Gongfan Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Gongfan Chen has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Min Liu
Syracuse Univ
5 shared publications - Simon M. Hsiang
Professor and Department Chair, Dept. of Systems Engineering and Engineering Management, Univ. of North Carolina at Charlotte, Charlotte, NC 28223. ORCID:
4 shared publications - Chuanni He
Syracuse Univ
3 shared publications - Edward J. Jaselskis
North Carolina State Univ
3 shared publications Simon M. Hsiang
Professor and Department Chair, Dept. of Systems Engineering and Engineering Management, Univ. of North Carolina at Charlotte, Charlotte, NC 28223
2 shared publications- Abdullah Alsharef
Department of Civil Engineering, King Saud University, Riyadh 11421, Saudi Arabia
1 shared publication
Latest Publications
- 1 September 2026
- Published by American Society of Civil Engineers (ASCE) in Journal of Management in Engineering
- Vol. 42 (5)
Advancing Fit-for-Purpose Access to CII Best Practices Using Multimodal Large Language Models
The Construction Industry Institute (CII) has conducted extensive research over the past four decades, culminating in the identification of 17 best practices (BPs) proven to enhance overall project success when effectively implemented. However, the BPs remains underutilized in the construction industry due to the vastness of the related knowledgebase, heterogeneous data formats, and time-intensive nature of interpretation. This research addresses these challenges by developing a new CII BP handbook and an artificial intelligence (AI) tool designed to improve CII knowledge accessibility and usability for member companies. The first tool, BP Primer , was developed using a hybrid approach that combines qualitative analysis with retrieval-augmented generation (RAG)–based question and +answering. It extracts actionable insights (termed as “golden nuggets”) from 54 CII research reports and organizes them across the 17 BPs and project lifecycle phases, enabling users to quickly locate strategies tailored to their specific needs. Additional features include BP-level and report-level executive summaries and frequently asked questions (FAQs) to support high-level CII BP comprehension. The second tool, a BP Conversational AI , is built on a multimodal RAG framework, allowing users to interact with the BP multimodal knowledge base through natural language queries and document-grounded responses. Both tools were piloted with industry partners, and key lessons learned from the implementation have been documented. This research establishes a foundation for applying multimodal large language model (MLLM)-driven frameworks to construction knowledge curation. The curated knowledge can effectively guide construction professionals toward fit-for-purpose insights that support informed decision-making.
- 1 September 2026
- Published by American Society of Civil Engineers (ASCE) in Journal of Management in Engineering
- Vol. 42 (5)
Advancing Fit-for-Purpose Access to CII Best Practices Using Multimodal Large Language Models
The Construction Industry Institute (CII) has conducted extensive research over the past four decades, culminating in the identification of 17 best practices (BPs) proven to enhance overall project success when effectively implemented. However, the BPs remains underutilized in the construction industry due to the vastness of the related knowledgebase, heterogeneous data formats, and time-intensive nature of interpretation. This research addresses these challenges by developing a new CII BP handbook and an artificial intelligence (AI) tool designed to improve CII knowledge accessibility and usability for member companies. The first tool, BP Primer , was developed using a hybrid approach that combines qualitative analysis with retrieval-augmented generation (RAG)–based question and +answering. It extracts actionable insights (termed as “golden nuggets”) from 54 CII research reports and organizes them across the 17 BPs and project lifecycle phases, enabling users to quickly locate strategies tailored to their specific needs. Additional features include BP-level and report-level executive summaries and frequently asked questions (FAQs) to support high-level CII BP comprehension. The second tool, a BP Conversational AI , is built on a multimodal RAG framework, allowing users to interact with the BP multimodal knowledge base through natural language queries and document-grounded responses. Both tools were piloted with industry partners, and key lessons learned from the implementation have been documented. This research establishes a foundation for applying multimodal large language model (MLLM)-driven frameworks to construction knowledge curation. The curated knowledge can effectively guide construction professionals toward fit-for-purpose insights that support informed decision-making.
- Open Access
Construction Jobsite Image Classification Using an Edge Computing Framework
Image classification is increasingly being utilized on construction sites to automate project monitoring, driven by advancements in reality-capture technologies and artificial intelligence (AI). Deploying real-time applications remains a challenge due to the limited computing resources available on-site, particularly on remote construction sites that have limited telecommunication support or access due to high signal attenuation within a structure. To address this issue, this research proposes an efficient edge-computing-enabled image classification framework for support of real-time construction AI applications. A lightweight binary image classifier was developed using MobileNet transfer learning, followed by a quantization process to reduce model size while maintaining accuracy. A complete edge computing hardware module, including components like Raspberry Pi, Edge TPU, and battery, was assembled, and a multimodal software module (incorporating visual, textual, and audio data) was integrated into the edge computing environment to enable an intelligent image classification system. Two practical case studies involving material classification and safety detection were deployed to demonstrate the effectiveness of the proposed framework. The results demonstrated the developed prototype successfully synchronized multimodal mechanisms and achieved zero latency in differentiating materials and identifying hazardous nails without any internet connectivity. Construction managers can leverage the developed prototype to facilitate centralized management efforts without compromising accuracy or extra investment in computing resources. This research paves the way for edge “intelligence” to be enabled for future construction job sites and promote real-time human-technology interactions without the need for high-speed internet.
Open AccessConstruction Jobsite Image Classification Using an Edge Computing Framework
Image classification is increasingly being utilized on construction sites to automate project monitoring, driven by advancements in reality-capture technologies and artificial intelligence (AI). Deploying real-time applications remains a challenge due to the limited computing resources available on-site, particularly on remote construction sites that have limited telecommunication support or access due to high signal attenuation within a structure. To address this issue, this research proposes an efficient edge-computing-enabled image classification framework for support of real-time construction AI applications. A lightweight binary image classifier was developed using MobileNet transfer learning, followed by a quantization process to reduce model size while maintaining accuracy. A complete edge computing hardware module, including components like Raspberry Pi, Edge TPU, and battery, was assembled, and a multimodal software module (incorporating visual, textual, and audio data) was integrated into the edge computing environment to enable an intelligent image classification system. Two practical case studies involving material classification and safety detection were deployed to demonstrate the effectiveness of the proposed framework. The results demonstrated the developed prototype successfully synchronized multimodal mechanisms and achieved zero latency in differentiating materials and identifying hazardous nails without any internet connectivity. Construction managers can leverage the developed prototype to facilitate centralized management efforts without compromising accuracy or extra investment in computing resources. This research paves the way for edge “intelligence” to be enabled for future construction job sites and promote real-time human-technology interactions without the need for high-speed internet.
- 1 November 2023
- Published by American Society of Civil Engineers (ASCE) in Journal of Management in Engineering
- Vol. 39 (6)
Motivating Reliable Collaboration for Modular Construction: Shapley Value–Based Smart Contract
- 1 November 2023
- Published by American Society of Civil Engineers (ASCE) in Journal of Management in Engineering
- Vol. 39 (6)
Motivating Reliable Collaboration for Modular Construction: Shapley Value–Based Smart Contract
- 1 March 2023
- Published by American Society of Civil Engineers (ASCE) in Journal of Management in Engineering
- Vol. 39 (2) , 04023002
Using Images to Detect, Plan, Analyze, and Coordinate a Smart Contract in Construction
Reliable construction workflow relies on timely discovery, analysis, and checking of compliance with contract terms, which are time consuming and inefficient tasks. Smart contracts enabled by blockchain technology have demonstrated promise in addressing the inefficiencies of data communications due to their merits of traceability, immutability, transparency, and self-enforceability. However, a smart contract’s inability to interact with real-world data is the main issue that impedes further implementation. Today’s increasing availability of as-built data provides automatic condition assessments that have great potential to automate smart contract executions. This research area is uncharted territory for the industry. This research selects a case study to present an automatic decentralized management framework by exploring image-based deep learning solutions to automate and decentralize the conditioning of smart contract executions enabled by a web3.js-based decentralized blockchain application. It was found that the model can automate management intelligence with minimal workflow interruptions by timely identification of bottleneck activities and enforcement of mitigation strategies. Project managers can use the blockchain prototype to enhance information sharing, remove key risks, and enable a reliable workflow with minimal management efforts.
- 1 March 2023
- Published by American Society of Civil Engineers (ASCE) in Journal of Management in Engineering
- Vol. 39 (2) , 04023002
Using Images to Detect, Plan, Analyze, and Coordinate a Smart Contract in Construction
Reliable construction workflow relies on timely discovery, analysis, and checking of compliance with contract terms, which are time consuming and inefficient tasks. Smart contracts enabled by blockchain technology have demonstrated promise in addressing the inefficiencies of data communications due to their merits of traceability, immutability, transparency, and self-enforceability. However, a smart contract’s inability to interact with real-world data is the main issue that impedes further implementation. Today’s increasing availability of as-built data provides automatic condition assessments that have great potential to automate smart contract executions. This research area is uncharted territory for the industry. This research selects a case study to present an automatic decentralized management framework by exploring image-based deep learning solutions to automate and decentralize the conditioning of smart contract executions enabled by a web3.js-based decentralized blockchain application. It was found that the model can automate management intelligence with minimal workflow interruptions by timely identification of bottleneck activities and enforcement of mitigation strategies. Project managers can use the blockchain prototype to enhance information sharing, remove key risks, and enable a reliable workflow with minimal management efforts.
- 1 March 2023
- Published by American Society of Civil Engineers (ASCE) in Journal of Management in Engineering
- Vol. 39 (2) , 04022071
Space–Time–Workforce Visualization and Conditional Capacity Synthesis in Uncertainty
Workspace, project duration, and workforce are three critical resources for construction projects. Project managers need to expend time and effort reviewing, comprehending, and coordinating these resources. However, the space–time–workforce interactions and their impact on decision-making in project scheduling are not fully known. Therefore, the objectives of this research were to understand the impact of workforce shifts on space, time, and labor cost performances, develop a three-dimensional (3D) visualization tool to reveal activity-level resource dynamics, and associate the risk aftermath with the occurrence probability to balance subjective risk tolerance and objective system reliability. This research developed a simulation model based on a case project to compare the workflow of five major specialty trades (i.e., bar placer, carpenter, scaffolder, pipefitter, and concreter) in 267 scenarios. A resource-oriented 3D visualization tool was developed to help project managers monitor project schedules. The research established a risk control framework using value-at-risk (VaR) and conditional value-at-risk (CVaR) approaches to associate extreme outcomes with their occurrence probability. Simulation results indicated that pipefitters significantly affected workspace overlap, whereas bar placers and carpenters predominantly impacted project duration. The scholarly contributions are (1) the creation of an intelligent system to generate a project schedule from workforce assignments specified by project managers, (2) development of a tool to visualize the three-way resource dynamics of workforce, time, and space on a 3D model for all possible scenarios, and (3) development of a framework for project managers to balance planning strategies between subjective risk tolerance and objective system reliability. This research provides project managers with a dynamic 3D visualization of space, time, and workforce utilization and interaction in uncertain environments, further facilitating reliable project scheduling decision-making.
- 1 March 2023
- Published by American Society of Civil Engineers (ASCE) in Journal of Management in Engineering
- Vol. 39 (2) , 04022071
Space–Time–Workforce Visualization and Conditional Capacity Synthesis in Uncertainty
Workspace, project duration, and workforce are three critical resources for construction projects. Project managers need to expend time and effort reviewing, comprehending, and coordinating these resources. However, the space–time–workforce interactions and their impact on decision-making in project scheduling are not fully known. Therefore, the objectives of this research were to understand the impact of workforce shifts on space, time, and labor cost performances, develop a three-dimensional (3D) visualization tool to reveal activity-level resource dynamics, and associate the risk aftermath with the occurrence probability to balance subjective risk tolerance and objective system reliability. This research developed a simulation model based on a case project to compare the workflow of five major specialty trades (i.e., bar placer, carpenter, scaffolder, pipefitter, and concreter) in 267 scenarios. A resource-oriented 3D visualization tool was developed to help project managers monitor project schedules. The research established a risk control framework using value-at-risk (VaR) and conditional value-at-risk (CVaR) approaches to associate extreme outcomes with their occurrence probability. Simulation results indicated that pipefitters significantly affected workspace overlap, whereas bar placers and carpenters predominantly impacted project duration. The scholarly contributions are (1) the creation of an intelligent system to generate a project schedule from workforce assignments specified by project managers, (2) development of a tool to visualize the three-way resource dynamics of workforce, time, and space on a 3D model for all possible scenarios, and (3) development of a framework for project managers to balance planning strategies between subjective risk tolerance and objective system reliability. This research provides project managers with a dynamic 3D visualization of space, time, and workforce utilization and interaction in uncertain environments, further facilitating reliable project scheduling decision-making.
- 1 March 2023
- Published by Canadian Science Publishing in Canadian Journal of Civil Engineering
- Vol. 50 (3) , 210-223
Knowing what is going on—a smart contract for modular construction
This research aims to develop an automatic incentive–penalty enforcement system for modular construction. Smart contract rules were developed for a project of 120 prefabricated bath units. The results show that the smart contract can automatically enforce rewards and penalties for all 19 scenarios. The findings can help project managers detect and reject any inappropriate or malicious operations deviated from predefined rules efficiently. The results show that if the prefabricated bathroom unit fabricator can perform at the highest reliability level following the smart contract rules, the project can save 4.7% overall cost compared with the benchmark scenario. The findings will be beneficial to modular construction project by ensuring efficient monitoring, motivating reliable performance, and improving productivity and project documentation.
- 1 March 2023
- Published by Canadian Science Publishing in Canadian Journal of Civil Engineering
- Vol. 50 (3) , 210-223
Knowing what is going on—a smart contract for modular construction
This research aims to develop an automatic incentive–penalty enforcement system for modular construction. Smart contract rules were developed for a project of 120 prefabricated bath units. The results show that the smart contract can automatically enforce rewards and penalties for all 19 scenarios. The findings can help project managers detect and reject any inappropriate or malicious operations deviated from predefined rules efficiently. The results show that if the prefabricated bathroom unit fabricator can perform at the highest reliability level following the smart contract rules, the project can save 4.7% overall cost compared with the benchmark scenario. The findings will be beneficial to modular construction project by ensuring efficient monitoring, motivating reliable performance, and improving productivity and project documentation.
- 1 July 2022
- Published by American Society of Civil Engineers (ASCE) in Journal of Management in Engineering
- Vol. 38 (4) , 04022027
Exploit Social Distancing in Construction Scheduling: Visualize and Optimize Space–Time–Workforce Tradeoff
The COVID pandemic has given rise to the necessity of social distancing regulations, which has brought the importance of workspace management on the construction site to an unprecedented level. Understanding and visualizing the interaction and tradeoff among space, time, and workforce is critical for construction managers to schedule and deliver projects on time. Therefore, the objectives of this research are to investigate how the critical path method (CPM) and Takt-time planning methods utilize space, time, and workforce differently, develop a tool to visualize the space–time–workforce interactions, and investigate the space–time–workforce tradeoff based on different managers’ preferences. This research selected a high-rise office building project and collected 889 sets of productivity data of five specialty trades. The research built a simulation model to investigate productivity and project performance under 267 scenarios of different combinations of the three resources. A dynamic tool was then developed to visualize workspace, time, and workforce interactions. Finally, a Choquet integral–based evaluation and decision tool was developed. The simulation results show that the Takt-time planning method can reduce up to 80% of workspace overlap compared with the actual production plan with less than 20% of duration extension. The contributions to the body of knowledge are (1) creating a visual framework for managers to understand the interaction and tradeoff among space, time, and workforce quickly and accurately, and (2) developing an innovative Choquet integral approach for managers to evaluate planning strategies according to project preferences. The framework and analysis method can be adapted to other construction projects to assist managers to visualize and optimize the space–time–workforce tradeoff under uncertain project drivers.
- 1 July 2022
- Published by American Society of Civil Engineers (ASCE) in Journal of Management in Engineering
- Vol. 38 (4) , 04022027
Exploit Social Distancing in Construction Scheduling: Visualize and Optimize Space–Time–Workforce Tradeoff
The COVID pandemic has given rise to the necessity of social distancing regulations, which has brought the importance of workspace management on the construction site to an unprecedented level. Understanding and visualizing the interaction and tradeoff among space, time, and workforce is critical for construction managers to schedule and deliver projects on time. Therefore, the objectives of this research are to investigate how the critical path method (CPM) and Takt-time planning methods utilize space, time, and workforce differently, develop a tool to visualize the space–time–workforce interactions, and investigate the space–time–workforce tradeoff based on different managers’ preferences. This research selected a high-rise office building project and collected 889 sets of productivity data of five specialty trades. The research built a simulation model to investigate productivity and project performance under 267 scenarios of different combinations of the three resources. A dynamic tool was then developed to visualize workspace, time, and workforce interactions. Finally, a Choquet integral–based evaluation and decision tool was developed. The simulation results show that the Takt-time planning method can reduce up to 80% of workspace overlap compared with the actual production plan with less than 20% of duration extension. The contributions to the body of knowledge are (1) creating a visual framework for managers to understand the interaction and tradeoff among space, time, and workforce quickly and accurately, and (2) developing an innovative Choquet integral approach for managers to evaluate planning strategies according to project preferences. The framework and analysis method can be adapted to other construction projects to assist managers to visualize and optimize the space–time–workforce tradeoff under uncertain project drivers.
- 30 May 2022
- Published by Springer Nature
- p. 363-373
Situation Awareness Based Smart Contract for Modular Construction
- 30 May 2022
- Published by Springer Nature
- p. 363-373
Situation Awareness Based Smart Contract for Modular Construction