On Generating Representative Data for Multiple Aspects Trajectory Data
Abstract
Trajectory data mining and analysis tasks have been widely studied in recent years. These tasks are complex due to the large volume of data generated and its heterogeneity. A solution to minimize these problems is the summarization of these data, aiming to generate representative data. Few works in the literature address these solutions, and none were found that consider all dimensions of a trajectory (spatial, temporal and unlimited semantic aspects), analyzing the peculiarities and singularities of each aspect. This doctoral thesis proposes a method based on a spatial grid for summarizing multi-aspect trajectories, called MAT-SG. Its main contributions are: (i) segmentation of trajectories in a spatial grid according to the dispersion of points; (ii) from a set of input trajectories, a representative trajectory is generated as a sequence of representative points with representative values for each dimension, considering the particularities of each type of aspect. An example demonstrates the potential of the proposal, being evaluated the volume reduction and the accuracy of the summarization.
References
Almeida, D. R. et al. (2020). A Survey on Big Data for Trajectory Analytics. ISPRS Int. J. Geo-Information, 9(2):88.
Buchin, K. et al. (2013). Median trajectories. Algorithmica, 66(3):595-614.
Buchin, M., Kilgus, B., and Kölzsch, A. (2019). Group diagrams for representing trajectories. International Journal of Geographical Information Science, 34(12):2401-2433.
Erwig, M. et al. (1999). Spatio-temporal data types: an approach to modeling and querying moving objects in databases. GeoInformatica, 3(3):269-296.
Fiore, M. et al. (2020). Privacy in trajectory micro-data publishing: a survey. Transactions on Data Privacy, 13:91-149.
Gao, C. et al. (2019). Semantic trajectory compression via multi-resolution synchronization-based clustering. Knowledge-Based Systems, 174:177-193.
Lee, J.-G., Han, J., and Whang, K.-Y. (2007). Trajectory clustering: A partition-and-group framework. In SIGMOD International Conference on Management of Data, page 593-604. ACM.
Li, H. (2021). Typical trajectory extraction method for ships based on ais data and trajectory clustering. In 2021 2nd International Conference on Artificial Intelligence and Information Systems, pages 1-8.
Machado, V. L., Mello, R. d. S., and Bogorny, V. (2022). A method for summarizing trajectories with multiple aspects. In International Conference on Database and Expert Systems Applications, pages 433-446. Springer.
Mello, R. et al. (2019). Master: A multiple aspect view on trajectories. Transactions in GIS, pages 805-822.
Panagiotakis, C. et al. (2012). Segmentation and sampling of moving object trajectories based on representativeness. IEEE Trans. on Know. and Data Eng., 24(7):1328-1343.
Parent, C. et al. (2013). Semantic trajectories modeling and analysis. ACM Comput. Surv., 45(4):42:1-42:32.
Petry, L. M. et al. (2019). Towards semantic-aware multiple-aspect trajectory similarity measuring. Transactions in GIS, 23(5):960-975.
Rodriguez, D. F. and Ortiz, A. E. (2020). Detecting representative trajectories in moving objects databases from clusters. In International Conference on Information Technology & Systems, pages 141-151. Springer.
Seep, J. and Vahrenhold, J. (2019). Inferring semantically enriched representative trajectories. In SIGSPATIAL International Workshop on Computing with Multifaceted Movement Data, pages 1-4. ACM.
Wang, S., Bao, Z., Culpepper, J. S., and Cong, G. (2021). A survey on trajectory data management, analytics, and learning. ACM Comput. Surv., 54(2).
Xie, P. et al. (2020). Urban flow prediction from spatiotemporal data using machine learning: a survey. Information Fusion, 59:1-12.
