Data from: Evaluation of sampling frequency, window size and sensor position for classification of sheep behaviour

Automated behavioural classification and identification through sensors has the potential to improve health and welfare of the animals. Position of a sensor, sampling frequency and window size of segmented signal data has a major impact on classification accuracy in activity recognition and energy needs for the sensor, yet, there are no studies in precision livestock farming that have evaluated effect of all these factors simultaneously. The aim of this study was to evaluate the effects of position (ear and collar), sampling frequency (8Hz, 16Hz and 32 Hz) of a tri-axial accelerometer and gyroscope sensor and window size (3s, 5s and 7s) of on the classification of important behaviours in sheep such as lying, standing and walking. Behaviours were classified using a random forest approach with forty-four feature characteristics. The best performance for walking, standing and lying classification in sheep (accuracy 95%, F-score 91-97%) was obtained using combination of 32Hz, 7s and 32Hz, 5s for both ear and collar sensors, although, results obtained with 16Hz and 7s window were comparable with accuracy of 91-93% and F-score 88-95%. Energy efficiency was best at a 7s window. This suggests that sampling at 16Hz with 7s window will offer benefits in a real-time behavioural monitoring system for sheep due to reduced energy needs.基于传感器的自动化行为分类与识别技术，有望提升畜禽的健康水平与福利状态。传感器安装位置、采样频率与分段信号数据的窗口时长，均会对活动识别的分类准确率及传感器能耗产生显著影响，但目前精准畜牧养殖（precision livestock farming）领域尚无研究同时评估这三类因素的综合效应。本研究旨在评估三轴加速度计（tri-axial accelerometer）与陀螺仪（gyroscope）传感器的安装位置（耳部与颈圈）、采样频率（8Hz、16Hz及32Hz）以及窗口时长（3s、5s与7s），对绵羊躺卧、站立与行走等核心行为的分类效果。本研究采用随机森林（random forest）算法结合44项特征指标完成行为分类任务。针对绵羊行走、站立与躺卧的分类任务，当耳部与颈圈传感器均采用32Hz采样频率搭配7s窗口时长，或32Hz采样频率搭配5s窗口时长时，可取得最优分类性能（准确率达95%，F值（F-score）区间为91%-97%）；而采用16Hz采样频率搭配7s窗口时长时所得结果与之相当，分类准确率为91%-93%，F值区间为88%-95%。窗口时长为7s时，传感器能耗表现最优。这表明，采用16Hz采样频率搭配7s窗口时长的方案，可在绵羊实时行为监测系统中兼顾性能与能耗优势，因其能有效降低传感器的能耗需求。