Name
Abstract | ||
|---|---|---|
We present a generic framework for spatio-temporal (ST) data modeling, analysis, and forecasting, with a special focus on data that is sparse in both space and time. Our multi-scaled framework is a seamless coupling of two major components: a self-exciting point process that models the macroscale statistical behaviors of the ST data and a graph structured recurrent neural network (GSRNN) to discover the microscale patterns of the ST data on the inferred graph. This novel deep neural network (DNN) incorporates the real time interactions of the graph nodes to enable more accurate real time forecasting. The effectiveness of our method is demonstrated on both crime and traffic forecasting. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Learning | Graph,Data modeling,Spacetime,Point process,Microscale chemistry,Recurrent neural network,Temporal database,Artificial intelligence,Artificial neural network,Mathematics,Machine learning |
DocType | Volume | Citations |
Journal | abs/1804.00684 | 2 |
PageRank | References | Authors |
0.39 | 9 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bao Wang | 1 | 11 | 2.55 |
| Xiyang Luo | 2 | 17 | 5.09 |
| Fangbo Zhang | 3 | 5 | 0.81 |
| Baichuan Yuan | 4 | 3 | 3.46 |
| Andrea L. Bertozzi | 5 | 486 | 61.55 |
| P. Jeffrey Brantingham | 6 | 51 | 7.56 |