Flow Prediction in Spatio-Temporal Networks Based on Multitask Deep Learning,IEEE Transactions on Knowledge and Data Engineering

当前位置： X-MOL 学术 › IEEE Trans. Knowl. Data. Eng. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Flow Prediction in Spatio-Temporal Networks Based on Multitask Deep Learning
IEEE Transactions on Knowledge and Data Engineering ( IF 8.9 ) Pub Date : 2020-03-01 , DOI: 10.1109/tkde.2019.2891537
Junbo Zhang , Yu Zheng , Junkai Sun , Dekang Qi

Predicting flows (e.g., the traffic of vehicles, crowds, and bikes), consisting of the in-out traffic at a node and transitions between different nodes, in a spatio-temporal network plays an important role in transportation systems. However, this is a very challenging problem, affected by multiple complex factors, such as the spatial correlation between different locations, temporal correlation among different time intervals, and external factors (like events and weather). In addition, the flow at a node (called node flow) and transitions between nodes (edge flow) mutually influence each other. To address these issues, we propose a multitask deep-learning framework that simultaneously predicts the node flow and edge flow throughout a spatio-temporal network. Based on fully convolutional networks, our approach designs two sophisticated models for predicting node flow and edge flow, respectively. These two models are connected by coupling their latent representations of middle layers, and trained together. The external factor is also integrated into the framework through a gating fusion mechanism. In the edge flow prediction model, we employ an embedding component to deal with the sparse transitions between nodes. We evaluate our method based on the taxicab data in Beijing and New York City. Experimental results show the advantages of our method beyond 11 baselines, such as ConvLSTM, CNN, and Markov Random Field.

更新日期：2020-03-01

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11