Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Sequential forecast of incident duration using Artificial Neural Network models.

Chien-Hung Wei¹, Ying Lee

¹Department of Transportation and Communication Management Science, National Cheng Kung University, 1 Ta-Hsueh Rd., Tainan 70101, Taiwan, ROC.

Accident; Analysis and Prevention

|February 17, 2007

Summary

This study introduces adaptive Artificial Neural Network models for sequential incident duration forecasting. These models provide reliable real-time duration estimates, aiding travelers and traffic management in Intelligent Transportation Systems.

Related Concept Videos

Steps in Outbreak Investigation

Steps in Outbreak Investigation

In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Retired contact sports athletes with cognitive concerns: promoting lifelong brain health.

Practical neurology·2025

Same author

Midlife plasma proteomic profiles indicate altered amyloid and tau processing in former elite rugby players.

Journal of neurology, neurosurgery, and psychiatry·2025

Same author

Brain health concerns in former rugby players: clinical and cognitive phenotypes.

Brain : a journal of neurology·2025

Same author

Biomarker evidence of neurodegeneration in mid-life former rugby players.

Brain : a journal of neurology·2025

Same author

Bringing PERT to Pediatrics: Initial Experience and Outcomes of a Pediatric Multidisciplinary Pulmonary Embolism Response Team (PERT).

Chest·2024

Same author

Social contagion of challenge-seeking behavior.

Journal of experimental psychology. General·2024

Area of Science:

Transportation Engineering
Artificial Intelligence
Traffic Management

Background:

Accurate prediction of traffic incident duration is crucial for effective traffic management and traveler information.
Existing methods often lack adaptivity and real-time updating capabilities for incident duration forecasting.

Purpose of the Study:

To develop an adaptive procedure for sequential forecasting of traffic incident duration.
To integrate Artificial Neural Network (ANN) models with data fusion techniques for improved duration prediction.
To provide timely and accurate incident duration estimates for travelers and traffic management units.

Main Methods:

Development of two adaptive ANN-based models (Model A for initial forecast, Model B for multi-period updates).

Related Experiment Videos

Utilization of data fusion techniques to combine predictions from both models.

Inclusion of diverse input data: incident characteristics, traffic data, time/space gaps, and geometric characteristics.

Main Results:

The proposed models achieved a mean absolute percentage error (MAPE) mostly under 40% for forecasted incident duration.
Sequential forecasting capability from incident notification to road clearance was demonstrated.
Feasibility of the models within the Intelligent Transportation Systems (ITS) context was confirmed.

Conclusions:

The adaptive ANN models offer a feasible and effective solution for sequential incident duration forecasting.
Real-time duration estimates enhance situational awareness for travelers and traffic management.
The developed procedure shows significant potential for improving traffic incident management in ITS environments.