Home
This Title All WIREs
WIREs RSS Feed
How to cite this WIREs title:
WIREs Data Mining Knowl Discov
Impact Factor: 2.541

Sensor selection to support practical use of health‐monitoring smart environments

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

Abstract The data mining and pervasive sensing technologies found in smart homes offer unprecedented opportunities for providing health monitoring and assistance to individuals experiencing difficulties in living independently at home. In order to monitor the functional health of smart home residents, we need to design technologies that recognize and track activities that people normally perform as part of their daily routines. One question that frequently arises, however, is how many smart home sensors are needed and where should they be placed in order to accurately recognize activities? We employ data mining techniques to look at the problem of sensor selection for activity recognition in smart homes. We analyze the results based on six datasets collected in five distinct smart home environments. © 2011 John Wiley & Sons, Inc. WIREs Data Mining Knowl Discov 2011 1 339–351 DOI: 10.1002/widm.20 This article is categorized under: Application Areas > Science and Technology

Activity recognition accuracy for the Bosch1 dataset with a naïve Bayes classifier applied before and after applying clustering‐based feature selection and construction.

[ Normal View | Magnified View ]

Activity recognition accuracy for the Cairo dataset with a naïve Bayes classifier applied before and after applying clustering‐based feature selection and construction.

[ Normal View | Magnified View ]

Activity recognition accuracy for the Kyoto2 dataset with a naïve Bayes classifier applied before and after applying clustering‐based feature selection and construction.

[ Normal View | Magnified View ]

Activity recognition accuracy for the Kyoto1 dataset with a naïve Bayes classifier applied before and after applying clustering‐based feature selection and construction.

[ Normal View | Magnified View ]

The original number of clusters found in the Bosch3 environment and the final number of distinct clusters that result from the clustering algorithm without any decrease in recognition accuracy.

[ Normal View | Magnified View ]

The original number of clusters found in the Bosch2 environment and the final number of distinct clusters that result from the clustering algorithm without any decrease in recognition accuracy.

[ Normal View | Magnified View ]

The original number of clusters found in the Bosch1 environment and the final number of distinct clusters that result from the clustering algorithm without any decrease in recognition accuracy.

[ Normal View | Magnified View ]

The original number of clusters found in the Cairo environment and the final number of distinct clusters that result from the clustering algorithm without any decrease in recognition accuracy.

[ Normal View | Magnified View ]

The original number of clusters found in the Kyoto2 environment and the final number of distinct clusters that result from the clustering algorithm without any decrease in recognition accuracy.

[ Normal View | Magnified View ]

The original number of clusters found in the Kyoto1 environment and the final number of distinct clusters that result from the clustering algorithm without any decrease in recognition accuracy.

[ Normal View | Magnified View ]

Activity recognition accuracy (vertical axis) as a function of the number of sensors that are removed from the environment (horizontal axis) for each of the datasets.

[ Normal View | Magnified View ]

Charted activity occurrences for six datasets (from top left, these are Bosch1, Bosch2, Bosch3, Kyoto1, Kyoto2, and Cairo).

[ Normal View | Magnified View ]

Hidden Markov model for an activity recognition task with four hidden states (activities) and a set of observable nodes that correspond to possible sensor events.

[ Normal View | Magnified View ]

Bosch3 smart apartment which housed a single older adult resident.

[ Normal View | Magnified View ]

Bosch2 smart apartment which housed a single older adult resident.

[ Normal View | Magnified View ]

Bosch1 smart apartment which housed a single older adult resident.

[ Normal View | Magnified View ]

Cairo smart home which housed an older adult couple and a cat.

[ Normal View | Magnified View ]

Kyoto smart apartment testbed.

[ Normal View | Magnified View ]

Activity recognition accuracy for the Bosch3 dataset with conditional random fields applied before and after applying clustering‐based feature selection and construction.

[ Normal View | Magnified View ]

Activity recognition accuracy for the Bosch2 dataset with conditional random fields applied before and after applying clustering‐based feature selection and construction.

[ Normal View | Magnified View ]

Activity recognition accuracy for the Bosch1 dataset with conditional random fields applied before and after applying clustering‐based feature selection and construction.

[ Normal View | Magnified View ]

Activity recognition accuracy for the Cairo dataset with conditional random fields applied before and after applying clustering‐based feature selection and construction.

[ Normal View | Magnified View ]

Activity recognition accuracy for the Kyoto2 dataset with conditional random fields applied before and after applying clustering‐based feature selection and construction.

[ Normal View | Magnified View ]

Activity recognition accuracy for the Kyoto1 dataset with conditional random fields applied before and after applying clustering‐based feature selection and construction.

[ Normal View | Magnified View ]

Activity recognition accuracy for the Bosch3 dataset with a naïve Bayes classifier applied before and after applying clustering‐based feature selection and construction.

[ Normal View | Magnified View ]

Activity recognition accuracy for the Bosch2 dataset with a naïve Bayes classifier applied before and after applying clustering‐based feature selection and construction.

[ Normal View | Magnified View ]

Browse by Topic

Application Areas > Science and Technology

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts