Abstract
This paper deals with discriminant problems to classify samples with fuzzy multi-attribute into fuzzy groups. In this problem, the objective is to determine the linear discriminant function that provides the maximum separation of fuzzy groups in a real space. For this purpose, we define the fuzzy variance ratio and employ maximization of the fuzzy variance ratio as a criterion. Furthermore, a partial correlation coefficient in the fuzzy groups is defined to estimate the influence of each attribute itself on the discrimination between fuzzy groups.
| Original language | English |
|---|---|
| Pages (from-to) | 261-271 |
| Number of pages | 11 |
| Journal | Fuzzy Sets and Systems |
| Volume | 19 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - 1986 |
| Externally published | Yes |
Keywords
- Classification
- Fuzzy discriminant analysis
- Fuzzy mean
- Fuzzy partial correlation coefficient
- Fuzzy variance
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Science Applications
- Computer Vision and Pattern Recognition
- Information Systems and Management
- Statistics, Probability and Uncertainty
- Electrical and Electronic Engineering
- Statistics and Probability