ABSTRACT
The increasing availability of GPS-enabled devices is changing the way people interact with the Web, and brings us a large amount of GPS trajectories representing people's location histories. In this paper, based on multiple users' GPS trajectories, we aim to mine interesting locations and classical travel sequences in a given geospatial region. Here, interesting locations mean the culturally important places, such as Tiananmen Square in Beijing, and frequented public areas, like shopping malls and restaurants, etc. Such information can help users understand surrounding locations, and would enable travel recommendation. In this work, we first model multiple individuals' location histories with a tree-based hierarchical graph (TBHG). Second, based on the TBHG, we propose a HITS (Hypertext Induced Topic Search)-based inference model, which regards an individual's access on a location as a directed link from the user to that location. This model infers the interest of a location by taking into account the following three factors. 1) The interest of a location depends on not only the number of users visiting this location but also these users' travel experiences. 2) Users' travel experiences and location interests have a mutual reinforcement relationship. 3) The interest of a location and the travel experience of a user are relative values and are region-related. Third, we mine the classical travel sequences among locations considering the interests of these locations and users' travel experiences. We evaluated our system using a large GPS dataset collected by 107 users over a period of one year in the real world. As a result, our HITS-based inference model outperformed baseline approaches like rank-by-count and rank-by-frequency. Meanwhile, when considering the users' travel experiences and location interests, we achieved a better performance beyond baselines, such as rank-by-count and rank-by-interest, etc.
- Bikely: http://www.bikely.com/Google Scholar
- GPS Track route exchange forum: http://www.gpsxchange.com/Google Scholar
- GPS sharing: http://gpssharing.com/.Google Scholar
- Abowd, G. D. Cyberguide: a mobile context-aware tour guide, wireless network, 3(5), 421--433. Google ScholarDigital Library
- Ashbrook, D., and Starner, T. Using GPS to learn significant locations and predict movement across multiple users. Personal and Ubiquitous Computing 7(5), 275--286. Google ScholarDigital Library
- Beeharee, A. et al. Exploiting real world knowledge in ubiquitous applications. Personal and Ubiquitous Computing 11(6), 429--437. Google ScholarDigital Library
- Eagle, N. et al. Reality mining: sensing complex social systems. Personal and Ubiquitous Computing 10(4), 255--268. Google ScholarDigital Library
- Gonotti, F., et al. Trajectory pattern mining. In Proceedings of KDD'07 (San Jose USA, Aug. 2007), ACM Press, 330--339 Google ScholarDigital Library
- Hariharan, R. et al. Project Lachesis: Parsing and Modeling Location Histories, In Proceedings of GIScience, (Park Utah, October 2004), ACM Press: 106--124.Google Scholar
- Horozov, T., et al. Using Location for Personalized POI Recommendations in Mobile Environments. In Proceedings of SAINT, (Phoenix, USA, Jan. 2006), IEEF Press: 124--129. Google ScholarDigital Library
- Krumm, J.et al. Predestination: Inferring Destinations from Partial Trajectories. In Proceedings of the Ubicomp'03, (Orange County USA, September 2003). Springer Press: 243--260. Google ScholarDigital Library
- Li, Q. and Zheng, Y. et al. Mining user similarity based on location history. In Proc. of GIS'08 (Santa Ana, CA, Nov. 2008). ACM Press: 298--307 Google ScholarDigital Library
- Liao, L., et al. Building Personal Maps from GPS Data. In proceedings of IJCAI MOO05, Springer Press(2005): 249--265Google Scholar
- Park, M., H. Location-Based Recommendation System Using Bayesian User's Preference Model in Mobile Devices. In Proc. UIC'07 (Hong Kong, China, July 2007). Springer Press:1130--1139 Google ScholarDigital Library
- Patterson, D., J. et al. Inferring High--Level Behavior from Low-Level Sensors. In Proc. of Ubicomp'03, Springer Press (2003), 73--89Google Scholar
- Mamoulis, N. et al. Mining, Indexing and Querying Historical Spatiotemporal Data. In Proceedings of KDD'04 (Seattle USA, August 2004), ACM Press: 236--245. Google ScholarDigital Library
- Simon R., et al. A Mobile Application Framework for the Geospatial Web. In Proceedings of WWW '07 (Banff Canada, May 2007). ACM Press: 381--390. Google ScholarDigital Library
- Takeuchi, Y. et al. CityVoyager: An Outdoor Recommendation System Based on User Location History. In Proceedings of UIC'2006, (Berlin, 2006), Springer Press: 625--636. Google ScholarDigital Library
- Zheng, Y, et al. Learning transportation modes from raw GPS data for geographic applications on the Web. In Proceedings of WWW 2008, (Beijing China, April 2008), ACM Press: 247--256. Google ScholarDigital Library
- Zheng, Y., et al. GeoLife: Managing and understanding your past life over maps. In Proceedings of MDM'09, (Beijing China, April 2008), IEEE Press: 211--212 Google ScholarDigital Library
- Zheng, Y. et al. Understanding mobility based on GPS data. In Proc. Ubicomp'08, (Seoul Korea, Sept. 2008), ACM Press: 312--321 Google ScholarDigital Library
Index Terms
- Mining interesting locations and travel sequences from GPS trajectories
Recommendations
Mining GPS data to determine interesting locations
IIWeb '11: Proceedings of the 8th International Workshop on Information Integration on the Web: in conjunction with WWW 2011It is possible to obtain fine grained location information fairly easily using Global Positioning System (GPS) enabled devices. It becomes easy to track an individual's location and trace her trajectory using such devices. By aggregating this data and ...
Learning Location Correlation from GPS Trajectories
MDM '10: Proceedings of the 2010 Eleventh International Conference on Mobile Data ManagementPeople’s location histories imply the location correlation that states the relations between geographical locations in the space of human behavior. With the correlation, we can enable many valuable services, such as location recommendation and sales ...
Mining significant semantic locations from GPS data
With the increasing deployment and use of GPS-enabled devices, massive amounts of GPS data are becoming available. We propose a general framework for the mining of semantically meaningful, significant locations, e.g., shopping malls and restaurants, ...
Comments