Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Hyperparameters Analysis of Machine Learning Techniques for Classification of Marine Targets in SAR Images
Centro de Guerra Acústica e Eletrônica da Marinha (CGAEM), Brazil.
Instituto Tecnológico de Aeronáutica (ITA), Brazil.
Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences.ORCID iD: 0000-0003-0423-9927
Instituto Tecnológico de Aeronáutica (ITA), Brazil.
2023 (English)In: Proceedings of the XX Brazilian Symposium on Remote Sensing: Anais do XX Simpósio Brasileiro de Sensoriamento Remoto, 2023, Vol. 20, p. 1095-1098, article id 155793Conference paper, Published paper (Refereed)
Abstract [en]

Due to the extensive coastal area of Brazil, pattern recognition techniques based on artificial intelligence can search for targets at sea faster for surveillance, rescue, or illicit combat activities. This article presents a hyperparameter analysis of machine learning techniques to classify targets in SAR images. We considered a data set with vertical horizontal polarization SAR images from Campos Basin, Rio de Janeiro, to classify oil platforms and ships. The classification attributes are extracted through a convolutional neural network VGG-16 pre-trained with the ImageNet data set. Then, four machine learning techniques are evaluated, random forest, decision tree, k-nearest-neighbors, and logistic regression. As a metric for assessing the classifiers, accuracy (Acc) and area under the curve (AUC) are used. The grid search technique is used to identify the best combination of parameters of the classifiers with the highest Acc and AUC. Finally, the best result is the logistic regression classifier.

Place, publisher, year, edition, pages
2023. Vol. 20, p. 1095-1098, article id 155793
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:bth-25533ISBN: 9786589159049 (print)OAI: oai:DiVA.org:bth-25533DiVA, id: diva2:1808801
Conference
XX SBSR Brazilian Symposium on Remote Sensing, Florianopolis, 2-5 april, 2023
Available from: 2023-11-01 Created: 2023-11-01 Last updated: 2023-11-01Bibliographically approved

Open Access in DiVA

fulltext(951 kB)104 downloads
File information
File name FULLTEXT01.pdfFile size 951 kBChecksum SHA-512
1148c83bc43b4b3a4bf0dbce331809b828ba19a46cbcc82c040e49d78d90b6b61aed6302e209c4b5b3f400b7dc1c45cac36943e0ab9f3d03b74374cd1400fd2d
Type fulltextMimetype application/pdf

Authority records

Palm, Bruna

Search in DiVA

By author/editor
Palm, Bruna
By organisation
Department of Mathematics and Natural Sciences
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 104 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 344 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf