在无脚本和无约束活动期间对震颤和运动障碍进行动态支持向量机检测。
Dynamic SVM detection of tremor and dyskinesia during unscripted and unconstrained activities.
作者信息
Cole Bryan T, Ozdemir Pinar, Nawab S Hamid
机构信息
Dept. of Electrical and Computer Engineering ECE, Boston University, Boston, MA 02215, USA.
出版信息
Annu Int Conf IEEE Eng Med Biol Soc. 2012;2012:4927-30. doi: 10.1109/EMBC.2012.6347040.
In this paper, we report an experimental comparison of dynamic support vector machines (SVMs) to dynamic neural networks (DNNs) in the context of a system for detecting dyskinesia and tremor in Parkinson's disease (PD) patients wearing accelerometer (ACC) and surface electromyographic (sEMG) sensors while performing unscripted and unconstrained activities of daily living. These results indicate that SVMs and DNNs of comparable computational complexities yield approximately identical performance levels when using an identical set of input features.
在本文中，我们报告了在一个用于检测帕金森病（PD）患者运动障碍和震颤的系统中，动态支持向量机（SVM）与动态神经网络（DNN）的实验比较。该系统中，帕金森病患者佩戴加速度计（ACC）和表面肌电图（sEMG）传感器，同时进行无脚本、无约束的日常生活活动。这些结果表明，当使用相同的输入特征集时，具有可比计算复杂度的支持向量机和神经网络产生的性能水平大致相同。
Zotero 插件