Journal
EXPERT SYSTEMS WITH APPLICATIONS
Volume 229, Issue -, Pages -Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2023.120226
Keywords
r-Quasi-grouping functions; Pre-aggregation functions; Information fusion; Classifier ensemble
Ask authors/readers for more resources
This paper continues to study the r-quasi-grouping functions proposed by the author recently based on grouping functions. It shows the relationship among certain classes of r-quasi-grouping functions and provides the constructions and equivalent characterizations of these functions and their generalized forms. Finally, a r-quasi-grouping functions-based classifier ensemble algorithm (G-CEA) is proposed, and its performance is tested through numerical experiments, comparative analysis with three classical machine learning ensemble algorithms, and sensitivity analysis of parameter r.
Grouping functions, as one kind of binary continuous aggregation functions, have attracted the continuous attention of scholars since they were proposed. Meanwhile, since Lucca, Sanz and Dimuro et al. proposed the notion of pre-aggregation functions lately, the study on such new aggregation-likefunctions has become a hot topic in the research fields of information fusion. This paper continues to consider the r-quasi-grouping functions proposed by the author recently based on the grouping functions. At first, we show the relationship among certain classes of r-quasi-grouping functions. Second, we give the constructions and equivalent characterizations of r-quasi-grouping functions along with their generalized forms, respectively. Finally, we propose a r-quasi-grouping functions-based classifier ensemble algorithm (G-CEA), test the performance of G-CEA through numerical experiments, and verify the effectiveness and stability of G-CEA from comparative analysis with three classical machine learning ensemble algorithms and sensitivity analysis of parameter r.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available