About

Dr. Edward Jaselskis is the Jimmy D. Clark Distinguished Professor in the Department of Civil, Construction, and Environmental Engineering at North Carolina State University. He holds a BS in general engineering from the University of Illinois, an MS in civil engineering with an emphasis in construction engineering and project management from MIT, and a PhD in civil engineering with a similar emphasis from the University of Texas at Austin. His professional experience includes work as a cost and schedule engineer for ExxonMobil, a field engineer on an open pit coal mine project in Colombia, and roles at Perkins and Will as an electrical designer and at Bechtel as a civil field engineer. Dr. Jaselskis has served as a program director for the National Science Foundation and as director for the Engineering Policy and Leadership Institute, as well as professor-in-charge of the construction program at Iowa State University. He is a registered professional engineer in Iowa and a member of several professional organizations, including the American Society of Civil Engineering, the Construction Institute, and the National Academy of Construction. His research interests focus on determinants of construction project success and innovative construction technologies aimed at improving jobsite productivity. He has conducted research funded by federal, state, and industrial sponsors, exploring topics such as construction project success, advanced information technologies, RFID technology for personnel tracking, and project performance assessment.

Research topics

• Engineering
• Business
• Medicine
• Political Science
• Computer Science
• Physical therapy
• Surgery
• Forensic engineering
• Public relations
• Economics
• Risk analysis (engineering)
• Economic growth
• Marketing
• Process management
• Knowledge management
• Medical emergency

Selected publications

• Relationship between project performance and accidents

  2026-01-23

  book-chapter

  This paper explores relationships between project performance characteristics and the timing and frequency of construction accidents. Accident data (e.g., first aid case rate and recordable rate) were superimposed over standard project control s-curves related to design, procurement, and construction activities (e.g., % design complete and % actual construction cost) on a project-by-project basis and trends were observed. Relevant data were collected for seventeen industrial projects from the start of detailed design to the end of construction. General information associated with the projects (e.g., size and type of contracting approach) was also obtained. Results show that projects that were consistently behind schedule and over budget experienced a greater occurrence of recordable accidents. Knowing the relationships between project control s-curve profiles and safety performance is beneficial for safety representatives as it will give them an advanced warning of the timing and frequency of accidents that may occur on their projects. Safety representatives can better focus their worker safety programs during the different phases of construction and this can lead to fewer accidents. Limitations and recommendations are also included.

  PublisherDOI

• A Novel Edge Computing Framework for Construction Nail Detection under Conditions of Constrained Computing Resources

  2025-12-11

  articleSenior authorCorresponding

  Construction housekeeping promotes a safe working environment but often lacks an effective approach for monitoring and maintenance. Recent research has used artificial intelligence (AI) techniques to detect construction objects automatically to facilitate the work of safety managers. However, none of the research has considered implementing real-time AI applications for automatic construction housekeeping monitoring. We propose a framework that integrates edge computing and a computer vision model to detect boards with nails that may be scattered throughout construction sites. First, we trained a MobileNet machine learning (ML) model to identify boards with or without nails. Then, we quantized the model using TensorFlow Lite to allow the model’s optimal deployment in edge devices. Lastly, we assembled an edge device module based on Raspberry Pi and embedded the ML model to realize real-time offline housekeeping monitoring. The experimental results show great promise for both lab settings and in practice at construction sites. The proposed framework can facilitate AI applications in various construction fields under computing resource-constrained conditions.

  PublisherDOI

• Using an LLM-Powered Framework for Automatic Risk Identification and Mitigation from Past Claims and Supplemental Agreements

  Journal of Computing in Civil Engineering · 2025-11-25 · 1 citations

  article

  Examining historical claims and supplemental agreements (CSAs) can provide critical insights into the underlying factors driving project claims and change orders, thereby strengthening an organization’s overall risk management practices. However, thoroughly understanding these CSA descriptions and developing coherent risk taxonomies is both complex and time-consuming. Moreover, current methods for identifying appropriate mitigation strategies remain slow and inefficient. To address these challenges, this study presents a language model-powered framework, named Change to Mitigate (change2mitigate or C2M), that automates both the classification of risk categories and the generation of tailored mitigation strategies for historical CSAs. Specifically, bidirectional encoder representations from transformers (BERT)opic modeling is employed to cluster CSAs into major risk topics based on semantic content, after which a large language model (LLM) refines and enhances the representation of these risk categories. For mitigation, a multimodal retrieval-augmented generation (RAG)-enabled risk mitigation AI agent (RMAIA) leverages various transportation risk management databases, encompassing textual and visual resources such as best practices (BPs) and lessons learned (LL), to retrieve and synthesize effective response strategies. North Carolina State Department of Transportation bridge replacement projects are employed as pilot cases to test and validate the proposed framework. Our findings revealed that the top root causes for claims are utility relocation delays, closeout conference issues, and plan errors, whereas supplemental agreements (SAs) predominantly resulted from plan/design/method challenges, pavement issues, and underground utility complications. Validation results showed that the RMAIA can deliver timely multimodal mitigation solutions. Other transportation agencies can readily adapt this research to enhance their current risk management practices.

  PublisherDOI

• Strategic Web-Based Data Dashboards as Monitoring Tools for Promoting Organizational Innovation

  Buildings · 2025-06-24 · 3 citations

  articleOpen accessSenior author

  Knowledge extraction and sharing is one of the biggest challenges organizations face to ensure successful and long-lasting knowledge repositories. The North Carolina Department of Transportation (NCDOT) commissioned a web-based knowledge management program called Communicate Lessons, Exchange Advice, Record (CLEAR) for end-users to promote employee-generated innovation and to institutionalize organizational knowledge. Reusing knowledge from an improperly managed database is problematic and potentially causes substantial financial loss and reduced productivity for an organization. Poorly managed databases can hinder effective knowledge dissemination across the organization. Data-driven dashboards offer a promising solution by facilitating evidence-driven decision-making through increased information access to disseminate, understand and interpret datasets. This paper describes an effort to create data visualizations in Tableau for CLEAR’s gatekeeper to monitor content within the knowledge repository. Through the three web-based strategic dashboards relating to lessons learned and best practices, innovation culture index, and website analytics, the information displays will aid in disseminating useful information to facilitate decision-making and execute appropriate time-critical interventions. Particular emphasis is placed on utility-related issues, as data from the NCDOT indicate that approximately 90% of projects involving utility claims experienced one or two such incidents. These claims contributed to an average increase in project costs of approximately 2.4% and schedule delays averaging 70 days. The data dashboards provide key insights into all 14 NCDOT divisions, supporting the gatekeeper in effectively managing the CLEAR program, especially relating to project performance, cost savings, and schedule improvements. The chronological analysis of the CLEAR program trends demonstrates sustained progress, validating the effectiveness of the dashboard framework. Ultimately, these data dashboards will promote organizational innovation in the long run by encouraging end-user participation in the CLEAR program.

  PublisherOA PDFDOI

• Integrating Sensor-Empowered Federated Learning and Smart Contracts for Automatic Flood Risk Management

  2025-12-11

  articleSenior authorCorresponding

  This paper proposes a distributed computing framework that integrates federated learning (FL) and blockchain-enabled smart contracts for automatic flood response management. FL is deployed to process time series sensor data locally for separate sensor devices by training a machine learning (ML) model and then aggregating the trained model parameters obtained from each sensor device to yield final predictions in terms of rainfall levels. The predicted precipitation levels are input into a predefined smart contract to automatically trigger mitigation strategies to be used by frontline safety and maintenance personnel. The results obtained using the proposed framework demonstrate both improved prediction accuracy and data privacy preservation. The validation effort shows that smart contracts can execute context-aware actions, thus enabling fast decision-making for flood response. The developed framework holds the potential to revolutionize decentralized data management, enhance efficient data processing, and ensure data privacy, transparent and secure data communication, and resilience against centralized failures, thereby enabling a more intelligent infrastructure management system to mitigate flood impacts.

  PublisherDOI

• Toward the Development of a Fit-for-Purpose Handbook for the Upstream, Midstream, and Mining (UMM) Sector

  2024-03-18 · 2 citations

  articleCorresponding

  Projects in the upstream, midstream, and mining (UMM) sectors present unique complexity. The Construction Industry Institute’s (CII) Research Team 398 aimed at developing the criteria that define project complexity in the UMM sector, a matrix that describes the different levels of complexity and assign tools from the CII database that can be used to manage complexity. The eventual goal is to create a fit-for-purpose handbook for the UMM sector. This project is divided into phases; the first phase is to develop a complexity matrix for the UMM sector CII companies with more mature project management organizations. The team used convenience sampling and conducted interviews with owners and contractors for this purpose. The methodology also included reviewing literature from research into complexity, the characteristics of the UMM sector and incorporating the findings of other complexity models developed within and outside of CII. The result was a complexity matrix that includes factors relevant to all the three sectors. The vision for the next phase includes validating the current complexity matrix and identifying key information (“golden nuggets”) for addressing complexity.

  PublisherDOI

• Meet2mitigate: An Llm-Powered Framework for Real-Time Issue Identification and Mitigation from Construction Meeting Discourse

  SSRN Electronic Journal · 2024-01-01

  preprintOpen accessSenior author
  PublisherDOI

• Examining Contingency and Inflation Practices Within Several Departments of Transportation in the United States

  Transportation Research Record Journal of the Transportation Research Board · 2024-03-29 · 1 citations

  article

  Transportation projects are notorious, among both the public and transportation professionals, for missing their intended cost and schedule targets as a result of project complexity and uncertainties. The significant discrepancy between cost estimates and final project costs remains a major concern for state Departments of Transportation (DOTs). Several risk factors, including estimation errors and price fluctuations, contribute to these discrepancies and are typically managed by adding a contingency to project estimates. Cost escalation can also result from inadequate adjustment for inflation in estimates, given the current economic environment and the lengthy duration of major transportation projects. This paper summarizes how several state DOTs apply contingencies to mitigate the impact of certain risks and adjust their State Transportation Improvement Program (STIP) revenues and costs to account for inflation. The study surveyed 13 state DOTs to understand how contingencies are applied to the three major components of transportation projects (construction, right of way, and utilities). Additionally, interviews were conducted with 15 state DOTs to understand how they address inflation, particularly as it pertains to the STIP process. The results indicate that most DOTs apply contingency allowances to their project estimates during the early project development and maintain some level of contingency allowance at the plans, specifications, and estimate (PS&E) stage. As for addressing inflation, most state DOTs include inflation of the project cost in the project estimates to the time of bid letting or year of expenditure. The findings of this study can benefit state DOTs that are reassessing their strategies for implementing contingency and inflation within their STIP.

  PublisherDOI

• Meet2Mitigate: An LLM-powered framework for real-time issue identification and mitigation from construction meeting discourse

  Advanced Engineering Informatics · 2024-12-24 · 17 citations

  articleSenior author
  PublisherDOI

• Construction Jobsite Image Classification Using an Edge Computing Framework

  Sensors · 2024-10-13 · 7 citations

  articleOpen accessSenior author

  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.

  PublisherDOI

Frequent coauthors

• Abdullah Alsharef

  King Saud University

  44 shared

• Cliff Schexnayder

  Arizona State University

  30 shared

• Christine Fiori

  Drexel University

  30 shared

• Gerardo Chang Recavarren

  University of Piura

  29 shared

• Siddharth Banerjee

  ORCID

  29 shared

• Manuel Celaya

  27 shared

• Russell C. Walters

  Iowa State University

  26 shared

• Timothy C. Becker

  Arizona State University

  16 shared

Education

• Ph.D., Civil Engineering

  University of California, Berkeley

  1984

• M.S., Civil Engineering

  University of California, Berkeley

  1981

• B.S., Civil Engineering

  University of California, Berkeley

  1978

Awards & honors

• E.I. Clancy Distinguished Professor