GPS-enabled mobile devices have generated massive trajectory data. Existing estimation approaches fail to consider the path as a whole and do not fully leverage the natural supervised labels of the data. This paper present an end-to-end estimation model DEEPTRAVEL to estimating the travel time. It introduces the dual interval loss, which elegantly matches the characteristic of BiLSTM with that of trajectory data.

附件: DEEPTRAVEL论文介绍_江丽英.pdf [登录 后查看]