Smart Mobility

KITS: Inductive Spatio-Temporal Kriging with Increment Training Strategy

Sensors are commonly deployed to perceive the environment. However, due to the high cost, sensors are usually sparsely deployed. Kriging is the tailored task to infer the unobserved nodes (without sensors) using the observed source nodes (with …

Correlated Time Series Self-Supervised Representation Learning via Spatiotemporal Bootstrapping

Correlated time series analysis plays an important role in many real-world industries. Learning an efficient representation of this large-scale data for further downstream tasks is necessary but challenging. In this paper, we propose a …

A Unified Probabilistic Framework for Spatiotemporal Passenger Crowdedness Inference within Urban Rail Transit Network

This paper proposes the Spatio-Temporal Crowdedness Inference Model (STCIM), a framework to infer the passenger distribution inside the whole urban rail transit (URT) system in real-time. Our model is practical since the model is designed in a …

A Privacy-preserving Heart Rate Prediction System for Drivers in Connected Vehicles

The prediction of health metrics for drivers has become increasingly crucial due to the potential impact of drivers' health conditions on traffic accidents. Heart attack is one of the primary causes of health-related traffic tragedies. However, …

Advanced Machine Learning for Smart Transportation (with GaTech)

Intelligent Transport Systems (ITS) have been an essential chapter in smart city blueprint. There are numbers of real practical applications of ITS: For instance, when you are driving on the road, the ITS could predict how crowded the traffic will be …

Jointly contrastive representation learning on road network and trajectory

Road network and trajectory representation learning are essential for traffic systems since the learned representation can be directly used in various downstream tasks (e.g., traffic speed inference, travel time estimation). However, most existing …

Individualized Passenger Travel Pattern Multi-Clustering based on Graph Regularized Tensor Latent Dirichlet Allocation

Individual passenger travel patterns have significant value in understanding passenger’s behavior, such as learning the hidden clusters of locations, time, and passengers. The learned clusters further enable commercially beneficial actions such as …

Tensor Topic Models with Graphs and Applications on Individualized Travel Patterns

Individualized passenger travel pattern is of significant research value since the abundant information from individual trajectory data could help discover the useful insights about the multi-clustering of origin, destination, time, etc., and the …

Long-Short Term Spatiotemporal Tensor Prediction for Passenger Flow Profile

This paper is awarded with IEEE CASE 2020 Best Conference Paper Award

Tensor Completion for Weakly-dependent Data on Graph for Metro Passenger Flow Prediction

Low-rank tensor decomposition and completion have attracted significant interest from academia given the ubiquity of tensor data. However, the low-rank structure is a global property, which will not be fulfilled when the data presents complex and …