Machine Learning algorithms for Demand and Turning Movement Count Prediction

Posted March 9, 2020 in Infrastructure and the Built Environment

Principal Investigator: Sanjay Ranka

Sponsor: Florida Department of Transportation

Start Date: June 26, 2018

End Date: June 30, 2020

Amount: $225,758

Abstract

Turning movement counts (TMC) have been the industry standard input for traffic signal warrants, intersection design, and signal timing plans for decades. Traditionally, these applications only require a sample of data for a small time period at a single intersection.

Meanwhile, there have been several advances in traffic control technologies and applications that are driving additional needs for continuous, real-time, quality TMC data. These technologies include:

  • Adaptive control technologies – these systems dynamically change the signal phasing pattern locally at an intersection based on traffic demand.
  • Regional Integrated Corridor Management System (R-ICMS) – this system will perform a mesoscopic simulation of the network using TMCs to validate the improvement to the network if a diversion route response plan is implemented or an optimized set of signal timing plans are deployed.
  • Miscellaneous – There have been several requests for TMC data for various traffic studies and ongoing research whose need cannot be met by dispatching a traffic counts crew to an intersection for a sampling of data.

These applications have introduced additional traffic data needs beyond what has been provided with the traditional TMC data collection efforts.