A hybrid genetic algorithm based on mutative scale chaos optimization strategy

In order to avoid such problems as low convergent speed and local optimal solution in simple genetic algorithms, a new hybrid genetic algorithm is proposed. In this algorithm, a mutative scale chaos optimization strategy is operated on the population after a genetic operation. And according to the searching process, the searching space of the optimal variables is gradually diminished and the regulating coefficient of the secondary searching process is gradually changed which will lead to the quick evolution of the population. The algorithm has such advantages as fast search, precise results and convenient using etc. The simulation results show that the performance of the method is better than that of simple genetic algorithms.     

Nearest neighbor search algorithm forGBD tree spatial data structure

： This paper describes the nearest neighbor （NN） search algorithm on the GBD（generalized BD） tree. The GBD tree is a spatial data structure suitable for two- or three-dimensional data and has good performance characteristics with respect to the dynamic data environment. On GIS and CAD systems, the R-tree and its-successors have been used. In addition, the NN search algorithm is also proposed in an attempt to obtain good performance from the R-tree. On the other hand, the GBD tree is superior to the R-tree with respect to exact match retrieval, because the GBD tree has auxiliary data that uniquely determines the position of the object in the structure. The proposed NN search algorithm depends on the property of the GBD tree described above. The NN search algorithm on the GBD tree was studied and the performance thereof was evaluated through experiments.     

Hand Gesture Recognition Based on Improved FRNN

The trained Gaussian mixture model is used to make skincolour segmentation for the input image sequences. The hand gesture region is extracted, and the relative normalization images are obtained by interpolation operation. To solve the proem of hand gesture recognition, Fuzzy-Rough based nearest neighbour（RNN） algorithm is applied for classification. For avoiding the costly compute, an improved nearest neighbour classification algorithm based on fuzzy-rough set theory （FRNNC） is proposed. The algorithm employs the represented cluster points instead of the whole training samples, and takes the hand gesture data＇s fuzziness and the roughness into account, so the campute spending is decreased and the recognition rate is increased. The 30 gestures in Chinese sign language alphabet are used for approving the effectiveness of the proposed algorithm. The recognition rate is 94.96%, which is better than that of KNN （K nearest neighbor）and Fuzzy- KNN （Fuzzy K nearest neighbor）.     

Incremental Web Usage Mining Based on Active Ant Colony Clustering

To alleviate the scalability problem caused by the increasing Web using and changing users＇ interests, this paper presents a novel Web Usage Mining algorithm-Incremental Web Usage Mining algorithm based on Active Ant Colony Clustering. Firstly, an active movement strategy about direction selection and speed, different with the positive strategy employed by other Ant Colony Clustering algorithms, is proposed to construct an Active Ant Colony Clustering algorithm, which avoid the idle and ＂flying over the plane＂ moving phenomenon, effectively improve the quality and speed of clustering on large dataset. Then a mechanism of decomposing clusters based on above methods is introduced to form new clusters when users＇ interests change. Empirical studies on a real Web dataset show the active ant colony clustering algorithm has better performance than the previous algorithms, and the incremental approach based on the proposed mechanism can efficiently implement incremental Web usage mining.     

Immune Based Intrusion Detector Generating Algorithm

Immune-based intrusion detection approaches are studied. The methods of constructing self set and generating mature detectors are researched and improved. A binary encoding based self set construction method is applied. First, the traditional mature detector generating algorithm is improved to generate mature detectors and detect intrusions faster. Then, a novel mature detector generating algorithm is proposed based on the negative selection mechanism. According to the algorithm, less mature detectors are needed to detect the abnormal activities in the network. Therefore, the speed of generating mature detectors and intrusion detection is improved. By comparing with those based on existing algorithms, the intrusion detection system based on the algorithm has higher speed and accuracy.     

Fast Fractal Image Encoding Using an Improved Search Scheme

As fractal image encoding algorithms can yield high-resolution reconstructed images at very high compression ratio, and therefore, have a great potential for improving the efficiency of image storage and image transmission. However, the baseline fractal encoding algorithm requires a great deal of time to complete the best matching search between the range and domain blocks, which greatly limits practical applications of the algorithm. In order to solve this problem, a necessary condition of the best matching search based on an image feature is proposed in this paper. The proposed method can reduce the search space significantly and excludes the most inappropriate domain blocks for each range block before carrying out the best matching search. Experimental results show that the proposed algorithm can produce good quality reconstructed images and requires much less time than the baseline encoding algorithm. Specifically, the new algorithm can speed up encoding by about 85 times with a loss of just 3 dB in the peak signal to noise ratio (PSNR), and yields compression ratios close to 34.     

Feature Selection Based on Difference and Similitude in Data Mining

Feature selection is the pretreatment of data mining. Heuristic search algorithms are often used for this subject. Many heuristic search algorithms are based on discernibility matrices, which only consider the difference in information system. Because the similar characteristics are not revealed in discernibility matrix, the result may not be the simplest rules. Although differencesimilitude（DS） methods take both of the difference and the similitude into account, the existing search strategy will cause some important features to be ignored. An improved DS based algorithm is proposed to solve this problem in this paper. An attribute rank function, which considers both of the difference and similitude in feature selection, is defined in the improved algorithm. Experiments show that it is an effective algorithm, especially for large-scale databases. The time complexity of the algorithm is O（｜ C ｜^2｜U ｜^2）.     

Data Reduction and Triangulation Approach to Scattered Points

For the generation of the model in reverse engineering, a laser scanner is currently used a lot due to the fast measuring speed and high precision. Direct triangulation of data points captured from a physical object has a great advantage in that it can reduce the time and error in modeling process. It is important to reduce the number of data points for triangulating points with maintaining precision. To triangulate data points within a tolerance ε a new approach is developed in this paper. Different level of triangulations can be generated directly from data points using the proposed strategy that reduces and triangulates data points based on triangulation of 3D parametric surfaces. An experimental example is presented to demonstrate the effectiveness and efficiency of the proposed algorithm.     

Personalized Recommendation Algorithm Based on Preference Features

A hybrid collaborative filtering algorithm based on the user preferences and item features is proposed.A thorough investigation of Collaborative Filtering （CF） techniques preceded the development of this algorithm.The proposed algorithm improved the user-item similarity approach by extracting the item feature and applying various item features＇ weight to the item to confirm different item features.User preferences for different item features were obtained by employing user evaluations of the items.It is expected that providing better recommendations according to preferences and features would improve the accuracy and efficiency of recommendations and also make it easier to deal with the data sparsity.In addition,it is expected that the potential semantics of the user evaluation model would be revealed.This would explain the recommendation results and increase accuracy.A portion of the MovieLens database was used to conduct a comparative experiment among the proposed algorithms,i.e.,the collaborative filtering algorithm based on the item and the collaborative filtering algorithm based on the item feature.The Mean Absolute Error （MAE） was utilized to conduct performance testing.The experimental results show that employing the proposed personalized recommendation algorithm based on the preference-feature would significantly improve the accuracy of evaluation predictions compared to two previous approaches.     

A Chinese Web page clustering algorithm based on the suffix tree

In this paper, an improved algorithm, named STC-I. is proposed for Chinese Web page clustering based on Chinese language characteristics, which adopts a new unit choice principle and a novel suffix tree construction policy. The experimental results show that the new algorithm keeps advantages of STC, and is better than STC in precision and speed when they are used to cluster Chinese Web page.     

基于图像熵分类的移动终端数字水印算法

本文围绕移动终端多媒体数据版权保护问题，针对移动终端处理能力弱和内存小的特点，采用基于图像熵分类的方法设计码书；同时在水印嵌入过程，优先将水印信息嵌入于复杂度较高的纹理区域，以提高嵌入水印后的图像质量，并采用等均值等方差最近邻码字搜索算法代替传统搜索算法以缩短编码时间。实验证明，本算法在提高码书质量的同时，能有效的减少码书训练时间；并对JPEG压缩、剪切、小角度旋转等图像攻击具有较强的鲁棒性。     

一种对于K-means算法的改进

数据聚类是一个功能强大的技术,它能够把数据特征相似的对象划分为一类,但是并不是所有的聚类算法的实现都能产生相同的聚类结果;并且K均值算法的结果很大程度上依赖它的初始中心的选择;提出了一种新颖的关于K均值初始中心选择的策略;该算法是基于反向最近邻(RNN)搜索,检索一个给定的数据集,其最近的邻居是一个给定的查询点中的所有点;使用这种方法计算初始聚类中心结果发现是非常接近聚类算法所需的迭代聚类中心;对提出的算法应用到K均值聚类中给予了证明;用几种流行的数据集的实验结果表明了该算法的优点。     

基于K-medoids项目聚类的协同过滤推荐算法

针对传统协同过滤推荐算法通常针对整个评分矩阵进行计算,存在效率不高的问题,提出一种基于K-medoids项目聚类的协同过滤推荐算法.该算法根据项目的类别属性对项目进行聚类,构建用户的偏好领域,使用用户偏好领域内的评分矩阵进行用户间相似度的计算,得到目标用户的最近邻居集,并生成推荐结果.与常用的K-means聚类方法相比,采用K-medoids方法对项目类别属性进行聚类,不仅克服了评分聚类可靠性不高的问题,而且算法还具有更好的鲁棒性.实验结果表明,该算法能有效提高推荐质量.     

基于自适应流形正则化自表示的无监督特征选择算法

针对基于流形正则化自表示(MRSR)的无监督特征选择算法直接从原始的样本空间构造相似矩阵可能会 导致重构空间中样本的相似性描述得不够准确的问题,提出了基于自适应流形正则化自表示的无监督特征选择 (AMRSR)算法。 基于自适应流形正则化自表示的无监督特征选择算法在 MRSR 算法的基础上通过对相似矩阵施 加概率最近邻约束将相似矩阵的学习嵌入到优化过程中,在重构空间中自适应地学习样本的相似性,使得在每一 次迭代中获取更加精确的样本局部几何流形结构,从而选择具有代表性且保持局部几何流形结构的特征。 最后, 在四个公开数据集上进行了大量的对比实验,通过将算法的特征选择结果用于 K-means 聚类并采取两种常见的聚 类评价指标:聚类精确度和归一化互信息评价聚类效果。 实验结果表明,AMRSR 算法与现有的一些算法相比有更 高的聚类精确度和归一化互信息,进一步表明该算法特征选择效果更好。     

基于模糊聚类的多类簇归属电力实体行为异常检测算法

针对数字化主动电网中电力实体行为复杂化、攻击手段隐蔽化等问题,提出了一种基于模糊聚类的多类别归属异常检测算法。首先,对电力实体行为相似性的度量方式进行优化,并基于优化后的度量方法构建模糊聚类算法,通过多次迭代得到实体行为对应各类别的隶属度矩阵;其次,根据类别软划分隶属度矩阵,分别计算实体在各个类别内的近邻距离、近邻密度与近邻相对异常因子等参数;最后,分析实体在各类簇内的相对异常情况,判断该电力实体行为是否属于异常行为。结果表明,与LOF,K-Means和Random Forest算法相比,新方法具有更高的异常行为检出数量和更优的异常检测评价指标,解决了传统异常检测算法样本评价角度单一的问题,进一步提高了数字化主动电网抵御未知威胁的能力。     

基于权重搜索树改进K近邻的高维分类算法

信息采集技术日益发展导致的高维、大规模数据,给数据挖掘带来了巨大挑战,针对K近邻分类算法在高维数据分类中存在效率低、时间成本高的问题,提出基于权重搜索树改进K近邻(K-nearest neighbor algorithm based on weight search tree,KNN-WST)的高维分类算法,该算法根据特征属性权重的大小,选取部分属性作为结点构建搜索树,通过搜索树将数据集划分为不同的矩阵区域,未知样本需查找搜索树获得最"相似"矩阵区域,仅与矩阵区域中的数据距离度量,从而降低数据规模,以减少时间复杂度.并研究和讨论最适合高维数据距离度量的闵式距离.6个标准高维数据仿真实验表明,KNN-WST算法对比K近邻分类算法、决策树和支持向量机(support vector machine,SVM)算法,分类时间显著减少,同时分类准确率也优于其他算法,具有更好的性能,有望为解决高维数据相关问题提供一定参考.     

一种提高文本聚类算法质量的方法

针对基于VSM(vector space model)的文本聚类算法存在的主要问题,即忽略了词之间的语义信息、忽略了各维度之间的联系而导致文本的相似度计算不够精确,提出基于语义距离计算文档间相似度及两阶段聚类方案来提高文本聚类算法的质量.首先,从语义上分析文档,采用最近邻算法进行第一次聚类;其次,根据相似度权重,对类特征词进行优胜劣汰;然后进行类合并;最后,进行第二次聚类,解决最近邻算法对输入次序敏感的问题.实验结果表明,提出的方法在聚类精度和召回率上均有显著的提高,较好解决了基于VSM的文本聚类算法存在的问题.     

结合PCA的t-SNE算法的并行化实现方法

为了提高大数据环境下高维非线性数据的处理速度和精确度,提出一种结合主成分分析(PCA)的基于t分布的随机近邻嵌入(t-SNE)算法.首先,通过主成分分析法对原始数据进行预处理,去除噪声点;然后,结合t-SNE算法,构建K最邻近(K-NN)图,以表示高维空间中数据的相似关系;最后,在Spark平台上进行并行化运算,并在BREAST CANCER,MNIST和CIFAR-10数据集上进行实验.结果表明:文中算法完成了高维数据至低维空间的有效映射,提升了算法的效率和精确度,可应用于大规模高维数据的降维.     

基于RGB空间的非经典K最近邻算法应用研究

为迅速、准确、无过多人工干预的进行图像分割,提出了一种K最近邻算聚类方法并将其应用于图像处理。与经典K最近邻算法在样本库中寻找最近邻点不同,该算法在待分割图像的RGB空间中寻找每一个像素点的K个最近邻点,参考所有像素点同最近邻点之间的平均距离,引入聚类阈值并对像素点的归属进行判断。对火焰图像的分割实验结果表明,在分割精度相接近的情况下,该算法的分割速度要快于其它几种常见算法。     

基于矩阵聚类的协作过滤算法

通过分析现有的协作过滤技术,提出了基于矩阵聚类的协作过滤算法,把矩阵聚类算法和协作过滤相结合,自动划分原始用户———资源评分矩阵,依据划分后的子数据矩阵生成推荐结果.实验结果表明,提出的基于矩阵聚类的协作过滤算法优于传统协作过滤算法,减少了近邻搜索范围,提高了算法的推荐精度.