Description: Cskmeans clustering algorithm
1. Partitioning methods: given a data set with N tuples or records, the division method will construct K groups, each of which is represented by a cluster. N. And the K grouping satisfies the following conditions: (1) each group contains at least one data record; (2) each data record belongs to and belongs to only one group (note: this requirement can be relaxed in some fuzzy clustering algorithm); For a given K, the algorithm firstly give an initial grouping method, through repeated iteration method after change the grouping, makes every improvement after the grouping scheme is a good before, and a good standard is: close as possible to the records of the same group, and the record as far as possible in the different groups. The algorithm using this basic idea has: k-means algorithm, k-medoids algorithm, and CLARANS algorithm.
- [CART] - data mining algorithms, K-means clusteri
- [vqKmeans] - Test k-means on 2-D data
- [medoids] - to a complete category in the form of k-
- [motkaluo] - Monte Carlo algorithm, can understand an
- [Medoidshift] - Center drift is a non-supervised cluster
- [work] - err
- [EM] - em algorithm which is used in data clust
- [ImagePatternRecognition] - Image Pattern Recognition
- [Mo3] - test of
- [K_means] - K-means MATLAB programe
File list (Check if you may need any files):
Download