搜索资源列表
kmeans1
- 实现对图片进行k均值聚类,也可以修改初始值,修改图片名直接可以运行-Implementation to k-means clustering of images, can also modify the initial value, the images can be run directly
Iris_s1
- Kmeans+PSO算法,处理IRIS数据集,输出fitness function的值,和粒子变化的动态图像,亲测可行。-Kmeans based PSO algorithms, dealing with classic dataset iris. the output is the value of fitness function, and the dynamic plot of the change of particle position
zishiyingguolvfa
- 自适应过滤法是根据一组给定的权数对时间数列的历史观察值进行加权平均计算一个预测值,然后根据预测误差调整权数以减少误差,这样反复进行直至找出一组“最佳”权数,使误差减少到最低限度,再利用最佳权数进行加权平均预测。-Adaptive filtering method is based on the number of a given set of rights to compute a weighted average of the predicted value of historical tim
pca_exercise
- 这是一份介绍PCA在图像处理里面的例子,里面代码都有详细介绍,很有价值-This is a descr iption of the image processing inside PCA example, which codes are detailed, great value
degreediscountic2
- 改进的基于节点度的影响最大化算法,度打折是指,每一次迭代时,度的值会根据种子节点而发生变化。-Improved based on node degree maximization algorithm, and the influence of the degree of discount means that each iteration, the degree of value will change according to the seed node
multi-dimensional-particle
- 一维及二维数据粒子算法寻优,包括1)二维粒子算法参数寻优-替代网格寻优;2)一维数据粒子算法寻优(极值)。- One dimensional and two dimensional data particle algorithm optimization, including 1) two dimensional particle algorithm parameter optimization- alternative grid optimization 2) one dimens
IG
- 实现计算特征的信息增益,最后一列为样本标签,输出为特征的信息增益值及对应的序列号-Calculated to achieve gain characteristic information, and finally as a sample of tag output information characteristic of the gain value and the sequence number corresponding to
CHI
- 计算特征的卡方校验值,最后一列为样本标签,输出为特征的卡卡校验值及对应的特征序列号-The chi-square calculate checksum feature, the last one as a sample label, the output characteristics of the card verification value and the corresponding serial number feature
mixBern
- Just like EM of Gaussian Mixture Model, this is the EM algorithm for fitting Bernoulli Mixture Model. GMM is useful for clustering real value data. However, for binary data (such as bag of word feature) Bernoulli Mixture is more suitable.
k_meansPP
- K-means++算法是K-means算法的一个改进算法,其中主要改进了k值的选取不会在影响聚类的效果,具有高度的自动性-K-means++ algorithm K-means algorithm, an improved algorithm, in which the major improvements k value does not affect the clustering effect, a high degree of automaticity
svd
- 奇异值分解在某些方面与对称矩阵或厄米矩阵基于特征向量的对角化类似。然而这两种矩阵分解尽管有其相关性,但还是有明显的不同。-Singular value decomposition in some respects symmetric matrix or Hermitian matrix based on a similar feature vectors diagonalization. However, the two matrix decomposition in spite of its
ThemeCrawler
- 现在常见的搜索策略主要分为两种:一种是基于网页链接结构的搜索策略,另一种是基于内容评价的搜索策略。第一种是通过网页之间的链接关系来确定网页的重要性,从而决定链接访问的顺序。此方法虽然考虑了网页链接结构和网页之间的链接关系,但忽略了网页内容与主题的相关度,容易出现网页搜索“主题漂移”。第二种主要考虑网页内容,好处就是思路清晰且计算简单。但这种方法忽略了网页的链接关系,故在预测链接网页价值方面存在不足。考虑到这些问题,提出将布谷鸟搜索算法应用到主题爬虫中。-Now the common search
Naive-bayes
- 本文以拼写检查作为例子,讲解Naive Bayes分类器是如何实现的。对于用户输入的一个单词(words),拼写检查试图推断出最有可能的那个正确单词(correct)。当然,输入的单词有可能本身就是正确的。比如,输入的单词thew,用户有可能是想输入the,也有可能是想输入thaw。为了解决这个问题,Naive Bayes分类器采用了后验概率P(c|w)来解决这个问题。P(c|w)表示在发生了w的情况下推断出c的概率。为了找出最有可能c,应找出有最大值的P(c|w),即求解问题-In this
NJU-SSDR
- 半监督判别分析(SSDR),是南京大学数据挖掘研究所提出的一种新的半监督降维算法,对于数据挖掘和类别样本的获取有着十分重要的借鉴价值。-A semi-supervised discriminant analysis (SSDR), is one of the types of data mining research institute of nanjing university puts forward new a semi-supervised dimensionality reductio
douban
- 网络爬虫编码,可爬取数据,可以用于初学者学习,具有较好的参考价值。-Network crawler coding, crawling data can be used for beginners to learn, with a good reference value.
Wind-Speed-Combined-Prediction
- 针对风电场短期风速的预测提出一种基于小波变换的组合预测方法。首先利用Mallat 算法对短期风速时间序列进行db3 小波三层分解与重构,得到短期风速时间序列的近似分量和细节分量。针对近似分量和细节分量的不同特性,对近似分量利用粒子群算法优化的最小二乘支持向量机进行预测,对细节分量利用自回归求和滑动平均模型进行预测。最后各预测模型预测值组合叠加得到最终的短期风速预测值。仿真结果表明该方法具有较高的预测准确度。-In order to improve short-term wind speed pr
BinaryNet-master
- 二值化程序代码,对数据进行很好地优化,实用于图像处理,图像去噪(Two value of the program code, the data is well optimized)
K_Means
- K-Means是聚类算法中的一种,其中K表示类别数,Means表示均值。顾名思义K-Means是一种通过均值对数据点进行聚类的算法。K-Means算法通过预先设定的K值及每个类别的初始质心对相似的数据点进行划分。并通过划分后的均值迭代优化获得最优的聚类结果。(K-Means is one of the clustering algorithms, in which K represents the number of classes, and Means means the mean. As t
07 RFM建模实战
- 1、通过Python的Pandas库实现客户价值分层的RFM模型; 2、提供源数据(1. Through Python pandas library, the RFM model of customer value stratification is realized; 2. Provide source data)
