×

Fixed-order optimal deconvolution filter with irregular missing data. (English) Zbl 1193.93173

Summary: In general, the reconstruction performance of the conventional deconvolution filter is deteriorated by the missing data. In this paper, a fixed-order deconvolution filter design method is proposed for the signal reconstruction from received signal with irregular missing data. The missing data model is based on a probabilistic structure. The probability of occurrence of missing data is unknown a priori. In this situation, the deconvolution filter design problem becomes a complicated nonlinear estimation problem. In this study, a design method based on genetic algorithms is proposed to treat the signal reconstruction design problem with irregular missing data. Finally, two examples are given to illustrate the simulation results of the proposed deconvolution filter. The results show that the reconstruction performance is improved significantly if the missing probability is considered in the deconvolution filter design procedure.

MSC:

93E11 Filtering in stochastic control theory
90C59 Approximation methods and heuristics in mathematical programming
93C55 Discrete-time control/observation systems
Full Text: DOI

References:

[1] Silvia, Deconvolution Under Line of Geophysical Time Series in the Exploration for Oil and Natural Gas (1979)
[2] Hung, Genetic algorithm approach to fixed-order mixed H2/H optimal deconvolution filter designs, IEEE Transactions on Signal Processing 48 (12) pp 3451– (2000)
[3] Berkhout, Least-square inverse filter and wavelet inverse, Geophysics 42 (12) pp 1369– (1977)
[4] Demoment, Fast minimum variance deconvolution, IEEE Transactions on Acoustics, Speech, and Signal Processing 33 pp 1324– (1985)
[5] Prasad, Adaptive filter structures for deconvolution of seismic signals, IEEE Transactions on Geoscience and Remote Sensing 18 (3) pp 267– (1980)
[6] Lainiotis, Adaptive deconvolution of seismic signals-performance, computational analysis, parallelism, IEEE Transactions on Acoustics, Speech, and Signal Processing 36 (11) pp 1715– (1988) · Zbl 0825.94209
[7] Tuncer, LSE and MSE optimum partition-based FIR-IIR deconvolution filters with best delay, IEEE Transactions on Signal Processing 53 pp 3780– (2005) · Zbl 1370.94259
[8] Grimble, Solution of the H optimal filtering problem for discrete time systems, IEEE Transactions on Acoustics, Speech, and Signal Processing 38 (7) pp 1092– (1990) · Zbl 0712.93053
[9] Chi, Performance of minimum-variance deconvolution filter design, IEEE Transactions on Acoustics, Speech, and Signal Processing 32 (1) pp 1145– (1983)
[10] Mendel, Optimal Seismic Deconvolution, An Estimation-based Approach (1986)
[11] Parzen, On spectral analysis with missing observations and amplitude modulation, Sankhya 25 pp 323– (1963) · Zbl 0136.40701
[12] Dunsmir, Estimation of time series models in the presence of missing data, Journal of the American Statistical Association 76 pp 560– (1981)
[13] Jones, Maximum likelihood fitting of ARMA model to time series with missing observations, Technometric 22 pp 389– (1980) · Zbl 0451.62069
[14] Sakai, Fitting autoregression with regularly missed observation, Annals of the Institute of Statistical Mathematics 43 pp 383– (1980) · Zbl 0456.62071
[15] Astrom, Computer Control Systems: Theory and Design (1984)
[16] Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning (1989) · Zbl 0721.68056
[17] Holland, Adaptive in Natural and Artificial Systems (1975)
[18] Papulis, Probability, Random Variable and Stochastic Processes (1984)
[19] Grefensteete, Optimization of control parameters for genetic algorithms, IEEE Transactions on Systems, Man, and Cybernetics 16 (1) pp 122– (1986)
[20] Rudolph, Convergence analysis of canonical genetic algorithms, IEEE Transactions on Neural Networks 5 (1) pp 96– (1994)
[21] Manoharan, A comparison of search mechanisms for structural optimization, Computers and Structures 73 (12) pp 363– (1999) · Zbl 1125.74372
[22] Liang, An equivalent genetic algorithm based on extended strings and its convergence analysis, Information Sciences 138 (10) pp 119– (2001) · Zbl 1004.68134
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.