An investigation of preprocessing filters and deep learning methods for vessel type classification with underwater acoustic data

Página do item simplificado
dc.contributor.authorDOMINGOS, L. C. F.
dc.contributor.authorPaulo Santos
dc.contributor.authorSKELTON, P. S. M.
dc.contributor.authorBRINKWORTH, R. S. A.
dc.contributor.authorSAMMUT, K.
dc.contributor.authorOrcidhttps://orcid.org/0000-0001-8484-0354
dc.date.accessioned2022-12-01T06:03:19Z
dc.date.available2022-12-01T06:03:19Z
dc.date.issued2022-01-05
dc.description.abstractAuthorThe illegal exploitation of protected marine environments has consistently threatened the biodiversity and economic development of coastal regions. Extensive monitoring in these – often remote – areas is challenging. Machine learning methods are useful in object detection and classification tasks and have the potential to underpin techniques for the development of robust monitoring systems to overcome this problem. However, development is hindered due to the limited number of publicly available labelled and curated datasets. Furthermore, there are relatively few open-source state-of-the-art methods to be used for evaluation. This paper presents an investigation of automated classification methods using underwater acoustic signals to infer the presence and type of vessels navigating in coastal regions. Various combinations of deep convolutional neural network architectures, and preprocessing filter layers, were evaluated using a new dataset based on a subset of the extensive open-source Ocean Networks Canada hydrophone data. Tests were conducted in which VGGNet and ResNet networks were applied to classify the input data. The data was preprocessed using either Constant Q Transform (CQT), Gammatone, Mel spectrogram, or a combination of these filters. With over 97% accuracy, using all three preprocessing representations simultaneously yielded the most reliable result. However, high accuracies of 94.95% were achieved using CQT as the preprocessing filter for a ResNet-based convolutional neural network, providing a trade-off between model complexity and accuracy; a result that is more than 10% higher than previously reported approaches. This more accurate classifier for underwater acoustics could be used as a reliable autonomous monitoring system in maritime environments.
dc.identifier.citationDOMINGOS, L. C. F.; SANTOS, P. E.; SKELTON, P. S. M.; BRINKWORTH, R. S. A.; SAMMUT, K. An investigation of preprocessing filters and deep learning methods for vessel type classification with underwater acoustic data. IEEE Access, v. 4, p. 1, 2022.
dc.identifier.doi10.1109/ACCESS.2022.3220265
dc.identifier.issn2169-3536
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/4648
dc.relation.ispartofIEEE Access
dc.rightsAcesso Aberto
dc.rights.licenseCreative Commons "Este é um artigo publicado em acesso aberto sob uma licença Creative commons (CC BY 4.0). Fonte:https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85141602836&origin=inward. Acesso em 08 dez. 2022.
dc.subject.otherlanguageAcoustics
dc.subject.otherlanguageDeep learning
dc.subject.otherlanguagedeep learning
dc.subject.otherlanguagehydrophones
dc.subject.otherlanguagemarine environment
dc.subject.otherlanguageMarine equipment
dc.subject.otherlanguageship type
dc.subject.otherlanguageSonar equipment
dc.subject.otherlanguagesound
dc.subject.otherlanguageSpectrogram
dc.subject.otherlanguageSurveillance
dc.subject.otherlanguageTime-frequency analysis
dc.subject.otherlanguageUnderwater acoustics
dc.titleAn investigation of preprocessing filters and deep learning methods for vessel type classification with underwater acoustic data
dc.typeArtigo
fei.scopus.citations2
fei.scopus.eid2-s2.0-85141602836
fei.scopus.subjectCoastal regions
fei.scopus.subjectDeep learning
fei.scopus.subjectMarine environment
fei.scopus.subjectMonitoring system
fei.scopus.subjectShip type
fei.scopus.subjectSonar equipment
fei.scopus.subjectSpectrograms
fei.scopus.subjectSurveillance
fei.scopus.subjectTime-frequency Analysis
fei.scopus.updated2024-07-01
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85141602836&origin=inward
Arquivos
Pacote Original
Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
Santo_pdf
Tamanho:
3.05 MB
Formato:
Adobe Portable Document Format
Baixar
Coleções
Artigos