ABSTRACT
Trajectory recovery can benefit many applications such as migration pattern studies of animal and finding hot routes in the urban city. It is necessary to recover trajectory with limited trajectory points to utilize collected trajectory data in a reasonable and efficient way and to provide the better location based service for users. However, the trajectory data involves complex and nonlinear spatial-temporal impacts which cannot be captured by traditional trajectory recovery methods. Moreover, the existing methods consider little about the correlations between trajectory and traffic pattern in the urban city. The superiority of deep neural network makes it possible to recover trajectory with low data quality. We propose a Multi-Task Representation Learning Network (MRL-Net) framework which models the complex nonlinear spatial-temporal correlations in trajectory data with representation learning technique and capture the dependencies of trajectory points with recurrent neural networks. To the best of our knowledge, it is the first paper to address the trajectory recovery problem with representation learning and multi-task learning. Experiments on real-world trajectory data show that our model is superior to state-of-the-art methods.
- Ozdemir, E., Topcu, A. E., & Ozdemir, M. K. (2018). A hybrid HMM model for travel path inference with sparse GPS samples. Transportation, 45(1), 233--246.Google ScholarCross Ref
- Hunter, T., Abbeel, P., & Bayen, A. (2013). The path inference filter: model-based low-latency map matching of probe vehicle data. IEEE Transactions on Intelligent Transportation Systems, 15(2), 507--529.Google ScholarCross Ref
- Ren, S., He, K., Girshick, R., & Sun, J. 2015. Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis & Machine Intelligence, 39(6), 1137--1149.Google ScholarDigital Library
- Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.Google Scholar
- Li, X., Zhao, K., Cong, G., Jensen, C. S., & Wei, W. (2018, April). Deep representation learning for trajectory similarity computation. In 2018 IEEE 34th International Conference on Data Engineering (ICDE) (pp. 617--628). IEEE.Google ScholarCross Ref
- Maaten, L. V. D., & Hinton, G. (2008). Visualizing data using t-SNE. Journal of machine learning research, 9(Nov), 2579--2605.Google ScholarDigital Library
- Hochreiter, S., & Schmidhuber, J. 1997. Long short-term memory. Neural computation, 9(8), 1735--1780.Google Scholar
- Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., & Mei, Q. 2015. Line: Large-scale information network embedding. In Proceedings of the 24th international conference on world wide web, 1067--1077.Google ScholarDigital Library
- Zheng, K., Zheng, Y., Xie, X., & Zhou, X. (2012, April). Reducing uncertainty of low-sampling-rate trajectories. In 2012 IEEE 28th International Conference on Data Engineering (pp. 1144--1155). IEEE.Google Scholar
- Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.Google Scholar
- Nair, V., & Hinton, G. E. 2010. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th international conference on machine learning, 807--814.Google ScholarDigital Library
- Park, S. H., Kim, B., Kang, C. M., Chung, C. C., & Choi, J. W. (2018, June). Sequence-to-sequence prediction of vehicle trajectory via LSTM encoder-decoder architecture. In 2018 IEEE Intelligent Vehicles Symposium (IV) (pp. 1672--1678). IEEE.Google ScholarDigital Library
- Li, Y., Fu, K., Wang, Z., Shahabi, C., Ye, J., & Liu, Y. 2018. Multi-task representation learning for travel time estimation. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 1695--1704.Google ScholarDigital Library
- Kingma, D. P., & Ba, J. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.Google Scholar
- Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE transactions on Signal Processing, 45(11), 2673--2681.Google ScholarDigital Library
Index Terms
- Multi-Task Representation Learning Network for Trajectory Recovery
Recommendations
SimiDTR: Deep Trajectory Recovery with Enhanced Trajectory Similarity
Database Systems for Advanced ApplicationsAbstractThe pervasiveness of GPS-equipped smart devices and the accompanying deployment of sensing technologies generates increasingly massive amounts of trajectory data that cover applications such as personalized location recommendation and urban ...
A Critical Perceptual Pre-trained Model for Complex Trajectory Recovery
GeoSearch '23: Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Searching and Mining Large Collections of Geospatial DataTrajectory on the road traffic is commonly collected at a low sampling rate, and trajectory recovery aims to recover a complete and continuous trajectory from the sparse and discrete inputs. Recently, sequential language models have been innovatively ...
Trajectory splicing
AbstractWith continued development of location-based systems, large amounts of trajectories become available which record moving objects’ locations across time. If the trajectories collected by different location-based systems come from the same moving ...
Comments