Accurate prediction of traffic congestion at the granularity of road segment is important for planning travel routes and optimizing traffic control in urban areas. Previous works often calculated only the average congestion levels of a large region covering many road segments and did not take into account spatial correlation between road segments, resulting in inaccurate and coarse-grained prediction. To overcome these issues, we propose in this paper CPM-ConvLSTM, a spatiotemporal model for short-term prediction of congestion level in each road segment. Our model is built on a spatial matrix which incorporates both the congestion propagation pattern and the spatial correlation between road segments. The preliminary experiments on the traffic data set collected from Helsinki, Finland prove that CPM-ConvLSTM greatly outperforms 6 counterparts in terms of prediction accuracy.

GPS sensors have been widely used to track people's everyday life trajectories, generating massive trajectory datasets. The trajectory data typically contains sparse GPS points, and completing trajectories is often necessary. State-of-the-art methods [3, 4] essentially complete the entire route by using a single metric, e.g., either the shortest distance or the fastest driving/walking time. Unfortunately, using a single metric may not always work in real life due to the diversity of mobility patterns. In this demo abstract, we propose a frequent pattern (FP)-based trajectory completion approach, and demonstrate a system prototype to showcase the advantages of our approach over four previous works, in terms of accuracy and running time.