Road Accident Predictions as a Classification Problem
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10174/33846 |
Resumo: | This paper aims at evaluating the performance of various classification methods for road accident prediction. The data is collected under MO- PREVIS [3] project which aims at improving road safety in Portugal. The data is highly imbalanced as there are fewer accident instances than the non-accident ones and due to this imbalance, it is observed that the tra- ditional classification algorithms do not perform well. Using sampling techniques (undersampling and oversampling) improved the results but not significantly. Some methods resulted in increased recall but that de- creased precision as the algorithm returned more false positives to make up for data imbalance. |
id |
RCAP_68b48cd9d8fe4ba63f4b5517bfcf8e3b |
---|---|
oai_identifier_str |
oai:dspace.uevora.pt:10174/33846 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Road Accident Predictions as a Classification ProblemThis paper aims at evaluating the performance of various classification methods for road accident prediction. The data is collected under MO- PREVIS [3] project which aims at improving road safety in Portugal. The data is highly imbalanced as there are fewer accident instances than the non-accident ones and due to this imbalance, it is observed that the tra- ditional classification algorithms do not perform well. Using sampling techniques (undersampling and oversampling) improved the results but not significantly. Some methods resulted in increased recall but that de- creased precision as the algorithm returned more false positives to make up for data imbalance.2023-02-03T12:10:03Z2023-02-032021-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10174/33846http://hdl.handle.net/10174/33846engMadhulika Agrawal, Teresa Gonçalves, and Paulo Quaresma. Road Accident Predictions as a Classification Problem. In Proceedings of the 27th Portuguese Conference on Pattern Recognition, RECPAD 2021, 2021.ndtcg@uevora.ptnd283Agrawal, MadhulikaGonçalves, TeresaQuaresma, Pauloinfo: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:RCAAP2024-01-03T19:35:57Zoai:dspace.uevora.pt:10174/33846Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T01:22:35.225492Repositório 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 |
Road Accident Predictions as a Classification Problem |
title |
Road Accident Predictions as a Classification Problem |
spellingShingle |
Road Accident Predictions as a Classification Problem Agrawal, Madhulika |
title_short |
Road Accident Predictions as a Classification Problem |
title_full |
Road Accident Predictions as a Classification Problem |
title_fullStr |
Road Accident Predictions as a Classification Problem |
title_full_unstemmed |
Road Accident Predictions as a Classification Problem |
title_sort |
Road Accident Predictions as a Classification Problem |
author |
Agrawal, Madhulika |
author_facet |
Agrawal, Madhulika Gonçalves, Teresa Quaresma, Paulo |
author_role |
author |
author2 |
Gonçalves, Teresa Quaresma, Paulo |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Agrawal, Madhulika Gonçalves, Teresa Quaresma, Paulo |
description |
This paper aims at evaluating the performance of various classification methods for road accident prediction. The data is collected under MO- PREVIS [3] project which aims at improving road safety in Portugal. The data is highly imbalanced as there are fewer accident instances than the non-accident ones and due to this imbalance, it is observed that the tra- ditional classification algorithms do not perform well. Using sampling techniques (undersampling and oversampling) improved the results but not significantly. Some methods resulted in increased recall but that de- creased precision as the algorithm returned more false positives to make up for data imbalance. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-01-01T00:00:00Z 2023-02-03T12:10:03Z 2023-02-03 |
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 |
http://hdl.handle.net/10174/33846 http://hdl.handle.net/10174/33846 |
url |
http://hdl.handle.net/10174/33846 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Madhulika Agrawal, Teresa Gonçalves, and Paulo Quaresma. Road Accident Predictions as a Classification Problem. In Proceedings of the 27th Portuguese Conference on Pattern Recognition, RECPAD 2021, 2021. nd tcg@uevora.pt nd 283 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
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 |
|
_version_ |
1799136707342237696 |