Predicting driving direction with weighted markov model
Contribuinte(s) |
Zhou, Shuigeng Zhang, Songmao Karypis, George |
---|---|
Data(s) |
01/01/2012
|
Resumo |
Driving direction prediction can be useful in different applications such as driver warning and route recommendation. In this paper, a framework is proposed to predict the driving direction based on weighted Markov model. First the city POI (Point of Interesting) map is generated from trajectory data using weighted PageRank algorithm. Then, a weighted Markov model is trained for the near term driving direction prediction based on the POI map and historical trajectories. The experimental results on real-world data set indicate that the proposed method can improve the original Markov prediction model by 10% at some circumstances and 5% overall.<br /> |
Identificador | |
Idioma(s) |
eng |
Publicador |
Springer |
Relação |
http://dro.deakin.edu.au/eserv/DU:30083690/huang-predictingdriving-2013.pdf http://dro.deakin.edu.au/eserv/DU:30083690/huang-predictingdriving-evid-2013.pdf http://www.dx.doi.org/10.1007/978-3-642-35527-1_34 |
Direitos |
2013, Springer |
Palavras-Chave | #driving direction prediction #trajectory mining #weighted PageRank |
Tipo |
Conference Paper |