Cluster analysis data mining

Any form of statistical methods exceeding simple descriptive statistics, such as statistical tests, correlations, regression analysis, factorial or cluster analysis, data mining techniques,. .. ... 

Unsupervised Data Mining. Searching large volumes of data for hidden descriptive relationships. Unlike supervised data mining, no response variables are used. The techniques used include various display and data reduction methods, as well as cluster analysis and association analysis. 

Another important class of MVA is represented by cluster analysis methods and principal component analysis (PCA). The latter is a representative of data reduction methods that exploit linear algebra. We do not, however, believe all the important patterns can be captured by linear algebraic methods. Finear mathematical methods are ideal for data compression, because to recover the original data distortion is undesirable. Thus, data compression is essentially applied Fourier analysis [2], In contrast, data mining is a kind of pattern... 

Since cluster analysis methods are of limited nature, and MVA methods are not really data-driven, we must conclude that these methods as well as the metric MDS methods are not qualified as maximally data-driven data-mining aids. Therefore, our only hope is to promote the methods broadly called nonmetric MDS (nMDS) as a versatile general reduction methodology for relational data. 

Virtual libraries Cluster analysis Molecular modeling QSAR Unification of data mining, development of a common approach... 

The two main applications of molecular descriptors have been for screens in substructure searching [4] and for attributes in similarity calculations [5]. Historically, many descriptors were developed first for substructure searching (see Chapter 19 of this book) and then used in similarity calculations for applications such as similarity analysis, clustering, combinatorial library design, and data mining (see Chapters 14,... 

Conformational searching and data mining produce large amounts of data which need special techniques for their analysis. One commonly used method is cluster... 

Combining interactive tools with the powerful data-mining approaches, especially clustering analysis, is essential to help users effectively explore and understand multidimensional datasets, but at the same time it presents several challenges. 

The design of the interactive interface for such tools should deal with the issues about how to naturally integrate dynamic interaction techniques into the exploration process and how to effectively provide sufficient contextual explanation about the analysis result (for example, in case of cluster analysis, why they are clustered together). Furthermore, it might be difficult to implement interactive visualization systems that practically combine the rapid, incremental updates of visualization with the computational requirements of data mining. 

---