Description: 本程序实做MLP(Multi-layer perceptron)算法，使用者可以自行设定训练数据集与测试数据集，将训练数据集加载，在2、3维下可以显示其分布状态，并分别设定键节值、学习率、迭代次数来训练其类神经网络，最后可观看辨识率与RMSE（Root Mean squared error）来判别训练是否可以停止。-This procedure is to do MLP (Multi-layer perceptron) algorithm, the user can set their own training data set and test data sets, the training data set is loaded, in the 2,3-dimensional display of their distribution, and were set key section of the value of learning rate, number of iterations to train the neural network can watch the final recognition rate and the RMSE (Root Mean squared error) to determine whether the training can stop. Platform: |
Size: 1213440 |
Author:楊易 |
Hits:
Description: 若不希望用与估计输入信号矢量有关的相关矩阵来加快LMS算法的收敛速度，那么可用变步长方法来缩短其自适应收敛过程，其中一个主要的方法是归一化LMS算法（NLMS算法），变步长 的更新公式可写成
W（n+1）=w（n）+ e（n）x（n）
=w（n）+ （3.1）
式中， = e（n）x（n）表示滤波权矢量迭代更新的调整量。为了达到快速收敛的目的，必须合适的选择变步长 的值，一个可能策略是尽可能多地减少瞬时平方误差，即用瞬时平方误差作为均方误差的MSE简单估计，这也是LMS算法的基本思想。
-Want to estimate if the input signal vector and the relevant matrix to speed up the convergence rate of LMS algorithm, then the variable step size method can be used to shorten its adaptive convergence process, one of the main method is normalized LMS algorithm (NLMS algorithm) , variable step-size update formula can be written W (n+ 1) = w (n)+ e (n) x (n) = w (n)+ (3.1) where, = e (n) x (n) the right to express filter update vector iterative adjust the volume. In order to achieve the purpose of fast convergence, we must choose the appropriate value of variable step size, a possible strategy is as much as possible to reduce the instantaneous squared error, which uses the instantaneous squared error as the mean square error MSE of the simple estimate, which is the basic LMS algorithm思想. Platform: |
Size: 3072 |
Author:闫丰 |
Hits:
Description: Here we design the minimum mean-squared error (MMSE) equalizer coefficients {q[k]}assuming that the input symbols {a[n]} and the noise { ˜ w[k]} are white random sequencesthat are uncorrelated with each other.-Here we design the minimum mean-squared error (MMSE) equalizer coefficients {q[k]}assuming that the input symbols {a[n]} and the noise { ˜ w[k]} are white random sequencesthat are uncorrelated with each other. Platform: |
Size: 70656 |
Author:Allen |
Hits:
Description: MATLAB code on linear minimum mean square error (LMMSE) estimation and its application to the problem of channel equalization in digital communication systems.
amr amin: code on the application of channel equalization in digital communication systems. - MATLAB code on linear minimum mean square error (LMMSE) estimation and its application to the problem of channel equalization in digital communication systems.
amr amin: code on the application of channel equalization in digital communication systems. Platform: |
Size: 1024 |
Author:amr |
Hits:
Description: 经典的频谱共享的EI检索算法，运用动态频谱租用来提高频谱利用率。-Dynamic Spectrum Leasing (DSL) is a new
paradigm for efficient spectrum sharing in cognitive radio
networks that was recently proposed in [1]–[3]. Unlike in a
hierarchical dynamic spectrum access (DSA) network, DSL
allows active participation of both the primary and the secondary
users in the spectrum sharing process. In this paper we further
generalize the DSL game introduced in [2] by allowing for linear
multiuser detectors, in particular the matched filter (MF) and
linear minimum mean squared error (LMMSE) receivers, at the
secondary base stations. We establish the conditions so that the
DSL game has desired equilibrium properties. Performance of
the proposed system at the equilibrium is compared through
simulations Platform: |
Size: 183296 |
Author:刘小洋 |
Hits:
Description: Abstract—In this paper, we study the joint estimation of inphase
and quadrature-phase (I/Q) imbalance, carrier frequency
offset (CFO), and channel response for multiple-input multipleoutput
(MIMO) orthogonal frequency division multiplexing
(OFDM) systems using training sequences. A new concept called
channel residual energy (CRE) is introduced. We show that by
minimizing the CRE, we can jointly estimate the I/Q imbalance
and CFO without knowing the channel response. The proposed
method needs only one OFDM block for training and the training
symbols can be arbitrary. Moreover when the training block
consists of two repeated sequences, a low complexity two-step
approach is proposed to solve the joint estimation problem.
Simulation results show that the mean-squared error (MSE) of
the proposed method is close to the Cramer-Rao bound (CRB).
Index Terms—MIMO OFDM, CFO, I/Q imbalance, channel
estimation. Platform: |
Size: 551936 |
Author:santhu |
Hits:
Description: Abstract—In this paper, we study the joint estimation of inphase
and quadrature-phase (I/Q) imbalance, carrier frequency
offset (CFO), and channel response for multiple-input multipleoutput
(MIMO) orthogonal frequency division multiplexing
(OFDM) systems using training sequences. A new concept called
channel residual energy (CRE) is introduced. We show that by
minimizing the CRE, we can jointly estimate the I/Q imbalance
and CFO without knowing the channel response. The proposed
method needs only one OFDM block for training and the training
symbols can be arbitrary. Moreover when the training block
consists of two repeated sequences, a low complexity two-step
approach is proposed to solve the joint estimation problem.
Simulation results show that the mean-squared error (MSE) of
the proposed method is close to the Cramer-Rao bound (CRB).
Index Terms—MIMO OFDM, CFO, I/Q imbalance, channel
estimation. Platform: |
Size: 277504 |
Author:santhu |
Hits:
Description: An Adaptive Block-Based Eigenvector Equalization for Time-Varying Multipath Fading Channels.In this paper we present an adaptive Block-
Based EigenVector Algorithm (BBEVA) for blind equalization
of time-varying multipath fading channels. In addition
we assess the performance of the new algorithm for different
configurations and compare the results with the
least mean squares (LMS) algorithm. The new algorithm is
evaluated in terms of intersymbol interference (ISI) suppression,
mean squared error (MSE) and by examining the
signal constellation at the output of the equalizer. Platform: |
Size: 261120 |
Author:abd091 |
Hits:
Description: 均方误差信噪比 峰值信噪平均绝对误差的计算-Write MATLAB functions that take two grayscale images as input, and calculate the
following image difference metrics:
Mean Squared Error (MSE)
Signal to Noise Ratio(SNR)
Peak Signal to Noise Ratio (PSNR)
Mean Absolute Error (MAE)
Process the given test images “Lena” with its original and after-adding-noise Platform: |
Size: 3072 |
Author:宁可 |
Hits:
Description: 图像去噪-A Generative Perspective on MRFs in Low-Level Vision-A Generative Perspective on MRFs in Low-Level Vision
Markov random fields (MRFs) are popular and generic
probabilistic models of prior knowledge in low-level vision.
Yet their generative properties are rarely examined, while
application-specific models and non-probabilistic learning
are gaining increased attention. In this paper we revisit
the generative aspects of MRFs, and analyze the quality of
common image priors in a fully application-neutral setting.
Enabled by a general class of MRFs with flexible potentials
and an efficient Gibbs sampler, we find that common models
do not capture the statistics of natural images well. We
show how to remedy this by exploiting the efficient sampler
for learning better generative MRFs based on flexible potentials.
We perform image restoration with these models
by computing the Bayesian minimum mean squared error
estimate (MMSE) using sampling. This addresses a number
of shortcomings that have limited generative MRFs so far,
and le Platform: |
Size: 1216512 |
Author:孙文义 |
Hits:
Description: Bayesian Deblurring with Integrated Noise Estimation-Bayesian Deblurring with Integrated Noise Estimation
Conventional non-blind image deblurring algorithms
involve natural image priors and maximum a-posteriori
(MAP) estimation. As a consequence of MAP estimation,
separate pre-processing steps such as noise estimation and
training of the regularization parameter are necessary to
avoid user interaction. Moreover, MAP estimates involving
standard natural image priors have been found lacking in
terms of restoration performance. To address these issues
we introduce an integrated Bayesian framework that unifies
non-blind deblurring and noise estimation, thus freeing the
user of tediously pre-determining a noise level. A samplingbased
technique allows to integrate out the unknown noise
level and to perform deblurring using the Bayesian minimum
mean squared error estimate (MMSE), which requires
no regularization parameter and yields higher performance
than MAP estimates when combined with a learned highorder
image prior. A quan Platform: |
Size: 904192 |
Author:孙文义 |
Hits:
Description: k均值聚类算法，使各个样本与所在类均值的误差平方和达到最小，并且附有显示程序-k-means clustering algorithm, where the class so that each sample and the mean squared error to a minimum, and with the display program Platform: |
Size: 2048 |
Author:木木 |
Hits:
Description: matlab下ESN的工具This software is intended for research use by experienced Matlab users
and includes no warranties or services.-In alphabetical order here is what the routines are doing:
analogToUnitCoded:
- helper function for coding a 1-dim analog signal into a unit-coded
signal (aka "local coding")
compute_NRMSE:
- computes the normalized mean squared error of the esn, given the
output of the esn and the actual teacher.
compute_statematrix:
- runs the input through the ESN. The reservoir (plus input) states of
the units are collected in matrix which is returned by the function Platform: |
Size: 67584 |
Author:max |
Hits:
Description: K-均值聚类算法,基本算法代码，算法的目的是使各个样本与所在类均值的误差平方和达到最小。-The purpose of K-means clustering algorithm, the basic algorithm code, the algorithm is to make the class where each sample mean squared error is minimized. Platform: |
Size: 2048 |
Author:angelia |
Hits:
Search - mean squared error