RT Journal Article
T1 Hybridizing Cartesian Genetic Programming and Harmony Search for adaptive feature construction in supervised learning problems
A1 Elola, Andoni
A1 Del Ser, Javier
A1 Bilbao, Miren Nekane
A1 Perfecto, Cristina
A1 Alexandre, Enrique
A1 Salcedo-Sanz, Sancho
AB The advent of the so-called Big Data paradigm has motivated a flurry of research aimed at enhancing machine learning models by following very diverse approaches. In this context this work focuses on the automatic construction of features in supervised learning problems, which differs from the conventional selection of features in that new characteristics with enhanced predictive power are inferred from the original dataset. In particular this manuscript proposes a new iterative feature construction approach based on a self-learning meta-heuristic algorithm (Harmony Search) and a solution encoding strategy (correspondingly, Cartesian Genetic Programming) suited to represent combinations of features by means of constant-length solution vectors. The proposed feature construction algorithm, coined as Adaptive Cartesian Harmony Search (ACHS), incorporates modifications that allow exploiting the estimated predictive importance of intermediate solutions and, ultimately, attaining better convergence rate in its iterative learning procedure. The performance of the proposed ACHS scheme is assessed and compared to that rendered by the state of the art in a toy example and three practical use cases from the literature. The excellent performance figures obtained in these problems shed light on the widespread applicability of the proposed scheme to supervised learning with legacy datasets composed by already refined characteristics.
SN 1872-9681
YR 2016
FD 2016
LA eng
NO Elola , A , Del Ser , J , Bilbao , M N , Perfecto , C , Alexandre , E & Salcedo-Sanz , S 2016 , ' Hybridizing Cartesian Genetic Programming and Harmony Search for adaptive feature construction in supervised learning problems ' , Applied Soft Computing , vol. 52 , pp. 760-770 . https://doi.org/10.1016/j.asoc.2016.09.049
NO Publisher Copyright: © 2016 Elsevier B.V.
DS TECNALIA Publications
RD 1 jul 2024