Search research articles

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Metal-Free Doping Strategies in Two-Dimensional Carbon Nitride C<sub>4</sub>N<sub>2</sub> for Enhanced Hydrogen Evolution Catalysis.

ACS omega·2025

Same author

Evaluation of Cluster Algorithms for Radar-Based Object Recognition in Autonomous and Assisted Driving.

Sensors (Basel, Switzerland)·2024

Same author

Functionalized few-layer silicene nanosheets: stability, elastic, structural, and electronic properties.

Physical chemistry chemical physics : PCCP·2022

Same author

Elastic anomalies in a spin-crossover system: ferropericlase at lower mantle conditions.

Physical review letters·2013

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 Video

Updated: Jul 11, 2025

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Automatic Calibration of Microscopic Traffic Simulation Models Using Artificial Neural Networks.

Rodrigo F Daguano¹, Leopoldo R Yoshioka¹, Marcio L Netto¹

¹Department of Electronic Systems Engineering, Escola Politécnica da Universidade de São Paulo, São Paulo CEP 05508-010, SP, Brazil.

Sensors (Basel, Switzerland)

|November 14, 2023

Summary

This study introduces an automated method using artificial neural networks (ANNs) to calibrate traffic simulation parameters. The approach accurately mimics real-world traffic conditions, improving urban mobility planning.

Keywords:

artificial neural network automatic simulation calibration microsimulation traffic models

More Related Videos

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Related Experiment Videos

Last Updated: Jul 11, 2025

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Area of Science:

Transportation Engineering
Artificial Intelligence
Urban Planning

Background:

Microscopic traffic simulation models are crucial for urban mobility planning and operation.
Manual calibration of simulation parameters is time-consuming and lacks systematic methodology.
Accurate calibration is essential for effective traffic simulation to mirror real-world scenarios.

Purpose of the Study:

To propose and evaluate a novel methodology for the automatic calibration of traffic simulation parameters.
To leverage artificial neural networks (ANNs) for learning and optimizing simulation model behavior.
To enhance the efficiency and accuracy of traffic simulation calibration for urban mobility studies.

Main Methods:

Developed a methodology using Multi-Layer Perceptron (MLP) artificial neural networks trained with back-propagation.
Trained the MLP to learn transport network behavior and optimize simulation parameters.
Tested the methodology on microscopic traffic models in São Paulo, Brazil, using Wiedemann 74 and 99 psychophysical models and various back-propagation algorithms (SGD, Adam, Adagrad, etc.).

Main Results:

The proposed ANN-based methodology achieved accurate and efficient calibration, with correlation coefficients exceeding 0.8 for parameters with significant network effects (travel times, vehicle counts, average speeds).
For psychophysical parameters in the simplified Wiedemann 74 model, the correlation coefficient surpassed 0.7.
The system demonstrated effectiveness across different MLP configurations and back-propagation training methods.

Conclusions:

Artificial neural networks provide a systematic and automated approach to calibrating traffic simulation parameters.
This method significantly improves the ability of traffic engineers to conduct comprehensive studies on diverse future scenarios.
The automated calibration facilitates more robust urban mobility planning and operational strategies.