Open AccessMEGA: Predicting the best classifier combination using meta-learning and a genetic algorithm
Author(s) -
Paria Golshanrad,
Hossein Rahmani,
Banafsheh Karimian,
Fatemeh Karimkhani,
Gerhard Weiß
Publication year - 2021
Publication title -
intelligent data analysis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.231
H-Index - 47
eISSN - 1571-4128
pISSN - 1088-467X
DOI - 10.3233/ida-205494
Subject(s) - artificial intelligence , machine learning , computer science , classifier (uml) , random subspace method , decision tree , mega , a priori and a posteriori , ensemble learning , genetic algorithm , meta learning (computer science) , pattern recognition (psychology) , algorithm , data mining , task (project management) , engineering , philosophy , epistemology , physics , systems engineering , astronomy
Classifier combination through ensemble systems is one of the most effective approaches to improve the accuracy of classification systems. Ensemble systems are generally used to combine classifiers; However, selecting the best combination of individual classifiers is a challenging task. In this paper, we propose an efficient assembling method that employs both meta-learning and a genetic algorithm for the selection of the best classifiers. Our method is called MEGA, standing for using MEta-learning and a Genetic Algorithm for algorithm recommendation. MEGA has three main components: Training, Model Interpretation and Testing. The Training component extracts meta-features of each training dataset and uses a genetic algorithm to discover the best classifier combination. The Model Interpretation component interprets the relationships between meta-features and classifiers using a priori and multi-label decision tree algorithms. Finally, the Testing component uses a weighted k-nearest-neighbors algorithm to predict the best combination of classifiers for unseen datasets. We present extensive experimental results that demonstrate the performance of MEGA. MEGA achieves superior results in a comparison of three other methods and, most importantly, is able to find novel interpretable rules that can be used to select the best combination of classifiers for an unseen dataset.