dc.contributor | Universidade Estadual Paulista (Unesp) | |
dc.contributor | University of Fortaleza | |
dc.date.accessioned | 2020-12-12T02:42:52Z | |
dc.date.accessioned | 2022-12-19T21:21:13Z | |
dc.date.available | 2020-12-12T02:42:52Z | |
dc.date.available | 2022-12-19T21:21:13Z | |
dc.date.created | 2020-12-12T02:42:52Z | |
dc.date.issued | 2020-09-01 | |
dc.identifier | Applied Soft Computing Journal, v. 94. | |
dc.identifier | 1568-4946 | |
dc.identifier | http://hdl.handle.net/11449/201828 | |
dc.identifier | 10.1016/j.asoc.2020.106442 | |
dc.identifier | 2-s2.0-85085731896 | |
dc.identifier.uri | https://repositorioslatinoamericanos.uchile.cl/handle/2250/5382462 | |
dc.description.abstract | Feature selection plays an essential role in machine learning since high dimensional real-world datasets are becoming more popular nowadays. The very basic idea consists in selecting a compact but representative set of features that reduce the computational cost and minimize the classification error. In this paper, the authors propose single, multi- and many-objective binary versions of the Artificial Butterfly Optimization (ABO) in the context of feature selection. The authors also propose two different approaches: (i) the first one (MO-I) aims at optimizing the classification accuracy of each class individually, while (ii) the second one (MO-II) considers the feature set minimization in the process either. The experiments were conducted over eight public datasets, and the proposed approaches are compared against the well-known Particle Swarm Optimization, Firefly Algorithm, Flower Pollination Algorithm, Brainstorm Optimization, and the Black Hole Algorithm. The results showed that the binary single-objective ABO performed better than the other meta-heuristic techniques, selecting fewer features and also figuring a lower computational burden. Concerning multi- and many-objective feature selection, both MO-I and MO-II approaches performed better than their single-objective meta-heuristic counterparts. | |
dc.language | eng | |
dc.relation | Applied Soft Computing Journal | |
dc.source | Scopus | |
dc.subject | Machine learning | |
dc.subject | Many-objective optimization | |
dc.subject | Meta-heuristic algorithms | |
dc.subject | Pattern recognition | |
dc.title | A multi-objective artificial butterfly optimization approach for feature selection | |
dc.type | Artículos de revistas | |