Please use this identifier to cite or link to this item:
Title: Incremental evolution of classifier agents using incremental genetic algorithms
Keywords: incremental learning, classifier agents, genetic algorithms, incremental genetic algorithms
Issue Date: 30-Mar-2004
Source: ZHU FANGMING (2004-03-30). Incremental evolution of classifier agents using incremental genetic algorithms. ScholarBank@NUS Repository.
Abstract: This thesis explores the incremental evolution properties of software agents with a focus on the incremental learning of classifier agents. Genetic algorithms (GAs) are employed as our basic evolutionary algorithms and incremental genetic algorithms (IGAs) are proposed for incremental learning of classifier agents in a multi-agent environment. Various IGA approaches for incremental learning on new attributes and classes are designed, implemented, and evaluated. Continuous incremental genetic algorithms (CIGAs) are further proposed for continuous incremental learning and training of input attributes for classifier agents. Class decomposition and feature selection are proposed to improve the performance of classifier agents. The study in this thesis has shown that incremental evolution of classifier agents is feasible with specially designed algorithms such as IGAs, and the performance of classifiers can be improved by employing these proposed approaches.
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
PHDThesis_ZhuFM.pdf2.81 MBAdobe PDF



Page view(s)

checked on Jan 14, 2018


checked on Jan 14, 2018

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.