EchoBERT: A Transformer-Based Approach for Behavior Detection in Echograms

Måløy, Håkon

doi:10.1109/access.2020.3042337

Cited by 19 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• An EchoBERT (echo bidirectional encoder representation transformer) has been proposed for behavioural assessments using spatiotemporal properties from echograms, e.g., pancreas disease detection purely from abnormal behaviour patterns in the echogram data (Maloy 2020).…”

Section: Other Recent Advancesmentioning

confidence: 99%

A Review of Factors Affecting Farmed Atlantic Salmon (Salmo salar) Welfare in Australia and Beyond

Layman,

Kadar,

Lyall

et al. 2024

Preprint

View full text Add to dashboard Cite

With the increasingly global scale and scope of aquaculture, the need to match this development with improvements in fish welfare is a central societal and industry goal. We provide a comprehensive assessment of the farmed Atlantic salmon (Salmo salar) literature with targeted examples focusing on Atlantic salmon farmed in Tasmania, Australia. We synthesise insights from both small- and industry-scale perspectives, highlighting other reviews that provide discussions of particular sub-areas of farmed salmon research. We focus on recent advances and improved methods for farmed Atlantic salmon handling and management, behaviour, health issues and breeding. We also address wildlife interactions resulting from fish farming, as well as future research directions and system development. This review can serve as the basis for the development of aquaculture management guidelines that place individual fish welfare as a primary goal.

show abstract

Section: Other Recent Advancesmentioning

confidence: 99%

A Review of Factors Affecting Farmed Atlantic Salmon (Salmo salar) Welfare in Australia and Beyond

Layman,

Kadar,

Lyall

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep learning has also been applied to identification from audio recordings and sonar data, including bird and bat sounds, and even wing beats of mosquitoes (Chen, Zhao, et al, 2020; Fanioudakis et al, 2018; Mac Aodha et al, 2018; Maloy, 2020; Stowell et al, 2019). Unsurprisingly, the technology has been applied most often to bird calls, where it has been used not only to identify species, but also monitor their abundance (see Priyadarshani et al (2018) for a review).…”

Section: Applications In Ecology and Evolutionmentioning

confidence: 99%

Section: Classificationmentioning

confidence: 99%

Deep learning as a tool for ecology and evolution

et al. 2022

View full text Add to dashboard Cite

Deep learning is driving recent advances behind many everyday technologies, including speech and image recognition, natural language processing and autonomous driving. It is also gaining popularity in biology, where it has been used for automated species identification, environmental monitoring, ecological modelling, behavioural studies, DNA sequencing and population genetics and phylogenetics, among other applications. Deep learning relies on artificial neural networks for predictive modelling and excels at recognizing complex patterns. In this review we synthesize 818 studies using deep learning in the context of ecology and evolution to give a discipline‐wide perspective necessary to promote a rethinking of inference approaches in the field. We provide an introduction to machine learning and contrast it with mechanistic inference, followed by a gentle primer on deep learning. We review the applications of deep learning in ecology and evolution and discuss its limitations and efforts to overcome them. We also provide a practical primer for biologists interested in including deep learning in their toolkit and identify its possible future applications. We find that deep learning is being rapidly adopted in ecology and evolution, with 589 studies (64%) published since the beginning of 2019. Most use convolutional neural networks (496 studies) and supervised learning for image identification but also for tasks using molecular data, sounds, environmental data or video as input. More sophisticated uses of deep learning in biology are also beginning to appear. Operating within the machine learning paradigm, deep learning can be viewed as an alternative to mechanistic modelling. It has desirable properties of good performance and scaling with increasing complexity, while posing unique challenges such as sensitivity to bias in input data. We expect that rapid adoption of deep learning in ecology and evolution will continue, especially in automation of biodiversity monitoring and discovery and inference from genetic data. Increased use of unsupervised learning for discovery and visualization of clusters and gaps, simplification of multi‐step analysis pipelines, and integration of machine learning into graduate and postgraduate training are all likely in the near future.

show abstract