Generative Adversarial Networks (GANs) for human mobility trajectory generation

    Type: Bachelor Master UROP
    Status: Available

    GANs are a type of neural networks that once trained on a specific dataset, they can generate new samples, similar but not same, as the samples in the training dataset (e.g., see 15). This generative characteristic can be used to generate human mobility trajectories, and thus enhance existing labeled human mobility datasets, in order to improve the performance of existing methods for human mobility modeling.

    In the context of a BSc project, you will: (i) overview methods and datasets for trajectory generation (e.g., [4]); (ii) use an existing GAN method for trajectory generation on new datasets; (iii) compare the generated trajectories with original trajectories and analyze the behavior of the network for a variety of parameters; (iv) summarize the results and propose future work.

    In the context of an MSc thesis or UROP project, you will: (i) overview methods and datasets for trajectory generation (e.g., [4]); (ii) pre-process datasets appropriate for the task (e.g., [1][2]); (iii) create a novel GAN method for trajectory generation; (iv) use the generated trajectories to enhance existing datasets and evaluate machine-learning models for next-task prediction on enhanced vs. original dataset; (v) summarize the results and propose future work.


    1. Mokhtar, Sonia Ben, Antoine Boutet, Louafi Bouzouina, Patrick Bonnel, Olivier Brette, Lionel Brunie, Mathieu Cunche et al. “PRIVA’MOV: Analysing Human Mobility Through Multi-Sensor Datasets.” 2017 []
    2. Moro, Arielle, Vaibhav Kulkarni, Pierre-Adrien Ghiringhelli, Bertil Chapuis, and Benoit Garbinato. “Breadcrumbs: A Feature Rich Mobility Dataset with Point of Interest Annotation.” arXiv preprint arXiv:1906.12322 (2019) []
    3. Luca, Massimiliano, Gianni Barlacchi, Bruno Lepri, and Luca Pappalardo. “Deep Learning for Human Mobility: a Survey on Data and Models.” arXiv preprint arXiv:2012.02825 (2020). []
    4. Feng, Jie, Zeyu Yang, Fengli Xu, Haisu Yu, Mudan Wang, and Yong Li. “Learning to Simulate Human Mobility.” In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3426-3433. 2020.
    5. Feng, Jie, Yong Li, Chao Zhang, Funing Sun, Fanchao Meng, Ang Guo, and Depeng Jin. “Deepmove: Predicting human mobility with attentional recurrent networks.” In Proceedings of the 2018 world wide web conference, pp. 1459-1468. 2018. []
    6. Yu, Lantao, Weinan Zhang, Jun Wang, and Yong Yu. “Seqgan: Sequence generative adversarial nets with policy gradient.” In Thirty-first AAAI conference on artificial intelligence. 2017. []
    7. scikit-mobility: mobility analysis in Python
    8. Brown, Tom B., Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan et al. “Language models are few-shot learners.” arXiv preprint arXiv:2005.14165 (2020). []
    9. Vaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. “Attention is all you need.” In Advances in neural information processing systems, pp. 5998-6008. 2017. []
    10. Devlin, Jacob, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. “Bert: Pre-training of deep bidirectional transformers for language understanding.” arXiv preprint arXiv:1810.04805 (2018). [—————————]
    11. “Open Sourcing BERT: State-of-the-Art Pre-training for Natural Language Processing”. Google AI Blog. Retrieved 2019-11-27.

    For more information contact: