1. Animal‐borne accelerometers have been used across more than 120 species to infer biologically significant information such as energy expenditure and broad behavioural categories. While the accelerometer's high sensitivity to movement and fast response times present the unprecedented opportunity to resolve fine‐scale behaviour, leveraging this opportunity will require overcoming the challenge of developing general, automated methods to analyse the nonstationary signals generated by nonlinear processes governing erratic, impulsive movement characteristic of fine‐scale behaviour.
2. We address this issue by conceptualising fine‐scale behaviour in terms of characteristic microevents: impulsive movements producing brief (<1 s) shock signals in accelerometer data. We propose a ‘seek‐and‐learn’ approach: a novel microevent detection step first locates where shock signals occur (‘seek’) by searching for peaks in envelopes of acceleration data. Robust machine learning (‘learn’) employing meaningful features then separates microevents. We showcase the application of our method on tri‐axial accelerometer data collected on 10 free‐living meerkats Suricata suricatta for four fine‐scale foraging behaviours – searching for digging sites, one‐armed digging, two‐armed digging and head jerks during prey ingestion. Annotated videos served as groundtruth, and performance was benchmarked against that of a variety of classical machine learning approaches.
3. Microevent identification (μEvId) with eight features in a three‐node hierarchical classification scheme employing logistic regression at each node achieved a mean overall accuracy of >85% during leave‐one‐individual‐out cross‐validation, and exceeded that of the best classical machine learning approach by 8.6%. μEvId was found to be robust not only to inter‐individual variation but also to large changes in model parameters.
4. Our results show that microevents can be modelled as impulse responses of the animal body‐and‐sensor system. The microevent detection step retains only informative regions of the signal, which results in the selection of discriminative features that reflect biomechanical differences between microevents. Moving‐window‐based classical machine learning approaches lack this prefiltering step, and were found to be suboptimal for capturing the nonstationary dynamics of the recorded signals. The general, automated technique of μEvId, together with existing models that can identify broad behavioural categories, provides future studies with a powerful toolkit to exploit the full potential of accelerometers for animal behaviour recognition.

中文翻译：

---

寻求和学习：使用加速度数据和机器学习的信封自动识别动物行为中的微事件

1. 动物载加速度计已被用于120多种物种，以推断具有生物学意义的信息，例如能量消耗和广泛的行为类别。尽管加速度计对运动的高灵敏度和快速的响应时间为解决精细行为提供了前所未有的机会，但利用这一机会将需要克服开发通用的自动化方法来分析由支配不稳定，冲动运动的非线性过程产生的非平稳信号的挑战。精细行为的特征。
2. 我们通过概念化微事件的特征性微事件来解决这个问题：脉冲运动在加速度计数据中产生短暂的（<1 s）冲击信号。我们提出了一种“寻求学习”的方法：一种新颖的微事件检测步骤，首先通过搜索加速度数据包络中的峰值来定位震动信号发生的位置（“寻求”）。然后，采用有意义的功能的强大的机器学习（“学习”）将微事件分开。我们展示了我们的方法在从10个自由活动猫鼬Suricata suricatta收集的三轴加速度计数据中的应用进行四种精细的觅食行为-在猎物摄食期间搜索挖掘地点，单臂挖掘，两臂挖掘和头部抽搐。带批注的视频充当了现实，并且其性能相对于多种经典机器学习方法的性能进行了基准测试。
3. 在三节点分层分类方案中，在每个节点处采用逻辑回归的微事件识别（μEvId）具有八项功能，在留一单交叉验证中获得的平均整体准确度> 85％，超过了最佳经典标准机器学习方法减少了8.6％。人们发现，μEvId不仅对个体之间的变异具有鲁棒性，而且对模型参数的较大变化也具有鲁棒性。
4. 我们的结果表明，微事件可以建模为动物身体和传感器系统的冲激响应。微事件检测步骤仅保留信号的信息区域，从而导致选择可区分微事件之间生物力学差异的区分特征。基于移动窗口的经典机器学习方法缺少此预滤波步骤，因此对于捕获记录信号的非平稳动态而言不是最佳选择。μEvId的通用自动化技术，以及可以识别广泛行为类别的现有模型，为将来的研究提供了一个强大的工具包，以利用加速度计的全部潜力来识别动物行为。