Focus Area
Transportation Systems Management & Operations
Submitting On Behalf Of
TRB Committee on Freeway Operations
Urgency
Critical - High Priority
Cost
$250,000 - 499,000
Timeframe
1 - 2 years
Type of Research
Full Research Project
Date Posted
Jul 16, 2021
Status
Not Funded

Research Description

There is a need to improving machine learning capacity in order to achieving full or nearly full DSS automation. Decision Support System (DSS) has been approved to be one of effective tools in supporting integrated corridor management (ICM). The traditional DSS systems in supporting ICM commonly used traditional technologies such as data fusion and decision tree. The advanced development of machine learning (ML) and deep learning base Artificial Intelligence (AI) methodologies and algorithms provide new improving spaces of DSS enhancements.

Additional Supporting Information

To achieve robust ML and AI capabilities, there are many issues desired in-deep researches, such as • Sustainability of ML algorithms. – Most of the existing ML algorithms might be only working for certain dataset and will low it performance in dealing with living data environments. Decent questions need to answer such as, how long the models need to be re-trained, etc. • Distributed and collaborative AI capability. – ICM is normally a complex system with widely deployed device and data sources integration. • Deployment efficiency. – How to rapidly deploy matured ML technologies and what’s the potential standards and guidance for data preparing and models training? • How to incorporation of ML models with living simulation systems in supporting ICM functions.


Submitted By
Jim Katsafanas
Michael Baker International
412-269-4635

Attachments

This idea has no attachments.

Comments

Join the Discussion

You can make your thoughts known by commenting, and by rating the idea and other comments. All you need to do is sign in, or register for an account with us!