Efficient genetic algorithm for feature selection for early time series classification

• Published in: Computers & industrial engineering Vol. 142; p. 106345
• Main Authors: Ahn, Gilseung, Hur, Sun
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.04.2020
• Subjects: Earliness; Feature selection; Genetic algorithm; Time series classification; Feature selection; Earliness; Time series classification; Genetic algorithm
• ISSN: 0360-8352; 1879-0550
• DOI: 10.1016/j.cie.2020.106345

•A multi-objective feature selection for early classification is considered.•Starting time of classification is important for early classification.•Our model minimizes the starting time and execution time of classification.•We designed a genetic algorithm with better performance and faster convergence. This paper addresses a multi-objective feature selection problem for early time series classification. Previous research has focused on how many features to consider for a classifier, but has not considered the starting time of classification, which is also important for early classification. Motivated by this, we developed a mathematical model for which the objectives are to maximize classification performance and minimize the starting time and execution time of classification. We designed an efficient genetic algorithm to generate solutions with high probability. In experiment, we compared the proposed algorithm and general genetic algorithm under various experimental settings. From the experiment, we verified that the proposed algorithm can find a better feature set in terms of classification performance, starting time and execution time of classification than feature set found by general genetic algorithm.