摘要: |
To improve the quality and effectiveness of the Texas surface transportation system, it is important to be able to predict where and when prolonged congestion will start and how it will spread, as well as to track atypical events and estimate their evolution. Artificial intelligence (AI) approaches provide a unique opportunity to estimate precise congestion measures by utilizing data from agency-owned sensors, third-party providers, and big enterprise data. This project envisions to mitigate the current research gap by conducting two major project phases. The first phase can confirm the validity of commercial data sources for planning and operations, while the second involves understanding which AI models/ algorithm are the most suitable for addressing TxDOT needs based on desirable use cases and data availability. Furthermore, it is important to analyze the required data models and workflows to determine whether it is sustainable to train, test, and validate the proposed AI techniques. The research teams understand that achieving the research goals requires a comprehensive analysis and documentation of commercial big data platforms and datasets, appropriate AI algorithms, and robust prototype tool to foster return on investment (ROI) and reduce freeway congestion. |