Shui Liu
5 Papers
4 Citations
Shui Liu is an academic researcher. The author has contributed to research in topics: Computer science & Duration (music). The author has an hindex of 1, co-authored 3 publications.
Chat about Author
Papers
Uncertainty-Aware Probabilistic Travel Time Prediction for On-Demand Ride-Hailing at DiDi
Hao Liu,Wenzhao Jiang,Shui Liu,Xi Chen +3 more
- 04 Aug 2023
TL;DR: A probabilistic framework for uncertainty-aware travel time prediction, ProbTTE, which first transforms the single-label regression task to a multi-class classification problem to estimate the implicit travel time distribution, and construct a route-wise log-normal distribution regularizer to absorb prior knowledge from large-scale historical trip data.
12
Deep Fusion for Travel Time Estimation Based on Road Network Topology
TL;DR: An end-to-end Deep Fusion framework for Travel Time Estimation (DFTTE) is proposed, which exploits multi-source heterogeneous traffic information within an Encoder-Decoder architecture and employs an attention mechanism to capture efficient correlations among spatial and temporal features.
9
TimeBird: Context-Aware Graph Convolution Network for Traffic Incident Duration Prediction
TL;DR: Wang et al. as discussed by the authors proposed a context-aware spatio-temporal graph convolution framework, named TimeBird, to estimate the duration time of traffic incidents and designed a contextaware attention mechanism to adaptively learn the heterogeneous traffic features for incident duration prediction.
SASNet: Stage-aware Sequential Matching for Online Travel Recommendation
Fanwei Zhu,Zulong Chen,Fan Zhang,Jiazhen Lou,Hong Wen,Shui Liu,Qi Rao,Tengfei Yuan,Shenghua Ni,Jinxin Hu,Fuzhen Sun,Quan Lu +11 more
- 17 Oct 2022
TL;DR: This paper proposes to capture the deep sequential context by modeling the evolving of user stages, and develops a novel stage-aware deep sequential matching network (SASNet) that incorporates inter-stage and intra-stage dependencies over stage-augmented interaction sequence for more accurate and interpretable recommendation.
iETA: A Robust and Scalable Incremental Learning Framework for Time-of-Arrival Estimation
Jindong Han,Hao Liu,Shui Liu,Xi Chen,Naiqiang Tan,Hua Chai,Hui Xiong +6 more
- 04 Aug 2023
TL;DR: A robust and scalable incremental ETA learning framework to continuously exploit spatio-temporal traffic patterns from massive floating-car data and thus achieve better estimation performances, and proposes an adversarial training module to improve the learning robustness by proactively mitigating and resisting traffic noise perturbations.