Shorta??term traffic flow prediction in urban area remains a difficult yet important problem in intelligent transportation systems. Current spatioa??temporala??based urban traffic flow prediction techniques trend aims to discover the relationship between adjacent upstream and downstream road segments using specific models, while in this paper, we advocate to exploit the spatial and temporal information from all available road segments in a partial road network. However, the available traffic states can be high dimensional for higha??density road networks. Therefore, we propose a spatioa??temporal variable selectiona??based support vector regression (VSa??SVR) model fed with the higha??dimensional traffic data collected from all available road segments. Our prediction model can be presented as a twoa??stage framework. In the first stage, we employ the multivariate adaptive regression splines model to select a set of predictors most related to the target one from the higha??dimensional spatioa??temporal variables, and different weights are assigned to the selected predictors. In the second stage, the kernel learning method, support vector regression, is trained on the weighted variables. The experimental results on the reala??world traffic volume collected from a suba??area of Shanghai, China, demonstrate that the proposed spatioa??temporal VSa??SVR model outperforms the statea??ofa??thea??art. Copyright ?? 2015 John Wiley & Sons, Ltd.
展开▼
