The crossover strategy based on the cellular automata for genetic Algorithms with binary chromosomes population
Primary Area: reinforcement learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Genetic Algorithms (GA), Cellular Automata (CA), Elementary Cellular Automata (ECA), Crossover Operators, K-nearest neighbors (KNN), Kmeans, Face Images Classification, Principal Component Analysis (PCA)
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: -
Abstract: In this paper we propose a crossover operator for genetic algorithms with binary chromosomes population based on the cellular automata (CGACell). After presenting the fundamental elements regarding cellular automata with specific examples for one- and two- dimensional cases, the the most widely used crossover operators in applications with genetic algorithms are described and the crossover operator based on cellular automata is defined. Specific forms of the crossover operator based on the ECA and 2D CA cases are described and exemplified. The CGACell crossover operator is used in the genetic structure to improved the KNN algorithm in terms of the parameter represented by the number of nearest neighbors selected by the data classification method. Validity and practical performance testing is performed on image data classification problems by optimizing the nearest-neighbors-based algorithm. The experimental study on the proposed crossover operator, by comparing the algorithm based on CGACell with standard data classification algorithms such as PCA, Kmeans or KNN, attests good qualitative performance in terms of correctness percentages in the recognition of new images, in classification applications of facial image classes corresponding to several persons.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 7933
Loading