TY - GEN
T1 - A Machine Learning Whale Algorithm Applied to the Matrix Covering Problem
AU - Valenzuela, Matias
AU - Moraga, Paola
AU - Causa, Leonardo
AU - Pinto, Hernan
AU - Rubio, José Miguel
N1 - Publisher Copyright:
© 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2021
Y1 - 2021
N2 - In the industry, the need for optimization naturally arises, with which there is a large number of optimization problems, particularly combinatorial and NP-hard type. Therefore, there is an important motivation for the development of algorithms that address these types of problems. IN this line, a large number of metaheuristic algorithms have been developed which work only in continuous spaces. Modifying the latter in order to address combinatorial problems has important applications. In this article, we will study a general binarization mechanism of continuous metaheuristics based on clustering techniques and it will be applied to the whale algorithm. Experiments are designed in order to demonstrate the contribution of the clustering technique in the binarization process. The results indicate that the Ballena binary optimization algorithm (MLWH) obtains adequate results when it is evaluated with a combinatorial problem such as the SCP.
AB - In the industry, the need for optimization naturally arises, with which there is a large number of optimization problems, particularly combinatorial and NP-hard type. Therefore, there is an important motivation for the development of algorithms that address these types of problems. IN this line, a large number of metaheuristic algorithms have been developed which work only in continuous spaces. Modifying the latter in order to address combinatorial problems has important applications. In this article, we will study a general binarization mechanism of continuous metaheuristics based on clustering techniques and it will be applied to the whale algorithm. Experiments are designed in order to demonstrate the contribution of the clustering technique in the binarization process. The results indicate that the Ballena binary optimization algorithm (MLWH) obtains adequate results when it is evaluated with a combinatorial problem such as the SCP.
UR - http://www.scopus.com/inward/record.url?scp=85120671889&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-90321-3_33
DO - 10.1007/978-3-030-90321-3_33
M3 - Conference contribution
AN - SCOPUS:85120671889
SN - 9783030903206
T3 - Lecture Notes in Networks and Systems
SP - 413
EP - 422
BT - Data Science and Intelligent Systems - Proceedings of 5th Computational Methods in Systems and Software 2021
A2 - Silhavy, Radek
A2 - Silhavy, Petr
A2 - Prokopova, Zdenka
PB - Springer Science and Business Media Deutschland GmbH
T2 - 5th Computational Methods in Systems and Software, CoMeSySo 2021
Y2 - 1 October 2021 through 1 October 2021
ER -