Reliable context capturing for smart offices using a sensor network

Hiroto Aida, Jin Nakazawa, Hideyuki Tokuda

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In order to realise smart offices, which provides users with comfort via various digital services, we need to acquire context information about the target space. Contexts can be obtained from raw sensor data using context classification methods, such as Bayesian network. However, packet losses and disrupted communications in wireless sensor networks disables the context classification methods to collect all the necessary data, hence reduce quality of contexts. In this paper, we propose Reliable Hybrid Bayesian Inference Mechanism (RHBIM) that features in-network disruption-tolerant Bayesian inference with server-side calculation of Posterior Probability Tables. In this paper, we show the design and implementation of the mechanism with a range of disruption-tolerance schemes, and apply the mechanism to an application that controls air conditioners based on the ('comfort level') context. We also show the effectiveness of the mechanism comparing the different disruption-tolerance schemes.

Original languageEnglish
Pages (from-to)174-183
Number of pages10
JournalInternational Journal of Ad Hoc and Ubiquitous Computing
Volume7
Issue number3
DOIs
Publication statusPublished - 2011 May

Fingerprint

Sensor networks
Bayesian networks
Packet loss
Wireless sensor networks
Servers
Communication
Sensors
Air

Keywords

  • Air conditioning
  • Bayesian network
  • Sensor network
  • Smart office: Context classification

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Software

Cite this

Reliable context capturing for smart offices using a sensor network. / Aida, Hiroto; Nakazawa, Jin; Tokuda, Hideyuki.

In: International Journal of Ad Hoc and Ubiquitous Computing, Vol. 7, No. 3, 05.2011, p. 174-183.

Research output: Contribution to journalArticle

@article{2faedc095b4a47e7b1722a85d662c8d7,
title = "Reliable context capturing for smart offices using a sensor network",
abstract = "In order to realise smart offices, which provides users with comfort via various digital services, we need to acquire context information about the target space. Contexts can be obtained from raw sensor data using context classification methods, such as Bayesian network. However, packet losses and disrupted communications in wireless sensor networks disables the context classification methods to collect all the necessary data, hence reduce quality of contexts. In this paper, we propose Reliable Hybrid Bayesian Inference Mechanism (RHBIM) that features in-network disruption-tolerant Bayesian inference with server-side calculation of Posterior Probability Tables. In this paper, we show the design and implementation of the mechanism with a range of disruption-tolerance schemes, and apply the mechanism to an application that controls air conditioners based on the ('comfort level') context. We also show the effectiveness of the mechanism comparing the different disruption-tolerance schemes.",
keywords = "Air conditioning, Bayesian network, Sensor network, Smart office: Context classification",
author = "Hiroto Aida and Jin Nakazawa and Hideyuki Tokuda",
year = "2011",
month = "5",
doi = "10.1504/IJAHUC.2011.040117",
language = "English",
volume = "7",
pages = "174--183",
journal = "International Journal of Ad Hoc and Ubiquitous Computing",
issn = "1743-8225",
publisher = "Inderscience Enterprises Ltd",
number = "3",

}

TY - JOUR

T1 - Reliable context capturing for smart offices using a sensor network

AU - Aida, Hiroto

AU - Nakazawa, Jin

AU - Tokuda, Hideyuki

PY - 2011/5

Y1 - 2011/5

N2 - In order to realise smart offices, which provides users with comfort via various digital services, we need to acquire context information about the target space. Contexts can be obtained from raw sensor data using context classification methods, such as Bayesian network. However, packet losses and disrupted communications in wireless sensor networks disables the context classification methods to collect all the necessary data, hence reduce quality of contexts. In this paper, we propose Reliable Hybrid Bayesian Inference Mechanism (RHBIM) that features in-network disruption-tolerant Bayesian inference with server-side calculation of Posterior Probability Tables. In this paper, we show the design and implementation of the mechanism with a range of disruption-tolerance schemes, and apply the mechanism to an application that controls air conditioners based on the ('comfort level') context. We also show the effectiveness of the mechanism comparing the different disruption-tolerance schemes.

AB - In order to realise smart offices, which provides users with comfort via various digital services, we need to acquire context information about the target space. Contexts can be obtained from raw sensor data using context classification methods, such as Bayesian network. However, packet losses and disrupted communications in wireless sensor networks disables the context classification methods to collect all the necessary data, hence reduce quality of contexts. In this paper, we propose Reliable Hybrid Bayesian Inference Mechanism (RHBIM) that features in-network disruption-tolerant Bayesian inference with server-side calculation of Posterior Probability Tables. In this paper, we show the design and implementation of the mechanism with a range of disruption-tolerance schemes, and apply the mechanism to an application that controls air conditioners based on the ('comfort level') context. We also show the effectiveness of the mechanism comparing the different disruption-tolerance schemes.

KW - Air conditioning

KW - Bayesian network

KW - Sensor network

KW - Smart office: Context classification

UR - http://www.scopus.com/inward/record.url?scp=79957441044&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79957441044&partnerID=8YFLogxK

U2 - 10.1504/IJAHUC.2011.040117

DO - 10.1504/IJAHUC.2011.040117

M3 - Article

AN - SCOPUS:79957441044

VL - 7

SP - 174

EP - 183

JO - International Journal of Ad Hoc and Ubiquitous Computing

JF - International Journal of Ad Hoc and Ubiquitous Computing

SN - 1743-8225

IS - 3

ER -