Premium
Tracks real‐time classification based on fuzzy rules
Author(s) -
Ayoun André,
Grabisch Michel
Publication year - 1997
Publication title -
international journal of intelligent systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.291
H-Index - 87
eISSN - 1098-111X
pISSN - 0884-8173
DOI - 10.1002/(sici)1098-111x(199711/12)12:11/12<865::aid-int5>3.0.co;2-v
Subject(s) - computer science , fuzzy logic , artificial intelligence , data mining , classifier (uml) , false alarm , set (abstract data type) , alarm , machine learning , materials science , composite material , programming language
A real‐time track classifier based on fuzzy logic is presented here. The application deals with false alarm rejection in an airborne Infra‐Red Search and Track (IRST) system. The approach is based on the use of a set of rules representing heterogeneous knowledge on behavior and appearance of physical objects. Uncertainty rules are considered to model knowledge on classes, while gradual rules are used to compute some auxiliary variables. Examples of rules are given, as well as results on simulated data. © 1997 John Wiley & Sons, Inc.