Showing papers by "James C. Bezdek published in 1980"
TL;DR: The theory of Zangwill is used to prove that arbitrary sequences generated by these (Picard iteration) procedures always terminates at a local minimum, or at worst, always contains a subsequence which converges to aLocal minimum of the generalized least squares objective functional which defines the problem.
Abstract: In this paper the convergence of a class of clustering procedures, popularly known as the fuzzy ISODATA algorithms, is established. The theory of Zangwill is used to prove that arbitrary sequences generated by these (Picard iteration) procedures always terminates at a local minimum, or at worst, always contains a subsequence which converges to a local minimum of the generalized least squares objective functional which defines the problem.
965 citations
01 Jan 1980
TL;DR: A new measure of consensus in small groups based on fuzzy mathematics which overcomes the difficulties found in other fuzzy consensus measures is examined, useful in analyzing how groups reach a decision.
Abstract: This paper examines a new measure of consensus in small groups based on fuzzy mathematics which overcomes the difficulties found in other fuzzy consensus measures. The method involves the construction of α-Consensus measures from fuzzy relations. These measures are integrated over a to produce a measure of small group consensus. This procedure is useful in analyzing how groups reach a decision. Results of an experimental application of this fuzzy analysis procedure are given to illustrate the proposed technique.
83 citations
TL;DR: The theoretical mean and variance of two related cluster validity functionals, namely, the classification entropy and partition coefficients associated with fuzzyc-partitions of finite data sets, are derived to provide a basis for statistical tests of fuzzy cluster validity.
Abstract: In this paper we derive the theoretical mean and variance of two related cluster validity functionals, namely, the classification entropy and partition coefficients associated with fuzzyc-partitions of finite data sets. These results can be used to eliminate monotonicity of the original validity functionals, and may provide a basis for statistical tests of fuzzy cluster validity.
36 citations
TL;DR: The method yields pro-totypical distribution pattern shapes as well as an indica-tion of the range of nozzle sizes and sprinkler operating pressures over which the prototype shapes may be con-sidered valid.
Abstract: A method is presented for identifying characteristic distribution pattern shapes for a sprinkler. The pro-cess involves normalizing distribution test data and then applying the K-Means clustering algorithm to the resulting dimensionless curves. The method yields pro-totypical distribution pattern shapes as well as an indica-tion of the range of nozzle sizes and sprinkler operating pressures over which the prototype shapes may be con-sidered valid. The method is applied to data for a typical gun type sprinkler. Three pattern shapes were found to be representative of the performance of this sprinkler.
21 citations
TL;DR: In this article, a simulation model is used to study the influence of the shape of an automatic flushing emitter's pressure-discharge curve on the hydraulic behavior of trickle laterals using such emitters.
Abstract: A simulation model is used to study the influence of the shape of an automatic flushing emitter's pressure-discharge curve on the hydraulic behavior of trickle laterals using such emitters. Characteristic features of the pressure discharge relationship are iden-tified and parameterized. This paper reports and inter-prets the results of lateral line simulations based on hypothetical emitters with various flushing mode characteristics. The results indicate significant features of the emitter flushing mode which should be considered in emitter evaluation and selection.
1 citations