Loading...
Please wait, while we are loading the content...
Similar Documents
Evaluation of fuzzy inference systems using fuzzy least squares
| Content Provider | NASA Technical Reports Server (NTRS) |
|---|---|
| Author | Barone, Joseph M. |
| Copyright Year | 1992 |
| Description | Efforts to develop evaluation methods for fuzzy inference systems which are not based on crisp, quantitative data or processes (i.e., where the phenomenon the system is built to describe or control is inherently fuzzy) are just beginning. This paper suggests that the method of fuzzy least squares can be used to perform such evaluations. Regressing the desired outputs onto the inferred outputs can provide both global and local measures of success. The global measures have some value in an absolute sense, but they are particularly useful when competing solutions (e.g., different numbers of rules, different fuzzy input partitions) are being compared. The local measure described here can be used to identify specific areas of poor fit where special measures (e.g., the use of emphatic or suppressive rules) can be applied. Several examples are discussed which illustrate the applicability of the method as an evaluation tool. |
| File Size | 642606 |
| Page Count | 10 |
| File Format | |
| Alternate Webpage(s) | http://archive.org/details/NASA_NTRS_Archive_19930020350 |
| Archival Resource Key | ark:/13960/t6xw9bc7n |
| Language | English |
| Publisher Date | 1992-12-01 |
| Access Restriction | Open |
| Subject Keyword | Theoretical Mathematics Inference Fuzzy Sets Control Theory Control Systems Design Least Squares Method Fuzzy Systems Ntrs Nasa Technical Reports Server (ntrs) Nasa Technical Reports Server Aerodynamics Aircraft Aerospace Engineering Aerospace Aeronautic Space Science |
| Content Type | Text |
| Resource Type | Article |
