Utilizing Multiple Data Sources for Localization in Wireless Sensor Networks Based on Support Vector Machines
Summary :
Localization in wireless sensor networks is the problem of estimating the geographical locations of wireless sensor nodes. We propose a framework to utilizing multiple data sources for localization scheme based on support vector machines. The framework can be used with both classification and regression formulation of support vector machines. The proposed method uses only connectivity information. Multiple hop count data sources can be generated by adjusting the transmission power of sensor nodes to change the communication ranges. The optimal choice of communication ranges can be determined by evaluating mutual information. We consider two methods for integrating multiple data sources together; unif method and align method. The improved localization accuracy of the proposed framework is verified by simulation study.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E96-A No.11 pp.2081-2088
- Publication Date
- 2013/11/01
- Publicized
- Online ISSN
- 1745-1337
- DOI
- 10.1587/transfun.E96.A.2081
- Type of Manuscript
- Special Section PAPER (Special Section on Smart Multimedia & Communication Systems)
- Category
- Mobile Information Network and Personal Communications
Authors
Prakit JAROENKITTICHAI
Chulalongkorn University
Ekachai LEELARASMEE
Chulalongkorn University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Prakit JAROENKITTICHAI, Ekachai LEELARASMEE, "Utilizing Multiple Data Sources for Localization in Wireless Sensor Networks Based on Support Vector Machines" in IEICE TRANSACTIONS on Fundamentals,
vol. E96-A, no. 11, pp. 2081-2088, November 2013, doi: 10.1587/transfun.E96.A.2081.
Abstract: Localization in wireless sensor networks is the problem of estimating the geographical locations of wireless sensor nodes. We propose a framework to utilizing multiple data sources for localization scheme based on support vector machines. The framework can be used with both classification and regression formulation of support vector machines. The proposed method uses only connectivity information. Multiple hop count data sources can be generated by adjusting the transmission power of sensor nodes to change the communication ranges. The optimal choice of communication ranges can be determined by evaluating mutual information. We consider two methods for integrating multiple data sources together; unif method and align method. The improved localization accuracy of the proposed framework is verified by simulation study.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E96.A.2081/_p
Copy
@ARTICLE{e96-a_11_2081,
author={Prakit JAROENKITTICHAI, Ekachai LEELARASMEE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Utilizing Multiple Data Sources for Localization in Wireless Sensor Networks Based on Support Vector Machines},
year={2013},
volume={E96-A},
number={11},
pages={2081-2088},
abstract={Localization in wireless sensor networks is the problem of estimating the geographical locations of wireless sensor nodes. We propose a framework to utilizing multiple data sources for localization scheme based on support vector machines. The framework can be used with both classification and regression formulation of support vector machines. The proposed method uses only connectivity information. Multiple hop count data sources can be generated by adjusting the transmission power of sensor nodes to change the communication ranges. The optimal choice of communication ranges can be determined by evaluating mutual information. We consider two methods for integrating multiple data sources together; unif method and align method. The improved localization accuracy of the proposed framework is verified by simulation study.},
keywords={},
doi={10.1587/transfun.E96.A.2081},
ISSN={1745-1337},
month={November},}
Copy
TY - JOUR
TI - Utilizing Multiple Data Sources for Localization in Wireless Sensor Networks Based on Support Vector Machines
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2081
EP - 2088
AU - Prakit JAROENKITTICHAI
AU - Ekachai LEELARASMEE
PY - 2013
DO - 10.1587/transfun.E96.A.2081
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E96-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 2013
AB - Localization in wireless sensor networks is the problem of estimating the geographical locations of wireless sensor nodes. We propose a framework to utilizing multiple data sources for localization scheme based on support vector machines. The framework can be used with both classification and regression formulation of support vector machines. The proposed method uses only connectivity information. Multiple hop count data sources can be generated by adjusting the transmission power of sensor nodes to change the communication ranges. The optimal choice of communication ranges can be determined by evaluating mutual information. We consider two methods for integrating multiple data sources together; unif method and align method. The improved localization accuracy of the proposed framework is verified by simulation study.
ER -
English
