资源列表
Data-partitioning
- 在海量数据处理中可以用到，对大量数据的预处理，可以知道数据分布情况，并进行归类。 -In the mass data processing can be used for a large number of pre-processing of data, we can know the distribution of data, and collation.
P1-s2.0-S0957417410001107-main
- Business cycle predictions face various sources of uncertainty and imprecision. The uncertainty is usually linguistically determined by the beliefs of decision makers. Thus, the fuzzy set theory is ideally suited to depict vague and uncertain feature
DM_BayesAndKNN
- C++实现数据挖掘的贝叶斯分类方法和k-近邻分类方法，有源码，有示例数据，有说明文档-C++ implementation of data mining methods and Bayesian classification k- nearest neighbor classification method, there is source code, sample data, documentation
Kmeans
- 直接输入图片，以及类别数，返回分类结果，聚类中心，跌代次数。-Directly enter the picture, as well as the number of categories, the classification result is returned, the cluster center, down the number of generations.
SVMshift
- 支持向量机漂移程序，用于将多类别分割的数据支持向量推移到稳定的边界-SVM shift
PCA
- 利用MATLAB语言，主成分分析源代码，有具体分析距离，程序有详细注释-Using MATLAB language, principal component analysis source code, a detailed analysis the program detailed notes
bp
- 可以采用神经网络对时间序列进行预测，具有较好的效果-The neural network can be used to predict the time series, which has better effect.
EMOTION
- 介绍了情感分析与数据挖掘的相关算法，大数据智能-Introduces the sentiment analysis algorithms and data mining
GAKMeans
- 由于Kmeans聚类分析是一个局部的搜索过程，因此加入遗传算法进行全局搜索选择最优的初始中心点使得Kmeans算法产生较大的改进-Since Kmeans Cluster analysis is a local search process, so join a global search for the genetic algorithm to the optimal initial centers such Kmeans algorithm produces greater improve
EMKmeans
- 在线KMeans算法不同于一般的聚类，其主要算法为梯度下降法-Online KMeans Unlike clustering algorithm, the main gradient descent algorithm
LogitTwice
- 基于逻辑回归的二分类算法代码，能很好的实现-Binary logistic regression based algorithm code, can achieve a good
LogitMul
- 基于逻辑回归的多分类问题，可以实现至少三类数据的分类-Classification based on multiple logistic regression, classification can be achieved at least three types of data