Please use this identifier to cite or link to this item:
Title: A multiobjective adaptive approach for the inference of evolutionary relationships in protein-based scenarios
Authors: Santander Jiménez, Sergio
Vega Rodríguez, Miguel Ángel
Sousa, Leonel
Keywords: Computación bioinspirada;Bioinspired computing;Optimización multiobjetivo;Multiobjective optimization;Algoritmos adaptativos;Adaptive algorithms;Bioinformática;Bioinformatics
Issue Date: 2019
Publisher: Elsevier
Abstract: Complex optimization problem solving is a constant issue in a wide range of scientific domains. Robust bioinspired procedures with accurate search capabilities are therefore required to address the challenge that such optimization problems represent. This work explores different design alternatives for the metaheuristic Multiobjective Shuffled Frog-Leaping Algorithm, a novel method that combines parallel searches and swarm-based operators to undertake the processing of complex search spaces. Three variants of the metaheuristic are adopted: a dominance-based approach, an indicator-based alternative, and an adaptive proposal that incorporates both multiobjective strategies (dynamically assigning during the execution more resources to the most successful strategy). The performance of the proposed designs is examined when tackling, as a case study, the inference of ancestral relationships from protein data, using different multiobjective metrics and bio-statistical testing procedures. Experimental results show the additional robustness that the adaptive technique provides to the metaheuristic, allowing its search engine to exploit the most fitting multiobjective approach according to the status of the optimization process.
Description: Publicado en: Information Sciences (Volume: 485, June 2019, pp. 281-300).
ISSN: 0020-0255
DOI: 10.1016/j.ins.2019.02.020
Appears in Collections:DTCYC - Artículos

Files in This Item:
File Description SizeFormat 
j_ins_2019_02_020.pdf2,71 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons