Use of density-based cluster analysis and classification techniques for traffic congestion prediction and visualisation
The field of Intelligent Transportation Systems has lately raised increasing interest due to its high socio-economic impact. This work aims on developing efficient techniques for traffic congestion prediction and visualisation. We have designed a simple, yet effective and scalable model to handle sparse data from GPS observations and reduce the problem of congestion prediction to a binary classification problem (jam, non-jam). An attempt to generalise the problem is performed by exploring the impact of discriminative versus generative classifiers when employed to produce results in a 30-minute interval ahead of present time. In addition, we present a novel congestion prediction algorithm based on using correlation metrics to improve feature selection. Concerning the visualisation of traffic jams, we present a traffic jam visualisation approach based on cluster analysis that identifies dense congestion areas.
-
-
Corporate Authors:
14-20 bd Newton, Cité Descartes, Champs su Marne
77447 Marne la Vallée, France Cedex 2 -
Authors:
- Diamantopoulos, T
- Kehagias, D
- König, F G
- Tzovaras, D
-
Conference:
- Transport Research Arena (TRA) 5th Conference: Transport Solutions from Research to Deployment
- Location: Paris , France
- Date: 2014-4-14 to 2014-4-17
- Publication Date: 2014-4
Language
- English
Media Info
- Pagination: 10p
- Monograph Title: Transport Research Arena (TRA) 2014 Proceedings
Subject/Index Terms
- TRT Terms: Data analysis; Forecasting; Highway traffic control; Intelligent transportation systems; Traffic congestion; Traffic density
- ATRI Terms: Data analysis; Forecast; Intelligent transport systems (ITS); Traffic concentration; Traffic congestion; Traffic management
- ITRD Terms: 8735: Intelligent transport system
- Subject Areas: Operations and Traffic Management;
Filing Info
- Accession Number: 01530706
- Record Type: Publication
- Source Agency: ARRB
- Files: VTI, TRIS, ATRI
- Created Date: Jul 23 2014 12:54PM