A Novel Frequent Trajectory Mining Method Based on GSP
With the development and popularity of various location technologies (GPS, Wireless cellular networks and etc.), people can easily access the location information of moving objects and use a variety of location-based services. In this paper, based on the feature that the location information of moving object is consecutive, we introduce the continuity in temporal and spatial as a constraint into the Sequential Pattern Mining algorithm GSP (Generalized Sequential Patterns) [3,4], and to mine frequent trajectories, and then display them in Google maps. We evaluated our method by using a large GPS dataset in real world and verified the feasibility and effectiveness of Sequential Pattern Mining algorithm in mining the frequent trajectories of multiple moving objects.
KeywordsFrequent trajectories mining GSP GPS dataset
Unable to display preview. Download preview PDF.
- 1.Agrawal, R., Srikant, R.: Mining Sequential Patterns. In: The 11th International Conference on Data Engineering. IEEE Computer Society Press, Los Alamitos (1995)Google Scholar
- 2.Srikant, R., Agrawal, R.: Mining sequential pattern: Generalizations and performance improvements. In: Pro. 5th Int. Conf. Extending Database Technology(EDBT’s 1996), Avignon, France, pp. 3–17 (1996)Google Scholar
- 3.Xia, M.-b., Wang, X.-c., Sun, Y.-q., Jin, S.-y.: Research on Sequential Pattern Mining Algorithms. Computer Technology and Development 16(4), 4–6 (2006)Google Scholar
- 4.Hu, X.-g., Zhang, Y.-y.: An improved algorithm for mining sequential patterns with time constraints. CAAI Transactions on Intelligent Systems 4(2), 89–93 (2007)Google Scholar
- 5.Lv, C., Zhang, B.: An analysis and comparison between the main two algorithms for mining sequential patterns. Journal of Hubei Normal University (Natural Science) 26(4) (2006)Google Scholar
- 6.Zheng, Y., Xie, X.: Learning Location Correlation from GPS Trahectories. In: Eleventh International Conference on Mobile Data Management (2010)Google Scholar
- 7.Rtree Pportal, http://www.rtreeportal.org