Clarke Thomas M, Whitmarsh Sasha K, Hounslow Jenna L, Gleiss Adrian C, Payne Nicholas L, Huveneers Charlie
College of Science and Engineering, Flinders University, Adelaide, Australia.
Centre for Sustainable Aquatic Ecosystems, Harry Butler Institute, Murdoch University, 90 South Street, Murdoch, 6150, WA, Australia.
Mov Ecol. 2021 May 24;9(1):26. doi: 10.1186/s40462-021-00248-8.
Tri-axial accelerometers have been used to remotely describe and identify in situ behaviours of a range of animals without requiring direct observations. Datasets collected from these accelerometers (i.e. acceleration, body position) are often large, requiring development of semi-automated analyses to classify behaviours. Marine fishes exhibit many "burst" behaviours with high amplitude accelerations that are difficult to interpret and differentiate. This has constrained the development of accurate automated techniques to identify different "burst" behaviours occurring naturally, where direct observations are not possible.
We trained a random forest machine learning algorithm based on 624 h of accelerometer data from six captive yellowtail kingfish during spawning periods. We identified five distinct behaviours (swim, feed, chafe, escape, and courtship), which were used to train the model based on 58 predictive variables.
Overall accuracy of the model was 94%. Classification of each behavioural class was variable; F scores ranged from 0.48 (chafe) - 0.99 (swim). The model was subsequently applied to accelerometer data from eight free-ranging kingfish, and all behaviour classes described from captive fish were predicted by the model to occur, including 19 events of courtship behaviours ranging from 3 s to 108 min in duration.
Our findings provide a novel approach of applying a supervised machine learning model on free-ranging animals, which has previously been predominantly constrained to direct observations of behaviours and not predicted from an unseen dataset. Additionally, our findings identify typically ambiguous spawning and courtship behaviours of a large pelagic fish as they naturally occur.
三轴加速度计已被用于远程描述和识别一系列动物的原位行为，而无需直接观察。从这些加速度计收集的数据集（即加速度、身体位置）通常很大，需要开发半自动分析来对行为进行分类。海洋鱼类表现出许多具有高振幅加速度的“爆发”行为，难以解释和区分。这限制了准确的自动化技术的发展，以识别自然发生的不同“爆发”行为，而在这些情况下无法进行直接观察。
我们基于六只圈养黄尾鰤在产卵期的624小时加速度计数据训练了一种随机森林机器学习算法。我们识别出五种不同的行为（游泳、进食、摩擦、逃避和求偶），并基于58个预测变量使用这些行为来训练模型。
模型的总体准确率为94%。每个行为类别的分类各不相同；F分数范围从0.48（摩擦）到0.99（游泳）。该模型随后被应用于八只自由游动的鰤鱼的加速度计数据，模型预测了圈养鱼所描述的所有行为类别都会出现，包括19次持续时间从3秒到108分钟的求偶行为。
我们的研究结果提供了一种将监督机器学习模型应用于自由放养动物的新方法，此前这种方法主要局限于对行为的直接观察，而不是从未见过的数据集进行预测。此外，我们的研究结果识别出了一种大型中上层鱼类自然发生的通常模糊的产卵和求偶行为。
