| Title | Signal System Data Mining |
|---|---|
| Record ID | 23527 |
| Personal Name Creator |
Hauser, Trisha; Scherer, William T.; Smith, Brian L., 1967- |
| Source | Final report of ITS Center project: Signal system data mining |
| Corporate Contributor |
University of Virginia. Center for Transportation Studies; National ITS Implementation Research Center (Va.) |
| Publisher | University of Virginia. Center for Transportation Studies |
| Publication Date | 20000900 |
| Language | English |
| Abstract | Intelligent transportation systems (ITS) include large numbers of traffic sensors that collect enormous quantities of data. The data provided by ITS is necessary for advanced forms of control, however basic forms of control, primarily time-of-day (TOD) which are prevalent in the United States do not directly rely on the data. Thus sensor data is typically unused and discarded in this country. The sensor data is in fact capable of providing abundant amounts of information that can aid in the development of improved TOD signal timing plans. Data mining tools are necessary to extract the information necessary from the data to improve on timing plan development and in turn would allow the timing plan development and monitoring process to be automated. This paper describes a research program that is investigating the application data mining tools, including statistical clustering and classification techniques to aid in the development of traffic signal timing plans. Specifically, a case study was conducted that illustrated that the use of Hierarchical Cluster analysis can be used to identify temporal interval break points that support the design of a time-of-day (TOD) signal control system. The cluster analysis approach was able to utilize a high resolution system state definition that takes full advantage of the extensive set of sensors deployed in a traffic signal system. Finally, the case study also demonstrated that a Classification and Regression Tree (CART) could be developed that can be used to automatically monitor the quality of TOD intervals as traffic conditions change through time. The results of this research indicate that advanced data mining techniques hold high potential to provide automated techniques that assist traffic engineers in signal control system design and operations. |
| Rosap ID | dot:5456 |
| Rosap URL | https://rosap.ntl.bts.gov/view/dot/5456 |
| TRT Terms | Traffic signal timing; Traffic engineers; Traffic signal control systems; Periods of the day; Data mining; Cluster analysis; Statistical analysis; Research; Development; Monitoring; Implementation; Traffic signal intervals; Case studies |
| General Subjects | Classification and Regression Tree (CART); Clustering; Northern Virginia; Sensor data; Time-of-day (TOD) |
| Classification | NTL - OPERATIONS AND TRAFFIC CONTROLS - OPERATIONS AND TRAFFIC CONTROLS |
| Geographical Coverage |
United States |
| Report Number | UVA-CE-ITS_01-3 |
| Resource type | Tech Report |
| URL | https://ntlrepository.blob.core.windows.net/lib/23000/23500/23527/paper-Smith-SignalSystemData.pdf |
| Format | |
| Database | NTL Digital Repository |