Inferring high-level behavior from low-level sensors

被引：0

作者：

Patterson, DJ ^{[1
]}

Lin, LA ^{[1
]}

Fox, D ^{[1
]}

Kautz, H ^{[1
]}

机构：

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

来源：

UBICOMP 2003: UBIQUITOUS COMPUTING | 2003年 / 2864卷

关键词：

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

We present a method of learning a Bayesian model of a traveler moving through an urban environment. This technique is novel in that it simultaneously learns a unified model of the traveler's current mode of transportation as well as his most likely route, in an unsupervised manner. The model is implemented using particle filters and learned using Expectation-Maximization. The training data is drawn from a GPS sensor stream that was collected by the authors over a period of three months. We demonstrate that by adding more external knowledge about bus routes and bus stops, accuracy is improved.

引用

页码：73 / 89

页数：17