1:00, SPTM-P6.1
AN EFFICIENT ROBUST ADAPTIVE FILTERING SCHEME BASED ON PARALLEL SUBGRADIENT PROJECTION TECHNIQUES
I. YAMADA, K. SLAVAKIS, K. YAMADA
This paper presents a novel robust adaptive filtering scheme based on the interactive use of statistical noise information and an extension of the ideas developed originally for efficient algorithmic solutions to the convex feasibility problems. The statistical noise information is quantitatively formulated as stochastic property closed convex sets by the simple design formulae developed in this paper. The proposed adaptive algorithm is computationally efficient and robust to noise because it requires only an iterative parallel projection onto a series of closed half spaces highly expected to contain the unknown system to be identified. The numerical examples show that the proposed adaptive filtering scheme achieves low estimation error and realizes dramatically fast and stable convergence even for highly colored excited input signals in severe noise situations.

1:00, SPTM-P6.2
MULTI-SPLIT ADAPTIVE FILTERING
L. RESENDE, J. ROMANO, M. BELLANGER
In this paper a novel transversal split filter configuration is proposed and the split optimum Wiener filter is introduced, as well as the symmetric and antisymmetric linear phase Wiener filter. The approach consists of combining the idea of split filtering with a linearly- constrained optimization scheme. Then, the continuously split procedure is introduced and the multi-split adaptive filter is derived. It is also shown that such structure can be viewed as a Hadamard-domain adaptive filter when the number of coefficients is set to a power of two. Simulation results obtained with the normalized LMS algorithm are presented and compared with DCT-domain adaptive filter.

1:00, SPTM-P6.3
A NEW UNBIASED EQUATION ERROR ALGORITHM FOR IIR ADF AND ITS APPLICATION TO ALE
J. OKELLO, Y. KINUGASA, Y. ITOH, Y. FUKUI, M. KOBAYASHI
In this paper, a new online algorithm for updating equation error IIR ADF is proposed. The proposed algorithm, which involves maintaining a constant power of the desired signal, is independent of the white disturbance signal, and hence there is no bias in the coefficient's estimate of the ADF. We also provide the analysis and simulation results which verify this kind of performance. Application of the proposed algorithm to adaptive line enhancer (ALE) is also provided. When compared with the method which uses cascaded notch filter, we observe a considerable improvement in performance due to the complete elimination of effect of white noise under mean sense condition.

1:00, SPTM-P6.4
A SYNCHRONIZED LEARNING ALGORITHM FOR REFLECTION COEFFICIENTS AND TAP WEIGHTS IN A JOINT LATTICE PREDICTOR AND TRANSVERSAL FILTER
N. TOKUI, K. NAKAYAMA, A. HIRANO
In order to achieve fast convergence and less computation for adaptive filters, a joint method combining a whitening process and the NLMS algorithm is a hopeful approach. One of them is to combine a lattice predictor and a transversal filter supervised by the NLMS algorithm. However, the filter coefficient adaptation is very sensitive to the reflection coefficient fluctuation. In this paper, the reason of this instability is analyzed. The filter coefficients are updated one sample behind the reflection coefficient update. This causes large error, in other words, sensitivity of their mismatch is very high on filter characteristics. An improved learning method is proposed in order to compensate for this mismatch. The convergence property is close to that of the RLS algorithm. Computational complexity can be well reduced from that of the RLS algorithm. Simulation results using real voices demonstrate usefulness of the proposed method.

1:00, SPTM-P6.5
DATA-SELECTIVE CONSTRAINED AFFINE PROJECTION ALGORITHM
S. WERNER, J. APOLINARIO JR., M. DE CAMPOS
This paper introduces a constrained version of the recently proposed set-membership affine projection algorithm based on the set-membership criteria for coefficient update. The algorithm is suitable for linearly-constrained minimum-variance filtering applications. The data selective property of the proposed algorithm greatly reduces the computational burden as compared with a nonselective approach. Simulation results show the good performance in terms convergence, final misadjustment, and reduced computational complexity.

1:00, SPTM-P6.6
A SINGLE-PARAMETER ADAPTIVE COMB FILTER
N. CHERNOGUZ
A SINGLE-PARAMETER ADAPTIVE COMB FILTER Naum G. Chernoguz ABSTRACT The study is concerned with a single-parameter adaptive comb filter (ACF), a multi-notch filter with periodically located nulls. The filter is suggested to retrieve a waveform modeled by superposition of harmonics, in particular, periodic non-sinusoidal signal. Using trigonometric constrains between the signal fundamental frequency and over tones results in a non-linear estimation problem. In the present study, the parameter adjustment relies on the extended Kalman filter scheme. Particularly, the 2, 3 and 4 notch ACF are derived and tested under different conditions. Given a multi-tone scenario, the ACF significantly outperformes common adaptive multi-notch filter.

1:00, SPTM-P6.7
ADAPTIVE STEP SIZE SIGN ALGORITHM FOR APPLICATION TO ADAPTIVE FILTERING IN DIGITAL QAM COMMUNICATIONS
S. KOIKE
A new Adaptive Step Size control algorithm is proposed to be combined with the Sign Algorithm for use in complex-valued adaptive filters for application to QAM communications. The algorithm, ASSSA, is fully analyzed to yield a set of difference equations for calculating the transient behavior, hence the steady-state performance, of the filter convergence in terms of the excess mean squared error (EMSE). An approximation method for multilevel QAM is further proposed to reduce the amount of computation. The results of experiment with some examples verify the effectiveness of the proposed ASSSA in significantly improving the convergence rate, and also show that the theoretical convergence is in good agreement with that of simulations, which validates the analysis.

1:00, SPTM-P6.8
QR BASED ITERATIVE UNBIASED EQUATION ERROR FILTERING
B. DUNNE, G. WILLIAMSON
A QR-decomposition based algorithm is presented for unbiased, equation error adaptive IIR filtering. The algorithm is based on casting the adaptive IIR filtering in a mixed Least Squares - Total Least Squares (LS-TLS) framework. This formulation is shown to be equivalent to the minimization of the mean-square equation error subject to a unit norm constraint on the denominator parameter vector. An efficient implementation of the mixed LS-TLS solution is achieved through the use of back substitution and inverse iteration. Unbiasedness of the system parameter estimates is established for the mixed LS-TLS solution in the case of uncorrelated output noise, and the algorithm is shown to converge to this solution.

1:00, SPTM-P6.9
A COMPLEX ADAPTIVE DELAY FILTER
K. KUSABA, A. OKAMURA, A. OKAMURA, T. SEKIGUCHI, T. SEKIGUCHI
In this paper, an adaptive delay filter with complex coefficients for identifying the unknown system with complex sparse impulse response is proposed. The delay taps could not be determined by the conventional real adaptive delay filter, which evaluates the mean squared error with one constant gain in the system with complex coefficients. In proposed method, a modified evaluation function, which consists of the mean squared error value with a complex constant gain and one with the conjugate value of the complex constant gain, is introduced in order to estimate the delay taps correctly. We also clarify by some simulations that the identification error is significantly reduced by means of the proposed complex adaptive delay filter.

1:00, SPTM-P6.10
GENERAL PARAMETER-BASED ADAPTIVE EXTENSION TO FIR FILTERS
O. VAINIO, S. OVASKA
A class of computationally efficient adaptive algorithms for transversal filters is discussed. The algorithms, which are based on the so-called general parameter method, use typically one or a few dynamically adjusted parameters, each to be added to a block of coefficients of a fixed basis FIR filter. Thus the overall filter is adapted so that the output error is minimized. The adaptive extension can be constructed as an 'add-on' element to be used in parallel with fixed-coefficient filters. An efficient implementation structure is proposed, and the stability and convergence properties of the multiple-parameter algorithm are analyzed.

1:00, SPTM-P6.11
ADAPTIVE SIGNAL PROCESSING BY PARTICLE FILTERS AND DISCOUNTING OF OLD MEASUREMENTS
P. DJURIC, J. KOTECHA, J. TOURNERET, S. LESAGE
In adaptive signal processing the principle of exponentially weighted recursive least-squares plays a major role in developing various estimation algorithms. It is based on the concept of discounting of old measurements and allows for better performance in problems with time-varying signals and signals in nonstationary noise. In this paper we show how this concept can be combined with the Bayesian methodology. We propose that the discounting of old measurements within the Bayesian framework be implemented by employing particle filters. The main idea is presented by way of a simple example. The methodology is very attractive and can be used in a very wide range of scenarios including ones that involve highly nonlinear models and non-Gaussian noise.