Synthetic Trajectory Data

Synthetic trajectory data generation aims to create realistic, privacy-preserving substitutes for real-world movement data, addressing limitations in data collection and privacy concerns. Current research focuses on developing advanced generative models, including generative adversarial networks (GANs), recurrent neural networks (RNNs), diffusion probabilistic models (DPMs), and temporal point processes, often incorporating techniques like differential privacy to enhance data protection. These efforts are crucial for enabling research and applications across diverse fields, such as urban planning, epidemiology, and transportation, where access to high-quality mobility data is essential but often constrained by privacy regulations. The ultimate goal is to balance the utility of the synthetic data with robust privacy guarantees.

Papers

September 20, 2024

Revisiting Synthetic Human Trajectories: Imitative Generation and Benchmarks Beyond Datasaurus
Bangchao Deng, Xin Jing, Tianyue Yang, Bingqing Qu, Philippe Cudre-Mauroux, Dingqi Yang
New Benchmark Human Trajectory Synthetic Trajectory Trajectory Datasets Dataset Management Synthetic Trajectory Data

July 24, 2024

Synthetic Trajectory Generation Through Convolutional Neural Networks
Jesse Merhi, Erik Buchholz, Salil S. Kanhere
Convolutional Neural Network Handwritten Trajectory Synthetic Trajectory Synthetic Trajectory Data Location Trajectory

April 10, 2024

Differentially Private GANs for Generating Synthetic Indoor Location Data
Vahideh Moghtadaiee, Mina Alishahi, Milad Rabiei
Differential Privacy Private Generative Adversarial Network Synthetic Trajectory Data

March 12, 2024

SoK: Can Trajectory Generation Combine Privacy and Utility?
Erik Buchholz, Alsharif Abuadbba, Shuo Wang, Surya Nepal, Salil S. Kanhere
Task Utility Generative Trajectory Synthetic Trajectory Data Location Trajectory Privacy Preserving Trajectory Trajectory Based

February 19, 2024

Synthetic location trajectory generation using categorical diffusion models
Simon Dirmeier, Ye Hong, Fernando Perez-Cruz
Synthetic Data Synthetic Data Generation Probabilistic Model Synthetic Trajectory Data

September 20, 2023

CATS: Conditional Adversarial Trajectory Synthesis for Privacy-Preserving Trajectory Data Publication Using Deep Learning Approaches
Jinmeng Rao, Song Gao, Sijia Zhu
Deep Learning Trajectory Datasets Synthetic Trajectory Data Adversarial Trajectory Privacy Preserving Trajectory

June 24, 2023

Spatio-temporal Storytelling? Leveraging Generative Models for Semantic Trajectory Analysis
Shreya Ghosh, Saptarshi Sengupta, Prasenjit Mitra
Natural Language Processing Generative Model Generative Language Model Trajectory Data Mining Narrative Map Synthetic Trajectory Data

March 17, 2023

Inferring Traffic Models in Terminal Airspace from Flight Tracks and Procedures
Soyeon Jung, Mykel J. Kochenderfer
Synthetic Trajectory Traffic Model Medical Procedure Aircraft Trajectory Synthetic Trajectory Data Terminal Airspace

June 26, 2022

Estimating Link Flows in Road Networks with Synthetic Trajectory Data Generation: Reinforcement Learning-based Approaches
Miner Zhong, Jiwon Kim, Zuduo Zheng
Positive Reinforcement Learning Based Approach Road Network Vehicle Trajectory Vehicle Trajectory Data Synthetic Trajectory Data