Building personal maps from GPS data

被引：53

作者：

Liao, Lin ^{[1
]}

Patterson, Donald J. ^{[1
]}

Fox, Dieter ^{[1
]}

Kautz, Henry ^{[1
]}

机构：

[1] Univ Washington, Dept Comp Sci & Engn, Seattle, WA 98195 USA

来源：

PROGRESS IN CONVERGENCE: TECHNOLOGIES FOR HUMAN WELLBEING | 2006年 / 1093卷

关键词：

personal map; GPS; Relational Markov Network (RMN); dynamic Bayesian Network (DBN);

D O I：

10.1196/annals.1382.017

中图分类号：

TB3 [工程材料学];

学科分类号：

0805 ; 080502 ;

摘要：

In this article we discuss an assisted cognition information technology system that can learn personal maps customized for each user and infer his daily activities and movements from raw GPS data. The system uses discriminative and generative models for different parts of this task. A discriminative relational Markov network is used to extract significant places and label them; a generative dynamic Bayesian network is used to learn transportation routines, and infer goals and potential user errors at real time. We focus on the basic structures of the models and briefly discuss the inference and learning techniques. Experiments show that our system is able to accurately extract and label places, predict the goals of a person, and recognize situations in which the user makes mistakes, such as taking a wrong bus.

引用

页码：249 / 265

页数：17