Latent Space Model for Road Networks to Predict Time-Varying Traffic
Dingxiong Deng*, USC; Cyrus Shahabi, USC; Ugur Demiryurek, ; Linhong Zhu, ; Rose Yu, University of Southern Cal; Yan Liu,
Real-time trafﬁc prediction from high-ﬁdelity spatiotemporal trafﬁc sensor datasets is an important problem for intelligent transportation systems and sustainability. However, it is challenging due to the complex topological dependencies and high dynamism associated with changing road conditions. In this paper, we pro-pose a Latent Space Model for Road Networks (LSM-RN) to ad-dress these challenges holistically. In particular, given a series of road network snapshots, we learn the attributes of vertices in latent spaces which capture both topological and temporal properties. As these latent attributes are time-dependent, they can estimate how trafﬁc patterns form and evolve. In addition, we present an incremental online algorithm which sequentially and adaptively learns the latent attributes from the temporal graph changes. Our frame-work enables real-time trafﬁc prediction by 1) exploiting real-time sensor readings to adjust/update the existing latent spaces, and 2) training as data arrives and making predictions on-the-ﬂy. By con-ducting extensive experiments with a large volume of real-world trafﬁc sensor data, we demonstrate the superiority of our frame-work for real-time trafﬁc prediction on large road networks over competitors as well as baseline graph-based LSM’s.
Filed under: Mining Rich Data Types