Diabetes classification using a redundancy reduction preprocessor
Autor(a) principal: | |
---|---|
Data de Publicação: | 2015 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Research on Biomedical Engineering (Online) |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S2446-47402015000200097 |
Resumo: | Introduction Diabetes patients can benefit significantly from early diagnosis. Thus, accurate automated screening is becoming increasingly important due to the wide spread of that disease. Previous studies in automated screening have found a maximum accuracy of 92.6%. Methods This work proposes a classification methodology based on efficient coding of the input data, which is carried out by decreasing input data redundancy using well-known ICA algorithms, such as FastICA, JADE and INFOMAX. The classifier used in the task to discriminate diabetics from non-diaibetics is the one class support vector machine. Classification tests were performed using noninvasive and invasive indicators. Results The results suggest that redundancy reduction increases one-class support vector machine performance when discriminating between diabetics and nondiabetics up to an accuracy of 98.47% while using all indicators. By using only noninvasive indicators, an accuracy of 98.28% was obtained. Conclusion The ICA feature extraction improves the performance of the classifier in the data set because it reduces the statistical dependence of the collected data, which increases the ability of the classifier to find accurate class boundaries. |
id |
SBEB-1_e16fecdae35df34fcbece84144044938 |
---|---|
oai_identifier_str |
oai:scielo:S2446-47402015000200097 |
network_acronym_str |
SBEB-1 |
network_name_str |
Research on Biomedical Engineering (Online) |
repository_id_str |
|
spelling |
Diabetes classification using a redundancy reduction preprocessorDiabetesClusteringEfficient codingIndependent Component AnalysisSupport Vector Machine Introduction Diabetes patients can benefit significantly from early diagnosis. Thus, accurate automated screening is becoming increasingly important due to the wide spread of that disease. Previous studies in automated screening have found a maximum accuracy of 92.6%. Methods This work proposes a classification methodology based on efficient coding of the input data, which is carried out by decreasing input data redundancy using well-known ICA algorithms, such as FastICA, JADE and INFOMAX. The classifier used in the task to discriminate diabetics from non-diaibetics is the one class support vector machine. Classification tests were performed using noninvasive and invasive indicators. Results The results suggest that redundancy reduction increases one-class support vector machine performance when discriminating between diabetics and nondiabetics up to an accuracy of 98.47% while using all indicators. By using only noninvasive indicators, an accuracy of 98.28% was obtained. Conclusion The ICA feature extraction improves the performance of the classifier in the data set because it reduces the statistical dependence of the collected data, which increases the ability of the classifier to find accurate class boundaries. Sociedade Brasileira de Engenharia Biomédica2015-06-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S2446-47402015000200097Research on Biomedical Engineering v.31 n.2 2015reponame:Research on Biomedical Engineering (Online)instname:Sociedade Brasileira de Engenharia Biomédica (SBEB)instacron:SBEB10.1590/1517-3151.0608info:eu-repo/semantics/openAccessRibeiro,Áurea CelesteBarros,Allan KardecSantana,EwaldoPríncipe,José Carloseng2015-07-23T00:00:00Zoai:scielo:S2446-47402015000200097Revistahttp://www.rbejournal.org/https://old.scielo.br/oai/scielo-oai.php||rbe@rbejournal.org2446-47402446-4732opendoar:2015-07-23T00:00Research on Biomedical Engineering (Online) - Sociedade Brasileira de Engenharia Biomédica (SBEB)false |
dc.title.none.fl_str_mv |
Diabetes classification using a redundancy reduction preprocessor |
title |
Diabetes classification using a redundancy reduction preprocessor |
spellingShingle |
Diabetes classification using a redundancy reduction preprocessor Ribeiro,Áurea Celeste Diabetes Clustering Efficient coding Independent Component Analysis Support Vector Machine |
title_short |
Diabetes classification using a redundancy reduction preprocessor |
title_full |
Diabetes classification using a redundancy reduction preprocessor |
title_fullStr |
Diabetes classification using a redundancy reduction preprocessor |
title_full_unstemmed |
Diabetes classification using a redundancy reduction preprocessor |
title_sort |
Diabetes classification using a redundancy reduction preprocessor |
author |
Ribeiro,Áurea Celeste |
author_facet |
Ribeiro,Áurea Celeste Barros,Allan Kardec Santana,Ewaldo Príncipe,José Carlos |
author_role |
author |
author2 |
Barros,Allan Kardec Santana,Ewaldo Príncipe,José Carlos |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Ribeiro,Áurea Celeste Barros,Allan Kardec Santana,Ewaldo Príncipe,José Carlos |
dc.subject.por.fl_str_mv |
Diabetes Clustering Efficient coding Independent Component Analysis Support Vector Machine |
topic |
Diabetes Clustering Efficient coding Independent Component Analysis Support Vector Machine |
description |
Introduction Diabetes patients can benefit significantly from early diagnosis. Thus, accurate automated screening is becoming increasingly important due to the wide spread of that disease. Previous studies in automated screening have found a maximum accuracy of 92.6%. Methods This work proposes a classification methodology based on efficient coding of the input data, which is carried out by decreasing input data redundancy using well-known ICA algorithms, such as FastICA, JADE and INFOMAX. The classifier used in the task to discriminate diabetics from non-diaibetics is the one class support vector machine. Classification tests were performed using noninvasive and invasive indicators. Results The results suggest that redundancy reduction increases one-class support vector machine performance when discriminating between diabetics and nondiabetics up to an accuracy of 98.47% while using all indicators. By using only noninvasive indicators, an accuracy of 98.28% was obtained. Conclusion The ICA feature extraction improves the performance of the classifier in the data set because it reduces the statistical dependence of the collected data, which increases the ability of the classifier to find accurate class boundaries. |
publishDate |
2015 |
dc.date.none.fl_str_mv |
2015-06-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S2446-47402015000200097 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S2446-47402015000200097 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/1517-3151.0608 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
Sociedade Brasileira de Engenharia Biomédica |
publisher.none.fl_str_mv |
Sociedade Brasileira de Engenharia Biomédica |
dc.source.none.fl_str_mv |
Research on Biomedical Engineering v.31 n.2 2015 reponame:Research on Biomedical Engineering (Online) instname:Sociedade Brasileira de Engenharia Biomédica (SBEB) instacron:SBEB |
instname_str |
Sociedade Brasileira de Engenharia Biomédica (SBEB) |
instacron_str |
SBEB |
institution |
SBEB |
reponame_str |
Research on Biomedical Engineering (Online) |
collection |
Research on Biomedical Engineering (Online) |
repository.name.fl_str_mv |
Research on Biomedical Engineering (Online) - Sociedade Brasileira de Engenharia Biomédica (SBEB) |
repository.mail.fl_str_mv |
||rbe@rbejournal.org |
_version_ |
1752126288176349184 |