Final Year Project 2010-2011:
gPhone-based Activity Recommendation from GPS Data

Advisor: Prof. Qiang Yang

TA: Vincent W. Zheng

Objective and Requirements

• In this project, we are trying to understand mobile user's behaviors based on their GPS location trajectories. In general, this project consists of two parts. The first part is about user location data collection, in which we will distribute some GPS-equipped smart phones (e.g. gPhone) to help logging the GPS location trajectories. The second part is about GPS data mining, in which we will design innovative algorithms to discover the user activity patterns for mobile recommendation.
  　
• Technically, a cloud computing framework (where all the resources are stored in some cloud and provided to mobile devices on-demand through internet) is preferred for the designed system, though a typical client-server mode is also acceptable. Programming with Android software stack would be required in developing the system on mobile devices such as gPhones. Several particular issues need to be carefully addressed, including battery life maximizing, consistent and simple user-interface design, system compatibility across platforms, system efficiency and accuracy.

Android Development for gPhone

• Android Developer (Suggested)
  　
  • Tutorial for Android Development
    　
• Stack Overflow: Android Development Forum (Suggested)
  　
• Google Groups - Android Beginners

Android Development for GPS Data Logging

• GPS Logger (Suggested)
  　
  • A Sample Code about GPS Logger in Google Code (Java)
    　
• Android GPS Programming
  　
• How to Program Google Android for GPS Data Logging

User Activity Recognition

• Wikipedia Page about Activity Recognition
  　
• Activity Recognition: Linking Low-Level Sensors to High-Level Intelligence (Suggested)
  　
  • Invited Paper in PDF Format
    　
• Lin Liao, Donald J. Patterson, Dieter Fox and Henry Kautz. Building Personal Maps from GPS Data. In New York Academy of Sciences, 2007. (Suggested)
  　
• Donald J. Patterson, Lin Liao, Dieter Fox and Henry Kautz. Inferring High-Level Behavior from Low-Level Sensors. In Proc. of the 5th International Conference on Ubiquitous Computing (UBICOMP-03), 2003.
  　
• Jie Yin, Xiaoyong Chai and Qiang Yang. High-level Goal Recognition in a Wireless LAN. In Proc. of the 19th National Conference on Artificial Intelligence (AAAI-04), San Jose, CA USA, July, 2004.
  　
• Derek H. Hu, Qiang Yang. CIGAR: Concurrent and Interleaving Goal and Activity Recognition. In Proc. of the 23rd AAAI Conference on Artificial Intelligence (AAAI-08), Chicago, Illinois, USA. July 2008.

GPS Data Mining

• Vincent W. Zheng, Yu Zheng, Xing Xie and Qiang Yang. Collaborative Location and Activity Recommendations with GPS History Data. In Proc. of the 19th International World Wide Web Conference  (WWW-10).  Raleigh, NC, USA, April 26-30, 2010. (Suggested)
  　
• Vincent W. Zheng, Bin Cao, Yu Zheng, Xing Xie and Qiang Yang. Collaborative Filtering Meets Mobile Recommendation: A User-centered Approach. In Proc. of the 24th AAAI Conference on Artificial Intelligence (AAAI-10).  Atlanta, Georgia, USA. July 11-15, 2010.
  　
• Daniel Ashbrook and Thad Starner. Using GPS to learn significant locations and predict movement across multiple users. In Personal and Ubiquitous Computing, Vol.7, Number 5 (2003), 275-286. (Suggested)
  　
• John Krumm and Eric Horvitz. Predestination: Inferring Destinations from Partial Trajectories. In Proc. of the 8th International Conference on Ubiquitous Computing (UbiComp-06), 2006.
  　
• Quannan Li, Yu Zheng, Yukun Chen and Xing Xie. Mining user similarity based on location history. In Proc. of ACM SIGSPATIAL conference on Geographical Information Systems (ACM GIS 2008), Irvine, CA, USA. (Suggested)

GPS Data Processing

• Yu Zheng, Like Liu, Longhao Wang and Xing Xie. Learning Transportation Modes from Raw GPS Data for Geographic Application on the Web. In Proc. of International conference on World Wild Web (WWW 2008), Beijing, China. (Suggested)
  　
• Longhao Wang, Yu Zheng, Xing Xie and Wei-Ying Ma. A Flexible Spatio-Temporal Indexing Scheme for Large-Scale GPS Track Retrieval, In Proc. of International conference on Mobile Data Management (MDM 2008), Beijing China.