Multi-dimensional Capon spectral estimation using discrete Zhang neural networks. (English) Zbl 1268.93134
Summary: The minimum variance spectral estimator, also known as the Capon spectral estimator, is a high resolution spectral estimator used extensively in practice. In this paper, we derive a novel implementation of a very computationally demanding matched filter-bank based a spectral estimator, namely the multi-dimensional Capon spectral estimator. To avoid the direct computation of the inverse covariance matrix used to estimate the Capon spectrum which can be computationally very expensive, particularly when the dimension of the matrix is large, we propose to use the discrete Zhang neural network for the online covariance matrix inversion. The computational complexity of the proposed algorithm for one-dimensional (1-D), as well as for two-dimensional (2-D) and three-dimensional (3-D) data sequences is lower when a parallel implementation is used.
MSC:
| 93E10 | Estimation and detection in stochastic control theory |
| 93B60 | Eigenvalue problems |
| 93E25 | Computational methods in stochastic control (MSC2010) |
Keywords:
multi-dimensional spectral estimation; covariance matrix; discrete Zhang neural network; 3-D imaging; multi-dimensional Capon spectral estimation; high resolution spectral estimator; inverse covariance matrix; computational complexityReferences:
| [1] | Benesty, J., Chen, J., & Huang, Y., (2007). Recursive and fast recursive Capon spectral estimators. EURASIP Journal on Advances in Signal Processing. doi:10.1155/2007/45194. · Zbl 1168.94399 |
| [2] | Capon J. (1969) High resolution frequency wave number spectrum analysis. Proceedings of the IEEE 57(8): 1408-1418 · doi:10.1109/PROC.1969.7278 |
| [3] | Eberhardt S. P., Tawel R., Brown T. X., Daud T., Thakoor A. P. (1992) Analog VLSI neural networks: Implementation issues and examples in optimization and supervised learning. IEEE Transactions on Industrial Electronics 39(6): 552-564 · doi:10.1109/41.170975 |
| [4] | Glentis G. O. (2008) A fast algorithm for APES and Capon spectral estimation. IEEE Transactions on Signal Processing 56(9): 4207-4220 · Zbl 1390.94193 · doi:10.1109/TSP.2008.925940 |
| [5] | Glentis G. O. (2010) Efficient algorithms for adaptive Capon and APES spectral estimation. IEEE Transactions on Signal Processing 58(1): 84-96 · Zbl 1392.94218 · doi:10.1109/TSP.2009.2028935 |
| [6] | Gohberg I., Olshevsky V. (1994) Complexity of multiplication with vectors for structured matrices. Linear Algebra and its Applications 202: 163-192 · Zbl 0803.65053 · doi:10.1016/0024-3795(94)90189-9 |
| [7] | Kay S., Pakula L. (2010) Convergence of the multidimensional minimum variance spectral estimator for continuous and mixed spectra. IEEE Signal Processing Letters 17(1): 1-4 · doi:10.1109/LSP.2009.2031715 |
| [8] | Kailath T., Sayed A. H. (1995) Displacement structure: Theory and applications. SIAM Review 37(3): 297-386 · Zbl 0839.65028 · doi:10.1137/1037082 |
| [9] | Kailath, T., Sayed, A. H. (eds) (1999) Fast reliable algorithms for matrices with structure. SIAM Publications, Philadelphia, PA · Zbl 0931.65018 |
| [10] | Kailath T., Kung S. Y., Morf M. (1979) Displacement ranks of matrices and linear equations. Journal of Mathematical Analysis and Applications 68(2): 395-407 · Zbl 0433.15001 · doi:10.1016/0022-247X(79)90124-0 |
| [11] | Larsson E., Stoica P. (2002) Fast implementation of two-dimensional APES and Capon spectral estimators. Multidimensional Systems and Signal Processing 13(1): 35-54 · Zbl 0996.93086 · doi:10.1023/A:1013891327453 |
| [12] | Li H., Li J., Stoica P. (1998) Performance analysis of forward-backward matched-filterbank spectral estimators. IEEE Transactions on Signal Processing 46(7): 1954-1966 · doi:10.1109/78.700967 |
| [13] | Liu Z. S., Li H., Li J. (1998) Efficient implementation of Capon and APES for spectral estimation. IEEE Transactions on Aerospace and Electronic Systems 34(4): 1314-1319 · doi:10.1109/7.722716 |
| [14] | Lombardini, F., Cai, F., & Pardini, M. (2009). Parametric differential SAR tomography of decorrelating volume scatterers. In Proceedings of the 6th European Radar conference. doi:270-273.978-2-87487-014-9. |
| [15] | Lombardini, F., Pardini, M., & Verrazzani, L. (2008). A robust multibaseline sector interpolator for 3D SAR imaging. In Proceedings of the EUSAR 2008, Friedrichshafen, Germany. · Zbl 1059.65032 |
| [16] | Marple, S. L., Jr. Adeli, M., & Liu, H. (2010). Super-fast algorithm for minimum variance (Capon) spectral estimation. In Conference on signals, systems and computers (ASILOMAR). doi:10.1109/ACSSC.2010.5757893. |
| [17] | McClellan J. H. (1982) Multidimensional spectral estimation. Proceeding of the IEEE 70(9): 1029-1039 · doi:10.1109/PROC.1982.12431 |
| [18] | Musicus B. R. (1985) Fast MLM power spectrum estimation from uniformly spaced correlations. IEEE Transactions on Acoustics, Speech and Signal Processing 33(4): 1333-1335 · doi:10.1109/TASSP.1985.1164696 |
| [19] | Pan V. Y., Barel M. V., Wang X., Codevico G. (2004) Iterative inversion of structured matrices. Theoretical Computer Science 315(2-3): 581-592 · Zbl 1059.65032 · doi:10.1016/j.tcs.2004.01.008 |
| [20] | Pan V. Y. (2001) Structured matrices and polynomials: Unified superfast algorithms. Birkhäser/Springer, Boston/New York · Zbl 0996.65028 · doi:10.1007/978-1-4612-0129-8 |
| [21] | Pan, V. Y., Rami, Y., & Wang, X. (2002). Structured matrices and Newton’s iteration: unified approach. In Linear algebra and its applications, (343-344), 233-265 · Zbl 0998.65039 |
| [22] | Raj P C. P., Pinjare S. L. (2009) Design and analog VLSI implementation of neural network architecture for signal processing. European Journal of Scientific Research 27(2): 199-216 |
| [23] | Rahman S. A., Ansari M. S. (2011) A neural circuit with transcendental energy function for solving system of linear equations. Analog Integrated Circuit and Signal Processing 66(3): 433-440. doi:10.1007/s10470-010-9524-2 · doi:10.1007/s10470-010-9524-2 |
| [24] | Xiao L., Zhang Y. (2011) Zhang neural network versus Gradient neural network for solving time-varying linear inequalities. IEEE Transactions on Neural Networks 22(10): 1676-1684 · doi:10.1109/TNN.2011.2163318 |
| [25] | Zhang, Y., Cai, B., Liang, M. & Ma, W. (2008). On the variable step-size of discrete-time Zhang neural network and Newton iteration for constant matrix inversion. In Second international symposium on intelligent information technology application. doi:10.1109/IITA.2008.128. |
| [26] | Zhang, Y., Chen, K., Ma, W., & Xiao, L. (2007). MATLAB simulation of gradient-based neural network for online matrix inversion. In D. S., Huang, L., Heute & Loog, M. (Eds.), ICIC 2007, LNCS(LNAI), (Vol. 4682, pp. 98-109). Heidelberg: Springer. |
| [27] | Zhang Y., Ge S. S. (2005) Design and analysis of a general recurrent neural network model for time-varying matrix inversion. IEEE Transaction on Neural Networks 16(6): 1477-1490 · doi:10.1109/TNN.2005.857946 |
| [28] | Zhang Y., Jiang D., Wang J. (2002) A recurrent neural network for solving Sylvester equation with time-varying coefficients. IEEE Transactions on Neural Networks 13(5): 1053-1063 · doi:10.1109/TNN.2002.1031938 |
| [29] | Zhang Y., Li Z. (2009) Zhang neural network for online solution of time-varying convex quadratic program subject to time-varying linear equality constraints. Physics Letters A 373(18-19): 1639-1643 · Zbl 1229.92008 · doi:10.1016/j.physleta.2009.03.011 |
| [30] | Zhang Y., Ma W., Cai B. (2009) From Zhang neural network to Newton iteration for matrix inversion. IEEE Transactions on Circuits and Systems I 56(7): 1405-1415 · Zbl 1468.65026 · doi:10.1109/TCSI.2008.2007065 |
| [31] | Zhang, Y., Ma, W., & Yi, C., (2008). The link between Newton iteration for matrix inversion and Zhang neural network (ZNN). In Proceeding of IEEE international conference on industrial technology, Chengdu, China. doi:10.1109/ICIT.2008.4608578. |
| [32] | Zhang Y., Xiao L., Ruan G., Li Z. (2011) Continuous and discrete time Zhang dynamics for time-varying 4th root finding. Numerical Algorithms 57(1): 35-51 · Zbl 1215.65090 · doi:10.1007/s11075-010-9410-0 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
