Inferring Long-term User Properties Based on Users' Location History

Recent development of location technologies enables us to obtain the location history of users. This paper proposes a new method to infer users' longterm properties from their respective location histories. Counting the instances of sensor detection for every user, we can obtain a sensor-user matrix. After generating features from the matrix, a machine learning approach is taken to automatically classify users into different categories for each user property. Inspired by information retrieval research, the problem to infer user properties is reduced to a text categorization problem. We compare weightings of several features and also propose sensor weighting. Our algorithms are evaluated using experimental location data in an office environment.

[1]  Antonio Krüger,et al.  Preface to the Special Issue on User Modeling in Ubiquitous Computing , 2005, User Modeling and User-Adapted Interaction.

[2]  Sunny Consolvo,et al.  Learning and Recognizing the Places We Go , 2005, UbiComp.

[3]  Hideyuki Nakashima,et al.  ID-CoBIT: a battery-less information terminal with data upload capability , 2003, IECON'03. 29th Annual Conference of the IEEE Industrial Electronics Society (IEEE Cat. No.03CH37468).

[4]  Gaetano Borriello,et al.  Location Systems for Ubiquitous Computing , 2001, Computer.

[5]  Christopher G. Atkeson,et al.  The Narrator : A Daily Activity Summarizer Using Simple Sensors in an Instrumented Environment , 2003 .

[6]  Henry A. Kautz,et al.  Location-Based Activity Recognition using Relational Markov Networks , 2005, IJCAI.

[7]  Dieter Fox,et al.  Knowledge Compilation Properties of Trees-of-BDDs, Revisited , 2009, IJCAI.

[8]  Judy Kay,et al.  Consistent Modelling of Users, Devices and Sensors in a Ubiquitous Computing Environment , 2005, User Modeling and User-Adapted Interaction.

[9]  Matthai Philipose,et al.  Maximum A Posteriori Path Estimation with Input Trace Perturbation: Algorithms and Application to Credible Rating of Human Routines , 2005, IJCAI.

[10]  Claudia Linnhoff-Popien,et al.  Personal and ubiquitous computing: special issue on location and context awareness , 2006, Personal and Ubiquitous Computing.

[11]  Alfred Kobsa,et al.  Generic User Modeling Systems , 2001, User modeling and user-adapted interaction.

[12]  Andy Hopper,et al.  The active badge location system , 1992, TOIS.

[13]  Thad Starner,et al.  Using GPS to learn significant locations and predict movement across multiple users , 2003, Personal and Ubiquitous Computing.

[14]  Anthony Jameson,et al.  Modelling both the Context and the User , 2001, Personal and Ubiquitous Computing.

[15]  Paul Dourish,et al.  What we talk about when we talk about context , 2004, Personal and Ubiquitous Computing.

[16]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[17]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[18]  Marko Grobelnik,et al.  Feature selection using linear classifier weights: interaction with classification models , 2004, SIGIR '04.

[19]  Blake Hannaford,et al.  A Hybrid Discriminative/Generative Approach for Modeling Human Activities , 2005, IJCAI.

[20]  Yoshiyuki Nakamura,et al.  A Compact Battery-Less Information Terminal for Real World Interaction , 2004, Pervasive.

[21]  Thorsten Joachims,et al.  Text categorization with support vector machines , 1999 .