Home > Publications
Home University of Twente
Prospective Students
Intranet (internal)

EEMCS EPrints Service

22478 Using Unsupervised Learning to Improve the Naive Bayes Classifier for Wireless Sensor Networks
Home Policy Brochure Browse Search User Area Contact Help

Zwartjes, G.J. and Havinga, P.J.M. and Smit, G.J.M. and Hurink, J.L. (2012) Using Unsupervised Learning to Improve the Naive Bayes Classifier for Wireless Sensor Networks. In: Proceedings of the Sixth International Conference on MObile Ubiquitous Computing, Systems, Services and Technologies, UBICOMM 2012, 23-28 Sep 2012, Barcelona, Spain. pp. 71-76. Xpert Publishing Services. ISBN 978-1-61208-236-3

Full text available as:

- Univ. of Twente only
1618 Kb

Official URL:

Exported to Metis


Online processing is essential for many sensor network applications. Sensor nodes can sample far more data than what can practically be transmitted using state of the art sensor network radios. Online processing, however, is complicated due to limited resources of individual nodes. The naive Bayes classifier is an algorithm proven to be suitable for online classification on Wireless Sensor Networks. In this paper, we investigate a new technique to improve the naive Bayes classifier while maintaining sensor network compatibility. We propose the application of unsupervised learning techniques to enhance the probability density estimation needed for naive Bayes, thereby achieving the benefits of binning histogram probability density estimation without the related memory requirements. Using an offline experimental dataset, we demonstrate the possibility of matching the performance of the binning histogram approach within the constraints provided by Wireless Sensor Network hardware. We validate the feasibility of our approach using an implementation based on Arduino Nano hardware combined with NRF24L01+ radios.

Item Type:Conference or Workshop Paper (Full Paper, Talk)
Research Group:EWI-CAES: Computer Architecture for Embedded Systems, EWI-PS: Pervasive Systems, EWI-DMMP: Discrete Mathematics and Mathematical Programming
Research Program:CTIT-WiSe: Wireless and Sensor Systems
Research Project:Real Time Enterprise
ID Code:22478
Deposited On:09 November 2012
More Information:statisticsmetis

Export this item as:

To request a copy of the PDF please email us request copy

To correct this item please ask your editor

Repository Staff Only: edit this item