Binary Archimedes Optimization Algorithm based Feature Selection for Regression Problem

The use of datasets became paramount in many searches in one hand, on the other hand the rapidly growth of data size involves computational complexity and reduces model performances, this encourage us to find new methods to deal with this problem. Features Selection is the one of the main task used...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2022 4th International Conference on Pattern Analysis and Intelligent Systems (PAIS) s. 1 - 7
Hlavní autori: Amine, Djermane, Hichem, Haouassi, Soumia, Zertal
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 12.10.2022
Predmet:
Archimedes optimization algorithm
Classification algorithms
Data mining
Data models
Feature extraction
feature selection
Metaheuristics
Prediction algorithms
Predictive models
regression
Search problems
swarm-based optimization
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The use of datasets became paramount in many searches in one hand, on the other hand the rapidly growth of data size involves computational complexity and reduces model performances, this encourage us to find new methods to deal with this problem. Features Selection is the one of the main task used to resolve this issue. In this paper we propose a novel features selection method for regression task based on AOA (Archimedes Optimization Algorithm), experimental results shows that the proposed method can efficiently reduce dataset size and improve model performance.
DOI:10.1109/PAIS56586.2022.9946903