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

Improved D-S evidence combination rule based on reliability of sensors

LI Changxi;ZHOU Yan;LIN Han;GUO Ge;Air Force Early Warning Academy;Unit No.66132 of PLA;Dongfang College,Fujian Agriculture and Forestry University;  
On target recognition algorithm of multi-source information fusion based on Dempster-Shafer(DS)evidence theory,the influence caused by combination results of sensors is rarely considered.In order to solve this problem,a D-S evidence combination rule considering the reliability of sensors was proposed.First,the confidence distance between the sensor and the reference sensor about any feature was established,the correlation coefficient of the traditional gray relational analysis method by confidence distance modified,and then the reliability of sensors calculated.Secondly,the global conflict coefficient was defined by any obtained evidence by similarity between evidences,and then the reliability of evidences was got by combining the reliability and global conflict coefficient.Finally,the D-S evidence theory was corrected according to the reliability of evidences and a new evidence combination rule proposed.Experimental data show that compared with pre-existing algorithm,the new method can recognize targets better and deal with conflict evidence more effective.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved