Search

Input noise causes inescapable bias to the weight vectors of the adaptive filters during the adaptation processes. Moreover, the impulse noise at the output of the unknown systems can prevent bias compensation from converging. This paper presents a robust bias compensation method for a sparse normalized quasi-Newton least-mean (BC-SNQNLM) adaptive filtering algorithm to address these issues. We have mathematically derived the biased-compensation terms in an impulse noisy environment. Inspired by the convex combination of adaptive filters' step sizes, we propose a novel variable mixing-norm method, BC-SNQNLM-VMN, to accelerate the convergence of our BC-SNQNLM algorithm. Simulation results confirm that the proposed method significantly outperforms other comparative works regarding normalized mean-squared deviation (NMSD) in the steady state. [ABSTRACT FROM AUTHOR]

Input noise causes inescapable bias to the weight vectors of the adaptive filters during the adaptation processes. Moreover, the impulse noise at the output of the unknown systems can prevent bias compensation from converging. This paper presents a robust bias compensation method for a sparse normalized quasi-Newton least-mean (BC-SNQNLM) adaptive filtering algorithm to address these issues. We have mathematically derived the biased-compensation terms in an impulse noisy environment. Inspired by the convex combination of adaptive filters’ step sizes, we propose a novel variable mixing-norm method, BC-SNQNLM-VMN, to accelerate the convergence of our BC-SNQNLM algorithm. Simulation results confirm that the proposed method significantly outperforms other comparative works regarding normalized mean-squared deviation (NMSD) in the steady state.

This paper comes up with a stable bias-compensated fractional order normalized least mean square (BC-FONLMS) algorithm with noisy inputs. This kind of bias-compensated algorithm needs the estimation of input noise variance to avoid the bias caused by noisy inputs. Yet, existing algorithms either cause instability because of the method used to estimate input noise variance, or surmount the instability problems at the price of performance diminishment. This paper introduces fractional order calculus into LMS algorithm to be a new BC-FONLMS algorithm. Then, analyze the stability of the BC-FONLMS algorithm through probing the recursive equations of mean deviation (MD) and mean square deviation (MSD). On the basis of the stability analysis, methods to estimate input noise variance and to adjust step size are suggested to stabilize the algorithm and likewise to enhance the performance such as convergence speed and steady-state error. Numerical simulations are given at last, whose results show that the proposed BC-FONLMS algorithm performs well. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM PUBLISHER]

The discovery of materials with improved properties can be accelerated by models with the ability to combine data from multiple experimental information sources. A recurring task in the toolbox of practitioners is to map input physical descriptors to output properties of interest. Typically, both the outputs and many of the inputs are experimentally measured and, thus, noisy. Probabilistic regression methods, e.g., Gaussian process regression, can easily deal with noisy outputs, even if the noise is input-dependent. However, most regression methods cannot process noisy inputs. Ignoring input uncertainty leads to inaccurate predictive uncertainty, a crucial ingredient for the sequential design of experiments. The objective of this paper is to develop a regression methodology that can deal with input uncertainty when one wishes to correlate an inexpensive experimental measurement (e.g., hardness) to an expensive one (e.g., yield strength). Our hierarchical Bayesian approach uses two Gaussian processes. The first one maps noiseless physical descriptors to the inexpensive experimental measurement. The second Gaussian process maps noiseless physical descriptors and the inexpensive experimental measurement to the expensive experimental measurement. The two Gaussian processes form a nested model that is not analytically tractable. To overcome this issue, we propose semi-analytical approximations to both the marginal likelihood and the posterior predictive distribution. The result is a model that is practical to train and use. We demonstrate the merits of the proposed method through a synthetic dataset in which we control all the uncertainties. The statistical tests clearly show that standard Gaussian process regression cannot cope with input uncertainty whereas our proposed method consistently yields better predictive distributions. Finally, we apply the method to the task of predicting the yield strength of high entropy alloys from hardness on an exhaustive dataset compiled from the available literature. [ABSTRACT FROM AUTHOR]

Design and implementation of a sequential controller based on the concept of artificial neural networks for a flexible manufacturing system are presented. The recurrent neural network (RNN) type is used for such a purpose. Contrary to the programmable controller, an RNN-based sequential controller is based on a definite mathematical model rather than depending on experience and trial and error techniques. The proposed controller is also more flexible because it is not limited by the restrictions of the finite state automata theory. Adequate guidelines of how to construct an RNN-based sequential controller are presented. These guidelines are applied to different case studies. The proposed controller is tested by simulations and real-time experiments. These tests prove the successfulness of the proposed controller performances. Theoretical as well as experimental results are presented and discussed indicating that the proposed design procedure using Elman's RNN can be effective in designing a sequential controller for event-based type manufacturing systems. In addition, the simulation results assure the effectiveness of the proposed controller to outperform the effect of noisy inputs. [ABSTRACT FROM AUTHOR]