Title: A New Hyper-heuristic Implementation in HyFlex: a Study on Generality
Authors: Misir, Mustafa ×
De Causmaecker, Patrick
Vanden Berghe, Greet
Verbeeck, Katja #
Issue Date: Nov-2011
Host Document: the 23rd Benelux Conference on Artificial Intelligence (BNAIC11)
Conference: the 23rd Benelux Conference on Artificial Intelligence (BNAIC11) location:Gent, Belgium date:3-4 November 2011
Abstract: Selection hyper-heuristics concentrate on using the strength of multiple low-level search mechanisms for solving instances from various problem domains. A traditional selection hyper-heuristic is composed of 1) a heuristic selection mechanism for choosing heuristics at each decision step and 2) a move acceptance strategy for deciding about whether or not to use the explored solutions by the selected heuristics. These mechanisms work together in a problem-independent manner to raise the level of generality on the one hand and to ease their applicability on the other hand. The present study provides a new selection hyper-heuristic equipped with various adaptive features.
Publication status: published
KU Leuven publication type: IMa
Appears in Collections:Computer Science Technology TC, Technology Campuses Ghent and Aalst
Technologiecluster Computerwetenschappen
Computer Science, Campus Kulak Kortrijk
Informatics Section
× corresponding author
# (joint) last author

Files in This Item:
File Description Status SizeFormat
bnaic2011_submission_66[1].pdf Published 58KbAdobe PDFView/Open


All items in Lirias are protected by copyright, with all rights reserved.