Research

Ongoing Project

My main research is to build a mobility data management system for cross-disciplinary applications, such as self-driving, green transport, and tourism planning. An overview can be found below (click to access our latest survey). Inevitably, such a system will be more and more complex in terms of pipeline configuration, including data cleaning, parameter setting, choice of similarity measures, etc. To make the system easy to use by various customer groups, I also want to achieve auto-configurations of learning and analytic pipelines, including data integration, clustering, and route planning.

I also actively contribute to the following projects at ViDA and CUSP:

D3M@ViDA: https://vida.engineering.nyu.edu/research/d3m/

Previous Projects

A whole view can be found in my thesis: Fast trajectory search for real-world applications.

T4: an end-to-end intelligent traffic analytic system built from Torch and enriched with traffic visualisation, prediction, altering and light controlling. It also integrates traffic, transportation and trip planning into one platform, to achieve a complete pipeline for real-time smart cities.

Vehicle Trajectory Search

Torch: a search engine for trajectory analytics in the road network. Play with our online system to conduct search. (SIGIR 2018, WSDM 2019)
k-paths: a fast large-scale clustering framework for trajectory data. (VLDB 2020)

Activity Trajectory Search

TISP: a trip planning system by an integrated search paradigm, it provides information about more than 20 cities' attractions, hotels, and restaurants. Play with our online system, or Watch video. (WSDM 2018, ICDE 2017, SIGMOD 2018), check our datasets.

Commuter Trajectory Search

RkNNT: a tool to estimate those potential passengers for a route in an existing bus network based on transition data. We clean the public transit data of NYC and LA, check our datasets. (TKDE)

Google Sites

Report abuse