Date of Award


Document Type


Degree Name

Master of Science (MS)

Legacy Department

Civil Engineering

Committee Member

Mashrur Chowdhury

Committee Member

Jim Martin

Committee Member

Yongxi (Eric) Huang


In this research, a novel framework was developed, using connected vehicle technology (CVT) integrated with the artificial intelligence (AI) paradigm, to improve the accuracy of real-time traffic condition assessment. Traffic density is a major indicator of traffic conditions, and the loop detector system has been widely used to estimate traffic density. To compare the effectiveness of the integrated CVT-AI method over the traditional loop detector density estimation algorithm, a simulated network of Interstate 26 in South Carolina was evaluated. In the proposed real-time traffic condition assessment framework, vehicle generated data collected by vehicle on-board units were forwarded to the roadside units for processing. Two distinct AI paradigms, Support Vector Machine and Case-based Reasoning, were evaluated to ensure sufficient accuracy of the processed data to estimate density in a freeway network. In addition to the density estimation, a detailed benefit-cost analysis was conducted to compare benefits of the integrated CVT-AI method over the loop detector density estimation system. This study revealed that the AI-aided CVT provided a minimum 85% accurate of density information when the connected vehicle penetration level was 50% or more. Compared to a loop detector density estimation algorithm, the developed method (CVT-AI) provided a greater accuracy in assessing traffic conditions. This study also demonstrated that the integrated CVT-AI method yielded a higher accuracy with an increasing penetration level of connected vehicles. A benefit-cost analysis indicated that this AI-facilitated CVT method produced higher return on investment compared to a loop detector based density estimation system. Once implemented, the developed CVT-AI based density estimation method will reduce the current use of traditional roadway sensor based density estimation systems.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.