Publication Details

Multi-Objective Evolutionary Design of Explainable EEG Classifier

HURTA Martin, OVESNÁ Anna, MRÁZEK Vojtěch and SEKANINA Lukáš. Multi-Objective Evolutionary Design of Explainable EEG Classifier. In: Genetic Programming, 28th European Conference, EuroGP 2025. Lecture Notes in Computer Science, vol. 15609. Terst: Springer Nature Switzerland AG, 2025, pp. 52-67. ISBN 978-3-031-89990-4. Available from: https://link.springer.com/chapter/10.1007/978-3-031-89991-1_4
Czech title
Vícekriteriální evoluční návrh interpretovatelného EEG klasifikátoru
Type
conference paper
Language
english
Authors
Hurta Martin, Ing. (DCSY FIT BUT)
Ovesná Anna, Bc. (FIT BUT)
Mrázek Vojtěch, Ing., Ph.D. (DCSY FIT BUT)
Sekanina Lukáš, prof. Ing., Ph.D. (DCSY FIT BUT)
URL
Keywords

Multi-objective design, Classification, Explainability, Co-evolution, Genetic algorithm, Cartesian genetic programming, EEG

Abstract

Deep neural networks (DNNs) have achieved impressive results in many fields. However, the use of black-box solutions based on DNNs in medical applications poses challenges, as understanding the rationale behind decisions is crucial for application in healthcare. For those reasons, we propose a new method for the evolutionary multi-objective design (MOD) of small and potentially explainable EEG (Electroencephalography) signal classifiers. We evaluate a combination of genetic algorithm (GA) for feature selection with multiple algorithms for the automated design of the classifier, including Support Vector Machine, k-Nearest Neighbors, and Naive Bayes. To further improve the classification quality and obtain less complex solutions, we compare three different MOD scenarios targeting the accuracy, specificity, sensitivity, and the number of used features. In addition, we evaluate the use of Cartesian Genetic Programming (CGP) as a way to achieve smaller and more interpretable solutions and combine it with the compositional co-evolution of selected features to improve computational requirements and find solutions in a reasonable time. The proposed methods are experimentally evaluated on tasks of alcohol use disorder and major depressive disorder classification. Experimental results show that newly proposed MOD scenarios lead to significantly better trade-offs between the accuracy and the number of features compared to the state-of-the-art method employing the NSGA-II algorithm. The proposed co-evolution of features (evolved by GA) and classifier (evolved by CGP) allowed the design of small and potentially explainable solutions and led to 20-100 times faster convergence than the baseline CGP-based approach.

Published
2025
Pages
52-67
Proceedings
Genetic Programming, 28th European Conference, EuroGP 2025
Series
Lecture Notes in Computer Science
Volume
15609
Conference
28th European Conference on Genetic Programming, Terst, IT
ISBN
978-3-031-89990-4
Publisher
Springer Nature Switzerland AG
Place
Terst, IT
DOI
BibTeX
@INPROCEEDINGS{FITPUB13198,
   author = "Martin Hurta and Anna Ovesn\'{a} and Vojt\v{e}ch Mr\'{a}zek and Luk\'{a}\v{s} Sekanina",
   title = "Multi-Objective Evolutionary Design of Explainable EEG Classifier",
   pages = "52--67",
   booktitle = "Genetic Programming, 28th European Conference, EuroGP 2025",
   series = "Lecture Notes in Computer Science",
   volume = 15609,
   year = 2025,
   location = "Terst, IT",
   publisher = "Springer Nature Switzerland AG",
   ISBN = "978-3-031-89990-4",
   doi = "10.1007/978-3-031-89991-1\_4",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/13198"
}
Back to top