Y
Yitian Jia
Researcher at DiDi
Publications - 4
Citations - 930
Yitian Jia is an academic researcher from DiDi. The author has contributed to research in topics: Traffic congestion & Block (telecommunications). The author has an hindex of 3, co-authored 4 publications receiving 447 citations.
Papers
More filters
Proceedings Article
Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
Huaxiu Yao,Fei Wu,Jintao Ke,Xianfeng Tang,Yitian Jia,Siyu Lu,Pinghua Gong,Jieping Ye,Zhenhui Li +8 more
TL;DR: A Deep Multi-View Spatial-Temporal Network (DMVST-Net) framework to model both spatial and temporal relations is proposed, which demonstrates effectiveness of the approach over state-of-the-art methods.
Posted Content
Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
Huaxiu Yao,Fei Wu,Jintao Ke,Xianfeng Tang,Yitian Jia,Siyu Lu,Pinghua Gong,Jieping Ye,Zhenhui Li +8 more
TL;DR: Wang et al. as discussed by the authors proposed a Deep Multi-View Spatial-Temporal Network (DMVST-Net) framework to model both spatial and temporal relations, which can help the city pre-allocate resources to meet travel demand and to reduce empty taxis on streets which waste energy and worsen the traffic congestion.
Journal ArticleDOI
Hexagon-Based Convolutional Neural Network for Supply-Demand Forecasting of Ride-Sourcing Services
TL;DR: This paper partitions a city area into various regular hexagon lattices, and proposes three hexagon-based convolutional neural networks (H-CNN), both the input and output of which are numerous local hexagon maps, which are found to significantly outperform the benchmark algorithms in terms of accuracy and robustness.
Patent
An online car-hailing supply and demand gap prediction method in a geographic area
TL;DR: In this paper, an online car-hailing supply and demand gap prediction method in a geographic area is proposed, which comprises the following steps: dividing the geographic area into a plurality of regular hexagonal area units; Splicing the plurality of area units to obtain at least one area block; determining a prediction characteristic parameter of the region block; Inputting the prediction characteristic parameters of the area blocks into a trained supply-demand gap prediction model; and outputting a prediction result by the prediction result is a combination of prediction results of each regular hexagon region unit contained in the region