Abstract

Wireless Sensor Networks are tiny devices equipped with sensors and wireless communication. These devices observe environments and communicatie about these observations. Machine Learning techniques are of interest for Wireless Sensor Network applications since they can reduce the amount of needed communication and as a result the amount of energy that is used. The application of Machine Learning for Wireless Sensor Networks is not straightforward. For example, distributed computations, energy constraints and memory limitations make the careful selection of algorithms and the application architecture critical. Most Machine Learning research was not conducted with these aspects in mind. Feed Forward Neural Networks, for example, have limited options for distributed execution, while the accuracy of Decision Trees is very sensitive to the failure of sensor nodes. This thesis introduces a new classification algorithm, named QUEST: QUantile Estimation after Supervised Training. QUEST is based on the Naive Bayes classifier and was designed to be suitable for Wireless Sensor Networks. Properties of interest that are inherited from regular Naive Bayes are flexibility with regard to distributed implementation and robustness with regard to hardware failure of individual components. A new property of QUEST is that it eliminates the need for online supervised learning by using unsupervised learning techniques to adapt itself to new environments. As such, QUEST enables the efficient deployment of Wireless Sensor Networks and reduces the manual maintenance required in case of battery depletion.
Original languageEnglish
Awarding Institution
  • University of Twente
Supervisors/Advisors
  • Havinga, Paul J.M., Supervisor
  • Smit, Gerardus Johannes Maria, Supervisor
  • Hurink, Johann L., Advisor
Date of Award24 Feb 2017
Place of PublicationEnschede
Publisher
Print ISBNs978-90-365-4263-0
DOIs
StatePublished - 24 Feb 2017

Fingerprint

Wireless sensor networks
Learning systems
Unsupervised learning
Feedforward neural networks
Communication
Supervised learning
Decision trees
Sensor nodes
Classifiers
Hardware
Sensors

Keywords

  • METIS-321460
  • IR-103464

Cite this

Zwartjes, G. J. (2017). Adaptive Naive Bayes classification for wireless sensor networks Enschede: Universiteit Twente DOI: 10.3990/1.9789036542630
Zwartjes, G.J.. / Adaptive Naive Bayes classification for wireless sensor networks. Enschede : Universiteit Twente, 2017. 117 p.
@misc{3bb93a87439c43b7b9824e74173e4c86,
title = "Adaptive Naive Bayes classification for wireless sensor networks",
abstract = "Wireless Sensor Networks are tiny devices equipped with sensors and wireless communication. These devices observe environments and communicatie about these observations. Machine Learning techniques are of interest for Wireless Sensor Network applications since they can reduce the amount of needed communication and as a result the amount of energy that is used. The application of Machine Learning for Wireless Sensor Networks is not straightforward. For example, distributed computations, energy constraints and memory limitations make the careful selection of algorithms and the application architecture critical. Most Machine Learning research was not conducted with these aspects in mind. Feed Forward Neural Networks, for example, have limited options for distributed execution, while the accuracy of Decision Trees is very sensitive to the failure of sensor nodes. This thesis introduces a new classification algorithm, named QUEST: QUantile Estimation after Supervised Training. QUEST is based on the Naive Bayes classifier and was designed to be suitable for Wireless Sensor Networks. Properties of interest that are inherited from regular Naive Bayes are flexibility with regard to distributed implementation and robustness with regard to hardware failure of individual components. A new property of QUEST is that it eliminates the need for online supervised learning by using unsupervised learning techniques to adapt itself to new environments. As such, QUEST enables the efficient deployment of Wireless Sensor Networks and reduces the manual maintenance required in case of battery depletion.",
keywords = "METIS-321460, IR-103464",
author = "G.J. Zwartjes",
year = "2017",
month = "2",
doi = "10.3990/1.9789036542630",
isbn = "978-90-365-4263-0",
publisher = "Universiteit Twente",
school = "University of Twente",

}

Zwartjes, GJ 2017, 'Adaptive Naive Bayes classification for wireless sensor networks', University of Twente, Enschede. DOI: 10.3990/1.9789036542630

Adaptive Naive Bayes classification for wireless sensor networks. / Zwartjes, G.J.

Enschede : Universiteit Twente, 2017. 117 p.

Research output: ScientificPhD Thesis - Research UT, graduation UT

TY - THES

T1 - Adaptive Naive Bayes classification for wireless sensor networks

AU - Zwartjes,G.J.

PY - 2017/2/24

Y1 - 2017/2/24

N2 - Wireless Sensor Networks are tiny devices equipped with sensors and wireless communication. These devices observe environments and communicatie about these observations. Machine Learning techniques are of interest for Wireless Sensor Network applications since they can reduce the amount of needed communication and as a result the amount of energy that is used. The application of Machine Learning for Wireless Sensor Networks is not straightforward. For example, distributed computations, energy constraints and memory limitations make the careful selection of algorithms and the application architecture critical. Most Machine Learning research was not conducted with these aspects in mind. Feed Forward Neural Networks, for example, have limited options for distributed execution, while the accuracy of Decision Trees is very sensitive to the failure of sensor nodes. This thesis introduces a new classification algorithm, named QUEST: QUantile Estimation after Supervised Training. QUEST is based on the Naive Bayes classifier and was designed to be suitable for Wireless Sensor Networks. Properties of interest that are inherited from regular Naive Bayes are flexibility with regard to distributed implementation and robustness with regard to hardware failure of individual components. A new property of QUEST is that it eliminates the need for online supervised learning by using unsupervised learning techniques to adapt itself to new environments. As such, QUEST enables the efficient deployment of Wireless Sensor Networks and reduces the manual maintenance required in case of battery depletion.

AB - Wireless Sensor Networks are tiny devices equipped with sensors and wireless communication. These devices observe environments and communicatie about these observations. Machine Learning techniques are of interest for Wireless Sensor Network applications since they can reduce the amount of needed communication and as a result the amount of energy that is used. The application of Machine Learning for Wireless Sensor Networks is not straightforward. For example, distributed computations, energy constraints and memory limitations make the careful selection of algorithms and the application architecture critical. Most Machine Learning research was not conducted with these aspects in mind. Feed Forward Neural Networks, for example, have limited options for distributed execution, while the accuracy of Decision Trees is very sensitive to the failure of sensor nodes. This thesis introduces a new classification algorithm, named QUEST: QUantile Estimation after Supervised Training. QUEST is based on the Naive Bayes classifier and was designed to be suitable for Wireless Sensor Networks. Properties of interest that are inherited from regular Naive Bayes are flexibility with regard to distributed implementation and robustness with regard to hardware failure of individual components. A new property of QUEST is that it eliminates the need for online supervised learning by using unsupervised learning techniques to adapt itself to new environments. As such, QUEST enables the efficient deployment of Wireless Sensor Networks and reduces the manual maintenance required in case of battery depletion.

KW - METIS-321460

KW - IR-103464

U2 - 10.3990/1.9789036542630

DO - 10.3990/1.9789036542630

M3 - PhD Thesis - Research UT, graduation UT

SN - 978-90-365-4263-0

PB - Universiteit Twente

ER -

Zwartjes GJ. Adaptive Naive Bayes classification for wireless sensor networks. Enschede: Universiteit Twente, 2017. 117 p. Available from, DOI: 10.3990/1.9789036542630