Abstract
This paper presents TrajGen, an approach to generate artificial datasets of mobility trajectories based on an original trajectory dataset while retaining the utility of the original data in supporting various mobility applications. The generated mobility data is disentangled with the original data and can be shared without compromising the data privacy. TrajGen leverages Generative Adversarial Nets combined with a Seq2Seq model to generate the spatial-temporal trajectory data. TrajGen is implemented and evaluated with real-world taxi trajectory data in Singapore. The extensive experimental results demonstrate that TrajGen is able to generate artificial trajectory data that retain key statistical characteristics of the original data. Two case studies, i.e. road map updating and Origin-Destination demand estimation are performed with the generated artificial data, and the results show that the artificial trajectories generated by TrajGen retain the utility of original data in supporting the two applications.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
