Abstract
GPS trajectories are crucial for urban planning, traffic prediction, and location-based services. These applications often require dense trajectories, which is often not the case due to power limitations and privacy concerns. To this end, we propose a novel generative adversarial network-based model, namely TIGAN, for trajectory imputation. TIGAN inserts artificial GPS points between real ones, resulting in imputed trajectories that closely resemble those collected at much higher sampling rates. Unlike existing works, TIGAN does not require prior knowledge such as underlying road networks. Moreover, TIGAN incorporates transportation modes into trajectory imputation, leading to much better performance. Evaluation in two real-world datasets demonstrates the superior performance of TIGAN over state-of-the-art methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Cao, W., Wang, D., Li, J., Zhou, H., Li, L., Li, Y.: BRITS: bidirectional recurrent imputation for time series. In: NeurIPS 2018, pp. 6776–6786 (2018)
Di, X., Xiao, Y., Zhu, C., Deng, Y., Zhao, Q., Rao, W.: Traffic congestion prediction by spatiotemporal propagation patterns. In: IEEE MDM 2019, pp. 298–303. IEEE (2019)
Elshrif, M.M., Isufaj, K., Mokbel, M.F.: Network-less trajectory imputation. In: Renz, M., Sarwat, M. (eds.) SIGSPATIAL 2022, pp. 1–10. ACM (2022)
Feng, J., et al.: DeepMove: predicting human mobility with attentional recurrent networks. In: WWW 2018, pp. 1459–1468. ACM (2018)
Goodfellow, I.J., et al.: Generative adversarial nets. In: NeurIPS 2014, pp. 2672–2680 (2014)
Hoteit, S., Secci, S., Sobolevsky, S., Ratti, C., Pujolle, G.: Estimating human trajectories and hotspots through mobile phone data. Comput. Netw. 64, 296–307 (2014)
Li, C., Xu, T., Zhu, J., Zhang, B.: Triple generative adversarial nets. In: Guyon, I., et al. (eds.) NeurIPS 2017 (2017)
Liu, Q., Wu, S., Wang, L., Tan, T.: Predicting the next location: a recurrent model with spatial and temporal contexts. In: Schuurmans, D., Wellman, M.P. (eds.) AAAI 2016 (2016)
Luo, Y., Cai, X., Zhang, Y., Xu, J., Yuan, X.: Multivariate time series imputation with generative adversarial networks. In: Bengio, S., Wallach, H.M., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) NeurIPS 2018 (2018)
Luo, Y., Zhang, Y., Cai, X., Yuan, X.: E2gan: end-to-end generative adversarial network for multivariate time series imputation. In: IJCAI 2019 (2019)
Mirza, M., Osindero, S.: Conditional generative adversarial nets. CoRR, abs/1411.1784 (2014)
Ren, H., et al.: MTrajRec: map-constrained trajectory recovery via seq2seq multi-task learning. In: KDD 2021 (2021)
Tian, L., Zhao, K., Yin, J., Vo, H., Rao, W.: The levy flight of cities: analyzing social-economical trajectories with auto-embedding. CoRR, abs/2112.14594 (2021)
Xia, T., et al.: AttnMove: history enhanced trajectory recovery via attentional network. In: AAAI 2021 (2021)
Yoon, J., Jordon, J., van der Schaar, M.: GAIN: missing data imputation using generative adversarial nets. In: Dy, J.G., Krause, A. (eds.) ICML 2018 (2018)
Zhang, Y., Rao, W., Zhang, K., Chen, L.: Outdoor position recovery from heterogeneous telco cellular data. CoRR, abs/2108.10613 (2021)
Zhao, J., Xu, J., Zhou, R., Zhao, P., Liu, C., Zhu, F.: On prediction of user destination by sub-trajectory understanding: a deep learning based approach. In: CIKM 2018, pp. 1413–1422 (2018)
Zheng, K., Zheng, Y., Xie, X., Zhou, X.: Reducing uncertainty of low-sampling-rate trajectories. In: ICDE 2012, pp. 1144–1155. IEEE Computer Society (2012)
Zheng, Y., Xie, X., Ma, W.: GeoLife: a collaborative social networking service among user, location and trajectory. IEEE Data Eng. Bull. 33(2), 32–39 (2010)
Zhu, F., et al.: City-scale localization with telco big data. In: ACM CIKM 2016, pp. 439–448. ACM (2016)
Acknowledge
This work is partially supported by National Key R &D Program of China (No. 2022YFE0208000, 2021YFE204500, 2021YFC3340601), National Natural Science Foundation of China (No. 61972286), the Shanghai Science and Technology Development Funds (No. 22410713200, 20ZR1460500), the Shanghai Municipal Science and Technology Major Project (2021SHZDZX0100), and Shanghai Key Lab of Vehicle Aerodynamics and Vehicle Thermal Management Systems, and the Fundamental Research Funds for the Central Universities.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shi, Y., Gao, H., Rao, W. (2023). TIGAN: Trajectory Imputation via Generative Adversarial Network. In: Yang, X., et al. Advanced Data Mining and Applications. ADMA 2023. Lecture Notes in Computer Science(), vol 14180. Springer, Cham. https://doi.org/10.1007/978-3-031-46677-9_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-46677-9_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46676-2
Online ISBN: 978-3-031-46677-9
eBook Packages: Computer ScienceComputer Science (R0)