Description: % EM algorithm for k multidimensional Gaussian mixture estimation
%
% Inputs:
% X(n,d) - input data, n=number of observations, d=dimension of variable
% k - maximum number of Gaussian components allowed
% ltol - percentage of the log likelihood difference between 2 iterations ([] for none)
% maxiter - maximum number of iteration allowed ([] for none)
% pflag - 1 for plotting GM for 1D or 2D cases only, 0 otherwise ([] for none)
% Init - structure of initial W, M, V: Init.W, Init.M, Init.V ([] for none)
%
% Ouputs:
% W(1,k) - estimated weights of GM
% M(d,k) - estimated mean vectors of GM
% V(d,d,k) - estimated covariance matrices of GM
% L - log likelihood of estimates
% Platform: |
Size: 3416 |
Author:Shaoqing Yu |
Hits:
Description: This directory contains code implementing the K-means algorithm. Source code
may be found in KMEANS.CPP. Sample data isfound in KM2.DAT. The KMEANS
program accepts input consisting of vectors and calculates the given
number of cluster centers using the K-means algorithm. Output is
directed to the screen.-This directory contains code implementing the K-means algorithm. Source code may be found in KMEANS.CPP. Sample data isfound in KM2.DAT. The KMEANS program accepts input consisting of vectors and calculates the given number of cluster centers using the K-means algorithm. Output is directed to the screen. Platform: |
Size: 270336 |
Author:赵丁香 |
Hits:
Description: EM算法+mean shift算法用于图像分割,同时有demo程序用来看最终的分割结果-EM algorithm mean shift algorithm for image segmentation, at the same time have demo program with the ultimate view of segmentation results Platform: |
Size: 6144 |
Author:周华 |
Hits:
Description: % EM algorithm for k multidimensional Gaussian mixture estimation
%
% Inputs:
% X(n,d) - input data, n=number of observations, d=dimension of variable
% k - maximum number of Gaussian components allowed
% ltol - percentage of the log likelihood difference between 2 iterations ([] for none)
% maxiter - maximum number of iteration allowed ([] for none)
% pflag - 1 for plotting GM for 1D or 2D cases only, 0 otherwise ([] for none)
% Init - structure of initial W, M, V: Init.W, Init.M, Init.V ([] for none)
%
% Ouputs:
% W(1,k) - estimated weights of GM
% M(d,k) - estimated mean vectors of GM
% V(d,d,k) - estimated covariance matrices of GM
% L - log likelihood of estimates
%- EM algorithm for k multidimensional Gaussian mixture estimation Inputs: X (n, d)- input data, n = number of observations, d = dimension of variable k- maximum number of Gaussian components allowed ltol- percentage of the log likelihood difference between 2 iterations ([] for none) maxiter- maximum number of iteration allowed ([] for none) pflag- 1 for plotting GM for 1D or 2D cases only, 0 otherwise ([] for none) Init- structure of initial W, M, V: Init.W, Init.M, Init.V ([] for none) Ouputs: W (1, k)- estimated weights of GM M (d, k)- estimated mean vectors of GM V (d, d, k)- estimated covariance matrices of GM L- log likelihood of estimates Platform: |
Size: 3072 |
Author:Shaoqing Yu |
Hits:
Description: 一维EM算法MATLAB实现,两分支高斯混合模型,均值和方差都不相同。-one dimensino EM algorithm implemented by MATLAB. Estimate the mean and variance of Gaussian Mixture Model with two branches. Platform: |
Size: 1024 |
Author:luoyong |
Hits:
Description: EM algorithm mean shift algorithm for image segmentation, at the same time have demo program with the ultimate view of segmentation results Platform: |
Size: 2048 |
Author:FOUFOU2 |
Hits:
Description: fit_mix_2D_gaussian - fit parameters for a 2D mixed-gaussian distribution using EM algorithm
format: [u,covar,t,iter] = fit_mix_2D_gaussian( X,M )
input: X - input samples, Nx2 vector
M - number of gaussians which are assumed to compose the distribution
output: u - fitted mean for each gaussian (each mean is a 2x1 vector)
covar - fitted covariance for each gaussian. this is a 2x2xM matrix.
t - probability of each gaussian in the complete distribution
iter - number of iterations done by the function-fit_mix_2D_gaussian - fit parameters for a 2D mixed-gaussian distribution using EM algorithm
format: [u,covar,t,iter] = fit_mix_2D_gaussian( X,M )
input: X - input samples, Nx2 vector
M - number of gaussians which are assumed to compose the distribution
output: u - fitted mean for each gaussian (each mean is a 2x1 vector)
covar - fitted covariance for each gaussian. this is a 2x2xM matrix.
t - probability of each gaussian in the complete distribution
iter - number of iterations done by the function Platform: |
Size: 2048 |
Author:resident e |
Hits:
Description: fit_mix_gaussian - fit parameters for a mixed-gaussian distribution using EM algorithm
format: [u,sig,t,iter] = fit_mix_gaussian( X,M )
input: X - input samples, Nx1 vector
M - number of gaussians which are assumed to compose the distribution
output: u - fitted mean for each gaussian
sig - fitted standard deviation for each gaussian
t - probability of each gaussian in the complete distribution
iter- number of iterations done by the function- fit_mix_gaussian - fit parameters for a mixed-gaussian distribution using EM algorithm
format: [u,sig,t,iter] = fit_mix_gaussian( X,M )
input: X - input samples, Nx1 vector
M - number of gaussians which are assumed to compose the distribution
output: u - fitted mean for each gaussian
sig - fitted standard deviation for each gaussian
t - probability of each gaussian in the complete distribution
iter- number of iterations done by the function Platform: |
Size: 1024 |
Author:resident e |
Hits:
Description: Using SAS/IML :
This code uses the EM algorithm to estimate the maximum likelihood (ML) covariance matrix and mean vector in the presence of missing data. This implementation of the EM algorithm or any similar ML approach assumes that the data are missing completely at random (MCAR) or missing at random (MAR: see Little & Rubin, 1987).-Using SAS/IML :
This code uses the EM algorithm to estimate the maximum likelihood (ML) covariance matrix and mean vector in the presence of missing data. This implementation of the EM algorithm or any similar ML approach assumes that the data are missing completely at random (MCAR) or missing at random (MAR: see Little & Rubin, 1987). Platform: |
Size: 9216 |
Author:jpsartre |
Hits:
Description: EM算法+mean shift算法用于图像分割,同时有deemo程序源码用来看最终的分割结果 可直接使用。 已通过测试。
-EM algorithm+ mean shift algorithm for image segmentation, while deemo program source with the point of view the final segmentation results can be used directly. Has been tested. Platform: |
Size: 6144 |
Author:拥抱 |
Hits:
Description: This the MATLAB code that was used to produce the figures and tables in Section V of
F. Forbes and G. Fort, Combining Monte Carlo and mean-field like methods for inference
in Hidden Markov Random Fields, Accepted for publication in IEEE Trans. on Image
Processing, 2006.
1
MATLAB has the capability of running functions written in C. The files which hold the source
for these functions are called MEX-Files. Some functions of our codes are written in C.
The purpose of this software is to implement the MCVEM algorithm, described in the paper
mentioned above, when applied to Image Segmentation. MCVEM consists in combining approximation
techniques - based on variational EM - and simulation techniques - based on MCMC
-.
This software is the first version that is made publicly available.
2 How to
2.1 Obtain the source code
Download it from
http://www.tsi.enst.fr/gfort/INRIA/MCVEM.html
After unpacking the archive, you should obtain
• two-This is the MATLAB code that was used to produce the figures and tables in Section V of
F. Forbes and G. Fort, Combining Monte Carlo and mean-field like methods for inference
in Hidden Markov Random Fields, Accepted for publication in IEEE Trans. on Image
Processing, 2006.
1
MATLAB has the capability of running functions written in C. The files which hold the source
for these functions are called MEX-Files. Some functions of our codes are written in C.
The purpose of this software is to implement the MCVEM algorithm, described in the paper
mentioned above, when applied to Image Segmentation. MCVEM consists in combining approximation
techniques - based on variational EM - and simulation techniques - based on MCMC
-.
This software is the first version that is made publicly available.
2 How to
2.1 Obtain the source code
Download it from
http://www.tsi.enst.fr/gfort/INRIA/MCVEM.html
After unpacking the archive, you should obtain
• two Platform: |
Size: 692224 |
Author:jeevithajaikumar |
Hits:
Description: 基于EM算法的混合高斯分布参数估计方法,包括权值、均值和标准差-Mixed Gaussian distribution parameter estimation method based on the EM algorithm, weights, including the mean and standard deviation Platform: |
Size: 2048 |
Author:董骏城 |
Hits:
Description: 对于混合高斯分布的情况,使用最大期望算法,通过不断计算每个样本的均值与方差,使得似然函数达到最大值。可以很好地处理满足一定概率分布的数据。
代码中通过mvnrnd()函数,设定其中的参数,产生符合混合高斯分布的一组数据集。-For the case of a mixed Gaussian distribution, using expectation-maximization algorithm, through continuous calculation of the mean and variance of each sample, so that the likelihood function is maximized. Well with the data meet certain probability distribution.
Code by mvnrnd () function, which set the parameters of a set of data that meets the set of mixed Gaussian distribution. Platform: |
Size: 1024 |
Author:小明 |
Hits:
Description: 实验报告,实现:对于混合高斯分布的情况,使用最大期望算法,通过不断计算每个样本的均值与方差,使得似然函数达到最大值。可以很好地处理满足一定概率分布的数据。
代码中通过mvnrnd()函数,设定其中的参数,产生符合混合高斯分布的一组数据集。-Lab reports, to achieve: the case of the mixed Gaussian distribution, using expectation-maximization algorithm, through continuous calculation of the mean and variance of each sample so that the likelihood function is maximized. Well with the data meet certain probability distribution.
Code by mvnrnd () function, which set the parameters of a set of data that meets the set of mixed Gaussian distribution. Platform: |
Size: 26624 |
Author:小明 |
Hits:
Description: 此算法实现高斯混合,可以对初始聚类算法选择c均值和EM,可以实现密度估计和分类。(This GMM algorithm can estimate the density and class, the initial steps can select the C-mean and EM.) Platform: |
Size: 10240 |
Author:永yong
|
Hits:
Description: 用EM算法求解高斯混合模型并可视化,数据是男女生的身高分布,前提是初始化男女生身高各自的均值和方差和比例,然后由EM算法求解,男女生身高的均值方差,以拟合数据。(The EM algorithm is used to solve the Gauss mixture model and visualize. The data is the height distribution of male and female. The premise is to initialize the mean, variance and proportion of the male and female height, then the mean variance of the height of male and female is solved by the EM algorithm, so as to fit the data.) Platform: |
Size: 1197056 |
Author:andyya |
Hits: