Advances in K-means Clustering: a Data Mining Thinking by Junjie Wu

By Junjie Wu

Nearly we all know K-means set of rules within the fields of knowledge mining and enterprise intelligence. however the ever-emerging facts with tremendous advanced features carry new demanding situations to this "old" set of rules. This ebook addresses those demanding situations and makes novel contributions in developing theoretical frameworks for K-means distances and K-means dependent consensus clustering, opting for the "dangerous" uniform impression and zero-value predicament of K-means, adapting correct measures for cluster validity, and integrating K-means with SVMs for infrequent category research. This publication not just enriches the clustering and optimization theories, but additionally offers reliable assistance for the sensible use of K-means, in particular for very important projects similar to community intrusion detection and credits fraud prediction. The thesis on which this booklet is predicated has gained the "2010 nationwide first-class Doctoral Dissertation Award", the top honor for no more than a hundred PhD theses in line with yr in China.

Show description

Read Online or Download Advances in K-means Clustering: a Data Mining Thinking PDF

Similar data mining books

Transactions on Rough Sets XIII

The LNCS magazine Transactions on tough units is dedicated to the total spectrum of tough units similar matters, from logical and mathematical foundations, via all elements of tough set idea and its purposes, akin to facts mining, wisdom discovery, and clever info processing, to relatives among tough units and different ways to uncertainty, vagueness, and incompleteness, reminiscent of fuzzy units and idea of facts.

Knowledge Discovery Practices and Emerging Applications of Data Mining: Trends and New Domains

Fresh advancements have vastly elevated the amount and complexity of knowledge to be had to be mined, top researchers to discover new how you can glean non-trivial info immediately. wisdom Discovery Practices and rising functions of knowledge Mining: developments and New domain names introduces the reader to fresh examine actions within the box of information mining.

Requirements Engineering in the Big Data Era: Second Asia Pacific Symposium, APRES 2015, Wuhan, China, October 18–20, 2015, Proceedings

This publication constitutes the court cases of the second one Asia Pacific specifications Engineering Symposium, APRES 2015, held in Wuhan, China, in October 2015. The nine complete papers provided including three device demos papers and one brief paper, have been rigorously reviewed and chosen from 18 submissions. The papers care for a variety of points of necessities engineering within the massive info period, similar to computerized requisites research, requisites acquisition through crowdsourcing, requirement procedures and requisites, specifications engineering instruments.

Extra info for Advances in K-means Clustering: a Data Mining Thinking

Sample text

Is a solution. Then the limit of any convergent subsequence of (x (l) )l=0 40 3 Generalizing Distance Functions for Fuzzy c-Means Clustering Remark The construction of a suitable solution set is often the key point when using this theorem. Also note that “global” here means the starting point of the sequence can be arbitrary, but is not the guarantee that the algorithm converges to the global optimum. 1 ([52]) Let C : M → S be a function and B : S → P(S ) is a point-to-set mapping. Assume that C is continuous at x and B is closed at C(x).

In: Proceedings of the Canadian Conference on, Artificial Intelligence, pp. 292–296 (2005) 25. : K-means clustering versus validation measures: a data-distribution perspective. IEEE Trans. Syst. Man Cybern. Part B Cybern. 39(2), 318–331 (2009) 26. : Classification, subtype discovery, and prediction of outcome in pediatric acute lymphoblastic leukemia by gene expression profiling. Cancer Cell 1, 133–143 (2002) 27. : Robust clustering by pruning outliers. IEEE Trans. Syst. Man Cybern. Part B 33(6), 983–998 (2003) 28.

Note that in Step 6, Eq. , ∗ = d ∗ = 0 for some x . However, a particular choice for U still must be ∃ i = j, dik k jk made when implementing FCM. We detail this in the experimental section below. To further describe the iteration, some notation is given as follows. Let G : M f c → Rcd be the function defined by G(U) = V = (v1 , . . , vc )T , where vi is calculated by Eq. 3), ∀ 1 ≤ i ≤ c. Let F : Rcd → P(M f c ) denote the point-to-set mapping defined by F(V ) = {U ∈ M f c |U satisfies Eq. 4)}.

Download PDF sample

Rated 4.74 of 5 – based on 47 votes