Electromagnetic interference source identification through fuzzy clustering

A practical solution to the problem of finding the Sup{Min(f1(x), f2(x)}, where f1(x) and f2(x) are N-dimensional fuzzy sets, is presented. A theorem describes an upper bound upon the maximal grade, which is demonstrated to be of use for cluster analysis. Numerical results are presented for an example of electromagnetic interference source identification. Tests indicate that fuzzy clustering, using the result of the theorem, is superior in the sense of minimum achievable error rate to template matching.