Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machines
Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machines
复制标题
DOI：
10.1016/j.applanim.2009.03.005
复制
发表时间：
2009-06-01
影响因子：
2.3
通讯作者：
Mononen, Jaakko
中科院分区：
文献类型：
--
作者：
Martiskainen, Paula;Jarvinen, Mikko;Mononen, Jaakko
自动化动物行为监测系统对于研究和动物生产管理目的越来越有吸引力。然而，许多现有系统适合于一次仅测量一个或两个行为模式或活动状态。我们的目的是开发和试点的方法，自动测量和识别奶牛的几种行为模式，使用三维加速度计和多类支持向量机（SVM）。基于9个特征构建SVM分类模型。使用30头奶牛的行为进行观察来训练模型，这些奶牛配备了一个颈环，该颈环带有一个记录水平、垂直和横向加速度的加速度计。测量的行为模式包括站立、躺下、反刍、进食、正常和跛行行走、躺下和站立。使用准确度、灵敏度、精密度和kappa指标评价模型性能。支持向量机分类模型实现了站立（80%灵敏度，65%准确率）、躺卧（80%，83%）、反刍（75%，86%）、进食（75%，81%）、正常行走（79%，79%）和跛行（65%，66%）的合理识别。躺下（0%，0%）和站立（71%，29%）的结果较差。多类模型的总体性能为78%的精度，kappa值为0.69。每个行为类别都有一个或两个其他的行为模式，这些行为模式最容易与它们混淆。有问题的行为是指那些在运动方面彼此相似的行为。对分类中存在的问题提出了可能的解决办法。总之，加速度计可用于轻松识别奶牛的各种行为模式。支持向量机被证明是有用的分类测量的行为模式。然而，需要进一步的工作，以完善分类模型中使用的功能，以获得最佳的分类性能。此外，还需要考虑加速度数据的质量，以改进结果。(C)2009 Elsevier B.V.保留所有权利。
Automated animal behaviour monitoring systems have become increasingly appealing for research and animal production management purposes. However, many existing systems are suited to measure only one or two behaviour patterns or activity states at a time. We aimed to develop and pilot a method for automatically measuring and recognising several behavioural patterns of dairy cows using a three-dimensional accelerometer and a multi-class support vector machine (SVM). SVM classification models were constructed based on nine features. The models were trained using observations made of the behaviour of 30 cows fitted with a neck collar bearing an accelerometer that recorded horizontal, vertical and lateral acceleration. Measured behaviour patterns included standing, lying, ruminating, feeding, normal and lame walking, lying down, and standing up. Accuracy, sensitivity, precision, and kappa measures were used to evaluate the model performance. The SVM classification models achieved a reasonable recognition of standing (80% sensitivity, 65% precision), lying (80%, 83%), ruminating (75%, 86%), feeding (75%, 81%), walking normally (79%,79%), and lame walking (65%,66%). The results were poor for lying down (0%, 0%) and standing up (71%, 29%). The overall performance of the multi-class model was 78% precision with a kappa value of 0.69. Each of the behaviour categories had one or two other behaviour patterns that became confused with them the most. The problematic behaviours were expectedly those that resemble each other in terms of movement. Possible solutions for the problems in classification are presented. In conclusion, accelerometers can be used to easily recognise various behaviour patterns in dairy cows. Support vector machines proved useful in classification of measured behaviour patterns. However, further work is needed to refine the features used in the classification models in order to gain the best possible classification performance. Also the quality of acceleration data needs to be considered to improve the results. (C) 2009 Elsevier B.V. All rights reserved.