An artificial intelligence platform for network-wide congestion detection and prediction using multi-source data

With the rapid growth of urban populations, traffic problems are getting worse, as indicated by increased traffic congestion. As a result, congestion detection and prediction analysis tools are essential for understanding the challenges and identifying solutions to the related issues. Recently, artificial intelligence (AI) has become one of the forefront technologies applied for developing smart cities. However, the application of AI technologies, especially deep learning, is still in its early stage in transportation area. The PI’s research team has already established an on-line transportation platform, Digital Roadway Interactive Visualization and Evaluation Network (DRIVE Net), for data sharing, integration, visualization, and analysis. The proposed research aims to extend the functions of DRIVE Net to develop an artificial intelligence platform for network-wide congestion detection and prediction using multi-source data. The Microsoft Trusted Data Platforms are employed to build the new database and implement sound data management. The AI platform architecture is redesigned with new models which can support network-wide analysis for identifying solutions for traffic congestion.

Language

  • English

Project

Subject/Index Terms

Filing Info

  • Accession Number: 01665933
  • Record Type: Research project
  • Source Agency: Connected Cities for Smart Mobility towards Accessible and Resilient Transportation Center (C2SMART)
  • Files: UTC, RiP
  • Created Date: Apr 11 2018 7:52PM