A new approach to learning linguistic control rules

Authors
Baldwin, JF Lawry, J
Citation
Jf. Baldwin et J. Lawry, A new approach to learning linguistic control rules, INT J UNC F, 8(1), 2000, pp. 21-43
Citations number
19
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
INTERNATIONAL JOURNAL OF UNCERTAINTY FUZZINESS AND KNOWLEDGE-BASED SYSTEMS
ISSN journal
02184885 → ACNP
Volume
8
Issue
1
Year of publication
2000
Pages
21 - 43
Database
ISI
SICI code
0218-4885(200002)8:1<21:ANATLL>2.0.ZU;2-C
Abstract
The mass assignment ID3 (MA-ID3) algorithm for generating linguistic decisi on trees is introduced together with the mass assignment semantics for ling uistic variables. The potential of this algorithm for learning control rule s is illustrated by means of the Van de Pol system. A data set of control p aths is generated using an existing on-line controller. This is then used t o generate a set of quantified linguistic control rules. The effectiveness and robustness of this rule-base is then demonstrated.