An investigation of preprocessing filters and deep learning methods for vessel type classification with underwater acoustic data
dc.contributor.author | DOMINGOS, L. C. F. | |
dc.contributor.author | Paulo Santos | |
dc.contributor.author | SKELTON, P. S. M. | |
dc.contributor.author | BRINKWORTH, R. S. A. | |
dc.contributor.author | SAMMUT, K. | |
dc.contributor.authorOrcid | https://orcid.org/0000-0001-8484-0354 | |
dc.date.accessioned | 2022-12-01T06:03:19Z | |
dc.date.available | 2022-12-01T06:03:19Z | |
dc.date.issued | 2022-01-05 | |
dc.description.abstract | AuthorThe 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.citation | DOMINGOS, 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.doi | 10.1109/ACCESS.2022.3220265 | |
dc.identifier.issn | 2169-3536 | |
dc.identifier.uri | https://repositorio.fei.edu.br/handle/FEI/4648 | |
dc.relation.ispartof | IEEE Access | |
dc.rights | Acesso Aberto | |
dc.rights.license | Creative 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.otherlanguage | Acoustics | |
dc.subject.otherlanguage | Deep learning | |
dc.subject.otherlanguage | deep learning | |
dc.subject.otherlanguage | hydrophones | |
dc.subject.otherlanguage | marine environment | |
dc.subject.otherlanguage | Marine equipment | |
dc.subject.otherlanguage | ship type | |
dc.subject.otherlanguage | Sonar equipment | |
dc.subject.otherlanguage | sound | |
dc.subject.otherlanguage | Spectrogram | |
dc.subject.otherlanguage | Surveillance | |
dc.subject.otherlanguage | Time-frequency analysis | |
dc.subject.otherlanguage | Underwater acoustics | |
dc.title | An investigation of preprocessing filters and deep learning methods for vessel type classification with underwater acoustic data | |
dc.type | Artigo | |
fei.scopus.citations | 2 | |
fei.scopus.eid | 2-s2.0-85141602836 | |
fei.scopus.subject | Coastal regions | |
fei.scopus.subject | Deep learning | |
fei.scopus.subject | Marine environment | |
fei.scopus.subject | Monitoring system | |
fei.scopus.subject | Ship type | |
fei.scopus.subject | Sonar equipment | |
fei.scopus.subject | Spectrograms | |
fei.scopus.subject | Surveillance | |
fei.scopus.subject | Time-frequency Analysis | |
fei.scopus.updated | 2024-07-01 | |
fei.scopus.url | https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85141602836&origin=inward |
Arquivos
Pacote Original
1 - 1 de 1