Cargando…

A Two-Phase Feature Selection Method for Identifying Influential Spreaders of Disease Epidemics in Complex Networks

Network epidemiology plays a fundamental role in understanding the relationship between network structure and epidemic dynamics, among which identifying influential spreaders is especially important. Most previous studies aim to propose a centrality measure based on network topology to reflect the i...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Xiya, Han, Yuexing, Wang, Bing
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10378310/
https://www.ncbi.nlm.nih.gov/pubmed/37510015
http://dx.doi.org/10.3390/e25071068
_version_ 1785079733798567936
author Wang, Xiya
Han, Yuexing
Wang, Bing
author_facet Wang, Xiya
Han, Yuexing
Wang, Bing
author_sort Wang, Xiya
collection PubMed
description Network epidemiology plays a fundamental role in understanding the relationship between network structure and epidemic dynamics, among which identifying influential spreaders is especially important. Most previous studies aim to propose a centrality measure based on network topology to reflect the influence of spreaders, which manifest limited universality. Machine learning enhances the identification of influential spreaders by combining multiple centralities. However, several centrality measures utilized in machine learning methods, such as closeness centrality, exhibit high computational complexity when confronted with large network sizes. Here, we propose a two-phase feature selection method for identifying influential spreaders with a reduced feature dimension. Depending on the definition of influential spreaders, we obtain the optimal feature combination for different synthetic networks. Our results demonstrate that when the datasets are mildly or moderately imbalanced, for Barabasi–Albert (BA) scale-free networks, the centralities’ combination with the two-hop neighborhood is fundamental, and for Erdős–Rényi (ER) random graphs, the centralities’ combination with the degree centrality is essential. Meanwhile, for Watts–Strogatz (WS) small world networks, feature selection is unnecessary. We also conduct experiments on real-world networks, and the features selected display a high similarity with synthetic networks. Our method provides a new path for identifying superspreaders for the control of epidemics.
format Online
Article
Text
id pubmed-10378310
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-103783102023-07-29 A Two-Phase Feature Selection Method for Identifying Influential Spreaders of Disease Epidemics in Complex Networks Wang, Xiya Han, Yuexing Wang, Bing Entropy (Basel) Article Network epidemiology plays a fundamental role in understanding the relationship between network structure and epidemic dynamics, among which identifying influential spreaders is especially important. Most previous studies aim to propose a centrality measure based on network topology to reflect the influence of spreaders, which manifest limited universality. Machine learning enhances the identification of influential spreaders by combining multiple centralities. However, several centrality measures utilized in machine learning methods, such as closeness centrality, exhibit high computational complexity when confronted with large network sizes. Here, we propose a two-phase feature selection method for identifying influential spreaders with a reduced feature dimension. Depending on the definition of influential spreaders, we obtain the optimal feature combination for different synthetic networks. Our results demonstrate that when the datasets are mildly or moderately imbalanced, for Barabasi–Albert (BA) scale-free networks, the centralities’ combination with the two-hop neighborhood is fundamental, and for Erdős–Rényi (ER) random graphs, the centralities’ combination with the degree centrality is essential. Meanwhile, for Watts–Strogatz (WS) small world networks, feature selection is unnecessary. We also conduct experiments on real-world networks, and the features selected display a high similarity with synthetic networks. Our method provides a new path for identifying superspreaders for the control of epidemics. MDPI 2023-07-15 /pmc/articles/PMC10378310/ /pubmed/37510015 http://dx.doi.org/10.3390/e25071068 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/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 (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wang, Xiya
Han, Yuexing
Wang, Bing
A Two-Phase Feature Selection Method for Identifying Influential Spreaders of Disease Epidemics in Complex Networks
title A Two-Phase Feature Selection Method for Identifying Influential Spreaders of Disease Epidemics in Complex Networks
title_full A Two-Phase Feature Selection Method for Identifying Influential Spreaders of Disease Epidemics in Complex Networks
title_fullStr A Two-Phase Feature Selection Method for Identifying Influential Spreaders of Disease Epidemics in Complex Networks
title_full_unstemmed A Two-Phase Feature Selection Method for Identifying Influential Spreaders of Disease Epidemics in Complex Networks
title_short A Two-Phase Feature Selection Method for Identifying Influential Spreaders of Disease Epidemics in Complex Networks
title_sort two-phase feature selection method for identifying influential spreaders of disease epidemics in complex networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10378310/
https://www.ncbi.nlm.nih.gov/pubmed/37510015
http://dx.doi.org/10.3390/e25071068
work_keys_str_mv AT wangxiya atwophasefeatureselectionmethodforidentifyinginfluentialspreadersofdiseaseepidemicsincomplexnetworks
AT hanyuexing atwophasefeatureselectionmethodforidentifyinginfluentialspreadersofdiseaseepidemicsincomplexnetworks
AT wangbing atwophasefeatureselectionmethodforidentifyinginfluentialspreadersofdiseaseepidemicsincomplexnetworks
AT wangxiya twophasefeatureselectionmethodforidentifyinginfluentialspreadersofdiseaseepidemicsincomplexnetworks
AT hanyuexing twophasefeatureselectionmethodforidentifyinginfluentialspreadersofdiseaseepidemicsincomplexnetworks
AT wangbing twophasefeatureselectionmethodforidentifyinginfluentialspreadersofdiseaseepidemicsincomplexnetworks