Node cooperation based support vector machine localization algorithm in mobile wireless sensor networks

Qing Guo; Tao Tang

doi:10.1117/12.880253

15 April 2011 Node cooperation based support vector machine localization algorithm in mobile wireless sensor networks

Qing Guo, Tao Tang

Proceedings Volume 7982, Smart Sensor Phenomena, Technology, Networks, and Systems 2011; 79820N (2011) https://doi.org/10.1117/12.880253
Event: SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring, 2011, San Diego, California, United States

Abstract

In wireless sensor networks (WSNs), locations of sensors play a critical role in many applications. For some applications, the nodes are constantly moving in the network. Therefore, the positions of nodes in mobile WSNs can not be determined by current static localization algorithms. To solve this problem, a new centralized localization algorithm called node cooperation based support vector machine localization (NCBSVML) algorithm for mobile wireless sensor networks is proposed. NCBSVML algorithm classified the network into many classes, and justifies which class is node in. Then the NCBSVML algorithm determines the node location by filtering the impossible locations based on new observations. Our approach does not require additional hardware and works even when the movement of anchors and nodes is uncontrollable. The properties of our technique are analyzed from simulations. Our scheme outperforms the best known mobile localization schemes in accuracy and precision under a wide range of conditions.

Citation Download Citation

Qing Guo and Tao Tang "Node cooperation based support vector machine localization algorithm in mobile wireless sensor networks", Proc. SPIE 7982, Smart Sensor Phenomena, Technology, Networks, and Systems 2011, 79820N (15 April 2011); https://doi.org/10.1117/12.880253

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available