A Hybrid Visualization Approach to Perform Analysis of Feature Spaces
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1007/978-3-030-43020-7_32 http://hdl.handle.net/11449/201829 |
Resumo: | In this paper, we propose a hybrid visualization by combining a projection based approach with star plot visualization to inspect feature spaces. While the projection based visualization is used to depict the instances similarities from high-dimensional spaces onto a bi-dimensional space, the star plot visual metaphor enables inspection of features (attributes) relationship. By inspecting feature spaces, analysts can assess their quality and analyze which features contribute for the formation of clusters. To validate our proposal, we demonstrate how to improve feature spaces to generate more cohesive clusters, as well as how to analyze deep learning features of distinct Convolutional Neural Network (CNN) architectures. |
id |
UNSP_c54ee3f34f0e9edba8cb91774081643f |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/201829 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
A Hybrid Visualization Approach to Perform Analysis of Feature SpacesExplainabilityExplainable artificial intelligenceFeature spaceInterpretabilityVisual analyticsIn this paper, we propose a hybrid visualization by combining a projection based approach with star plot visualization to inspect feature spaces. While the projection based visualization is used to depict the instances similarities from high-dimensional spaces onto a bi-dimensional space, the star plot visual metaphor enables inspection of features (attributes) relationship. By inspecting feature spaces, analysts can assess their quality and analyze which features contribute for the formation of clusters. To validate our proposal, we demonstrate how to improve feature spaces to generate more cohesive clusters, as well as how to analyze deep learning features of distinct Convolutional Neural Network (CNN) architectures.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Department of Mathematics and Computer Science São Paulo State University (UNESP)Department of Mathematics and Computer Science São Paulo State University (UNESP)FAPESP: 2018/17881-3FAPESP: 2018/25755-8Universidade Estadual Paulista (Unesp)Júnior, Wilson Estécio Marcílio [UNESP]Eler, Danilo Medeiros [UNESP]Garcia, Rogério Eduardo [UNESP]Correia, Ronaldo Celso Messias [UNESP]Silva, Lenon Fachiano [UNESP]2020-12-12T02:42:57Z2020-12-12T02:42:57Z2020-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject241-247http://dx.doi.org/10.1007/978-3-030-43020-7_32Advances in Intelligent Systems and Computing, v. 1134, p. 241-247.2194-53652194-5357http://hdl.handle.net/11449/20182910.1007/978-3-030-43020-7_322-s2.0-8508573941980310125732593610000-0003-1248-528XScopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengAdvances in Intelligent Systems and Computinginfo:eu-repo/semantics/openAccess2024-06-19T14:32:19Zoai:repositorio.unesp.br:11449/201829Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-06-19T14:32:19Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
A Hybrid Visualization Approach to Perform Analysis of Feature Spaces |
title |
A Hybrid Visualization Approach to Perform Analysis of Feature Spaces |
spellingShingle |
A Hybrid Visualization Approach to Perform Analysis of Feature Spaces Júnior, Wilson Estécio Marcílio [UNESP] Explainability Explainable artificial intelligence Feature space Interpretability Visual analytics |
title_short |
A Hybrid Visualization Approach to Perform Analysis of Feature Spaces |
title_full |
A Hybrid Visualization Approach to Perform Analysis of Feature Spaces |
title_fullStr |
A Hybrid Visualization Approach to Perform Analysis of Feature Spaces |
title_full_unstemmed |
A Hybrid Visualization Approach to Perform Analysis of Feature Spaces |
title_sort |
A Hybrid Visualization Approach to Perform Analysis of Feature Spaces |
author |
Júnior, Wilson Estécio Marcílio [UNESP] |
author_facet |
Júnior, Wilson Estécio Marcílio [UNESP] Eler, Danilo Medeiros [UNESP] Garcia, Rogério Eduardo [UNESP] Correia, Ronaldo Celso Messias [UNESP] Silva, Lenon Fachiano [UNESP] |
author_role |
author |
author2 |
Eler, Danilo Medeiros [UNESP] Garcia, Rogério Eduardo [UNESP] Correia, Ronaldo Celso Messias [UNESP] Silva, Lenon Fachiano [UNESP] |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Júnior, Wilson Estécio Marcílio [UNESP] Eler, Danilo Medeiros [UNESP] Garcia, Rogério Eduardo [UNESP] Correia, Ronaldo Celso Messias [UNESP] Silva, Lenon Fachiano [UNESP] |
dc.subject.por.fl_str_mv |
Explainability Explainable artificial intelligence Feature space Interpretability Visual analytics |
topic |
Explainability Explainable artificial intelligence Feature space Interpretability Visual analytics |
description |
In this paper, we propose a hybrid visualization by combining a projection based approach with star plot visualization to inspect feature spaces. While the projection based visualization is used to depict the instances similarities from high-dimensional spaces onto a bi-dimensional space, the star plot visual metaphor enables inspection of features (attributes) relationship. By inspecting feature spaces, analysts can assess their quality and analyze which features contribute for the formation of clusters. To validate our proposal, we demonstrate how to improve feature spaces to generate more cohesive clusters, as well as how to analyze deep learning features of distinct Convolutional Neural Network (CNN) architectures. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-12-12T02:42:57Z 2020-12-12T02:42:57Z 2020-01-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1007/978-3-030-43020-7_32 Advances in Intelligent Systems and Computing, v. 1134, p. 241-247. 2194-5365 2194-5357 http://hdl.handle.net/11449/201829 10.1007/978-3-030-43020-7_32 2-s2.0-85085739419 8031012573259361 0000-0003-1248-528X |
url |
http://dx.doi.org/10.1007/978-3-030-43020-7_32 http://hdl.handle.net/11449/201829 |
identifier_str_mv |
Advances in Intelligent Systems and Computing, v. 1134, p. 241-247. 2194-5365 2194-5357 10.1007/978-3-030-43020-7_32 2-s2.0-85085739419 8031012573259361 0000-0003-1248-528X |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Advances in Intelligent Systems and Computing |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
241-247 |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1803045392385835008 |