Learning a Taxonomy of Predefined and Discovered Activity Patterns

Narayanan Krishnan; Diane J Cook; Zachary Wemlinger

doi:10.3233/AIS-130230

Back

Learning a Taxonomy of Predefined and Discovered Activity Patterns

Journal article

Open access

Peer reviewed

Learning a Taxonomy of Predefined and Discovered Activity Patterns

Narayanan Krishnan, Diane J Cook and Zachary Wemlinger

Journal of ambient intelligence and smart environments, Vol.5(6), pp.621-637

2013

DOI: https://doi.org/10.3233/AIS-130230

Handle:

https://hdl.handle.net/2376/105091

PMCID: PMC4187388

PMID: 25302084

Files and links (1)

url

https://doi.org/10.3233/AIS-130230View

Published (Version of record) Open

Abstract

activity discovery

hierarchical clustering

activity recognition

Many intelligent systems that focus on the needs of a human require information about the activities that are being performed by the human. At the core of this capability is activity recognition. Activity recognition techniques have become robust but rarely scale to handle more than a few activities. They also rarely learn from more than one smart home data set because of inherent differences between labeling techniques. In this paper we investigate a data-driven approach to creating an activity taxonomy from sensor data found in disparate smart home datasets. We investigate how the resulting taxonomy can help analyze the relationship between classes of activities. We also analyze how the taxonomy can be used to scale activity recognition to a large number of activity classes and training datasets. We describe our approach and evaluate it on 34 smart home datasets. The results of the evaluation indicate that the hierarchical modeling can reduce training time while maintaining accuracy of the learned model.

Metrics

7 Record Views

Details

Title: Learning a Taxonomy of Predefined and Discovered Activity Patterns
Creators: Narayanan Krishnan - School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA 99164, USA
Diane J Cook - School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA 99164, USA
Zachary Wemlinger - School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA 99164, USA
Publication Details: Journal of ambient intelligence and smart environments, Vol.5(6), pp.621-637
Academic Unit: Electrical Engineering and Computer Science, School of
Publisher: Netherlands
Grant note: R01 EB009675 / NIBIB NIH HHS R01 EB015853 / NIBIB NIH HHS
Identifiers: 99900546929101842
Language: English
Resource Type: Journal article