scholarly journals Simulação do comportamento estocástico do algoritmo KLMS com diferentes kernels

2020 ◽  
Author(s):  
Patrick Medeiros De Luca ◽  
Wemerson Delcio Parreira
Keyword(s):  
Monte Carlo Simulation ◽  
Adaptive Filtering ◽  
Adaptive Filters ◽  
Linear Filter ◽  
Mean Square ◽  
Least Mean Square ◽  
Model Order ◽  
Different Types ◽  
Kernel Least Mean Square ◽  
Nonlinear Adaptive Filtering

The kernel least-mean-square (KLMS) algorithm is a popular algorithmin nonlinear adaptive filtering due to its simplicity androbustness. In kernel adaptive filtering, the statistics of the inputto the linear filter depends on the kernel and its parameters. Moreover,practical implementations on systems estimation require afinite non-linearity model order. In order to obtain finite ordermodels, many kernelized adaptive filters use a dictionary of kernelfunctions. Dictionary size also depends on the kernel and itsparameters. Therefore, KLMS may have different performanceson the estimation of a nonlinear system, the time of convergence,and the accuracy using a different kernel. In order to analyze theperformance of KLMS with different kernels, this paper proposesthe use of the Monte Carlo simulation of both steady-state and thetransient behavior of the KLMS algorithm using different types ofkernel functions and Gaussian inputs.

scholarly journals A Kernel Recursive Maximum Versoria-Like Criterion Algorithm for Nonlinear Channel Equalization

Symmetry ◽  
2019 ◽  
Vol 11 (9) ◽  
pp. 1067 ◽  
Author(s):  
Qishuai Wu ◽  
Yingsong Li ◽  
Wei Xue
Keyword(s):  
Adaptive Filtering ◽  
Impulse Noise ◽  
Channel Equalization ◽  
Mean Square ◽  
Least Mean Square ◽  
Mixed Mean ◽  
Non Gaussian ◽  
Kernel Least Mean Square ◽  
Nonlinear Adaptive Filtering ◽  
Better Than

In this paper, a kernel recursive maximum Versoria-like criterion (KRMVLC) algorithm has been constructed, derived, and analyzed within the framework of nonlinear adaptive filtering (AF), which considers the benefits of logarithmic second-order errors and the symmetry maximum-Versoria criterion (MVC) lying in reproducing the kernel Hilbert space (RKHS). In the devised KRMVLC, the Versoria approach aims to resist the impulse noise. The proposed KRMVLC algorithm was carefully derived for taking the nonlinear channel equalization (NCE) under different non-Gaussian interferences. The achieved results verify that the KRMVLC is robust against non-Gaussian interferences and performs better than those of the popular kernel AF algorithms, like the kernel least-mean-square (KLMS), kernel least-mixed-mean-square (KLMMN), and Kernel maximum Versoria criterion (KMVC).

Realization of Enhanced LMS Filter Using Carry Skip Adder And Quantum Dot Cellular Automation In VLSI For Removing Impulse Noises In Medical Image

2019 ◽  
Vol 14 ◽  
Author(s):  
K.R. Shankarkumar ◽  
Gokul Kumar
Keyword(s):  
Adaptive Filtering ◽  
Adaptive Filters ◽  
Pass Band ◽  
Least Mean Square ◽  
Low Pass ◽  
Parallel Prefix ◽  
Loop Feedback ◽  
Band Pass ◽  
The Difference ◽  
Prefix Adder

: Filtering is an important step in the field of image processing to suppress the required parts or to remove any artifacts present in it. There are different types of filters like low pass, high pass, Band pass, IIR, FIR and adaptive filtering etc.., in these filters adaptive filters is an important filter because it is used to remove the noisy signal and images. Least Mean Square filter is a type of an adaptive filtering which is used to remove the noises present in the medical images. The working of LMS is based on the minimization of the difference between the error images using a closed loop feedback. Therefore presented technique called as Q-CSKA. Here the CSKA performs its operation in stages which is based on the nucleus stage. In the traditional CSKA the nucleus stage is depend on the parallel prefix adder in this work it is replaced by the QCA adder. The QCA adder utilizes the less area compared to PPA and it can be realized in Nanometer range also. For multiplexers, And OR Invert, OR and Invert logic is used to reduce the area and delay. Due to these advantages of the QCA, AOI-OAI logic the proposed method outperformed the LMS implementation in area, power, and accuracy and delay, this based five type image noise of medical pictures related to the best technique is out comes. It helps to medicinal practitioner to resolve the symptoms of patient with ease.

scholarly journals A Novel Neuron in Kernel Domain

2013 ◽  
Vol 2013 ◽  
pp. 1-11 ◽  
Author(s):  
Zahra Khandan ◽  
Hadi Sadoghi Yazdi
Keyword(s):  
Neural Network ◽  
Online Learning ◽  
Mean Square ◽  
Least Mean Square ◽  
Backpropagation Neural Network ◽  
Adaptive Parameters ◽  
Kernel Parameter ◽  
Online Learning Algorithms ◽  
Adaptive Kernel ◽  
Kernel Least Mean Square

Kernel-based neural network (KNN) is proposed as a neuron that is applicable in online learning with adaptive parameters. This neuron with adaptive kernel parameter can classify data accurately instead of using a multilayer error backpropagation neural network. The proposed method, whose heart is kernel least-mean-square, can reduce memory requirement with sparsification technique, and the kernel can adaptively spread. Our experiments will reveal that this method is much faster and more accurate than previous online learning algorithms.

PARALLEL, LOCALLY CONNECTED ALGORITHMS FOR NONLINEAR ADAPTIVE FILTERING

1993 ◽  
Vol 04 (01) ◽  
pp. 85-98 ◽  
Author(s):  
HASSAN M. AHMED ◽  
FAWAD RAUF
Keyword(s):  
Adaptive Filtering ◽  
Layered Structure ◽  
Adaptive Filters ◽  
Computationally Efficient ◽  
Local Connectivity ◽  
Linear Filters ◽  
New Approach ◽  
Vlsi Layout ◽  
State Dependent ◽  
Nonlinear Adaptive Filtering

A new adaptive modular realization for nonlinear filters is presented whereby construction is both computationally efficient and readily implemented. The proposed layered structure consists of locally connected, locally adapted linear filters. Modularity and local connectivity make efficient VLSI layout easy and amenable to automation. The layered structure is based on "state dependent embedding", a new approach to the design of series based nonlinear adaptive filters.

Sign in / Sign up

Export Citation Format

Share Document