Bar chart comparing the average fitness values of various feature selection algorithms.

<p>Bar chart comparing the average fitness values of various feature selection algorithms.</p>

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Doaa Sami Khafaga (21463870) (author)
مؤلفون آخرون: El-Sayed M. El-kenawy (14581088) (author), Faris H. Rizk (21755909) (author), Marwa M. Eid (11251630) (author), Ehsaneh Khodadadi (22146329) (author), Nima Khodadadi (14581091) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852017151656853504
author Doaa Sami Khafaga (21463870)
author2 El-Sayed M. El-kenawy (14581088)
Faris H. Rizk (21755909)
Marwa M. Eid (11251630)
Ehsaneh Khodadadi (22146329)
Nima Khodadadi (14581091)
author2_role author
author
author
author
author
author_facet Doaa Sami Khafaga (21463870)
El-Sayed M. El-kenawy (14581088)
Faris H. Rizk (21755909)
Marwa M. Eid (11251630)
Ehsaneh Khodadadi (22146329)
Nima Khodadadi (14581091)
author_role author
dc.creator.none.fl_str_mv Doaa Sami Khafaga (21463870)
El-Sayed M. El-kenawy (14581088)
Faris H. Rizk (21755909)
Marwa M. Eid (11251630)
Ehsaneh Khodadadi (22146329)
Nima Khodadadi (14581091)
dc.date.none.fl_str_mv 2025-08-29T18:04:21Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0330228.g013
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Bar_chart_comparing_the_average_fitness_values_of_various_feature_selection_algorithms_/30014834
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biotechnology
Sociology
Hematology
Space Science
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
false negative rate
effective feature selection
driven deep learning
deep learning models
contributions include developing
clinical diagnostics quantifiably
average classification error
automated cytology technology
optimization also results
metaheuristic optimization techniques
enhancing cnn performance
ocoa ), designed
increases cnn accuracy
ocotillo optimization
hyperparameter optimization
study introduces
significantly reduced
sensitivity increasing
maximum accuracy
innovative bio
initial accuracy
highly dependent
findings highlight
expert knowledge
critical scenarios
continuous version
binary variant
accurate solution
61 %),
48 %.
24 %.
(+ 12
(+ 11
dc.title.none.fl_str_mv Bar chart comparing the average fitness values of various feature selection algorithms.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <p>Bar chart comparing the average fitness values of various feature selection algorithms.</p>
eu_rights_str_mv openAccess
id Manara_fbc797b104fec2f4de374464083f7bea
identifier_str_mv 10.1371/journal.pone.0330228.g013
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30014834
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Bar chart comparing the average fitness values of various feature selection algorithms.Doaa Sami Khafaga (21463870)El-Sayed M. El-kenawy (14581088)Faris H. Rizk (21755909)Marwa M. Eid (11251630)Ehsaneh Khodadadi (22146329)Nima Khodadadi (14581091)BiotechnologySociologyHematologySpace ScienceBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedfalse negative rateeffective feature selectiondriven deep learningdeep learning modelscontributions include developingclinical diagnostics quantifiablyaverage classification errorautomated cytology technologyoptimization also resultsmetaheuristic optimization techniquesenhancing cnn performanceocoa ), designedincreases cnn accuracyocotillo optimizationhyperparameter optimizationstudy introducessignificantly reducedsensitivity increasingmaximum accuracyinnovative bioinitial accuracyhighly dependentfindings highlightexpert knowledgecritical scenarioscontinuous versionbinary variantaccurate solution61 %),48 %.24 %.(+ 12(+ 11<p>Bar chart comparing the average fitness values of various feature selection algorithms.</p>2025-08-29T18:04:21ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0330228.g013https://figshare.com/articles/figure/Bar_chart_comparing_the_average_fitness_values_of_various_feature_selection_algorithms_/30014834CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/300148342025-08-29T18:04:21Z
spellingShingle Bar chart comparing the average fitness values of various feature selection algorithms.
Doaa Sami Khafaga (21463870)
Biotechnology
Sociology
Hematology
Space Science
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
false negative rate
effective feature selection
driven deep learning
deep learning models
contributions include developing
clinical diagnostics quantifiably
average classification error
automated cytology technology
optimization also results
metaheuristic optimization techniques
enhancing cnn performance
ocoa ), designed
increases cnn accuracy
ocotillo optimization
hyperparameter optimization
study introduces
significantly reduced
sensitivity increasing
maximum accuracy
innovative bio
initial accuracy
highly dependent
findings highlight
expert knowledge
critical scenarios
continuous version
binary variant
accurate solution
61 %),
48 %.
24 %.
(+ 12
(+ 11
status_str publishedVersion
title Bar chart comparing the average fitness values of various feature selection algorithms.
title_full Bar chart comparing the average fitness values of various feature selection algorithms.
title_fullStr Bar chart comparing the average fitness values of various feature selection algorithms.
title_full_unstemmed Bar chart comparing the average fitness values of various feature selection algorithms.
title_short Bar chart comparing the average fitness values of various feature selection algorithms.
title_sort Bar chart comparing the average fitness values of various feature selection algorithms.
topic Biotechnology
Sociology
Hematology
Space Science
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
false negative rate
effective feature selection
driven deep learning
deep learning models
contributions include developing
clinical diagnostics quantifiably
average classification error
automated cytology technology
optimization also results
metaheuristic optimization techniques
enhancing cnn performance
ocoa ), designed
increases cnn accuracy
ocotillo optimization
hyperparameter optimization
study introduces
significantly reduced
sensitivity increasing
maximum accuracy
innovative bio
initial accuracy
highly dependent
findings highlight
expert knowledge
critical scenarios
continuous version
binary variant
accurate solution
61 %),
48 %.
24 %.
(+ 12
(+ 11