An Extensible JCLEC-based Solution for the Implementation of Multi-Objective Evolutionary Algorithms

Abstract

The ongoing advances in multi-objective optimisation (MOO) are improving the way that complex real-world optimisation problems, mostly characterised by the definition of many conflicting objectives, are currently addressed. To put it into practice, developers require flexible implementations of these algorithms so that they can be adapted to the problemspecific needs. Here, metaheuristic optimisation frameworks (MOFs) are essential tools to provide end-user oriented development solutions. Even though consolidated MOFs are continuously evolving, they seem to have paid little attention to the new trends in MOO. Recently, new frameworks have emerged with the aim of providing support to these approaches, but they often offer less variety of basic functionalities like diversity of encodings and operators than other general-purpose solutions. In this paper we identify a number of relevant features serving to satisfy the requirements demanded by MOO nowadays, and propose a solution, called JCLEC-MOEA, on the basis of the JCLEC framework. As a key contribution, its architecture has been designed with a twofold purpose: reusing all the features already given by a mature framework like JCLEC, and extending it to enable new developments more flexibly than current alternatives.

A hyper-parameter tuning approach for cost-sensitive support vector machine classifiers

“…We used Sequential minimal optimization algorithm for SVM and Random Tree algorithm for DT. For that concerning NSGA-II algorithm, we used the framework named Java Class Library for Evolutionary Computation (JCLEC) Ramírez et al (2015Ramírez et al ( , 2019, which is a Java suite for solving multi-objective optimization problems using evolutionary algorithms. Algorithm 2 has been coded in Java using the NSGA II algorithm of the JCLEC framework.…”

jMetalPy: A Python framework for multi-objective optimization with metaheuristics

“…In the last two decades, a number of software frameworks devoted to the implementation of multi-objective metaheuristics has been contributed to the community, such as ECJ [33], EvA [34], JCLEC-MO [35], jMetal [5,6], MOEA Framework [36], and Opt4J [37], which are written in Java; ParadisEO-MOEO [38], and PISA [39], developed in C/C++; and PlatEMO [40], implemented in Matlab. They all have in common the inclusion of representative algorithms from the the state of the art, benchmark problems and quality indicators for performance assessment.…”

Multi-view Genetic Programming Learning to Obtain Interpretable Rule-Based Classifiers for Semi-supervised Contexts. Lessons Learnt

“…Algorithms were implemented in Java 1.8 as an extension of the JCLEC genetic programming module for classification [42][43][44]. To tune our proposal, most of the combinations of the parameters presented in Table 2 were considered.…”