Full-Text Search:
Home|About CNKI|User Service|中文
Add to Favorite Get Latest Update

Self-Localization Algorithms Based on Manifold Learning Algorithm in Wireless Sensor Networks

LI Shan-cang1,ZHANG De-yun1,YANG Gong-yuan2(School of Electronics and Information Engineering,Xi'an Jiaotong University,Xi'an 710049,China)  
Wireless sensor network is a novel technology platform for information processing,which have been proposed for a multitude of diverse applications.The localization of sensor nodes in wireless sensor networks determining where a given node is physically or relatively located in the networks,is a challenging one and yet crucial for many applications.Firstly,the sensor node localization framework based on multidimensional scaling(MDS)was presented,and a distributed sensor localization method by using iterative MDS(IMDS)was proposed.The main idea of this method is as follows:IMDS technique is applied to recover a series of local maps and the relative coordinates for adjacent sensors in two(or three)dimension space,the maps are stitched together to estimated the all sensors relative coordinates.Finally,the local mapping relation of nodes is matched according to the coordinates of the reference nodes so as to acquire the global mapping of node's coordinates.Simulation results demonstrated that the proposed algorithm can increase the locating precision and computing efficiency,and the locating error is about 15% less than that of dwMDS and the faster about 20% than dwMDS.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved