Deep generative models with data augmentation to learn robust representations of movement intention for powered leg prostheses.
Deep generative models with data augmentation to learn robust representations of movement intention for powered leg prostheses.
复制标题
DOI：
10.1109/tmrb.2019.2952148
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Hargrove, Levi
中科院分区：
文献类型：
--
作者：
Hu, Blair;Simon, Ann M.;Hargrove, Levi
意图识别是一种数据驱动的替代方案，可替代专家制定的规则，用于触发动力假肢的预编程活动模式之间的转换。在运动完成之前检测到的来自假肢传感器的运动相关信号用于预测即将进行的活动。通常，由每个活动的标记示例组成的训练数据是必要的；然而，从截肢者群体中收集足够大且丰富的训练数据集的过程非常繁琐。此外，如果分类器学习到的运动意图表示不够稳健，协变量偏移可能会对控制器的预测准确性产生不利影响。我们的目标是开发和评估使用数据增强和深度神经网络学习运动意图的稳健表示的技术。在对每三天从四名截肢受试者收集的数据进行离线分析时，我们证明了我们的方法产生了真实的合成传感器数据，有助于降低在不同日期和不同用户进行训练和测试时的错误率。我们的新颖方法引入了一种有效且可推广的策略来增强可穿戴机器人传感器数据，挑战了一种现有的观念，即康复机器人只能从通常需要更多数据的最先进的深度学习技术中获得有限的好处。
Intent recognition is a data-driven alternative to expert-crafted rules for triggering transitions between pre-programmed activity modes of a powered leg prosthesis. Movement-related signals from prosthesis sensors detected prior to movement completion are used to predict the upcoming activity. Usually, training data comprised of labeled examples of each activity are necessary; however, the process of collecting a sufficiently large and rich training dataset from an amputee population is tedious. In addition, covariate shift can have detrimental effects on a controller’s prediction accuracy if the classifier’s learned representation of movement intention is not robust enough. Our objective was to develop and evaluate techniques to learn robust representations of movement intention using data augmentation and deep neural networks. In an offline analysis of data collected from four amputee subjects across three days each, we demonstrate that our approach produced realistic synthetic sensor data that helped reduce error rates when training and testing on different days and different users. Our novel approach introduces an effective and generalizable strategy for augmenting wearable robotics sensor data, challenging a pre-existing notion that rehabilitation robotics can only derive limited benefit from state-of-the-art deep learning techniques typically requiring more vast amounts of data.
登录
查看更多内容
DOI：
10.3390/s17092020
发表时间：
2017-09-04
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Liu M;Zhang F;Huang HH
通讯作者：
Huang HH
DOI：
10.1109/tnsre.2016.2613020
发表时间：
2017-08
期刊：
IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society
影响因子：
--
作者：
Simon AM;Ingraham KA;Spanias JA;Young AJ;Finucane SB;Halsne EG;Hargrove LJ
通讯作者：
Hargrove LJ
DOI：
10.18178/ijmlc.2018.8.5.724
发表时间：
2018-10-01
期刊：
International journal of machine learning and computing
影响因子：
--
作者：
Li, Longze;Vakanski, Aleksandar
通讯作者：
Vakanski, Aleksandar
DOI：
10.1109/tbme.2011.2161671
发表时间：
2011-10
期刊：
IEEE transactions on bio-medical engineering
影响因子：
--
作者：
Huang H;Zhang F;Hargrove LJ;Dou Z;Rogers DR;Englehart KB
通讯作者：
Englehart KB
影响因子：
4
作者：
Spanias JA;Simon AM;Finucane SB;Perreault EJ;Hargrove LJ
通讯作者：
Hargrove LJ