İki- kanallı AR kafes yaklaşımı ile iki-boyutlu ARMA parametre tanılama

İki-boyutlu zamanla değişmeyen bir ARMA(M,N) sistemin parametrelerini tanılamak için yeni bir yöntem önerilmiştir. Burada M, AR kısmının derecesini, N ise MA kısmının derecesini temsil etmektedir. Bu yeni yöntem, önceden önerilen iki-kanallı AR kafes modelleme yaklaşımının, AR ve MA derecelerinin farklı olduğu durumları da içerecek şekilde genişletilmiş bir şeklidir. Yeni önerilen yöntem, hem iki-kanallı, hem de tek-kanallı kafes yapılarını barındırması nedeni ile bir “karma kafes yapısı” olarak da adlandırılabilir. Bu karma kafes yapısı, hem çeyrek düzlem, hem de simetrik olmayan yarı düzlem modellerine uygulanabilmektedir. AR derecesinin MA derecesine eşit olduğu durumlarda, karma kafes yapısı ortadan kalkmakta, yalnızca iki-kanallı iki-boyutlu AR kafes yapıları ile çözüme gidilmektedir. Bu çalışma kapsamında ayrıca, ARMA parametreleri hesaplamak için, b0 parametresini ve her iki kanala ilişkin ileri yönde öngörü süzgeçlerinin katsayı ağırlıklarını da içine alan ve M $geq$ N, M < N durumları için kullanılabilecek yeni bir formülasyon yaklaşımı önerilmiştir. Önerilen yöntemin doğrulanması amacıyla, bilgisayar benzetimleri kullanılmıştır. Bu benzetimlerin her birinde, karşılaştırmaya esas olarak LS kestirimleri alınmıştır. Ayrıca $L_1$, $L_2$ ve $L_{infty}$ vektör normları ile Itakura-Saito uzaklığı, başarım ölçütleri olarak kabul edilmiş ve her bir bilgisayar benzetimi için hesaplanmıştır. Elde edilen parametre tanılama sonuçları, karma kafes yönteminin, oldukça küçük veri alanı boyutları için bile kabul edilebilir nitelikte olduğunu göstermektedir.

Two-dimensional ARMA parameter identification with two-channel AR lattice approach

The field of multi-dimensional digital signal processing has become increasingly important in recent years due to a number of trends in digital signal processing. Parametric representations of two-dimensional (2-D) random fields in the form of autoregressive (AR), moving average (MA) and autoregressive moving average (ARMA) models are useful in many applications such as image synthesis, classification, spectral estimation, radar imaging, etc.There are a number of advantages and disadvantages related with AR and MA modelings. The major advantage of both models is that the solution for the model parameters involves only linear equations. In the MA models the solution is unbiased in the presence of additive noise on the system output as long as the noise and system input are uncorrelated. MA models are always stable since they are non-recursive. One of the most serious disadvantages of either AR or MA modeling is the fact that to adequately represent even simple linear systems, both methods may require a large number of parameters (a high order model). This problem arises since, from a transfer function standpoint, AR and MA models attempt to model the system using only poles or only zeros, in spite of the fact that physical systems may have both zeroes and poles. The ARMA (M, N) model is a generalization of the Mth order AR and Nth order MA models and accomplishes exactly modeling the unknown system with poles and zeroes, representing the system in rational transfer function form. Therefore this has motivated a considerable interest in the more general pole-zero (ARMA) model.The primary concern of this research is the determination of discrete time models for 2-D LSI systems from sampled observations of the system input $x(k_1, k_2)$ and system output $y(k_1, k_2)$, using 2-D orthogonal lattice structures, assuming that the order of the ARMA(M, N) model is known. The ARMA model order is represented by the (M, N) pair, where M represents the order of the AR polynomial and N represents the order of the MA polynomial.Here we present a “hybrid lattice” structure in order to identify the ARMA(M, N) system parameters, provided that $x(k_1, k_2)$ and $y(k_1, k_2)$ are given. This structure can be applied to both quarter-plane (QP) and asymmetric half plane (ASHP) models and it is based on the two-channel AR lattice approach proposed by Kayran for equal AR and MA orders. The novelties brought about by this proposed structure can be listed as follows.• We extend Kayran’s approach to the case where M and N can take arbitrary values different from each other. We accomplish this with the help of our proposed hybrid lattice structure where both 2-D two-channel AR and 2-D single-channel AR lattice stages are incorporated. We also propose a modification in terms of the channel inputs of the two-channel lattices. We drive the first channel input by a difference signal of $u(k_1, k_2)$ = $y(k_1, k_2)$-$x(k_1, k_2)$ instead of $y(k_1, k_2)$, which was formerly proposed. The second channel input, which was formerly proposed as $x(k_1, k_2)$, is driven by a newly defined signal $t(k_1, k_2)$, which is related with the orders of the AR and MA polynomials. If M > N, $t(k_1, k_2)$ is equal to $x(k_1, k_2)$, if (M < N, $t(k_1, k_2)$ is equal to $y(k_1, k_2)$.• We propose modifications in the b0 parameter estimates for the cases where (M $geq$ N and M < N, in accordance with our newly proposed channel inputs.• We derive a new formulation for the ARMA (M,N) parameter estimates, taking into account the estimated parameter b0 and the forward prediction error filters’ tap weights related with both channels.In order to make a verification of the proposed method, we give computer simulation examples where we compare the hybrid lattice estimates with the LS (Least Squares) estimates. As performance measures, we use the $L_1$, $L_2$ and $L_{infty}$ vector norms and the Itakura-Saito distance measure, which indicates the similarity between the original and identified power spectrums.

___

  • El-Jaroudi, A. ve Makhoul, J., (1991). Discrete All-Pole Modeling, IEEE Transactions on Signal Processing, 39(2), 411-423.
  • Ertüzün, A., Kayran, A.H. ve Panayırcı, E., (1992). An improved 2-D lattice filter and its entropy relations, Signal Processing, 28, 1-24.
  • Kayran, A.H., (1996a). 2D ARMA Lattice Modeling Using Two-Channel AR Lattice Approach, Electronics Letters, 32, 16, 1434-1435.
  • Kayran, A.H., (1996b). Two-dimensional orthogonal lattice structures for autoregresive modeling of random fields, IEEE Transactions on Signal Processing, 44, 4, 963-978.
  • Kwan, H.K ve Liu, Y.C., (1989). Normalized 2-D ARMA Lattice Parameter Modeling Algorithm, IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, Victoria, BC Canada, 1-2 June, 372-375.
  • Lim, Y.C. ve Parker, S.R., (1986). On the Identification of Systems from Data Measurements Using ARMA Lattice Models, IEEE Transactions on Acoustics, Speech and Signal Processing, ASSP-34, 4, 824-828.
  • Marzetta, T.L., (1980). Two-dimensional linear prediction: autocorrelation arrays, minimum-phase prediction error filters, and reflection coefficient arrays, IEEE Transactions on Acoustics, Speech and Signal Processing, ASSP-28, 6, 725-733.
  • Parker, S.R. ve Kayran, A.H., (1984). Lattice Parameter autoregressive modeling of two-dimensional fields-Part I: The quarter plane case, IEEE Transactions on Acoustics, Speech and Signal Processing, ASSP-32, 872-885.
  • Perry, F.A., (1980). Parametric Modeling of Linear and Nonlinear Systems, Ph.D. Dissertation, Naval Postgraduate School, Monterey, California.
  • Sarı, N.Y ve Kayran, A.H., (2005). 2D ARMA Parameter Identification Using A Hybrid Lattice Design, IEEE International Conference on Acoustics, Speech and Signal Processing, Philadelphia, PA, USA, 18-23 Mart, (IV-109)-(IV-112).
  • Strobach, P., (1988). Recursive Covariance Ladder Algorithms for ARMA System Identification, IEEE Transactions on ASSP, 36, 4, 560-580.