|
|||||
|
|
A benchmark calculation for the fuzzy c-means clustering algorithm: initial memberships |
|
| Authors: | Alex Rodriguez M Santos Tomas Jaime Rubio-Martinez |
| Institution: | 1. Department d’Enginyeria Química, Universitat Politècnica de Catalunya (UPC), ETS d’Enginyeria Industrial, Av. Diagonal 647, 08028, Barcelona, Spain 2. Sec. Matemàtiques i Informàtica ETSAB, Universitat Politècnica de Catalunya (UPC), ETS d’Arquitectura, Av. Diagonal 649, 08028, Barcelona, Spain 3. Dept. de Química Física, Universitat de Barcelona (UB) and the Institut de Recerca en Química Teòrica i Computacional (IQTCUB), Martí i Franqués 1, 08028, Barcelona, Spain |
| Abstract: | We report a benchmark calculation for the fuzzy c-means clustering algorithm that can be used as a reference in theoretical and practical studies related to classification methodologies. A full exploration of the hard-initialization space is done for all possible different groupings on a simple fifteen-pattern system to describe their stationary points. Numerical problems associated with the stopping criteria are discussed in relation with the calculation of some validity indexes. All necessary information to assure an easy reproduction of the obtained results is clearly reported. |
| Keywords: | |
| 本文献已被 SpringerLink 等数据库收录！ | |