Abstract
Probe vehicles equipped with GPS can be used
to permanently collect traffic speed information for an entire
road network, and the statistical mean value of link speeds
collected over time is often used as an estimator for mid-term
predictions. For road links with sparse probe vehicle data, the
estimated mean may be too inaccurate due to the low sample
size, and speeds for road links with missing probe vehicle
data must be imputed from other data. This paper proposes
to apply a Gaussian-mixture based technique to increase the
robustness of speed estimates. Typical shapes of the diurnal
speed curve are learnt from historical data of all links in the
road network. The model is able to provide robust estimates of
mean speed curves based on only a few available observations
and drastically reduces the amount of data needed to store
them by 95 %. Experimental results on a comprehensive set of
857527 day speed curves show that the predictions are superior
to traditional approaches based on aggregated or disaggregated
historical mean values.
Original language | English |
---|---|
Title of host publication | Proceedings 15th IEEE Intelligent Transportation Systems Conference |
Number of pages | 6 |
Publication status | Published - 2012 |
Event | Intelligent Transportation Systems Conference 2012 - Duration: 16 Sept 2012 → 19 Sept 2012 |
Conference
Conference | Intelligent Transportation Systems Conference 2012 |
---|---|
Period | 16/09/12 → 19/09/12 |
Research Field
- Former Research Field - Mobility Systems