Fast detection and location of failed array elements using the fast SVM algorithm

With the increased proliferation of array antennas, for a myriad of wireless applications, the monitoring and correction of array element failure is becoming more critical. In this paper, a fast Support Vector Machine (SVM) classifier, based on low-degree polynomial kernel is developed, to expeditiously detect and locate the failed elements of an arbitrary analog array, while categorizing the level of failure, at the same time. This method will work on any analog array configuration, and the results for a linear array sample are illustrated to demonstrate its effectiveness.

[1]  Patrick Haffner,et al.  Support vector machines for histogram-based image classification , 1999, IEEE Trans. Neural Networks.

[2]  Yoav Goldberg,et al.  splitSVM: Fast, Space-Efficient, non-Heuristic, Polynomial Kernel Computation for NLP Applications , 2008, ACL.

[3]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[4]  C.G. Christodoulou,et al.  Detecting failure of antenna array elements using machine learning optimization , 2007, 2007 IEEE Antennas and Propagation Society International Symposium.

[5]  S.H. Zainud-Deen,et al.  Array failure correction with orthogonal method , 2004, Proceedings of the Twenty-First National Radio Science Conference, 2004. NRSC 2004..

[6]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[7]  R. J. Mailloux,et al.  Array failure correction with a digitally beamformed array , 1996 .

[8]  Robert J. Mailloux,et al.  Source synthesis for training array neural networks , 1995 .

[9]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[10]  S.A. Mitilineos,et al.  On array failure mitigation using genetic algorithms and a priori joint optimization , 2005, IEEE Antennas and Propagation Magazine.

[11]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[12]  Marco Gori,et al.  On the problem of local minima in recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[13]  Yilong Lu,et al.  Array failure correction with a genetic algorithm , 1999 .

[14]  A. Patnaik,et al.  Finding failed element positions in linear antenna arrays using neural networks , 2006, 2006 IEEE Antennas and Propagation Society International Symposium.

[15]  Hampapathalu A. Nagarajaram,et al.  Support Vector Machine-based classification of protein folds using the structural properties of amino acid residues and amino acid residue pairs , 2007, Bioinform..

[16]  Jerzy Korczak,et al.  Optimization and global minimization methods suitable for neural networks , 1999 .

[17]  Francesca Odone,et al.  Histogram intersection kernel for image classification , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[18]  Da-Gang Fang,et al.  Combination of genetic algorithm and fast Fourier transform for array failure correction , 2003, 6th International SYmposium on Antennas, Propagation and EM Theory, 2003. Proceedings. 2003.