RLS channel estimation with adaptive forgetting factor in space-time coded MIMO-OFDM systems

Considering that channel estimation plays a crucial role in coherent detection, this paper addresses a method of Recursive-least-squares (RLS) channel estimation with adaptive forgetting factor in wireless space-time coded multiple-input and multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. Because there are three different forgetting factor scenarios including adaptive, two-step and conventional ones applied to RLS channel estimation, this paper describes the principle of RLS channel estimation and analyzes the impact of different forgetting factor scenarios on the performances of RLS channel estimation. Simulation results proved that the RLS algorithm with adaptive forgetting factor (RLS-A) outperformed that with two-step forgetting factor (RLS-T) or with conventional forgetting factor (RLS-C) in both estimation accuracy and robustness over the multiple-input multiple-output (MIMO) channel, i.e., a wide-sense stationary uncorrelated scattering (WSSUS) and frequency-selective slowly fading channel. Hence, we can employ the RLS-A method by adjusting forgetting factor adaptively to track and estimate channel state parameters successfully in space-time coded MIMO-OFDM systems.

Application of RLS adaptive filteringin signal de-noising

In view of the problem that noises are prone to be mixed in the signals,an adaptive signal de-noising system based on reursive least squares （RLS） algorithm is introduced.The principle of adaptive filtering and the process flow of RLS algorithm are described.Through example simulation,simulation figures of the adaptive de-noising system are obtained.By analysis and comparison,it can be proved that RLS adaptive filtering is capable of eliminating the noises and obtaining useful signals in a relatively good manner.Therefore,the validity of this method and the rationality of this system are demonstrated.

B-Spline-Based Curve Fitting to Cam Pitch Curve Using Reinforcement Learning

Directly applying the B-spline interpolation function to process plate cams in a computer numerical control(CNC)system may produce verbose tool-path codes and unsmooth trajectories.This paper is devoted to addressing the problem of B-splinefitting for cam pitch curves.Considering that the B-spline curve needs to meet the motion law of the follower to approximate the pitch curve,we use the radial error to quantify the effects of thefitting B-spline curve and the pitch curve.The problem thus boils down to solving a difficult global optimization problem tofind the numbers and positions of the control points or data points of the B-spline curve such that the cumulative radial error between thefitting curve and the original curve is minimized,and this problem is attempted in this paper with a double deep Q-network(DDQN)reinforcement learning(RL)algorithm with data points traceability.Specifically,the RL envir-onment,actions set and current states set are designed to facilitate the search of the data points,along with the design of the reward function and the initialization of the neural network.The experimental results show that when the angle division value of the actions set isfixed,the proposed algorithm can maximize the number of data points of the B-spline curve,and accurately place these data points to the right positions,with the minimum average of radial errors.Our work establishes the theoretical foundation for studying splinefitting using the RL method.

A fast learning algorithm of neural network with tunable activation function

This paper presents a modified structure of a neural network with tunable activation function and provides a new learning algorithm for the neural network training. Simulation results of XOR problem, Feigenbaum function, and Henon map show that the new algorithm has better performance than BP (back propagation) algorithm in terms of shorter convergence time and higher convergence accuracy. Further modifications of the structure of the neural network with the faster learning algorithm demonstrate simpler structure with even faster convergence speed and better convergence accuracy.

Fast Affine Projection Algorithm for Adaptive Noise Canceling and Its Application on the Fetal Electrocardiogram Extraction

Aimed at the problem of adaptive noise canceling(ANC),three implementary algorithms which are least mean square(LMS) algorithm,recursive least square(RLS) algorithm and fast affine projection(FAP) algorithm,have been researched.The simulations were made for the performance of these algorithms.The extraction of fetal electrocardiogram(FECG) is applied to compare the application effect of the above algorithms.The proposed FAP algorithm has obvious advantages in computational complexity,convergence speed and steadystate error.

Fast adaptive principal component extraction based on a generalized energy function

By introducing an arbitrary diagonal matrix, a generalized energy function (GEF) is proposed for searching for the optimum weights of a two layer linear neural network. From the GEF, we derive a recur- sive least squares (RLS) algorithm to extract in parallel multiple principal components of the input covari- ance matrix without designing an asymmetrical circuit. The local stability of the GEF algorithm at the equilibrium is analytically verified. Simulation results show that the GEF algorithm for parallel multiple principal components extraction exhibits the fast convergence and has the improved robustness resis- tance to the eigenvalue spread of the input covariance matrix as compared to the well-known lateral inhi- bition model (APEX) and least mean square error reconstruction (LMSER) algorithms.