Title :
A pattern recognition machine with fuzzy clustering analysis
Author_Institution :
Autom. Dept., Beijing Polytech. Univ., China
Abstract :
A pattern recognition machine with fuzzy clustering analysis, PRM, is proposed in this paper, which is with a twofold task, learning knowledge from the sample patterns and applying the knowledge to the observed patterns. With the same fuzzy clustering procedure, the PRM does its twofold work. By fuzzy clustering analysis on the sample patterns in the pattern space, the PRM establishes its clustering criteria, the sample cluster structure and the expected cluster structure. The observed pattern is added to the sample pattern set to form the extended sample set, and the same clustering scheme for the sample pattern set is applied to the extended sample set by the PRM so that the observed pattern is recognized under the clustering criteria. The paper examines the PRM theoretically and develops some significant conclusions. At the end of this paper, an illustrative example is given to show how the PRM works
Keywords :
fuzzy set theory; learning (artificial intelligence); pattern clustering; PRM; cluster structure; extended sample set; fuzzy clustering analysis; knowledge learning; pattern clustering; pattern recognition machine; Automation; Fuzzy set theory; Fuzzy sets; Fuzzy systems; Humans; Machine learning; Pattern analysis; Pattern recognition; Set theory; Uncertainty;
Conference_Titel :
Intelligent Control and Automation, 2000. Proceedings of the 3rd World Congress on
Conference_Location :
Hefei
Print_ISBN :
0-7803-5995-X
DOI :
10.1109/WCICA.2000.862503