Trajectory Privacy Protection

Deep Learning & Geo-Privacy Protection

LSTM-TrajGAN: A deep learning method combining LSTM and generative adversarial network for trajectory privacy protection.

Funding Source

UW-Madison Office of the Vice Chancellor
Wisconsin Alumni Research Foundation
My Role

Team Leader
(January 2020 - May 2020)
My Contribution

Trajectory Data Processing
Deep Learning Model Design
Model Training
Experiment and Evaluation
Paper Writing

Reference:

Rao, J.‚úČ, Gao, S.*, Kang, Y., & Huang, Q. (2020). LSTM-TrajGAN: A Deep Learning Approach to Trajectory Privacy Protection. In the Proceedings of the 11th International Conference on Geographic Information Science (GIScience 2021), pp. 1-16. DOI: 10.4230/LIPIcs.GIScience.2021.12

Introduction

The prevalence of location-based services contributes to the explosive growth of individual-level trajectory data and raises public concerns about privacy issues. In this research, we propose a novel LSTM-TrajGAN approach, which is an end-to-end deep learning model to generate privacy-preserving synthetic trajectory data for data sharing and publication. We design a loss metric function TrajLoss to measure the trajectory similarity losses for model training and optimization. The model is evaluated on the trajectory-user-linking task on a real-world semantic trajectory dataset. Compared with other common geomasking methods, our model can better prevent users from being re-identified, and it also preserves essential spatial, temporal, and thematic characteristics of the real trajectory data. The model better balances the effectiveness of trajectory privacy protection and the utility for spatial and temporal analyses, which offers new insights into the GeoAI-powered privacy protection.


Back to Home Page

Selected Works

Recent research works and projects

Stay-at-Home Order Effects

COVID-19 & Mobile Phone Location Data

Association of mobility data indications of travel and stay-at-Home mandates with COVID-19 infection rates in the US.

Read Me

Trajectory Privacy Protection

Deep Learning & Geo-Privacy Protection

LSTM-TrajGAN: A deep learning method combining LSTM and generative adversarial network for trajectory privacy protection.

Read Me

Mapping Mobility Changes

ESRI ArcGIS Online Dashboard

Mapping county-level mobility pattern changes in the United States in response to COVID-19.

Read Me

Mobile Augmented Reality

Computer Vision & Geovisualization

Focus on geovisualization and human-computer interaction through computer vision methods.

Read Me

Geospatial Data Processing

Python & Parallel Data Processing

Using Python and plenty of open source libraries to achieve parallel geospatial data processing.

Read Me

More Projects

More Research Works and Projects.

More projects, including research works, thesis projects, course projects, and personal projects.

Read Me