Sonar inspired optimization based feature selection
2020 (English)In: SETN 2020: 11th Hellenic Conference on Artificial Intelligence, ACM Digital Library, 2020, p. 195-201Conference paper, Published paper (Refereed)
Abstract [en]
One of the problems that Machine Learning (ML) algorithms face in classification tasks is the Curse of Dimensionality, which refers to the sensitivity of their performance to the data dimensionality. The solution to this problem is to select the features that are of higher importance for the model produced. To improve the performance of a classifier, various meta-heuristic algorithms have been implemented due to their ability to provide optimal solutions in problems that there are multiple candidate solutions, such as in Feature Selection (FS). In this study, Sonar Inspired Optimization (SIO) algorithm is used to perform FS in order to improve the performance of a state-of-the-art classifier, i.e. k-NN. SIO's performance is compared with other nature-inspired meta-heuristic algorithms that have been used for the same task.
Place, publisher, year, edition, pages
ACM Digital Library, 2020. p. 195-201
Series
ACM International Conference Proceeding Series
Keywords [en]
Feature selection, Nature-inspired algorithms, Sonar inspired optimization, Biomimetics, Feature extraction, Machine learning, Nearest neighbor search, Sonar, Classification tasks, Curse of dimensionality, Data dimensionality, Meta heuristic algorithm, Optimal solutions, State of the art, Heuristic algorithms
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:hj:diva-63832DOI: 10.1145/3411408.3411438Scopus ID: 2-s2.0-85091062581ISBN: 9781450388788 (print)OAI: oai:DiVA.org:hj-63832DiVA, id: diva2:1845918
Conference
11th International Conf erence on Artificial Intelligence, SETN 2020, 2-4 September 2020
2024-03-202024-03-202024-03-20Bibliographically approved