Analyzing Activity Recognition Uncertainties in Smart Home Environments

Eunju Kim, Sumi Helal, CD Nugent, Mark Beattie

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

In spite of the importance of activity recognition (AR) for intelligent human-computer interaction in emerging smart space applications, state-of-the-art AR technology is not ready or adequate for real-world deployments due to its insufficient accuracy. The accuracy limitation is directly attributed to uncertainties stemming from multiple sources in the AR system. Hence, one of the major goals of AR research is to improve system accuracy by minimizing or managing the uncertainties encountered throughout the AR process. As we cannot manage uncertainties well without measuring them, we must first quantify their impact. Nevertheless, such a quantification process is very challenging given that uncertainties come from diverse and heterogeneous sources. In this article, we propose an approach, which can account for multiple uncertainty sources and assess their impact on AR systems. We introduce several metrics to quantify the various uncertainties and their impact. We then conduct a quantitative impact analysis of uncertainties utilizing data collected from actual smart spaces that we have instrumented. The analysis is intended to serve as groundwork for developing “diagnostic” accuracy measures of AR systems capable of pinpointing the sources of accuracy loss. This is to be contrasted with the currently used accuracy measures.
LanguageEnglish
Pages1-28
JournalACM Transactions on Intelligent Systems and Technology
Volume6
Issue number4
DOIs
Publication statusPublished - 2015

Fingerprint

Activity Recognition
Smart Home
Uncertainty
Smart Spaces
Quantify
Diagnostic Accuracy
Space applications
Human computer interaction
Quantification
Metric
Interaction

Keywords

  • Reasoning under uncertainty

Cite this

@article{2b9dca5a176b4a8b80b1e0c4ee4c0daf,
title = "Analyzing Activity Recognition Uncertainties in Smart Home Environments",
abstract = "In spite of the importance of activity recognition (AR) for intelligent human-computer interaction in emerging smart space applications, state-of-the-art AR technology is not ready or adequate for real-world deployments due to its insufficient accuracy. The accuracy limitation is directly attributed to uncertainties stemming from multiple sources in the AR system. Hence, one of the major goals of AR research is to improve system accuracy by minimizing or managing the uncertainties encountered throughout the AR process. As we cannot manage uncertainties well without measuring them, we must first quantify their impact. Nevertheless, such a quantification process is very challenging given that uncertainties come from diverse and heterogeneous sources. In this article, we propose an approach, which can account for multiple uncertainty sources and assess their impact on AR systems. We introduce several metrics to quantify the various uncertainties and their impact. We then conduct a quantitative impact analysis of uncertainties utilizing data collected from actual smart spaces that we have instrumented. The analysis is intended to serve as groundwork for developing “diagnostic” accuracy measures of AR systems capable of pinpointing the sources of accuracy loss. This is to be contrasted with the currently used accuracy measures.",
keywords = "Reasoning under uncertainty",
author = "Eunju Kim and Sumi Helal and CD Nugent and Mark Beattie",
year = "2015",
doi = "10.1145/2651445",
language = "English",
volume = "6",
pages = "1--28",
journal = "ACM Transactions on Intelligent Systems and Technology",
issn = "2157-6904",
number = "4",

}

Analyzing Activity Recognition Uncertainties in Smart Home Environments. / Kim, Eunju; Helal, Sumi; Nugent, CD; Beattie, Mark.

In: ACM Transactions on Intelligent Systems and Technology, Vol. 6, No. 4, 2015, p. 1-28.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Analyzing Activity Recognition Uncertainties in Smart Home Environments

AU - Kim, Eunju

AU - Helal, Sumi

AU - Nugent, CD

AU - Beattie, Mark

PY - 2015

Y1 - 2015

N2 - In spite of the importance of activity recognition (AR) for intelligent human-computer interaction in emerging smart space applications, state-of-the-art AR technology is not ready or adequate for real-world deployments due to its insufficient accuracy. The accuracy limitation is directly attributed to uncertainties stemming from multiple sources in the AR system. Hence, one of the major goals of AR research is to improve system accuracy by minimizing or managing the uncertainties encountered throughout the AR process. As we cannot manage uncertainties well without measuring them, we must first quantify their impact. Nevertheless, such a quantification process is very challenging given that uncertainties come from diverse and heterogeneous sources. In this article, we propose an approach, which can account for multiple uncertainty sources and assess their impact on AR systems. We introduce several metrics to quantify the various uncertainties and their impact. We then conduct a quantitative impact analysis of uncertainties utilizing data collected from actual smart spaces that we have instrumented. The analysis is intended to serve as groundwork for developing “diagnostic” accuracy measures of AR systems capable of pinpointing the sources of accuracy loss. This is to be contrasted with the currently used accuracy measures.

AB - In spite of the importance of activity recognition (AR) for intelligent human-computer interaction in emerging smart space applications, state-of-the-art AR technology is not ready or adequate for real-world deployments due to its insufficient accuracy. The accuracy limitation is directly attributed to uncertainties stemming from multiple sources in the AR system. Hence, one of the major goals of AR research is to improve system accuracy by minimizing or managing the uncertainties encountered throughout the AR process. As we cannot manage uncertainties well without measuring them, we must first quantify their impact. Nevertheless, such a quantification process is very challenging given that uncertainties come from diverse and heterogeneous sources. In this article, we propose an approach, which can account for multiple uncertainty sources and assess their impact on AR systems. We introduce several metrics to quantify the various uncertainties and their impact. We then conduct a quantitative impact analysis of uncertainties utilizing data collected from actual smart spaces that we have instrumented. The analysis is intended to serve as groundwork for developing “diagnostic” accuracy measures of AR systems capable of pinpointing the sources of accuracy loss. This is to be contrasted with the currently used accuracy measures.

KW - Reasoning under uncertainty

U2 - 10.1145/2651445

DO - 10.1145/2651445

M3 - Article

VL - 6

SP - 1

EP - 28

JO - ACM Transactions on Intelligent Systems and Technology

T2 - ACM Transactions on Intelligent Systems and Technology

JF - ACM Transactions on Intelligent Systems and Technology

SN - 2157-6904

IS - 4

ER -