Scholarlink

<p>Modern neuroscience and ecology are increasingly adopting machine learning (ML) methods to automate the tracking and classification of animal behaviour. These techniques are particularly valuable for quantifying fitness-related behaviours such as hunting in invasive predators. Here, we evaluate the effectiveness of two ML tools, DeepLabCut for pose estimation and SimBA for random-forest behaviour classification, at distinguishing four behaviours in the invasive lionfishes (<i>Pterois volitans</i> and <i>P. miles</i>): hovering, resting, hunting, and swimming, and benchmark the ML outputs against annotations from trained human observers. Lionfish were selected for their large ecological impact on invaded reefs, where quantifying behaviours directly informs management. We also introduce a customized, user-friendly feature-extraction script tailored to lionfish. The script converts landmark coordinates extracted by DeepLabCut into a comprehensive set of kinematic metrics (e.g., body-angle variance, fin-beat frequency), essential for behaviour classification. A companion GitHub guide further clarifies which specific metrics are most informative under different behavioural scenarios. To our knowledge, this is the first study to explore how a wide-angle camera lens influences the DeepLabCut–SimBA workflow. Behavioural trials, conducted in controlled aquarium settings, showed that the models classified high-motion behaviours (hunting and swimming) with high precision and recall, likely owing to distinctive kinematic signatures. In contrast, low-motion behaviours such as hovering and resting were harder to detect because of subtle movement cues, suboptimal body orientation, and distortions introduced by the wide-angle camera. While demonstrated on lionfish, the workflow generalizes to other mid-bodied fishes and supports management and conservation via large-scale video screening for target behaviours.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Applying machine learning tools for automated behaviour classification in invasive lionfish and comparison with human observations

  • 期刊论文

  • 发表日期：

    2026年2月16日

查看全文
  • Amirreza Khodaparast-Kelidbari,
  • Katelyn T. Moffat,
  • Iris M. George,
  • Nicola S. Smith

摘要

Modern neuroscience and ecology are increasingly adopting machine learning (ML) methods to automate the tracking and classification of animal behaviour. These techniques are particularly valuable for quantifying fitness-related behaviours such as hunting in invasive predators. Here, we evaluate the effectiveness of two ML tools, DeepLabCut for pose estimation and SimBA for random-forest behaviour classification, at distinguishing four behaviours in the invasive lionfishes (Pterois volitans and P. miles): hovering, resting, hunting, and swimming, and benchmark the ML outputs against annotations from trained human observers. Lionfish were selected for their large ecological impact on invaded reefs, where quantifying behaviours directly informs management. We also introduce a customized, user-friendly feature-extraction script tailored to lionfish. The script converts landmark coordinates extracted by DeepLabCut into a comprehensive set of kinematic metrics (e.g., body-angle variance, fin-beat frequency), essential for behaviour classification. A companion GitHub guide further clarifies which specific metrics are most informative under different behavioural scenarios. To our knowledge, this is the first study to explore how a wide-angle camera lens influences the DeepLabCut–SimBA workflow. Behavioural trials, conducted in controlled aquarium settings, showed that the models classified high-motion behaviours (hunting and swimming) with high precision and recall, likely owing to distinctive kinematic signatures. In contrast, low-motion behaviours such as hovering and resting were harder to detect because of subtle movement cues, suboptimal body orientation, and distortions introduced by the wide-angle camera. While demonstrated on lionfish, the workflow generalizes to other mid-bodied fishes and supports management and conservation via large-scale video screening for target behaviours.