Cargando…

FASTENER Feature Selection for Inference from Earth Observation Data

In this paper, a novel feature selection algorithm for inference from high-dimensional data (FASTENER) is presented. With its multi-objective approach, the algorithm tries to maximize the accuracy of a machine learning algorithm with as few features as possible. The algorithm exploits entropy-based...

Descripción completa

Detalles Bibliográficos
Autores principales: Koprivec, Filip, Kenda, Klemen, Šircelj, Beno
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7712113/
https://www.ncbi.nlm.nih.gov/pubmed/33286966
http://dx.doi.org/10.3390/e22111198
_version_ 1783618298357743616
author Koprivec, Filip
Kenda, Klemen
Šircelj, Beno
author_facet Koprivec, Filip
Kenda, Klemen
Šircelj, Beno
author_sort Koprivec, Filip
collection PubMed
description In this paper, a novel feature selection algorithm for inference from high-dimensional data (FASTENER) is presented. With its multi-objective approach, the algorithm tries to maximize the accuracy of a machine learning algorithm with as few features as possible. The algorithm exploits entropy-based measures, such as mutual information in the crossover phase of the iterative genetic approach. FASTENER converges to a (near) optimal subset of features faster than other multi-objective wrapper methods, such as POSS, DT-forward and FS-SDS, and achieves better classification accuracy than similarity and information theory-based methods currently utilized in earth observation scenarios. The approach was primarily evaluated using the earth observation data set for land-cover classification from ESA’s Sentinel-2 mission, the digital elevation model and the ground truth data of the Land Parcel Identification System from Slovenia. For land cover classification, the algorithm gives state-of-the-art results. Additionally, FASTENER was tested on open feature selection data sets and compared to the state-of-the-art methods. With fewer model evaluations, the algorithm yields comparable results to DT-forward and is superior to FS-SDS. FASTENER can be used in any supervised machine learning scenario.
format Online
Article
Text
id pubmed-7712113
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-77121132021-02-24 FASTENER Feature Selection for Inference from Earth Observation Data Koprivec, Filip Kenda, Klemen Šircelj, Beno Entropy (Basel) Article In this paper, a novel feature selection algorithm for inference from high-dimensional data (FASTENER) is presented. With its multi-objective approach, the algorithm tries to maximize the accuracy of a machine learning algorithm with as few features as possible. The algorithm exploits entropy-based measures, such as mutual information in the crossover phase of the iterative genetic approach. FASTENER converges to a (near) optimal subset of features faster than other multi-objective wrapper methods, such as POSS, DT-forward and FS-SDS, and achieves better classification accuracy than similarity and information theory-based methods currently utilized in earth observation scenarios. The approach was primarily evaluated using the earth observation data set for land-cover classification from ESA’s Sentinel-2 mission, the digital elevation model and the ground truth data of the Land Parcel Identification System from Slovenia. For land cover classification, the algorithm gives state-of-the-art results. Additionally, FASTENER was tested on open feature selection data sets and compared to the state-of-the-art methods. With fewer model evaluations, the algorithm yields comparable results to DT-forward and is superior to FS-SDS. FASTENER can be used in any supervised machine learning scenario. MDPI 2020-10-23 /pmc/articles/PMC7712113/ /pubmed/33286966 http://dx.doi.org/10.3390/e22111198 Text en © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Koprivec, Filip
Kenda, Klemen
Šircelj, Beno
FASTENER Feature Selection for Inference from Earth Observation Data
title FASTENER Feature Selection for Inference from Earth Observation Data
title_full FASTENER Feature Selection for Inference from Earth Observation Data
title_fullStr FASTENER Feature Selection for Inference from Earth Observation Data
title_full_unstemmed FASTENER Feature Selection for Inference from Earth Observation Data
title_short FASTENER Feature Selection for Inference from Earth Observation Data
title_sort fastener feature selection for inference from earth observation data
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7712113/
https://www.ncbi.nlm.nih.gov/pubmed/33286966
http://dx.doi.org/10.3390/e22111198
work_keys_str_mv AT koprivecfilip fastenerfeatureselectionforinferencefromearthobservationdata
AT kendaklemen fastenerfeatureselectionforinferencefromearthobservationdata
AT sirceljbeno fastenerfeatureselectionforinferencefromearthobservationdata