A More Efficient Selection Scheme in iSMS-EMOA

Menchaca-Mendez, A; Montero, E; Riff, MC; Coello, CAC

Keywords: tuning, Multi-objective evolutionary algorithms, Hypervolume contribution

Abstract

In this paper, we study iSMS-EMOA, a recently proposed approach that improves the well-known S metric selection Evolutionary Multi-Objective Algorithm (SMS-EMOA). These two indicator-based multi-objective evolutionary algorithms rely on hypervolume contributions to select individuals. Here, we propose to define a probability of using a randomly selected individual within the iSMS-EMOA's selection scheme. In order to calibrate the value of such probability, we use the EVOCA tuner. Our preliminary results indicate that we are able to save up to 33% of computations of the contribution to hypervolume with respect to the original iSMS-EMOA, without any significant quality degradation in the solutions obtained. In fact, in some cases, the approach proposed here was even able to improve the quality of the solutions obtained by the original iSMS-EMOA.

Más información

Título según WOS: A More Efficient Selection Scheme in iSMS-EMOA
Título según SCOPUS: A more efficient selection sche in iSMS-EMOA
Título de la Revista: BIO-INSPIRED SYSTEMS AND APPLICATIONS: FROM ROBOTICS TO AMBIENT INTELLIGENCE, PT II
Volumen: 8864
Editorial: SPRINGER INTERNATIONAL PUBLISHING AG
Fecha de publicación: 2014
Página de inicio: 371
Página final: 380
Idioma: English
DOI:

10.1007/978-3-319-12027-0_30

Notas: ISI, SCOPUS