Sang Mok Jung

A Variable Step-Size Diffusion Normalized Least-Mean-Square Algorithm with a Combination Method Based on Mean-Square Deviation

A novel diffusion normalized least-mean-square algorithm is proposed for distributed network. For the adaptation step, the upper bound of the mean-square deviation (MSD) is derived instead of the exact MSD value, and then, the variable step size is obtained by minimizing it to achieve fast convergence rate and small steady-state error. For the diffusion step, the individual estimate at each node is constructed via the weighted sum of the intermediate estimates at its neighbor nodes, where the weights are designed by using a proposed combination method based on the MSD at each node. The proposed MSD-based combination method provides effective weights by using the MSD at each node as a reliability indicator. Simulations in a system identification context show that the proposed algorithm outperforms other algorithms in the literatures.

A diffusion subband adaptive filtering algorithm for distributed estimation using variable step size and new combination method based on the MSD

This paper proposes a novel diffusion subband adaptive filtering algorithm for distributed networks. To achieve a fast convergence rate and small steady-state errors, a variable step size and a new combination method is developed. For the adaptation step, the upper bound of the mean-square deviation (MSD) of the algorithm is derived and the step size is adaptive by minimizing it in order to attain the fastest convergence rate on every iteration. Furthermore, for a combination step realized by a convex combination of the neighbor-node estimates, the proposed algorithm uses the MSD, which contains information on the reliability of the estimates, to determine combination coefficients. Simulation results show that the proposed algorithm outperforms the existing algorithms in terms of the convergence rate and the steady-state errors. A subband adaptive filtering algorithm is adopted for distributed estimation.The upper bound of the intermediate MSD and its recursion with local MSD are investigated.The MSD-optimal step size achieves the fastest convergence rate on every iteration.The combination coefficients are assigned using the intermediate MSD.The algorithm achieves fast convergence rate and small steady-state errors.

Stabilization of a Bias-Compensated Normalized Least-Mean-Square Algorithm for Noisy Inputs

This paper proposes a stability-guaranteed bias-compensated normalized least-mean-square (BC-NLMS) algorithm for noisy inputs. The bias-compensated algorithms require the estimated input noise variance in the elimination process of the bias caused by noisy inputs. However, the conventional methods of estimating the input noise variance in those algorithms might cause the instability for a specific situation. This paper first analyzes the stability of the BC-NLMS algorithm by investigating the dynamics of both the mean deviation and the mean-square deviation in the BC-NLMS algorithm. Based on the analysis, the estimation of the input noise variance and the adjustment of the step size are carried out to perform a stabilization as well as a performance enhancement in terms of a steady-state error and a convergence rate. Simulations in system identification and acoustic echo cancellation scenarios with noisy inputs show that the proposed algorithm outperforms the existing bias-compensated algorithms in the aspect of the stability, the steady-state error, and the convergence rate.

Variable step-size non-negative normalised least-mean-square-type algorithm

This paper proposes a fast and precise adaptive filtering algorithm for online estimation under a non-negativity constraint. A novel variable step-size (VSS) non-negative normalised least-mean-square (NLMS)-type algorithm based on the mean-square deviation (MSD) analysis with a non-negativity constraint is derived. The NLMS-type algorithm under the non-negativity constraint is derived by using the gradient descent of the given cost function and the fixed-point iteration method. Furthermore, the VSS derived by minimising the MSD yields improvement of the filter performance in the aspects of the convergence rate and the steady-state estimation error. Simulation results show that the proposed algorithm outperforms existing algorithms.

A bias-compensated affine projection algorithm for noisy input data

This paper proposes a bias-compensated affine projection algorithm (BC-APA) to eliminate bias due to noisy input data and to reduce the performance degradation due to highly correlated input data. A new affine projection algorithm (new APA) using innovative input data is presented for highly correlated input data. We analyze the bias in this innovative new APA under noisy input data and remove it. To remove the bias, an estimation method for the input noise variance is presented and explained. In simulations, the BC-APA provided both fast convergence rate and small mean square deviation. Based on improved precision to estimate a finite impulse response of an unknown system, the BC-APA can be applied extensively in adaptive signal processing areas.

Acoustic echo cancellation in distributed network using improved diffusion subband adaptive filtering algorithm

This paper proposes an improved diffusion subband adaptive filtering algorithm for an acoustic echo cancellation (AEC) in distributed network. For the adaptation step, a variable individual step size that takes account of the characteristics of speech input signals is derived by minimizing the upper bound of the mean-square deviation. For the combination step, an error-variance-based combination method is proposed that enables to reflect information on the sudden interferences such as double talk. Simulation results show that the proposed algorithm outperforms the existing diffusion adaptive filtering algorithms in terms of the convergence rate and the steady-state errors in various AEC environment.

Variable Step-size NLMS Algorithm with Oblique Projection

For the case when the input signals are highly correlated, this paper introduces a innovative update form of the normalized least-mean-squares (NLMS) algorithm, where the concept of normalization is taken from the oblique projection. By supplying a lemma that the trace norm of any square matrix is preserved under the congruence transformation via the unitary matrices, this paper designs optimal variable step sizes minimizing the trace norm of the estimation-error covarinace matrices. Simuations confirms that the proposed algorithm outperforms exiting algorithms.

LPV controller design with multiple parameters for the nonlinear RTAC system

This paper proposes linear parameter varying (LPV) model with multiple parameters (LPV-MP) and statefeedback controller for the nonlinear rotational and translational actuator (RTAC) benchmark problem. First, based on LPV-MP, the conditions used for designing the state-feedback controller are formulated in terms of parameterized linear matrix inequalities (PLMIs) and the state-feedback LPV controller using multiple parameters-dependent Lyapunov function (MPDLF) is designed. Then, PLMI conditions are converted into linear matrix inequalities (LMIs) by using a parameter relaxation technique. The proposed method results in the reduced decision variables and simulation results show good performance of the proposed method.