Publication Date

8-2024

Date of Final Oral Examination (Defense)

5-20-2024

Type of Culminating Activity

Thesis

Degree Title

Master of Engineering in Civil Engineering

Department Filter

Civil Engineering

Department

Civil Engineering

Supervisory Committee Chair

Mandar Khanal, Ph.D.

Supervisory Committee Member

Mojtaba Sadegh, Ph.D.

Supervisory Committee Member

Kyungduk Ko, Ph.D.

Abstract

Turning Movement (TM) counts at intersections are crucial for several reasons. There has been extensive research on this topic throughout the history of traffic research, which reflects its importance in transportation engineering and urban planning. It can be said that one of the most significant applications of TMs is signal timing at intersections. Signal timing design requires data on the turning decisions of vehicles that travel through intersections to allow enough time for each movement at the intersection. Most of organizations around the USA are still applying traditional methods for collecting TM data, such as manual counts. These methods are not only costly and time-intensive but also do not provide real-time data. There have been alternative techniques used by a few organizations, such as video image processing that enables the near-real-time collection of approach volumes and turning movements. However, these methods require expensive, specialized equipment at the intersection, which limits their widespread use. As a result, manual counting has remained the predominant method for collecting TM data at intersections.

This study investigates two methods that can serve as alternatives to manual counting at intersections. The first method is to apply cutting-edge Connected Vehicle (CV) data to identify TMs at intersections. The second is to use Machine Learning (ML) methods as an alternative to manual counting.

Regarding the first method, which uses CV data, trajectories of vehicles through an intersection can be constructed and TMs can be obtained. However, because of the low number of CVs in the traffic stream, it is imprecise to consider TM data from CVs as representative of the whole traffic flow. To address this issue, a Kalman filter (KF) for estimating TM rates at intersections based on CV data under low market penetration levels was developed. Commercially available connected vehicle data was used to develop this study. This method is independent of intersection geometry or the presence of shared lanes. The algorithm was evaluated using data from an intersection in Salt Lake City, Utah. The manually collected TM counts at this intersection were compared with the raw CV data as well as the results obtained from the developed methodology. The comparison shows that while TM counts based on raw CV data show severe violations in accuracy, making them unreliable, the method developed in this research gives results that have much lower accuracy violations.

The procedure described in the second study endeavors to harness the power of ML techniques by training them on approach volume data. The objective is to discern the intricate relationship between approach volumes and the corresponding turning movements. The goal of this research is to create an estimation model for TMs based on data obtained from manual counts conducted at around 400 intersections located in Ada County, Idaho. This model takes three key inputs into account: approach volumes, intersection type, and lane configuration of intersection approaches. Its output is the predicted TM counts for any given intersection. The results indicate that the developed multi-output regression ML approach has a remarkable capability for accurately forecasting TMs. The proposed approach holds the potential to serve as a valuable platform for the utilization of approach volume data to estimate turning movements. By leveraging ML techniques, it can facilitate TM prediction using approach volume data that are routinely collected using automated methods. Using the methods described here transportation agencies will no longer need to employ crews to collect TM data at intersections.

DOI

https://doi.org/10.18122/td.2274.boisestate

Download

Share

COinS