Abstract
A modified version of fuzzy c-means, called fuzzy c-means with additional data (FCM-AD), is presented in order to achieve robustness against a few outliers. Usefulness of the algorithm is confirmed through simulation experiments on both artificial data sets and real remote sensing imagery data. Results of various fuzzy clustering algorithms applied to imagery data are also investigated from a viewpoint of subjective entropy of probabilistic sets.
Original language | English |
---|---|
Pages (from-to) | 213-230 |
Number of pages | 18 |
Journal | Information Sciences |
Volume | 45 |
Issue number | 2 |
DOIs | |
Publication status | Published - Jul 1988 |
Externally published | Yes |