Abstract
dc:description.abstractIn 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.
Degree
thesis:*- Name thesis:degree_name
- Master of Science (MS)
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- Civil Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Khan, Sakib Mahmud
- Contributors dc:contributor
-
- Mashrur Chowdhury
- Jim Martin
- Yongxi (Eric) Huang
Subjects
dc:subject × 6Identifiers
dc:identifier.*- Repository record dc:identifier
- https://open.clemson.edu/all_theses/2116