Name
Abstract | ||
|---|---|---|
It is believed that the evolution of traffic status follows certain temporal-spatial rules and patterns, and the challenge is to extract such patterns from mass traffic data. In this paper, the traffic status of multiple links in a certain region is considered. Self-Organizing Maps (SOMs) are applied to organize flow data of links into physically relevant clusters, with each cluster representing one pattern. The clustering results are then interpreted using several exploratory methods which utilize the SOM's advantages of topological preservation and easy visualization. Case studies on real-world data reveal some meaningful phenomena and rules of regional traffic status, which prove the effectiveness of our approaches. © 2006 IEEE. |
Year | DOI | Venue |
|---|---|---|
2006 | null | Toronto, Ont. |
Keywords | Field | DocType |
mathematical models,traffic flow,self organizing map | Data mining,Cluster (physics),Traffic flow,Visualization,Pattern clustering,Road traffic,Self-organizing map,Artificial intelligence,Engineering,Cluster analysis,Machine learning | Conference |
Volume | Issue | ISSN |
null | null | null |
ISBN | Citations | PageRank |
1-4244-0094-5 | 8 | 0.94 |
References | Authors | |
1 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chen, Yudong | 1 | 1044 | 55.41 |
| Zhang Yi | 2 | 261 | 43.00 |
| Jianming Hu | 3 | 162 | 21.14 |
| Danya Yao | 4 | 98 | 17.42 |