensions and weight as the core factors driving transportation efficiency. Furthermore, a DFT-DfMA synergy-conflict model is established to integrate DFT into the broader DfMA. The framework’s effectiveness is validated through two volumetric modular case studies, the Checkered Playroom and the Nomadic Museum. Through an in-depth analysis of stacking, transporting, and lifting phases, the study reveals two distinct logistical strategies: human-centered collaboration for small-scale modules and machine-driven operations for standardized containers. By transforming passive logistical constraints into active design variables, this research formally advances the traditional DfMA paradigm. Ultimately, it delivers a holistic decision-support tool that empowers stakeholders to achieve collaborative optimization across manufacturing, transportation, and assembly phases.
Abstract Effectively investigating cognitive factors underlying unsafe behaviors of construction workers is critical for reducing construction site accidents. While previous studies have emphasized perceptual and attentional mechanisms, limited research has examined how social information and individual traits jointly shape hazard processing in construction contexts. Drawing on social impact theory, this study investigates how social information source (leader versus colleague), information bias (overestimation and underestimation of risks), and individual risk preference (high versus low) interact to influence construction workers’ behavioral responses and neural dynamics during hazard evaluation. A modified judgment-association-selection paradigm was implemented in a behavioral and event-related potential (ERP) experiment with 36 participants possessing construction experience. Behavioral data showed that social information source and bias significantly influenced workers’ hazard severity rating adjustments and reaction time. Compared to colleague information, leader information induced faster response and greater bias-congruent rating adjustment. Risk preference moderated the relationship between information bias and reaction time, with high-risk preference workers responding more quickly. Time-domain analyses of ERP data revealed that leader information elicited enhanced P200 and P300 amplitudes and attenuated feedback-related negativity (FRN) responses, suggesting prioritized early attention and reduced conflict processing. Risk preference further moderated neural sensitivity to social information source at P200, FRN, and late positive potential stages. These findings advance the understanding of how social and individual factors shape hazard cognition at behavioral and neural levels, offering implications for safety strategies tailored to information source characteristics and individual risk profiles.
Abstract The mining and construction industries are vital to Australia’s economy, but are also characterized by demanding fly-in-fly-out (FIFO) arrangements that present unique psychosocial hazards. Drawing on the job demands-resources framework and conservation of resources theory, this study explores how team belongingness is shaped and how it helps workers manage the unique demands of FIFO work. Using an arts-based qualitative approach, 53 Draw, Write, Reflect sessions were conducted with FIFO workers on a remote mine site under construction. Thematic analysis revealed that team belongingness acted as a salient social and emotional buffer, with participants describing their teams as their ‘family away from home.” Laughter, humor, and banter were central mechanisms for fostering a sense of team belongingness and making long shifts more manageable. Everyday acts of mutual support and care further strengthened camaraderie across roles and hierarchies. However, the study also found that experiencing a sense of belongingness was more challenging for some managers and operators who felt isolated due to job demands and site structures. The findings highlight the importance of recognizing team belongingness as a core wellbeing resource that enables FIFO workers to cope with the unique demands of their work and sustain long-term participation. This has important implications for policy initiatives and organizational strategies for fostering inclusive team cultures to support safety and wellbeing.
Abstract The dynamic scheduling of ready-mixed concrete constitutes a critical bottleneck in construction automation. Following the design science paradigm and informed by a systematic literature review, this study develops the multistrategy ant colony optimization (MSACO) algorithm, which integrates three mechanisms: adaptive pheromone evaporation, elite ant guidance, and genetic mutation. Empirical validation based on the road network of a major Chinese city (involving four batching plants, six customer sites, and a fleet of seven fuel vehicles and five electric vehicles) demonstrates that MSACO significantly outperforms algorithms including the genetic algorithm, ant colony optimization, particle swarm optimization, and multistrategy adaptive ant colony optimization in terms of solution accuracy, convergence speed, and stability. The proposed algorithm achieves an average reduction in distribution costs of 7.06%, with advantages reaching 10.7% under highly constrained conditions ( p < 10 − 7 ). The main contributions are threefold: it proposes a triple adaptive mechanism tailored for dynamic scheduling scenarios; formulates a mathematical model incorporating plant capacity, load limits, and electric vehicle range; and provides a quantifiable basis for the digital transformation of construction logistics.
Abstract Accurate identification and tracking of construction workers is critical for real-time safety and productivity management on complex and dynamic construction sites. However, traditional sensor-based wearable tools for worker identifying face issues such as physical interference of workers, the need for recharging, the need for maintenance, and high cost. Computer vision technique (CVT)-based methods are limited to merely reidentifying the same workers in a single or multiple cameras, rather than identifying who the workers are on the construction site. This study focuses on reidentifying who the workers are, namely worker identity–aware tracking, by using entrance access images as personal identity anchors and multimodal data fusion techniques. Personal images from the entrance access system are exploited as identity anchors to be matched with personal images from multiple cameras on site, serving as personalized prototypes that are updated dynamically to maintain robustness under varying imaging conditions and temporal appearance changes. In addition, personal protective equipment (PPE) information contained in the entrance access records is integrated to enhance discriminability among workers with similar appearances. The proposed identity-aware tracking method was implemented, tested, and applied to a case construction site with multiple surveillance cameras and real operational scenarios. The proposed method achieved more stable and reliable identity association than approaches that match incoming images against a global gallery. This study provides domain knowledge of a nonintrusive, cost-effective and intelligent methodology for worker identity–aware tracking on construction sites. It also provides a digital platform to help achieve remote, timely, precise, and effective field management of workers, thus promoting construction productivity and safety.
Abstract Construction activities impose substantial cognitive demands on workers, making mental fatigue assessment critical for occupational health and safety (OHS) management. Portable wearable electroencephalography (EEG) devices offer practical advantages in mental fatigue identification. However, they are typically limited to a few channels, restricting the spatial coverage of brain activity and potentially limiting the ability to capture fatigue-related spatial patterns. To address this limitation, a sensor-level scalp EEG representation mapping framework was developed to enhance spatial information in fatigue assessment. First, a stacked long short-term memory (LSTM)-based regression model is developed to approximate multichannel scalp EEG representations from preprocessed single-channel in-ear EEG and electrocardiography (ECG) signals. Quantitative evaluation demonstrates stable predictive performance, with mean absolute error ( MAE ) and root mean square error ( RMSE ) both below 24 μV across fatigue states. Second, the predicted scalp EEG signals are transformed into EEG topographic maps to enhance spatial interpretability. The proposed framework enables portable yet spatially informative fatigue assessment and provides methodological support for future OHS-oriented monitoring systems.
Abstract Machine learning can contribute to more proactive, data-driven construction project management. However, most research efforts have focused on predicting final project outcomes, which may miss short-term variations that reveal emerging risks, thereby limiting the utility of their solutions as practical predictive tools for on-site project control. This paper develops and evaluates an early-warning machine learning model based on extreme gradient boosting (XGBoost) to classify next-month performance of building construction projects (Good, At-Risk, or Poor) using earned value management (EVM) and earned schedule (ES) metrics. Monthly EVM/ES records from 17 building projects were used along with schedule and cost performance indices to build the dataset. Three acceleration features were proposed to capture the trend in project performance. The model was trained on a time-aware experimental design using expanding-window cross-validation, light XGBoost tuning, probability calibration, and class-specific decision thresholds, and evaluated on a chronologically held-out test set. The model yielded a Macro- F 1 score of 0.760 on the test set, with a recall of 91% for “Poor” and 82% for “Good” classes, and a conservative behavior for “At-Risk” cases. Permutation importance and Shapley additive explanations (SHAP) analyses indicated that schedule indices are the main drivers of predicted performance outcomes, with cost and acceleration indicators providing complementary signals. In contrast to existing ML-based EVM studies that focus on final-outcome prediction, this study proposes a near-term multiclass early-warning approach that relies solely on standard EVM/ES metrics and achieves acceptable predictive performance using a relatively small dataset, providing guidance for designing feasible early-warning solutions under limited data availability and aligned with field managers’ information needs. The model can be implemented on-site using monthly control data to provide timely alerts on next-month project performance and support more proactive, data-driven project control.
Abstract This study introduces the Remote Automated Multi-Bolt Inspection Robot (RAMBIRobot), a novel system integrating machine vision and acoustic analysis for efficient, autonomous bolt inspection. Conventional bolt inspection methods are labor-intensive, prone to human error, and unsuitable for hazardous environments. RAMBIRobot addresses these limitations by combining the YOLOv5s visual recognition model, audio-based detection via Mel-Frequency Cepstral Coefficients (MFCCs), and a two-dimensional convolutional neural network (2D CNN) under the robot operating system (ROS) framework. The system features a robotic arm equipped with a depth camera for 3D bolt localization and a tapping device for acoustic analysis, providing robust and automated inspection capabilities. Experimental validation demonstrated that the audio recognition module achieved an accuracy of 79.3% at a 90° tapping angle, with loosened bolt detection precision of 90.2%. The YOLOv5s model achieved an accuracy of 98.9% under normal lighting and 93.5% in low-light conditions, confirming its reliability across diverse environments. Integrated system tests revealed an overall detection accuracy of 75.0%, highlighting the system’s efficiency in reducing dependency on manual labor while ensuring inspection precision. RAMBIRobot offers a cost-effective, scalable solution for industrial applications, enhancing structural health monitoring through automation. Compared to existing robotic inspection systems, RAMBIRobot uniquely integrates visual localization with acoustic analysis for bolt-specific looseness detection on a mobile platform. Future research will focus on optimizing environmental adaptability and exploring additional inspection scenarios.
Abstract The global architecture, engineering, and construction (AEC) sector faces a persistent productivity paradox characterized by stagnant growth, frequent schedule overruns, and slow digital adoption. While the emergence of Construction 4.0 introduces automation and data analytics, this technology-centric concept often risks marginalizing the indispensable cognitive abilities of human professionals on dynamic jobsites. Mixed reality (MR) presents a critical solution by offering an immersive, human-centric interface aligned with Industry 5.0 principles, yet a holistic understanding of its integration with other key digital technologies remains elusive. The current literature primarily offers bespoke, isolated proofs of concept for specific tasks, creating a critical knowledge gap regarding how to synthesize these disparate technological integrations into scalable solutions. Consequently, a systematic framework that translates complex technical capabilities into demonstrable on-site project management value is urgently needed. This paper addresses this gap by systematically reviewing the integration of MR with other prominent technologies to develop a unified framework. A rigorous two-phase review methodology was employed, beginning with a bibliometric analysis that identified robotics, computer vision, and digital twins as the most critical technologies integrated with MR technology. Subsequently, a systematic literature review of N = 85 publications analyzed the specific integration architectures, application domains, synergistic benefits, and implementation barriers for each technological pairing. The findings indicate that MR is evolving beyond a conventional visualization tool toward a human-centric cyber–physical interface that enables bidirectional coordination between physical site operations and digital project control systems. Theoretically, this study reframes MR as an intelligent integration interface situated at the human–system boundary, rather than merely a passive terminal display. Practically, this conceptualization is operationalized through a structured five-layer integrative framework comprising the physical layer, perception and interaction layer, data integration and middleware layer, data model and analytics layer, and management and decision-making layer. The proposed framework provides a systematic and actionable foundation for researchers, technology developers, and project managers to guide implementation strategies, address adoption challenges, and advance human-centered digital transformation in construction environments.
Abstract Despite growing attention to diversity in construction, mechanisms driving gender-based disparities in hiring and compensation remain insufficiently examined using experimental methods. Seventy construction workers across 22 US project sites completed a randomized vignette survey with matched applicant profiles. Hiring and salary outcomes were analyzed using mixed-effects logistic and linear regression models. Hiring decisions showed no statistically significant applicant-gender effect ( p = 0.730 ) under structured, qualification-matched conditions. No overall applicant-gender difference was detected in salary recommendations. In contrast, applicant experience and task risk significantly increased salary estimates, indicating that evaluators responded systematically to competence and context cues. Evaluator gender produced a substantial compensation effect: female evaluators recommended approximately $13,000 higher annual salaries than male evaluators ( B = − 13,240 ; p < 0.001 ; d = 0.50 ), persisting after controlling for experience and age ( B = − 10,831 ; p = 0.002 ). The applicant gender × task risk interaction was not statistically significant; further, descriptive patterns suggesting higher male pay for moderate-risk tasks are presented as exploratory. Attitudinal measures revealed large gender differences ( d = 0.73 to 1.16), with male evaluators expressing more traditional views. Overall, structured evaluation attenuated applicant-gender disparities, whereas evaluator identity and attitudinal orientation were strongly associated with compensation norms.
Abstract Offsite construction is a growing construction method that improves quality while reducing cost through optimal resource utilization in a controlled environment. Recently, resilience aspects, such as adaptable supply chain management, labor resource allocation, and dynamic scheduling, have been explored in the context of offsite construction, given the opportunity to allow workers to foresee, anticipate, and respond to unexpected disruptive events, as well as adapt after these events occur through the adoption of resiliency perspectives. However, the literature lacks a comprehensive review of the manner in which, and the extent to which, resilience has been incorporated into the offsite construction industry, particularly in regards to practices and frameworks for technological implementation. The aim underlying the present study is to identify trends and gaps in the body of knowledge regarding the integration of resilience with offsite construction over the last 25 years. For the literature review, a mixed-methods review approach is employed, searching the Scopus database for articles published during the 2000–2024 period. A scientometric review is carried out to identify prolific journals in the area of interest, their development over time, the co-occurrence network of keywords, and their citation bursts. Following this, a systematic review is carried out to identify the primary categories of research on resilience in the offsite construction domain. Four main categories of research are identified: supply chain management, design and construction processes, environmental and social sustainability, and workforce management–related areas. The systematic analysis reveals a significant research focus on supply chain management issues and the inclusion of resilience-related concepts. With regard to design and process control, meanwhile, a growth trend in studies developing optimization models for offsite construction–related projects is observed. With respect to environmental and social sustainability, research related to developing standardized sustainability assessment tools is found to exhibit a trend of emergence. Regarding workforce-related research, the inclusion of human-centered analysis and skills management is a notable trend. In addition to identifying the notable trends and gaps in this research domain, this study elaborates on the need for further integration of offsite construction with resilience-related elements in order to improve scheduling efficiency and effectiveness in offsite construction.
Abstract Knowledge diversity is essential for innovation in construction project teams, yet translating it into tangible outcomes remains challenging. Traditional management theories and static methods often fail to provide dynamic solutions. This study addresses the issue through a two-stage design combining empirical analysis and deep reinforcement learning (DRL)-based simulation. Using three waves of survey data from 20 construction projects, the empirical study shows that knowledge diversity significantly predicts knowledge creation, which in turn enhances overall project performance, as reflected in core outcomes such as quality, efficiency, cost control, and timeliness. Moreover, formal and informal leadership exert contrasting moderating effects: formal leadership strengthens the benefits of functional diversity but constrains expertise diversity, while informal leadership has the opposite pattern. Building on these findings, a DRL framework based on an improved Proximal Policy Optimization (PPO)-Clip (PPO-Clip) algorithm is developed to model how leadership support can be dynamically adjusted to guide the transition from diversity to creation under resource constraints. The simulation results demonstrate that PPO-Clip not only outperforms traditional optimization methods and other DRL algorithms, but more importantly, it provides stable, efficient strategies that minimize wasted interventions and concentrate resources where they generate the greatest impact on knowledge creation. Overall, this study enriches project management research by revealing the context-dependent role of leadership in leveraging different types of knowledge diversity and by introducing a computational approach that equips managers with actionable strategies to transform diversity into sustained innovation.
