A hidden Markov model-based stride segmentation technique applied to equine inertial sensor trunk movement data
A hidden Markov model-based stride segmentation technique applied to equine inertial sensor trunk movement data
复制标题
DOI：
10.1016/j.jbiomech.2007.08.004
复制
发表时间：
2008-01-01
影响因子：
2.4
通讯作者：
Wilson, Alan
中科院分区：
文献类型：
--
作者：
Pfau, Thilo;Ferrari, Marta;Wilson, Alan
惯性传感器现在足够小和轻，可以用于收集人类和动物的大型数据集。然而，这些大型数据集的处理需要一定程度的自动化来实现现实的工作负载。隐马尔可夫模型（HHMM）是广泛使用的随机模式识别工具，可以对非平稳数据进行分类。本文采用HISTORY方法对安装在躯干上的六自由度惯性传感器采集的纯种赛马的步态数据进行识别和步幅分割，将7匹马的混合步态序列数据集细分为训练集、交叉验证集和独立测试集。创建手动奔马步幅分割并用于训练以及用于评估交叉验证和测试集性能。在测试集上，91%的步幅被准确地检测到位于+/- 40 ms（
Inertial sensors are now sufficiently small and lightweight to be used for the collection of large datasets of both humans and animals. However, processing of these large datasets requires a certain degree of automation to achieve realistic workloads.Hidden Markov models (HMMs) are widely used stochastic pattern recognition tools and enable classification of non-stationary data. Here we apply HMMs to identify and segment into strides, data collected from a trunk-mounted six degrees of freedom inertial sensor in galloping Thoroughbred racehorses.A data set comprising mixed gait sequences from seven horses was subdivided into training, cross-validation and independent test set. Manual gallop stride segmentations were created and used for training as well as for evaluating cross-validation and test set performance. On the test set, 91% of the strides were accurately detected to lie within +/- 40 ms (