Fusion method of radar data and IFF data based on NMF

A new fusion method of radar data and IFF data based on nonnegative matrix factorization (NMF) is proposed in this paper, due to its strong part-based representation capability. The identification data from each sensor are put into one column of the input matrix and the fusion is realized by the converging process of a cost function. The proposed fusion method does not only show better performance in the credential level, but also has the advantage of limited computational load. The proposed method is simulated to validate the effectiveness and significant improvement in comparison with the data fusion algorithm under the framework of D-S evidential theory.

[1]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[2]  Zhi Huang,et al.  Application of Several Non-negative Matrix Factorization-Based Methods in Remote Sensing Image Fusion , 2008, 2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery.

[3]  P. van Genderen,et al.  A risk-based object-oriented approach to sensor management , 2005, 2005 7th International Conference on Information Fusion.

[5]  C. Cai,et al.  Multi-focus image fusing based on non-negative matrix factorization , 2007, 2007 14th International Conference on Mechatronics and Machine Vision in Practice.

[6]  Pingyuan Cui,et al.  An algorithm of data fusion combined neural networks with DS evidential theory , 2006, 2006 1st International Symposium on Systems and Control in Aerospace and Astronautics.

[7]  T. M. Schuck,et al.  Identification friend-or-foe (IFF) sensor uncertainties, ambiguities, deception and their application to the multi-source fusion process , 2000, Proceedings of the IEEE 2000 National Aerospace and Electronics Conference. NAECON 2000. Engineering Tomorrow (Cat. No.00CH37093).

[8]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[9]  Fuchun Sun,et al.  An adaptive PNN-DS approach to classification using multi-sensor information fusion , 2009, Neural Computing and Applications.