Resources for K-Mean Clustering

Aside from my tutorial (in Visual Basic Code or in Matlab code), there are many books and journals or Internet resources discuss about K-mean clustering, your search must be depending on your application. Below are a few list that you may consider. I welcome any feedback and input about other good resources that you want to include in this list; please tell me about it.

< Previous | Next | Contents>

Softwares/Codes
Other Tutorials
Downloadable Technical Papers
Applications

Softwares/Codes

• SPAETH2 is a collection of FORTRAN90 routines for analyzing data by grouping into clusters which include KMEANS
• WEKA is another Data mining software under GNU public license in Java which include k means clustering. You may download the source code from Waikato university.
• Biopython project provide tools for computational molecular biology in Python language. The tutorial is in here, which include kMeans clustering module. Other k means code in Python n be found here.
• Tapas Kanungo et al provide C++ code (for Unix, under GPL) and documentation for k-means clustering based on a combination of local search and Lloyd's algorithm (also known as the k-means algorithm).
• David J.C. MacKay give demonstration of using K mean clustering in Octave, a free software similar to Matlab
• Matlab Statistical Toolbox contain a function name kmeans. My own Matlab code is in this page.
• Clustan is special commercial software for clustering.
• XLMiner™ and XLStat are both commercial software that support k mean clustering in MS Excel
• Commercial software DTREG for modeling business also provide k means.
• Michael Eisen develop Cluster, an open source clustering software available here implement the most commonly used clustering methods for gene expression data analysis. Available for Mac, Windows and Unix.
• kmeans is also a function in R, a free software for Statistical Computing. More information about k means in R software is also available in here
• If you are using SPSS, it is also called quick clustering, more information is available in here
• Fuzzy c mean clustering in Matlab can be downloaded from Matlab Central File exchange
• Mathematica has kmeans function in the image processing package. You need to load teh package before using it. Clicks here for example and explanation.
• Institute for Signal and Information processing provides Java applet (with source code) of k means, PCA, LDA, SVM etc. Similarly, Jens Spehr and Simon Winkelbach also developed Java applet for k means that useful for teaching interactively.
• Kenichi Kurihara developed Bayesian k means similar to EM algorithm (code in Matlab)
• Cell-kmeans is an open source implementation of K-means algorithm on Cell Broadband Engine written in C
• Analytics1305 is useful public cloud service machine learning technology for extremely large and complex datasets. It contains k means and other clustering techniques

Other Tutorials

• Clustering tutorial including K-means, Fuzzy C-means, Hierarchical, Mixture of Gaussians Clustering with Java Applet
• Andrew More provides his lecture slide on k mean and hierarchical clustering
• Philip B. Ender has Multivariate lecture note, which include k mean clustering in Stata 7
• Brian T. Luke uses k mean clustering with Evolutionary Programming
• Eric W. Weisstein "K-Means Clustering Algorithm" description is related to Mathematica software
• Valerie Ohm provide tutorial with implementation for image in C

Downloadable Technical Papers

• The Analysis of a Simple k-Means Clustering Algorithm (2000) by Kanungo et al
• An efficient k-means clustering algorithm: Analysis and implementation (2002) by Kanungo et al
• k -Means: A new generalized k-means clustering algorithm (2003) by Yiu-Ming Cheung
• Speeding up k-means Clustering by Bootstrap Averaging (2002) by Ian Davidson and
  Ashwin Satyanarayana
• Constrained K-means Clustering with Background Knowledge (2001) by Wagstaff et al
• Visualizing non-hierarchical and hierarchical cluster analyses with clustergrams by Matthias Schonlau
• K-Means Clustering Over a Large, Dynamic Network (2006) by Souptik Datta, Chris Giannella, and Hillol Kargupta in Proceedings of the 2006 SIAM International Conference on Data Mining
• Bayesian K-Means as a "Maximization-Expectation" Algorithm,(2006) by Max Welling and Kenichi Kurihara
• Pierre Legendre developed K-Means least-squares partitioning method.
• Dhillon, Guan and Kulis linkage a theoretical connection between kernel k means and spectral clustering

Applications

• Matt Toews has interesting page of Image Quantization using K mean clustering
• K means for clustering malaria

< Previous | Next | Contents>