Skip to main content
ICTD 2024 Main banner
Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.

Abstract for presentation (Poster or Podium)

Intelligent Transportation Systems

Predicting Incident Duration & Clearance time on LA Urban Interstates through ML models

Monday, June 17, 2024
1:30 PM - 2:45 PM ET
Room: Galleria

    Primary Author(s)

  • Waseem Akhtar Khan, MS

    Graduate Research Assistant
    University of Louisiana at Lafayette
    Lafayette, LA, United States

    • Presenter(s)

  • Waseem Akhtar Khan, MS

    Graduate Research Assistant
    University of Louisiana at Lafayette
    Lafayette, LA, United States

    • Co-Author(s)

  • MM

    Milhan Moomen, PhD

    Assistant Professor, Research
    Louisiana Transportation Research Centre
    Baton Rouge, Louisiana, United States

    • Presenter(s)

  • MM

    Milhan Moomen, PhD

    Assistant Professor, Research
    Louisiana Transportation Research Centre
    Baton Rouge, Louisiana, United States

    • Co-Author(s)

  • MR

    M. Ashifur Rahman, PhD (he/him/his)

    Research Associate
    Louisiana Transportation Research Centre
    Baton Rouge, LA, United States

  • AK

    Adnan Khan, MS

    Graduate Research Assistant
    Southeast University
    Nanjing, Jiangsu, China (People's Republic)

  • JC

    Julius Codjoe, PhD, PE

    Special Studies Research Administrator
    Louisiana Transportation Research Centre
    Baton Rouge, Louisiana, United States

    • Submitter(s)

  • WK

    Waseem Akhtar Khan, MS

    University of Louisiana at Lafayette
    Lafayette, Louisiana, United States

Abstract:

Traffic crashes contribute significantly to non-recurrent congestion thereby increasing delay. It is therefore no surprise that traffic managers are constantly assessing strategies to mitigate the impacts of traffic crashes. To this end, it is important to have tools that enable accurate prediction of incident duration. It is also necessary to understand factors that affect incident duration for traffic crashes. To achieve these objectives, this study employed a complementary approach to predict and analyze factors that affect incident clearance time (ICT). Prediction models for crash-related ICT using different machine learning models were developed as a first step. The machine learning models utilized were Extreme Gradient Boosting (XGBoost), Random Forest (RF), Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP). The results of the analysis suggested that XGBoost outperformed the other machine learning models in this study based on several measures of prediction accuracy. Full parametric Weibull, log-logistic and lognormal Hazard-Based Duration Models (HBDMs) were also estimated to assess the influence of several factors on ICT. These models considered both fixed and random parameters. The results showed that the random parameters lognormal model had a better fit to the data in comparison to the other HBDMs considered. Variables related to heavy vehicles, road departure, hospitalization of crash victims, rescue, and alcohol/drugs significantly increased ICT. The results of this study are useful for traffic incident management agencies to develop and implement strategies that lead to reduced incident duration, congestion, pollution, and the risk of secondary crashes and economic losses. 

Learning Objectives:

Attendees can expect to learn the following from this session:
  • conduct and assess the efficacy of machine learning (ML) models in making incident clearance time (ICT) reliable predictions.
  • develop reliable ICT prediction models utilizing ML strategies like extreme gradient boosting (XGBoost), random forest (RF), support vector regression (SVR), and multi-layer perceptron neural network (MLP).
  • Analyze the impact of variables such as heavy vehicles, road departure, hospitalization, rescue, and drug/ alcohol use on ICT using Hazard-Based Duration Models (HBDMs).