Highly accurate classification of postures and activities by a shoe-based monitor through classification with rejection.
Highly accurate classification of postures and activities by a shoe-based monitor through classification with rejection.
复制标题
基于鞋子的监视器通过拒绝分类对姿势和活动进行高度准确的分类。
DOI：
10.1109/embc.2012.6346499
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Sazonov,EdwardS
中科院分区：
文献类型：
--
作者：
Tang,Wenlong;Sazonov,EdwardS
监测人类的主要日常活动对许多生物医学研究都很重要。一些监控应用可能需要高度可靠地识别某些姿势和活动，其期望的准确度远高于99%标记。本文提出了一种方法，用于执行高度准确的分类的姿势和活动的数据收集的可穿戴鞋监测器（SmartShoe）通过分类拒绝。在这项研究中使用的分类器是支持向量机，它使用后验概率的基础上的距离的观察分离超平面拒绝不可靠的意见。结果表明，与之前报道的准确度相比，拒绝后分类准确度显着提高（从95.2% ± 3.5%提高到99% ± 1%）。这样的方法将是特别有益的应用程序中，需要高精度的识别，而不是所有的观察需要分配一个类标签。
Monitoring human beings' major daily activities is important for many biomedical studies. Some monitoring applications may require highly reliable identification of certain postures and activities with desired accuracies well above 99% mark. This paper suggests a method for performing highly accurate classification of postures and activities from data collected by a wearable shoe monitor (SmartShoe) through classification with rejection. The classifier used in this study is support vector machines that uses posterior probability based on the distance of an observation to the separating hyperplane to reject unreliable observations. The results show that a significant improvement (from 95.2% ± 3.5% to 99% ± 1%) of the classification accuracy has been reached after the rejection, as compared to the accuracy reported previously. Such an approach will be especially beneficial in application where high accuracy of recognition is desired while not all observations need to be assigned a class label.