Deep Learning for Deep Waters: An ...
Type de document :
Article dans une revue scientifique: Article original
DOI :
Titre :
Deep Learning for Deep Waters: An Expert-in-the-Loop Machine Learning Framework for Marine Sciences
Auteur(s) :
Ryazanov, Igor [Auteur]
Göteborgs Universitet = University of Gothenburg [GU]
Nylund, Amanda [Auteur]
Department of Mechanics and Maritime Sciences, Chalmers University of Technology
Basu, Debabrota [Auteur]
Scool [Scool]
Göteborgs Universitet = University of Gothenburg [GU]
Hassellöv, Ida-Maja [Auteur]
Department of Mechanics and Maritime Sciences, Chalmers University of Technology
Schliep, Alexander [Auteur]
Göteborgs Universitet = University of Gothenburg [GU]
Göteborgs Universitet = University of Gothenburg [GU]
Nylund, Amanda [Auteur]
Department of Mechanics and Maritime Sciences, Chalmers University of Technology
Basu, Debabrota [Auteur]
Scool [Scool]
Göteborgs Universitet = University of Gothenburg [GU]
Hassellöv, Ida-Maja [Auteur]
Department of Mechanics and Maritime Sciences, Chalmers University of Technology
Schliep, Alexander [Auteur]
Göteborgs Universitet = University of Gothenburg [GU]
Titre de la revue :
Journal of Marine Science and Engineering
Pagination :
169
Éditeur :
MDPI
Date de publication :
2021-02
ISSN :
2077-1312
Mot(s)-clé(s) en anglais :
machine learning
marine sciences
deep learning
expert-in-the-loop
turbulent ship wake
environmental impact of shipping
marine sciences
deep learning
expert-in-the-loop
turbulent ship wake
environmental impact of shipping
Discipline(s) HAL :
Sciences de l'environnement/Ingénierie de l'environnement
Informatique [cs]/Apprentissage [cs.LG]
Informatique [cs]/Son [cs.SD]
Planète et Univers [physics]/Sciences de la Terre/Océanographie
Informatique [cs]/Apprentissage [cs.LG]
Informatique [cs]/Son [cs.SD]
Planète et Univers [physics]/Sciences de la Terre/Océanographie
Résumé en anglais : [en]
Driven by the unprecedented availability of data, machine learning has become a pervasive and transformative technology across industry and science. Its importance to marine science has been codified as one goal of the UN ...
Lire la suite >Driven by the unprecedented availability of data, machine learning has become a pervasive and transformative technology across industry and science. Its importance to marine science has been codified as one goal of the UN Ocean Decade. While increasing amounts of, for example, acoustic marine data are collected for research and monitoring purposes, and machine learning methods can achieve automatic processing and analysis of acoustic data, they require large training datasets annotated or labelled by experts. Consequently, addressing the relative scarcity of labelled data is, besides increasing data analysis and processing capacities, one of the main thrust areas. One approach to address label scarcity is the expert-in-the-loop approach which allows analysis of limited and unbalanced data efficiently. Its advantages are demonstrated with our novel deep learning-based expert-in-the-loop framework for automatic detection of turbulent wake signatures in echo sounder data. Using machine learning algorithms, such as the one presented in this study, greatly increases the capacity to analyse large amounts of acoustic data. It would be a first step in realising the full potential of the increasing amount of acoustic data in marine sciences.Lire moins >
Lire la suite >Driven by the unprecedented availability of data, machine learning has become a pervasive and transformative technology across industry and science. Its importance to marine science has been codified as one goal of the UN Ocean Decade. While increasing amounts of, for example, acoustic marine data are collected for research and monitoring purposes, and machine learning methods can achieve automatic processing and analysis of acoustic data, they require large training datasets annotated or labelled by experts. Consequently, addressing the relative scarcity of labelled data is, besides increasing data analysis and processing capacities, one of the main thrust areas. One approach to address label scarcity is the expert-in-the-loop approach which allows analysis of limited and unbalanced data efficiently. Its advantages are demonstrated with our novel deep learning-based expert-in-the-loop framework for automatic detection of turbulent wake signatures in echo sounder data. Using machine learning algorithms, such as the one presented in this study, greatly increases the capacity to analyse large amounts of acoustic data. It would be a first step in realising the full potential of the increasing amount of acoustic data in marine sciences.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Fichiers
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- jmse-09-00169.pdf
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- jmse-09-00169.pdf
- Accès libre
- Accéder au document