DocumentCode :
478273
Title :
Research on AIN Applied to Information Fusion
Author :
Ge, Hong ; Tian, Lian-Fang
Author_Institution :
Coll. of Autom. Sci. & Eng., South China Univ. of Technol., Guangzhou
Volume :
4
fYear :
2008
fDate :
18-20 Oct. 2008
Firstpage :
222
Lastpage :
227
Abstract :
Information fusion technology is a new method to integrate and manage multi-sensor data in order to obtain a more accurate detection or identification. With the improvement of intelligent level of modern technology, information fusion will become the inevitable choice of modern detection and identification technology. But how to integrate these multi-sources data together to obtain better results in pattern recognition area still remains a difficult problem. In this paper, a new information fusion algorithm is provided based on artificial immune network (AIN). Though there are many researches on using AIN as a clustering analysis method, there is no report about using AIN as an information fusion algorithm. The key techniques of detection and identification are clustering analysis and classification, and AIN can do these works well, so we suppose it possible and promising to use AIN as an information fusion algorithm. In this paper, a preliminary attempt is given, and the results of two experiments show that this attempt is practicable and effective.
Keywords :
neural nets; pattern classification; pattern clustering; sensor fusion; artificial immune network; clustering analysis method; detection technology; identification technology; information fusion technology; multisensor data; Algorithm design and analysis; Application software; Artificial immune systems; Clustering algorithms; Data engineering; Immune system; Information analysis; Information processing; Pattern recognition; Space technology; Arificial Immnue Network; Artificial Immune System; Information Fusion;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Natural Computation, 2008. ICNC '08. Fourth International Conference on
Conference_Location :
Jinan
Print_ISBN :
978-0-7695-3304-9
Type :
conf
DOI :
10.1109/ICNC.2008.397
Filename :
4667279
Link To Document :
بازگشت