Article details

Title: High-Performance HRR ATR System Using GANN Concept
Author(s): Constantin-Iulian Vizitiu   Lucian Anton   Stelian Spînu   

Abstract: In accordance to specialized literature, a major scientific research direction to improve the performance level assigned to ATR systems is to use the specific paradigms belonging to artificial intelligence. Starting from the advantages given by the neuro-genetic architectures used in solving pattern recognition tasks, the paper proposes the application of a GANN system concept in the design of a high-performance ATR system based on HRR imagery use. Consequently, a proper genetic technique to optimize both the connectivity and training rule of MLP neural network used to implement the recognition function of an ATR system, is described. Finally, using a real HRR database, the theoretical and experimental results obtained confirm the increased potential of the proposed design algorithm to be implemented into real ATR systems.

Keywords: ATR system, GANN system concept, HRR imagery.

References:
[1] W.H. LICATA - Automatic Target Recognition (ATR) Beyond the Year 2000, In "NATO-RTO-EN-018: Technologies for Future Precision Strike Missile Systems", pp. 9.1-9.16, RTO/NATO, Neuilly-sur-Seine, France, Jul. 2001
[2] F. SADJADI, B. JAVIDI (Eds.) - Physics of Automatic Target Recognition, Springer, New York, NY, 2007
[3] C.I. VIZITIU - Neuro-Fuzzy-Genetic Architectures: Theory and Applications, Military Technical Academy Publishing House, Bucharest, Romania, 2011 (in Romanian)
[4] B.D. RIPLEY - Pattern Recognition and Neural Networks, Cambridge University Press, Cambridge, UK, 2007
[5] C.I. VIZITIU - Neural Networks Used in Video Pattern Recognition, Military Technical Academy Publishing House, Bucharest, Romania, 2002 (in Romanian)
[6] J. WANG, X. LIAO, Z. YI (Eds.) - Advances in Neural Networks - ISNN 2005: Second International Symposium on Neural Networks, Chongqing, China, May 30 - June 1, 2005: Proceedings, Part I, Springer-Verlag, Berlin, Germany, 2005
[7] S. HAYKIN - Neural Networks and Learning Machines, 3rd Edition, Prentice Hall, New York, NY, 2009
[8] R. KEMP - An Introduction to Genetic Algorithms for Neural Networks, University of Cambridge, UK, Jun. 5, 2006, http://www.msm.cam.ac.uk/ phase-trans/2006/ga_html_files/ga.html
[9] C.I. VIZITIU - Genetic Algorithms and Neural Networks: Theory and Applications, Military Technical Academy Publishing House, Bucharest, Romania, 2004 (in Romanian)
[10] P.G. BENARDOS, G.-C. VOSNIAKOS - Optimizing Feedforward Artificial Neural Network Architecture, Engineering Applications of Artificial Intelligence, Vol. 20, No. 3, pp. 365-382, Apr. 2007
[11] L.Y. TSENG, W.C. CHEN - A Two-Phase Genetic Local Search Algorithm for Feedforward Neural Network Training, Proc. of the International Joint Conference on Neural Networks, IJCNN