Upgrading buildings for energy efficiency and sustainability is crucial for achieving national sustainable development goals (SDGs). Among the 17 SDGs, quality education and well-being are closely linked to education facilities. This study develops a strategic green remodeling (GR) framework for early childhood education centers in South Korea by (i) identifying key GR features and retrofit strategies and (ii) assessing energy efficiency improvements. The framework was applied to 30 case studies of green retrofitted daycare centers across Gyeonggi-do and Jeollanam-do. Energy consumption data for heating, cooling, domestic hot water, lighting, and ventilation were analyzed using descriptive analysis and the Wilcoxon signed-rank test. Results indicate an overall reduction in energy consumption, with 18 projects achieving over 30% energy savings. Significant improvements were observed in heating and lighting efficiency. Implementing this framework can help policymakers, educators, and stakeholders develop targeted retrofitting strategies, fostering healthier and more sustainable learning environments.

Ultra-high performance geopolymer concrete (UHPGC) presents a sustainable alternative to traditional ultrahigh performance concrete (UHPC). Accurate prediction of UHPGC compressive strength is crucial for its wider adoption in both industry and academia. However, the complex interplay of factors influencing UHPGC compressive strength, coupled with limited available data, makes this task challenging. Therefore, this study aims to establish a transfer learning (TL) framework for UHPGC compressive strength prediction. This work explored the ability of TL to leverage the knowledge acquired from normal-strength geopolymer concrete datasets to develop models for predicting the compressive strength of UHPGC. The results demonstrate that TL models (transferred Convolutional Neural Network (transferred CNN), transferred Tabnet, and Two-stage TrAdaboost.R2) outperform traditional machine learning (ML) models (CNN, Tabnet, Adaboost.R2), with the corresponding R-square score of 0.93, 0.93, and 0.94 (for the TL models) and 0.86, 0.89, and 0.90 (for the traditional ML models). Additionally, TL models exhibit 10%-30% lower RMSE than their traditional counterparts. Furthermore, the findings indicate that a minimum of 40 data samples in the target domain is necessary for reliable predictions. In conclusion, the study captures the effectiveness of the TL approach in overcoming data scarcity and the robustness of TL models to variations of features in the target domain. This research highlights the potential of knowledge transfer from well-researched geopolymers to develop predictive models for specialised geopolymer types with limited data.

There have been limited empirical studies that aimed to establish the tenability of the stationarity assumption in recurrent construction bidding, and thus the need for and importance of allowing for continuity in bidding models remain unexplored. This study examined the bidding trends of individual contractors according to their level of experience in recurrent bidding, to test the tenability of the stationarity assumption. The data sample was a past bidding dataset of Singapore public sector construction projects over a five-year period between 2017 and 2021, with over 8000 bidding records from more than 900 contractors. The results show that there were statistically significant changes in the contractors’ bidding trends, irrespective of their level of experience in recurrent bidding and different time periodicities, ranging between 10 and 20 months. Thus, the stationarity assumption that contractors behave in a probabilistically consistent way over time, regardless of changing conditions, was untenable for the data sample involved. The observed changes in the contractors’ bidding trends cannot be regarded as random, but represent a continuous strategic process in response to changes in market forces. It is postulated that the possible causes of changes vary among individual contractors, in which there are a set of varying internal and external factors they consider at the time of bidding. The findings have implications for future bidding modelling attempts, in allowing for continuity in recurrent bidding. Contractors should systematically review and re-optimize their bidding strategy by leveraging their historical bidding data and bidding feedback information from clients, since their potential competitors will do the same thing for recurrent bidding.

Over the last decade, a considerable amount of research has documented the application of machine learning (ML) and its potential for cleaner production of sustainable construction materials particularly on geopolymers. Conceptually, the use of ML could help optimize the mixture composition, predict the property and performance of geopolymers materials. However, existing studies seem to mainly concentrate on geopolymer concrete and thus overlook other forms such as mortar and paste, and the data requirements of ML. In addressing the gaps, the aim of this study is to provide a current status of art on the use of ML on geopolymer materials by specifically exploring (i) the progression of ML in geopolymer materials from 2012 to 2023; (ii) the forms and types of geopolymer being researched using ML; (iii) the data sources and sizes, and ML algorithms being used; and (iv) the tasks being performed using ML. The overall findings show that ML are primarily utilized for predicting geopolymer properties, particularly compressive strength, while their potential in mixture optimization and structural maintenance remains largely untapped. Additionally, the small training datasets and the predominant reliance on data from previous publications in most studies underscore the limited utilization of field data. In conclusion, this study informs researchers of the current challenges in the application of ML for geopolymer materials and proposes directions for future research in using ML for improved property prediction and mixture optimization of sustainable geopolymer materials.

Ready-mix concrete (RMC) production is a major contributor to upstream carbon emissions in the construction industry. However, the absence of reliable emissions data, coupled with inconsistencies in reporting practices, presents significant challenges for stakeholders in effectively identifying and managing carbon hotspots across regions. Thus, this study employed a web crawling technique to compile a high-quality dataset of 59,412 Environmental Product Declarations (EPD) of RMC products in North America, then utilized the Model-Agnostic Meta-Learning (MAML) algorithm to enhance the embodied carbon emissions prediction for these products. The model was trained using three datasets related to material use, resource consumption, and waste generation as base learners in the United States (U.S.). Then, we tested the model with a new dataset from Canada containing unseen features to evaluate its generalization capability under varying environmental and technological scenarios in RMC production. The results showed that the proposed task-oriented MAML model outperformed the base learners, achieving an R2 score of 0.902 for new task prediction, compared to scores of 0.759, 0.689, and 0.687 for the respective base learners. Furthermore, the MAML model exhibited 25 %-40 % reductions in MAE, RMSE, and MAPE relative to the base learners, highlighting its predictive performance in analyzing multi-task cases. Finally, a web-based platform framework incorporating the trained MAML model is proposed to support stakeholders in managing carbon emissions and to serve as a tool for validating EPD documents for RMC products. The findings of this study provide valuable insights to advance decarbonization efforts within the construction industry.

Purpose The number of bidders in upcoming tenders has important managerial implications for both construction clients and contractors in their decision-making in the competitive bidding process. However, there is a stagnation of research efforts on predicting the number of bidders with only a handful of studies over the past decades, which mainly focused on statistical distribution of the number of bidders. This study aims to provide a new perspective of predicting the number of bidders using machine learning (ML) algorithms. Design/methodology/approach This study adopted a case study approach with a bidding dataset of public sector construction projects in Singapore. Six ML models were developed, and linear regression was used as a baseline model is assessing the predictive performance of ML models. Findings The results show that ML models outperform the baseline linear regression model, in which XGBoost is the best performing model of R2 which is two times higher than the linear regression model. In addition, economic-related factors play a vital role in this prediction problem. Research limitations/implications While the predictive performance of the developed ML models is relatively low, it indicates the challenges and complexities in this prediction problem, even with the use of artificial intelligent techniques. Originality/value Being a pioneering work, this study sets a foundation for the use of ML models in this prediction problem and offers insights for future modelling attempts towards the development of a decision support system for construction clients and contractors.

With the rapid advancements in digital technologies, changes in regulatory and societal expectations, and increased environmental awareness and concerns among building owners and occupants, the design and effectiveness of building control systems and their energy usage are under constant scrutiny as never before. The reshaping and integration of building controls with Internet of Things (IoT) devices have led to the growing popularity of Reinforcement Learning (RL) in the built environment. Multi-objective reinforcement learning (MORL) is touted to be more effective than traditional RL in optimizing smart building operations by resolving multifaceted goals, improving policy adaptability and decision-making processes involving multiple stakeholders and criteria. Hitherto, little is known of the full potential of MORL and its application trends. In addressing this, this research aims to build a knowledge base around the application trends of MORL framework and its benefits for smart building energy design and control systems through a systematic and critical review using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 1071 studies were retrieved, of which 74 studies were included in the final assessment to present and discuss: (i) objectives RL typically in smart building context; (ii) overview of the design and control strategies of MORL in smart buildings; (iii) MORL applications and performance evaluation in smart building; and (iv) challenges and future research directions and opportunities. Overall, our findings reveal potential work done to explore the use of MORL towards controlling multiple policies and complex dynamic building environments, and that current studies tend to focus on incorporating occupancy patterns and/or occupant feedback into the MORL control loop.

AbstractAir pollution poses a significant threat to the health of the environment and human well-being. The air quality index (AQI) is an important measure of air pollution that describes the degree of air pollution and its impact on health. Therefore, accurate and reliable prediction of the AQI is critical but challenging due to the non-linearity and stochastic nature of air particles. This research aims to propose an AQI prediction hybrid deep learning model based on the Attention Convolutional Neural Networks (ACNN), Autoregressive Integrated Moving Average (ARIMA), Quantum Particle Swarm Optimization (QPSO)-enhanced-Long Short-Term Memory (LSTM) and XGBoost modelling techniques. Daily air quality data were collected from the official Seoul Air registry for the period 2021 to 2022. The data were first preprocessed through the ARIMA model to capture and fit the linear part of the data and followed by a hybrid deep learning architecture developed in the pretraining–finetuning framework for the non-linear part of the data. This hybrid model first used convolution to extract the deep features of the original air quality data, and then used the QPSO to optimize the hyperparameter for LSTM network for mining the long-terms time series features, and the XGBoost model was adopted to fine-tune the final AQI prediction model. The robustness and reliability of the resulting model were assessed and compared with other widely used models and across meteorological stations. Our proposed model achieves up to 31.13% reduction in MSE, 19.03% reduction in MAE and 2% improvement in R-squared compared to the best appropriate conventional model, indicating a much stronger magnitude of relationships between predicted and actual values. The overall results show that the attentive hybrid deep Quantum inspired Particle Swarm Optimization model is more feasible and efficient in predicting air quality index at both city-wide and station-specific levels.

Heating, ventilation, and air-conditioning (HVAC) systems are responsible for a considerable proportion of total building energy consumption but are also vital for improved indoor temperature comfort, indoor air quality and well-being of building occupants. Thus, developing control strategies for HVAC systems is critical for the total life cycle of any building projects. Particularly, HVAC and building operations are not stationary but are filled with fuelled by environmental dynamisms and unexpected disruptions such as users' activities, weather conditions, occupancy rate, and operation of machinery and systems. This research aims to develop and propose a strategic control learning framework for HVAC systems using the deep reinforcement learning (DRL) approach. The results show that the proposed Phasic Policy Gradient (PPG) based method is more adaptive to changes in real building's environments. Notably, PPG performs better and more reliable than the conventional method for HVAC control optimization with about 2-14% in energy consumption reduction and indoor temperature comfort enhancement, along with a 66% faster convergence rate. Overall, our findings demonstrate that our proposed DRL approach is less resource intensive and much easier than the conventional approach in deriving solutions for HVAC control optimization driven by energy efficiency and indoor temperature comfort.

Purpose The interest in corporate social responsibility (CSR) has become burgeoning in the construction industry as firms are under constant pressure from socially conscious stakeholders to demonstrate their efforts to address various CSR issues. This study aims to unveil the key practices and impact factors (KPIFs) of CSR implementation in construction firms and the interrelationships among different key impact factors toward attaining CSR practices. Design/methodology/approach Mobilizing the integrated institutional, stakeholder and self-determination theories, a theoretical framework was first developed to elaborate the potential inter-relationships among the key impact factors toward CSR implementation. Data were collected from extra-grade contractors through an online questionnaire survey and was then analyzed by the partial least square structural equation modeling method. Findings The results show that construction firms' CSR practices could be classified into eight distinct key dimensions, e.g. shareholders' interests, government commitment and environment preservation. It is found that three groups of key impact factors – external institutional factors (especially coercive-normative factors), intrinsic factors (especially strategic business direction and organizational culture) and identified factors (i.e. the perceived importance of CSR practices) – have statistically significant positive impacts on most key dimensions of CSR practices. Practical implications The research findings have implications for top management to better understand CSR implementation, thereby helping them secure legitimacy to survive and advance in the competitive construction businesses. Originality/value The findings contribute to the theoretical body of knowledge in CSR by modeling and empirically demonstrating the influence mechanism of CSR implementation in construction within an integrated model.

Waste management and minimization are touted to be two of the key drivers for greening the construction industry and a pathway to a circular economy. This research aims to revisit the attitudes and perceptions of project stakeholders towards construction and demolition (C&D) waste in the Australian construction industry and ascertain if the current state of play in construction would facilitate the transition to a circular economy. Statistical analysis was performed on an online survey dataset collected from 104 professionals within the Australian construction supply chain. The results reveal that construction professionals’ attitudes and perceptions to C&D waste could be classified into normative, regulatory and cultural cognitive drivers. Also, the perceived barriers and strategies of C&D waste management vary across design consultants and principal and sub-contractors. Overall, the evidence is suggestive that the Australian construction industry seems not fully ready for a circular economy. In terms of research implications, clearer guidelines and mandatory approaches to C&D waste management, involving a balance of incentivization and dis-incentivization actions, and close and stronger collaborations between the industry and government, are deemed necessary for better C&D waste management performance and the realization of a greener industry.

PurposeThis study aims to explore the gender differences in working from home (WFH) experiences during the pandemic from the Australia’s construction workforce perspective. Specifically, it explores gender differences in terms of: (1) the respondents’ family responsibilities during the pandemic; (2) their WFH experiences prior to and during the pandemic; and (3) their perceptions of the impacts of challenges associated with WFH on their work activities and performance along with their self-reported work performance when WFH, overall satisfaction with WFH and preference for WFH post-COVID.Design/methodology/approachThis study adopted a survey design to reach the targeted sample population, i.e. construction workforce in the Australian construction industry who has had experienced WFH during the pandemic. Data was collected using an online anonymous questionnaire survey.FindingsThe results show notable gender differences in various aspects including family responsibilities, workplace arrangements and perceptions of the impacts of the challenges associated with WFH on work activities and performance. Also, statistically significant associations are detected between gender and the respondents’ self-reported work performance when WFH, overall satisfaction with WFH and preference for WFH post-COVID.Originality/valueEven prior to the COVID-19 pandemic, little is known about WFH experiences among construction workforce due to the low prevalence of regular and planned remote working in the industry. This is the first study sheds light on construction workforce WFH experiences using gender lenses. The findings have implications for construction-related firms continuing with WFH arrangement post the pandemic, which may include the formulation of policy responses to re-optimize their present WFH practices.

Automated visual assessment report generation in structural health monitoring (SHM) offers advantages for building inspections. However, current vision-based approaches that focus primarily on local surface detection cannot be directly used for inspection reports without further interpretation of the detected labels and coordinator metrics for an appropriate serviceability assessment. To address this gap, this paper presents an automated textual assessment framework for retrieving and generating linguistic descriptions of building component images. Six attention-based captioning methods were constructed based on convolutional neural network (Inception-V3, Xception, and ResNet50) and recurrent neural network (GRU, LSTM), and experimented via 7430 pairs of building component images and captions. The results indicated that the proposed methods had good predictive power and ResNet50-LSTM outperformed other methods with average precision, recall, and F1 scores of 0.84, 0.74, and 0.79, respectively. This paper highlights the potential of the image captioning approach for producing accurate and timely periodic structural assessment reports.

This study aims to examine construction firms' awareness and implementation of various aspects of corporate social responsibility (CSR) practices and ascertain whether the level of CSR awareness and implementation would vary across firms with different ownership and control. An online questionnaire survey was undertaken across extra-grade construction firms in China. The results show that respondents' CSR priorities are built around the aspects of quality, safety, and environment. They tend to adopt a more integrated approach to managing the interests of diverse stakeholders. It is notable that there are positive correlations between the firms' CSR awareness and implementation and that listed firms tend to exhibit a higher level of CSR awareness and implementation than their counterparts. In conclusion, the findings inform policymakers and practitioners of the status quo of CSR, thus enabling them to configure targeted strategies to improve the overall CSR awareness and implementation in China's construction industry.

Early studies on the COVID-19 pandemic suggest that the working from home (WFH) mandate and unusual caregiving arrangements have dramatically impacted the employment of women, especially those with young children. This study explores women's perceptions of the WFH mandate arrangement. Data were collected from the female workforce in the Australian construction industry using an online questionnaire. The specific objectives were to (i) explore their WFH experiences; (ii) examine their perceived impacts of WFH challenges on work activities and performance; and (iii) explore the relationships among critical challenges, the respondents' demographic characteristics and their overall satisfaction with WFH and preference for WFH after COVID. Although most respondents were new to the WFH arrangement, there is evidence suggesting that they were adapting well to the sudden shift to a WFH arrangement. Sixteen (out of twenty-two) challenges recorded positive perceived impacts on work activities and performance. The top three critical challenges were (i) mutual trust between you and your work supervisor; (ii) availability of suitable space at home; and (iii) information and communication exchanges via virtual meetings. The respondents also indicated positive satisfaction with a WFH arrangement along with perceived positive work performance while WFH. Most of them indicated high preference for WFH after COVID, which was positively correlated with the level of education attainment. The critical challenges identified together with a set of negative factors might be useful for employment organizations to re-optimize their WFH practices.

Purpose - Contractors of different scales, operating in different construction industries of varying institutional and economic settings, have different considerations when making bid or no-bid and mark-up decisions. Focusing on the large and medium-sized contractors in the Jilin province, China, the purpose of this study is to examine important factors affecting their decision to bid (d2b) and mark-up decisions and investigate differences between large and medium-sized contractors in evaluating the importance of the various factors affecting their d2b and mark-up decisions. Design/methodology/approach - This study used a survey design for timely data collection from a large population. Contractors' bidding attitudes was collected using an online survey questionnaire with a list of 40 key factors. Statistical analytical methods were applied for comparing the two groups of contractors. Findings - The results of this study indicate that factors related to client conditions are most critical for both large and medium-sized contractors in their d2b and mark-up decisions. The results also show statistically significant differences between the two groups of contractors on a subset of factors affecting their d2b and mark-up decisions. The large contractors have placed more emphasis on projects' potential financial and strategic benefits. Another notable finding is that both groups of contractors have placed great emphasise on "government legislations" in their d2b and mark-up decisions. Research limitations/implications - These findings should be interpreted in consideration of several limitations. Firstly, the sample size is relatively small, and the focus was on a single province in the China construction industry. Next, this study only explores differences between large and medium-sized contractors in evaluating the importance of the various factors affecting their d2b and mark-up decisions. Practical implications - Contractors could refer list of critical factors in competing for jobs in Jilin province or other provinces of similar institutional and economic settings. Construction clients, on the other hand, should consider the list of critical factors in the formulation of their competitive tendering procedures, thus enhancing the efficiency in their procurement of construction services. Originality/value - Research on contractors' bidding decision-making in the context of Chinese construction industry remains scarce; the research findings have implications for the industry stakeholders.

Given the construction industry's culture of presenteeism and long work hours, construction workforce who used to working in the company workplace were affected by the sudden shift to working from home (WFH) setting due to the COVID-19 pandemic lockdowns. Focusing on consultants in the Australian construction industry, this exploratory study examines: (i) individual perceptions of the impacts of WFH challenges on work activities and performance, and (ii) their self-reported work productivity, overall WFH satisfaction and future preference for WFH post-pandemic. The online survey results show that most respondents were new to the WFH arrangement. However, the evidence is suggestive that they were adapting well as demonstrated by their perceived positive impacts of most WFH challenges on their work activities and performance. The results also show that as the respondents' self-reported work productivity increases, their overall satisfaction with WFH increases and they would welcome WFH arrangement post-pandemic, and vice versa. The female respondents demonstrated higher overall WFH satisfaction and preference for WFH post-pandemic compared to male respondents, signifying the relationship between gender and their perceptions. These findings have implications for employing organizations in addressing human resource management challenges to maximize the potential benefits of WFH practices post-pandemic.

With the increasing expectations of clients and the growing complexity of the built environment, property management teams are facing constant pressure to effectively manage and rectify defects for improved building operational efficiency and performance. This study aims to develop and validate a defect correlation evaluation model for project and property management professionals by specifically (i) examining the defect detection and management mechanisms of residential buildings and (ii) quantifying the mechanical characteristics of defects by using association rules mining (ARM) techniques. In addressing the limitations of current evaluation approaches, this study proposed an ARM evaluation model that integrated, contextualized, and operationalized building defects into work type, location, elements, and defect type. The association between these classifications was explored and mapped. Among the resulting 123 meaningful rules, rules occurred at a rate of about 62% of the same work type in the linked work type, nearly 193% of the same element in another element, and about 23% of the close location in the far location. In conclusion, this study informs project and property management professionals of the key and complex associations between defects of different characteristics and highlights the most common occurrence defects in residential apartment buildings. Thus, this helps reduce the ambiguity and subjectivity of prioritization in defect management and facilitates maintenance and repair planning.

Purpose With the aim to provide a global view of factors affecting mark-up size on construction projects, this study performs a meta-analytical review of the relevant studies over the past 20 years. Design/methodology/approach The analytical process involved the identification and evaluation of the importance of critical factors affecting mark-up size on construction projects, and the assessment of the generalisability of findings of the meta-analysis. A random-effects model was adopted in the statistical meta-analysis. Findings The results show that there are 23 critical factors, and the top five factors are: (1) competitiveness of other bidders; (2) number of bidders; (3) relationship and past experience with client; (4) experience on similar project; and (5) project size. A heterogeneity test further shows that there is no statistically significant heterogeneity across the studies, reinforcing the generalisability of the findings to a global context. Research limitations/implications The list of critical factors from a global perspective should form a good basis for future efforts in bidding model development. Practical implications The research findings have practical implications to both construction clients and contractors in formulating their contracting practices and strategies. Originality/value This is the first meta-analysis of a sizeable collection of replicated studies on factors affecting mark-up size on construction projects in the literature.