Hybrid Filter-Wrapper Feature Selection using Modified Flower Pollination Algorithm

A major challenge in machine learning and data science is feature selection. Feature selection involves selecting the optimal (or suboptimal) subset of features to derive useful conclusions from a dataset based on the relevant information contained in those features. Flower Pollination Algorithm (FP...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohammad Ansari Shiri, Najme Mansouri
Format: Article
Language:English
Published: Ferdowsi University of Mashhad 2025-05-01
Series:Computer and Knowledge Engineering
Subjects:
Online Access:https://cke.um.ac.ir/article_46933_475699be14f9d13fca29ac0c2b44265b.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849222517323988992
author Mohammad Ansari Shiri
Najme Mansouri
author_facet Mohammad Ansari Shiri
Najme Mansouri
author_sort Mohammad Ansari Shiri
collection DOAJ
description A major challenge in machine learning and data science is feature selection. Feature selection involves selecting the optimal (or suboptimal) subset of features to derive useful conclusions from a dataset based on the relevant information contained in those features. Flower Pollination Algorithm (FPA) is a metaheuristic algorithm developed recently based on flower pollination. In this paper, we propose a new type of binary FPA, called the Filter-Wrapper Modified Binary FPA (FWMBFPA), which aims to improve convergence rate and solution quality by combining filter and wrapper advantages. Using FWMBFPA, the exploration process is directed towards specific search areas by extracting the features of existing solutions. 18 UCI datasets are used to evaluate the performance of the method. FWMBFPA generally performs better than the other algorithms in terms of average classification accuracy. FWMBFPA achieves highest classification accuracy with the smallest number of selected features when compared to other algorithms when dealing with datasets with a large number of features.
format Article
id doaj-art-b97dfaceee3f491ebeba7d3bd87b93b2
institution Kabale University
issn 2538-5453
2717-4123
language English
publishDate 2025-05-01
publisher Ferdowsi University of Mashhad
record_format Article
series Computer and Knowledge Engineering
spelling doaj-art-b97dfaceee3f491ebeba7d3bd87b93b22025-08-26T04:35:20ZengFerdowsi University of MashhadComputer and Knowledge Engineering2538-54532717-41232025-05-0182557410.22067/cke.2025.89191.112446933Hybrid Filter-Wrapper Feature Selection using Modified Flower Pollination AlgorithmMohammad Ansari Shiri0Najme Mansouri1Department of Computer Science, Shahid Bahonar University of Kermanshahid ba honar university of kermanA major challenge in machine learning and data science is feature selection. Feature selection involves selecting the optimal (or suboptimal) subset of features to derive useful conclusions from a dataset based on the relevant information contained in those features. Flower Pollination Algorithm (FPA) is a metaheuristic algorithm developed recently based on flower pollination. In this paper, we propose a new type of binary FPA, called the Filter-Wrapper Modified Binary FPA (FWMBFPA), which aims to improve convergence rate and solution quality by combining filter and wrapper advantages. Using FWMBFPA, the exploration process is directed towards specific search areas by extracting the features of existing solutions. 18 UCI datasets are used to evaluate the performance of the method. FWMBFPA generally performs better than the other algorithms in terms of average classification accuracy. FWMBFPA achieves highest classification accuracy with the smallest number of selected features when compared to other algorithms when dealing with datasets with a large number of features.https://cke.um.ac.ir/article_46933_475699be14f9d13fca29ac0c2b44265b.pdffeature selectionflower pollination algorithmfilterwrapper
spellingShingle Mohammad Ansari Shiri
Najme Mansouri
Hybrid Filter-Wrapper Feature Selection using Modified Flower Pollination Algorithm
Computer and Knowledge Engineering
feature selection
flower pollination algorithm
filter
wrapper
title Hybrid Filter-Wrapper Feature Selection using Modified Flower Pollination Algorithm
title_full Hybrid Filter-Wrapper Feature Selection using Modified Flower Pollination Algorithm
title_fullStr Hybrid Filter-Wrapper Feature Selection using Modified Flower Pollination Algorithm
title_full_unstemmed Hybrid Filter-Wrapper Feature Selection using Modified Flower Pollination Algorithm
title_short Hybrid Filter-Wrapper Feature Selection using Modified Flower Pollination Algorithm
title_sort hybrid filter wrapper feature selection using modified flower pollination algorithm
topic feature selection
flower pollination algorithm
filter
wrapper
url https://cke.um.ac.ir/article_46933_475699be14f9d13fca29ac0c2b44265b.pdf
work_keys_str_mv AT mohammadansarishiri hybridfilterwrapperfeatureselectionusingmodifiedflowerpollinationalgorithm
AT najmemansouri hybridfilterwrapperfeatureselectionusingmodifiedflowerpollinationalgorithm