Technology & Innovation Archives

Automated daily report generation from construction videos using ChatGPT and computer vision

Xiao, B., Wang, Y., Zhang, Y., Chen, C., & Darko, A. (2024). Automated daily report generation from construction videos using ChatGPT and computer vision. Automation in Construction, 168, 105874-. https://doi.org/10.1016/j.autcon.2024.105874

View Publication

Abstract

Daily reports are important in construction management, informing project teams about status, enabling timely resolutions of delays and budget issues, and serving as official records for disputes and litigation. However, current practices are manual and time-consuming, requiring engineers to physically visit sites for observations. To fill this gap, this paper proposes an automated framework to generate daily construction reports from on-site videos by integrating ChatGPT and computer vision (CV)-based methods. The framework utilizes CV methods to analyze video footage and extract relevant productivity and activity information, which is then fed into ChatGPT using proper prompts to generate daily reports. A web application is developed to implement and validate the framework on a real construction site in Hong Kong, generating daily reports over a month. This research enhances construction management by significantly reducing documentation efforts through generative artificial intelligence, with potential applications in jobsite safety management, quality reporting, and stakeholder communication.

Keywords

Construction daily report generation; Computer vision; ChatGPT; Construction management; Project documentation

Professors Sturts Dossick and Wu present at 2024 NWCCC Annual Conference

Professor Carrie Sturts Dossick, Associate Dean for Research, and Assistant Professor Lingzi Wu both from the department of Construction Management, presented at the 2024 Northwest Construction Consumer Council (NWCCC) Conference, “AI and Digital Technology in Construction” and Distinguished Project Awards. Their presentations are linked below. Assistant Professor Wu gave a presentation entitled “AI-Powered Solutions for Next-Generation Construction Management.” Professor Sturts Dossick presented on Cybersecurity Planning.

Applications of blockchain for construction project procurement

Kim, M., & Kim, Y.-W. (2024). Applications of blockchain for construction project procurement. Automation in Construction, 165, 105550-. https://doi.org/10.1016/j.autcon.2024.105550

View Publication

Abstract

Blockchain technology has shown potential in enhancing project performance by instilling trust in data sharing among stakeholders, thereby encouraging the stakeholders to ensure a strategic acquisition and resource management through procurement activities. However, despite the recent research efforts on blockchain in the construction sector, there is a lack of knowledge of the status quo in that barely any research investigated the synergy of blockchain and procurement by recognizing the inextricable linkage between procurement management and project delivery system. This paper conducts a systematic review of 54 articles to assess blockchain's potential in addressing issues inherent in the current organizational structures and collaborative efforts. Findings offer profound insight into the current landscape of procurement-specific blockchain research, highlighting areas needing attention. This paper identified opportunities in construction procurement by investigating the extent to which the technology is integrated into the current project management context emphasizing integration and collaboration.

Keywords

Blockchain; Procurement; Construction industry; Procurement process; Project delivery system; Literature review

Acoustic design evaluation in educational buildings using artificial intelligence

Tabatabaei Manesh, M., Nikkhah Dehnavi, A., Tahsildoost, M., & Alambeigi, P. (2024). Acoustic design evaluation in educational buildings using artificial intelligence. Building and Environment, 261, 111695-. https://doi.org/10.1016/j.buildenv.2024.111695

View Publication

Abstract

Speech intelligibility is a critical aspect of building science, particularly in educational buildings where poor sound quality may have a detrimental impact on students' learning and teachers’ health. However, considering the numerous building regulations proposing varying definitions and ranges of acoustic comfort, calculating the necessary acoustic indicators can be challenging for designers. Speech intelligibility is a crucial component of indoor acoustics and acoustic comfort and can be calculated using formulas, simulation software, and data-based web tools. While formulas are fast, they lack details; acoustic simulation software is highly accurate but time-consuming and expensive. Data-based web tools, including machine learning algorithms, offer both speed and accuracy and are widely accessible. In this study, we present a system utilizing machine learning techniques to predict acoustic indicators, numeric and heatmap, in an educational building. The Pachyderm plugin in the Grasshopper was utilized to conduct extensive simulations in a single educational space, focusing on acoustic indicators in six different frequencies and general modes. Using Catboost and the pix2pix algorithm, the prediction models provide numerical and image indices on the developed dataset. Also, SHAP values were employed to interpret the Catboost model, analyzing the significance of each feature. The results showed remarkable accuracy, (i.e., between 89 % and 99 %) in the numerical portion, and PSNR index ranging from 0.817 to 0.970, and an SSIM index ranging from 15.56 to 31.57 in the image section. By utilizing data-driven methods, the system provides an efficient and accurate approach to calculating acoustic indicators, helping to ensure optimal acoustic environment in educational buildings.

Keywords

Building acoustics; Catboost; Pix2pix; Educational building; Speech intelligibility

Online toolkits for collaborative and inclusive global research in urban evolutionary ecology

Savage, A. M., Willmott, M. J., Moreno‐García, P., Jagiello, Z., Li, D., Malesis, A., Miles, L. S., Román‐Palacios, C., Salazar‐Valenzuela, D., Verrelli, B. C., Winchell, K. M., Alberti, M., Bonilla‐Bedoya, S., Carlen, E., Falvey, C., Johnson, L., Martin, E., Kuzyo, H., Marzluff, J., … Gotanda, K. M. (2024). Online toolkits for collaborative and inclusive global research in urban evolutionary ecology. Ecology and Evolution, 14(6), e11633-n/a. https://doi.org/10.1002/ece3.11633

View Publication

Abstract

Urban evolutionary ecology is inherently interdisciplinary. Moreover, it is a field with global significance. However, bringing researchers and resources together across fields and countries is challenging. Therefore, an online collaborative research hub, where common methods and best practices are shared among scientists from diverse geographic, ethnic, and career backgrounds would make research focused on urban evolutionary ecology more inclusive. Here, we describe a freely available online research hub for toolkits that facilitate global research in urban evolutionary ecology. We provide rationales and descriptions of toolkits for: (1) decolonizing urban evolutionary ecology; (2) identifying and fostering international collaborative partnerships; (3) common methods and freely-available datasets for trait mapping across cities; (4) common methods and freely-available datasets for cross-city evolutionary ecology experiments; and (5) best practices and freely available resources for public outreach and communication of research findings in urban evolutionary ecology. We outline how the toolkits can be accessed, archived, and modified over time in order to sustain long-term global research that will advance our understanding of urban evolutionary ecology.

From Tweets to Energy Trends (TwEn): An exploratory framework for machine learning-based forecasting of urban-scale energy behavior leveraging social media data

Abbasabadi, N., & Ashayeri, M. (2024). From Tweets to Energy Trends (TwEn): An exploratory framework for machine learning-based forecasting of urban-scale energy behavior leveraging social media data. Energy and Buildings, 317, 114440-. https://doi.org/10.1016/j.enbuild.2024.114440

View Publication

Abstract

TwEn framework links tweet frequency with urban energy use patterns. AI models forecast energy from social media data sourced from X. Framework predicts NYC electricity use with high accuracy. Tweet frequency’s seasonal stability enhances energy research. Real-time social data can aid sustainable urban energy policy. Understanding energy behavior is crucial in addressing climate change, yet the accuracy of energy predictions is often limited by reliance on oversimplified occupancy data. This study develops an exploratory framework, from Tweets to Energy Trends (TwEn), leveraging machine learning and geo-tagged social media data to investigate the social dynamics of urban energy behavior. TwEn explores the relationship between social media interactions, specifically the frequency of tweets using data from the X Platform, and energy use patterns on an hourly basis. Employing various machine learning models, including artificial neural networks (ANN), decision tree (DTREE), random forest (RDF), and gradient boosting machine (GBM), the study evaluates their efficiency in both static and time-series forecasting of energy use trends and investigates the capability of social media data in predicting urban energy patterns. In addition, the study carries out a series of sensitivity analyses to provide an examination of the data and models. Furthermore, comprehensive data acquisition methods are developed and implemented. Tested on New York City using actual hourly electricity consumption data, the framework demonstrates significant predictive power of tweet frequency on urban electricity use. The framework also exhibits significant seasonality in X data, identifying patterns and trends that can inform time series urban building energy models (UBEM). The results offer new insights into the determinants of urban energy behavior and provide crucial perspectives for augmenting UBEMs, ensuring they are closely aligned with the complex social dynamics of contemporary urban environments. By integrating both digital and physical data, this study sheds light on urban energy behavior, supporting the formulation of effective and sustainable energy policies for urban futures.

Keywords

Occupancy; Social Media; Time Series Forecast; Urban Building Energy Modeling (UBEM); Urban Energy Behavior

2024 Innovation in the Construction Industry

Prof. Dossick’s CM515 Spring 2024 Class. (2024). 2024 Innovation in the Construction Industry (Sturts Dossick, C., & Ray, L., Eds.). UW Libraries Pressbooks.

View Publication

Abstract

This book contains a series of case studies authored by graduate students in CM515 Virtual Construction Management Spring 2024. We explored how people, teams, and companies change practices with a variety of new technologies in the workplace. You will find cases of people who are innovators, teams who took on innovation, and specific design and construction projects that realized these innovation practice changes.

Keywords

Technology; Engineering; Agriculture; Industrial processes

Awareness, adoption readiness and challenges of railway 4.0 technologies in a developing economy

Awodele, I. A., Mewomo, M. C., Municio, A. M. G., Chan, A. P. C., Darko, A., Taiwo, R., Olatunde, N. A., Eze, E. C., & Awodele, O. A. (2024). Awareness, adoption readiness and challenges of railway 4.0 technologies in a developing economy. Heliyon, 10(4), e25934–e25934. https://doi.org/10.1016/j.heliyon.2024.e25934

View Publication

Abstract

The railway industry has witnessed increasing adoption of digital technologies, known as Railway 4.0, that is revolutionizing operations, infrastructure, and transportation systems. However, developing countries face challenges in keeping pace with these technological advancements. With limited research on Railway 4.0 adoption in developing countries, this study was motivated to investigate the awareness, readiness, and challenges faced by railway professionals towards implementing Railway 4.0 technologies. The aim was to assess the level of awareness and preparedness and identify the key challenges influencing Railway 4.0 adoption in Nigeria's railway construction industry. A questionnaire survey (was distributed to professionals in the railway construction sector to gather their perspectives on awareness of, preparation for, and challenges associated with the use of Railway 4.0 technologies. The results revealed that awareness of Railway 4.0 technologies was moderate, while readiness was low among the professionals. Using exploratory factor analysis, 10 underlying challenge constructs were identified including lack of technical know-how, resistance to change, infrastructure limitations, and uncertainty about benefits, amongst others. Partial Least Square Structural Equation Modelling (PLS-SEM) confirmed these constructs, with reliability and availability, lack of technical know-how, lack of training and resources, and uncertainties in benefit and gains having significant influence on awareness and readiness. The study concludes that focused efforts in training, infrastructure improvement, supportive policies, and communicating the advantages of Railway 4.0 are critical to drive adoption in Nigeria and other developing economies. The findings provide insights into tailoring Railway 4.0 implementation strategies for developing contexts.

Keywords

Railway 4.0; Awareness; Readiness; Challenges; Technologies

The impact of penalties, incentives, and monitoring costs on the stakeholders’ decision-making behaviors in non-compliance drone operations

Wang, X., Yang, Y., Darko, A., Chan, A. P. C., & Chi, H.-L. (2024). The impact of penalties, incentives, and monitoring costs on the stakeholders’ decision-making behaviors in non-compliance drone operations. Technology in Society, 77. https://doi.org/10.1016/j.techsoc.2024.102589

View Publication

Abstract

As an automated assistive tool, drones have revolutionized industrial activities and brought numerous potential benefits to society. However, irresponsible drone users often disregard compliance with regulations, leading to new challenges in drone usage. Although governments have implemented punishment and incentive mechanisms to prevent non-compliant drone operations, the extent to which they can effectively deter such activities remains unclear. To address this gap, the study employed evolutionary game theory to assess the impacts of penalties for non-compliance, incentives for public monitoring, and monitoring costs for the government on the multiple stakeholders' decision-making behaviors (SDBs). The study also used the Chinese construction market data to simulate how penalties, incentives, and monitoring costs influence SDBs. The numerical simulations reveal that penalties and incentives could reduce drone users' non-compliant operations, but this effect is useful only if the penalties and incentives exceed a certain value. In China, drone users' non-compliant operations can be controlled when penalties for drone users exceed 12,000 yuan, and incentives for the public's monitoring exceed 170 yuan/day. The current Chinese government's penalties that were administered for non-compliant drone operations have not achieved a deterrent effect, but the incentive is feasible. These findings provide a fresh insight into the decision-making behaviors of stakeholders in non-compliant drone operations. Additionally, the tripartite evolutionary game model developed in this study can assist other countries in determining optimal values for penalties, incentives, and monitoring costs to mitigate non-compliant drone operations effectively.

Life Cycle Lab

The Life Cycle Lab at UW’s College of Built Environments leads research to advance life cycle assessment (LCA) data, methods and approaches to enable optimization of materials, buildings and infrastructure. Our work is structured to inform impactful policies and practices that support global decarbonization efforts. We envision a transformed, decarbonized building industry – better buildings for a better planet.

Our group is led by Professor Kate Simonen. Since arriving at UW in 2009, she has conducted research and spearheaded initiatives focused on accelerating the transformation of the building sector to radically reduce the greenhouse gas emissions attributed to materials (also known as embodied carbon) used in buildings and infrastructure. From June 2010 until April 2024 she directed the Carbon Leadership Forum (CLF) as it was hosted in UW’s College of Built Environments. The core of CLF’s work has been to lay essential foundations for understanding embodied carbon: a framework for comprehensive strategy, rigorous analysis, and transparent reporting that can support design tools, effective policy, and collective action.

In April 2024, two new entities were created to expand the program’s influence and impact: the Carbon Leadership Forum launched as an independent nonprofit organization and the newly named Life Cycle Lab was created to support the next generation of researchers and pursue critical embodied carbon research with an increased focus on academic publications. Learn more about this transition via this announcement.

Life Cycle Lab members include professional research staff, research assistants, students advised by Prof. Simonen, undergraduate interns and student assistants. Many of our members are formally affiliated with the Carbon Leadership Forum and the two organizations continue to actively collaborate developing strategies and executing aligned initiatives.

Projects associated with Life Cycle Lab include: