brFCM

This project contains the source code for brFCM, an enhanced version of the Fuzzy C-Means clustering algorithm that can significantly improve the time required for FCM clustering, with little loss of precision. The source code implements the literal FCM clustering algorithm, a version of FCM that optimizes performance through caching of results and correct ordering of the formulas, and the brFCM algorithm.

For full details of this algorithm, please see:

S. Eschrich, J. Ke, L. O. Hall, and D. B. Goldgof, "Fast accurate fuzzy clustering through data reduction," IEEE Transactions on Fuzzy Systems, vol. 11, pp. 262-270, 2003.

The source code is made available under the GNU Public License.

Requirements

• A Unix-like system (it has been tested on Linux and Solaris)
• The gcc compiler
• The libtiff library for reading TIFF files (in the case of ATR support)