数据聚类是数据挖掘中的一个重要课题。
提出一种空间数据聚类中的网格粒度求解方法。
This paper proposes a solving method of grid granularity in spatial data clustering.
在子空间聚类引入核函数以提高数据聚类性能。
Kernel function is introduced to subspace clustering to improve the clustering performance.
数据聚类或分割就是其中的一种重要的数据发掘应用。
Clustering or segmentation of data is an important data mining application.
CURE算法是针对大规模数据聚类算法的典型代表。
CURE is a typical clustering algorithm that is designed for the mining of mass data.
本文提出了一个处理高维数据聚类的框架，并分析了该框架的性能。
In this paper, a framework of a mapping-based clustering approach to deal with high dimensional data is proposed, and its performance analysis is also given.
近年来，基于图论的聚类算法被广泛地应用在数据聚类和图像分割之中。
Recently, the graph-theoretical approaches are widely used in the fields of data clustering and image segmentation.
结合文本数据的语义相似度，给出一种基于语义密度文本数据聚类的方法。
Combined with semantic similarity of text data, this paper gives a method of text data clustering based on semantic density.
数据聚类在数据挖掘、模式识别、图像处理和数据压缩等领域有着广泛的应用。
Clustering is a promising application technique for many fields including data mining, pattern recognition, image processing, compression and other business applications.
这个算法可以用于数据聚类和人脸识别方面，实验结果也证明了该算法的效果。
This algorithm can be used in data clustering and face detection. Its effectiveness has been proven by the experiment results.
数据挖掘是本课题的研究核心，主要包括关联规则发现、数据聚类和数据分类。
Data mining is the core topic of this paper. Basically, it includes associate rule founding, data clustering and data assorting.
近年来随着聚类应用领域的扩展和深入，高维数据聚类越来越普遍，也越来越重要。
In recent years, with the application of clustering, high dimensional data clustering is becoming more common, and more important.
从多方面分析了该算法的性能，并将该算法应用于酵母细胞周期的芯片表达谱数据聚类。
The new clustering algorithm is analyzed on several aspects and tested on the published yeast cell-cycle microarray data.
系统研究了七种典型的空间数据聚类方法，积极探索基于约束条件的空间聚类问题的解决方案；
Seven kinds of spatial data clustering approaches are studied. And the technique to solve the problem of Constraint-based Spatial Cluster Analysis is explored.
同时，本文对流数据聚类算法的研究，对于促进同类问题的研究具有一定的理论价值和借鉴意义。
Meanwhile, the research of the stream data clustering algorithm would be useful references to the similar researches.
在此基础上，设计和实现了人工免疫网络算法，并应用该算法成功解决了一个模式识别和数据聚类问题。
We design and implement the artificial immune network algorithm, and successfully apply this algorithm in solving a pattern recognition problem and a data clustering problem.
对比实验结果表明，TART2网络更适用于带状分布的空间数据聚类，具有较高的可塑性和自适应性。
The comparative experimental results show that TART2 network is suitable for clustering about the ribbon distribution of spatial data, and it has higher plasticity and adaptability.
现有的数据聚类方法仍存在着各种不足，聚类速度和结果的质量不能满足大型、高维数据库上的聚类需求。
Owing to the sparsity of high-dimensional data and the features of categorical data, it needs to develop special methods for high-dimensional categorical data.
然后根据对多维数据聚类的实验分析结果，通过对样本集的训练进行标识和机器自学习过程来判别异常检测矩阵。
And based on the experimental results of multi-dimensional data clustering, anomaly detection matrix is determined through identifying the training sample set and the machine self-learning.
针对高属性维稀疏数据聚类问题，提出高属性维稀疏信息系统概念，给出一种新的基于稀疏特征差异度的动态抽象聚类方法。
The concepts of high attribute dimensional information system are firstly proposed, and a new dynamic clustering method on the basis of sparse feature difference degree is presented.
这种算法利用了数据挖掘中的聚类技术，可用于常规雷达和特殊雷达的信号分选。
The algorithm makes use of the clustering technology of data mining, can apply to general radar and special radar.
聚类是数据挖掘的基本方法之一。
提出了一种基于聚类和粗糙集的数据挖掘模型。
We propose a data mining model based on clustering and rough set.
聚类是一种重要的数据挖掘形式。
有效的离散化可以显著地提高系统对样本的聚类能力，增强系统对数据噪音的鲁棒性。
Effective data discretization can obviously improve system ability on clustering instances, and can also make systems more robust to data noise.
聚类是数据挖掘领域的重要研究内容之一。
Clustering is one of the most important research in data mining area.
该算法将具有足够高密度的区域划分为簇，并可以在带有“噪声”的空间数据库中发现任意形状的聚类。
It can handle spatial data and spot any-shape clusters in a noised spatial database by dividing them into clusters with high enough density.
本文提出了一种有效的支持海量图像数据库Q BE查询的聚类索引算法。
This paper proposes an indexing algorithm of clustering which supports QBE image retrieval for large image databases.
然后对数据先进行聚类，再在聚类结果中发掘频繁项目集；
The second, clustered the data, and then discovered frequent items sets in the result of clustering.
一种新的抽样方法是把数据挖掘技术中的分类、聚类及离群点挖掘等应用到审计风险管理中去。
A new sampling method is proposed, which USES the latest technologies of database. It applies classification rule mining, clustering rule and outlier mining to the management of Audit Risk.
应用推荐