For the current REF see the REF 2021 website REF 2021 logo

Output details

11 - Computer Science and Informatics

Robert Gordon University

Return to search Previous output Next output
Output 11 of 72 in the submission
Output title

Approaches to selection and their effect on fitness modelling in an Estimation of Distribution Algorithm

Type
E - Conference contribution
Name of conference/published proceedings
IEEE Congress on Evolutionary Computation, 2008. CEC 2008.
Volume number
-
Issue number
-
First page of article
2621
ISSN of proceedings
-
Year of publication
2008
URL
-
Number of additional authors
3
Additional information

Originality: the approach to selection for probabilistic model building; and use of product moment correlation to assess model quality. These have influenced other authors using low-quality or infeasible solutions in probabilistic model building (doi: 10.1109/FUZZY.2009.5277373 , DOI: 10.1145/2001576.2001659). Our approach was listed in 2010 as sole published method for qualitative analysis of Markov Network EDAs, in contrast to many available approaches for Bayesian Network EDAs [1]. This was published in a world-leading EDA track.

[1] Echegoyen, Carlos, et al. "Analyzing the k Most Probable Solutions in EDAs Based on Bayesian Networks." Exploitation of Linkage Learning in Evolutionary Algorithms (2010): 163-189.

Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
13
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-