Improving specific class mapping from remotely sensed data by Cost-Sensitive learning

Detalhes bibliográficos
Autor(a) principal: Silva, Joel
Data de Publicação: 2017
Outros Autores: Bacao, Fernando, Dieng, Maguette, Foody, Giles M., Caetano, Mario
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
DOI: 10.1080/01431161.2017.1292073
Texto Completo: https://doi.org/10.1080/01431161.2017.1292073
Resumo: Silva, J., Bacao, F., Dieng, M., Foody, G. M., & Caetano, M. (2017). Improving specific class mapping from remotely sensed data by Cost-Sensitive learning. International Journal Of Remote Sensing, 38(11), 3294-3316. https://doi.org/10.1080/01431161.2017.1292073
id RCAP_8ba88f185ac11598070a0fda83a09fab
oai_identifier_str oai:run.unl.pt:10362/82530
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Improving specific class mapping from remotely sensed data by Cost-Sensitive learningEarth and Planetary Sciences(all)SDG 15 - Life on LandSilva, J., Bacao, F., Dieng, M., Foody, G. M., & Caetano, M. (2017). Improving specific class mapping from remotely sensed data by Cost-Sensitive learning. International Journal Of Remote Sensing, 38(11), 3294-3316. https://doi.org/10.1080/01431161.2017.1292073In many remote-sensing projects, one is usually interested in a small number of land-cover classes present in a study area and not in all the land-cover classes that make-up the landscape. Previous studies in supervised classification of satellite images have tackled specific class mapping problem by isolating the classes of interest and combining all other classes into one large class, usually called others, and by developing a binary classifier to discriminate the class of interest from the others. Here, this approach is called focused approach. The strength of the focused approach is to decompose the original multi-class supervised classification problem into a binary classification problem, focusing the process on the discrimination of the class of interest. Previous studies have shown that this method is able to discriminate more accurately the classes of interest when compared with the standard multi-class supervised approach. However, it may be susceptible to data imbalance problems present in the training data set, since the classes of interest are often a small part of the training set. A result the classification may be biased towards the largest classes and, thus, be sub-optimal for the discrimination of the classes of interest. This study presents a way to minimize the effects of data imbalance problems in specific class mapping using cost-sensitive learning. In this approach errors committed in theminority class are treated as being costlier than errors committed in the majority class. Cost-sensitive approaches are typically implemented by weighting training data points accordingly to their importance to the analysis. By changing the weight of individual data points, it is possible to shift theweight from the larger classes to the smaller ones, balancing the data set. To illustrate the use of the cost-sensitive approach to map specific classes of interest, a series of experiments with weighted support vector machines classifier and Landsat Thematic Mapper data were conducted to discriminate two types of mangrove forest (high-mangrove and low-mangrove) in Saloum estuary, Senegal, a United Nations Educational, Scientific and Cultural Organisation World Heritage site. Results suggest an increase in overall classification accuracy with the use of cost-sensitive method (97.3%) over the standard multi-class (94.3%) and the focused approach (91.0%). In particular, cost-sensitive method yielded higher sensitivity and specificity values on the discrimination of the classes of interest when compared with the standard multi-class and focused approaches.NOVA Information Management School (NOVA IMS)Information Management Research Center (MagIC) - NOVA Information Management SchoolRUNSilva, JoelBacao, FernandoDieng, MaguetteFoody, Giles M.Caetano, Mario2019-09-27T23:04:25Z2017-06-032017-06-03T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article23application/pdfhttps://doi.org/10.1080/01431161.2017.1292073eng0143-1161PURE: 13193510http://www.scopus.com/inward/record.url?scp=85028874290&partnerID=8YFLogxKhttps://doi.org/10.1080/01431161.2017.1292073info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-05-22T17:41:15Zoai:run.unl.pt:10362/82530Portal AgregadorONGhttps://www.rcaap.pt/oai/openairemluisa.alvim@gmail.comopendoar:71602024-05-22T17:41:15Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Improving specific class mapping from remotely sensed data by Cost-Sensitive learning
title Improving specific class mapping from remotely sensed data by Cost-Sensitive learning
spellingShingle Improving specific class mapping from remotely sensed data by Cost-Sensitive learning
Improving specific class mapping from remotely sensed data by Cost-Sensitive learning
Silva, Joel
Earth and Planetary Sciences(all)
SDG 15 - Life on Land
Silva, Joel
Earth and Planetary Sciences(all)
SDG 15 - Life on Land
title_short Improving specific class mapping from remotely sensed data by Cost-Sensitive learning
title_full Improving specific class mapping from remotely sensed data by Cost-Sensitive learning
title_fullStr Improving specific class mapping from remotely sensed data by Cost-Sensitive learning
Improving specific class mapping from remotely sensed data by Cost-Sensitive learning
title_full_unstemmed Improving specific class mapping from remotely sensed data by Cost-Sensitive learning
Improving specific class mapping from remotely sensed data by Cost-Sensitive learning
title_sort Improving specific class mapping from remotely sensed data by Cost-Sensitive learning
author Silva, Joel
author_facet Silva, Joel
Silva, Joel
Bacao, Fernando
Dieng, Maguette
Foody, Giles M.
Caetano, Mario
Bacao, Fernando
Dieng, Maguette
Foody, Giles M.
Caetano, Mario
author_role author
author2 Bacao, Fernando
Dieng, Maguette
Foody, Giles M.
Caetano, Mario
author2_role author
author
author
author
dc.contributor.none.fl_str_mv NOVA Information Management School (NOVA IMS)
Information Management Research Center (MagIC) - NOVA Information Management School
RUN
dc.contributor.author.fl_str_mv Silva, Joel
Bacao, Fernando
Dieng, Maguette
Foody, Giles M.
Caetano, Mario
dc.subject.por.fl_str_mv Earth and Planetary Sciences(all)
SDG 15 - Life on Land
topic Earth and Planetary Sciences(all)
SDG 15 - Life on Land
description Silva, J., Bacao, F., Dieng, M., Foody, G. M., & Caetano, M. (2017). Improving specific class mapping from remotely sensed data by Cost-Sensitive learning. International Journal Of Remote Sensing, 38(11), 3294-3316. https://doi.org/10.1080/01431161.2017.1292073
publishDate 2017
dc.date.none.fl_str_mv 2017-06-03
2017-06-03T00:00:00Z
2019-09-27T23:04:25Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://doi.org/10.1080/01431161.2017.1292073
url https://doi.org/10.1080/01431161.2017.1292073
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 0143-1161
PURE: 13193510
http://www.scopus.com/inward/record.url?scp=85028874290&partnerID=8YFLogxK
https://doi.org/10.1080/01431161.2017.1292073
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 23
application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv mluisa.alvim@gmail.com
_version_ 1822181944197120001
dc.identifier.doi.none.fl_str_mv 10.1080/01431161.2017.1292073

Registros relacionados