Inferring High-Level Behavior from Low-Level Sensors.
Proc. of the International Conference on
Ubiquitous Computing (UBICOMP-03).
Abstract
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.
Download
Full paper [pdf]
(552 kb), [ps.gz] (628 kb), 18 pages.