Use of wireless sensor networks for distributed event detection in disaster management applications

M. Bahrepour, Nirvana Meratnia, Mannes Poel, Zahra Taghikhaki, Paul J.M. Havinga

Abstract

Recently, wireless sensor networks (WSNs) have become mature enough to go beyond being simple fine-grained continuous monitoring platforms and have become one of the enabling technologies for early-warning disaster systems. Event detection functionality of WSNs can be of great help and importance for (near) real-time detection of, for example, meteorological natural hazards and wild and residential fires. From the data-mining perspective, many real world events exhibit specific patterns, which can be detected by applying machine learning (ML) techniques. In this paper, we introduce ML techniques for distributed event detection in WSNs and evaluate their performance and applicability for early detection of disasters, specifically residential fires. To this end, we present a distributed event detection approach incorporating a novel reputation-based voting and the decision tree and evaluate its performance in terms of detection accuracy and time complexity.
Original languageUndefined
Pages (from-to)58-69
Number of pages12
JournalInternational Journal of Space-Based and Situated Computing
Volume2
Issue number1
DOIs
StatePublished - Feb 2012

Fingerprint

Wireless sensor networks
Disasters
Learning systems
Fires
Decision trees
Data mining
Hazards
Monitoring

Keywords

  • situated computing
  • EWI-21739
  • Event Detection
  • IR-80433
  • Wireless Sensor Networks
  • WSNs
  • METIS-296048
  • Disaster early warning systems

Cite this

@article{cce36918a4e449a792eda37cd9a91ad4,
title = "Use of wireless sensor networks for distributed event detection in disaster management applications",
abstract = "Recently, wireless sensor networks (WSNs) have become mature enough to go beyond being simple fine-grained continuous monitoring platforms and have become one of the enabling technologies for early-warning disaster systems. Event detection functionality of WSNs can be of great help and importance for (near) real-time detection of, for example, meteorological natural hazards and wild and residential fires. From the data-mining perspective, many real world events exhibit specific patterns, which can be detected by applying machine learning (ML) techniques. In this paper, we introduce ML techniques for distributed event detection in WSNs and evaluate their performance and applicability for early detection of disasters, specifically residential fires. To this end, we present a distributed event detection approach incorporating a novel reputation-based voting and the decision tree and evaluate its performance in terms of detection accuracy and time complexity.",
keywords = "situated computing, EWI-21739, Event Detection, IR-80433, Wireless Sensor Networks, WSNs, METIS-296048, Disaster early warning systems",
author = "M. Bahrepour and Nirvana Meratnia and Mannes Poel and Zahra Taghikhaki and Havinga, {Paul J.M.}",
note = "eemcs-eprint-21739",
year = "2012",
month = "2",
doi = "10.1504/IJSSC.2012.045569",
volume = "2",
pages = "58--69",
journal = "International Journal of Space-Based and Situated Computing",
issn = "2044-4893",
number = "1",

}

TY - JOUR

T1 - Use of wireless sensor networks for distributed event detection in disaster management applications

AU - Bahrepour,M.

AU - Meratnia,Nirvana

AU - Poel,Mannes

AU - Taghikhaki,Zahra

AU - Havinga,Paul J.M.

N1 - eemcs-eprint-21739

PY - 2012/2

Y1 - 2012/2

N2 - Recently, wireless sensor networks (WSNs) have become mature enough to go beyond being simple fine-grained continuous monitoring platforms and have become one of the enabling technologies for early-warning disaster systems. Event detection functionality of WSNs can be of great help and importance for (near) real-time detection of, for example, meteorological natural hazards and wild and residential fires. From the data-mining perspective, many real world events exhibit specific patterns, which can be detected by applying machine learning (ML) techniques. In this paper, we introduce ML techniques for distributed event detection in WSNs and evaluate their performance and applicability for early detection of disasters, specifically residential fires. To this end, we present a distributed event detection approach incorporating a novel reputation-based voting and the decision tree and evaluate its performance in terms of detection accuracy and time complexity.

AB - Recently, wireless sensor networks (WSNs) have become mature enough to go beyond being simple fine-grained continuous monitoring platforms and have become one of the enabling technologies for early-warning disaster systems. Event detection functionality of WSNs can be of great help and importance for (near) real-time detection of, for example, meteorological natural hazards and wild and residential fires. From the data-mining perspective, many real world events exhibit specific patterns, which can be detected by applying machine learning (ML) techniques. In this paper, we introduce ML techniques for distributed event detection in WSNs and evaluate their performance and applicability for early detection of disasters, specifically residential fires. To this end, we present a distributed event detection approach incorporating a novel reputation-based voting and the decision tree and evaluate its performance in terms of detection accuracy and time complexity.

KW - situated computing

KW - EWI-21739

KW - Event Detection

KW - IR-80433

KW - Wireless Sensor Networks

KW - WSNs

KW - METIS-296048

KW - Disaster early warning systems

U2 - 10.1504/IJSSC.2012.045569

DO - 10.1504/IJSSC.2012.045569

M3 - Article

VL - 2

SP - 58

EP - 69

JO - International Journal of Space-Based and Situated Computing

T2 - International Journal of Space-Based and Situated Computing

JF - International Journal of Space-Based and Situated Computing

SN - 2044-4893

IS - 1

ER -