Description: 利用最小互信息实现向量的特征选择，优化分类器的设计，原创-The use of mutual information to achieve the smallest feature selection vectors, optimizing the classifier design, originality Platform: |
Size: 1024 |
Author:王将 |
Hits:
Description: mRMR_0.9_compiled最小冗余和最大相关特征选取源代码，-This package is the mRMR (minimum-redundancy maximum-relevancy) feature selection method, whose better performance over the conventional top-ranking method has been demonstrated on a number of data sets in recent publications. This version uses mutual information as a proxy for computing relevance and redundancy among variables (features). Other variations such as using correlation or F-test or distances can be easily implemented within this framework, too.
Platform: |
Size: 1020928 |
Author:韩华 |
Hits:
Description: 有监督的特征选择和优化程序MATLAB代码，基于最小二乘算法。内有测试数据，和详细程序说明-Least-Squares Feature Selection (LSFS) is a feature selection method for supervised regression and classification. LSFS orders input features according to their dependence on output values. Dependency between inputs and outputs is evaluated based on an estimator of squared-loss mutual information called LSMI Platform: |
Size: 3072 |
Author:zy |
Hits:
Description: 基于互信息理论的最大相关排序算法，可应用于各领域的特征选择。-Maximum mutual information based relevance ranking algorithm theory can be applied to all areas of feature selection. Platform: |
Size: 3072 |
Author:crossrainbow8696 |
Hits:
Description: 粗糙集代码
data reduction with fuzzy rough sets or fuzzy mutual information
fuzzy preference rough set based feature evaluation and selection
-Rough code data reduction with fuzzy rough sets or fuzzy mutual information fuzzy preference rough set based feature evaluation and selection Platform: |
Size: 38912 |
Author:gq |
Hits:
Description: Hanchuan Peng, Fuhui Long, and Chris Ding, "Feature selection
based on mutual information: criteria of max-dependency,
max-relevance, and min-redundancy," IEEE Transactions on
Pattern Analysis and Machine Intelligence, Vol. 27, No. 8,
pp.1226-1238, 2005.- Hanchuan Peng, Fuhui Long, and Chris Ding, "Feature selection
based on mutual information: criteria of max-dependency,
max-relevance, and min-redundancy," IEEE Transactions on
Pattern Analysis and Machine Intelligence, Vol. 27, No. 8,
pp.1226-1238, 2005. Platform: |
Size: 493568 |
Author:yanyan |
Hits:
Description: 利用互信息赛选特征，赛选与类别不相关，冗余的特征，保留与类别相关的特征，对特征对类别的贡献率排序，保留前面的K个特征最为最后的特征-Feature selection using mutual information game, not related to race and class selection, redundancy features, retaining the characteristics associated with the category, the characteristics of the category' s contribution rate sort, keep the K in front of the most characteristic features of the final Platform: |
Size: 22528 |
Author:慕南 |
Hits:
Description: 音乐领域中文实体关系抽取研究
实体关系抽取的任务是从文本中抽取出两个或者多个实体之间预先定义
好的语义关系。本文将实体关系抽取定义为一个分类问题，主要研究内容是
中文音乐领域的实体关系抽取。针对这一问题，本文首先构建了中文音乐实
体关系语料库，然后分别采用了基于序列模式挖掘的无指导的方法和基于特
征提取的有指导的方法来解决这一问题。 -Dissertation for the Master Degree in Engineering urgently needed to deal with, efficient Web classification method is to extract the required letter from the online Sea Scout information, the interest rate on the key technology, feature selection is an important foundation for text classification mining, the tomb of generalized information theory as the theoretical basis, the tomb of selection methods at the secondary entropy of mutual trust Chi characteristics of each feature, independent assessment, then the feature set to analyze the relationship between the characteristics and categories, from high-dimensional feature space selected remove the lining of the characteristics of effective text classification, reducing the dimension of the text feature space, improve the nature of the text classification Platform: |
Size: 1445888 |
Author:xz |
Hits:
Description: A function to estimate the mutual information (MI) between pairs of features and target classes. A histogram approach is used in this implementation. This function can be used in feature selection. Platform: |
Size: 1024 |
Author:Ahmed |
Hits:
Description: In this paper, we systematically explore feature definition and selection strategies for sentiment polarity classification. We begin by exploring basic questions, such
as whether to use stemming, term frequency versus binary weighting, negation-enriched features, n-grams or
phrases. We then move onto more complex aspects
including feature selection using frequency-based vocabulary trimming, part-of-speech and lexicon selection (three types of lexicons), as well as using expected Mutual Information (MI). Using three product
and movie review datasets of various sizes, we show,
for example, that some techniques are more beneficial
for larger datasets than the smaller. A classifier trained
on only few features ranked high by MI outperformed
one trained on all features in large datasets, yet in small
dataset this did not prove to be true. Finally, we perform a space and computation cost analysis to further
understand the merits of various feature types. Platform: |
Size: 701440 |
Author:ibrahim |
Hits:
Description: 最小冗余最大相关性（MRMR）（MRMR.M）
需要外部库。详情请见MRMR。下载一个更新版本的互信息工具箱
偏最小二乘（PLS）回归系数（ReGCOEF.m）
使用MATLAB统计工具箱中的PLSReress
ReliefF（分类）和RReliefF（回归）（ReleFracePr.M.）
从Matlab STATS工具箱中包装Releff.m。这是Matlab R2010B以后提供的。
ReliefF的另一个选择是使用ASU特征选择工具箱中的代码。这使用WEKA工具箱的ReleFEF，因此需要额外的库。请参阅相应的文档。
费雪评分（Fisher评分）
围绕ASFS特征选择工具箱围绕FSFisher。M(Minimum Redundancy Maximum Relevance (mRMR) (mRMR.m)
Needs external library. See mRMR.m for details.
Download a newer version of the mutual information toolbox
Partial Least Squares (PLS) regression coefficients (regCoef.m)
Uses plsregress.m from MATLAB statistics toolbox
ReliefF (classification) and RReliefF (regression) (relieffWrapper.m)
Wraps around relieff.m from the MATLAB stats toolbox. This is available MATLAB r2010b onwards.
Another option for ReliefF is to use the code from ASU Feature Selection toolbox. This uses ReliefF from weka toolbox and hence needs additional libraries. Please see the corresponding documentation.
Fisher Score (fisherScore.m)
Wraps around fsFisher.m from the ASU Feature Selection toolbox) Platform: |
Size: 11264 |
Author:smilingcost |
Hits:
Search - mutual information feature selection