Semi-Supervised Adaptive Learning for Decoding Movement Intent from Electromyograms
Semi-Supervised Adaptive Learning for Decoding Movement Intent from Electromyograms
复制标题
DOI：
10.23919/eusipco.2019.8902698
复制
发表时间：
2019-09
期刊：
影响因子：
--
通讯作者：
H. Dantas;V. J. Mathews;D. J. Warren
中科院分区：
文献类型：
--
作者：
H. Dantas;V. J. Mathews;D. J. Warren
本文提出了一种自适应学习算法，用于使用肌电图 (EMG) 信号预测运动意图并控制假肢。自适应解码器可以长时间使用假肢系统，而无需重新训练。本文的方法采用基于神经网络的解码器，并提出了一种在操作阶段更新其参数的方法。最初，在训练阶段估计解码器参数。在正常运行期间，算法的参数基于运动模型以半监督方式更新。这里给出的结果是从单个截肢受试者身上获得的，表明本文的方法比当前最先进的技术提高了解码器的长期性能，具有统计意义。
This paper presents an adaptive learning algorithm for predicting movement intent using electromyogram (EMG) signals and controlling a prosthetic arm. The adaptive decoder enables use of the prosthetic systems for long periods of time without the necessity to retrain them. The method of this paper employs a neural network-based decoder and we present a method to update its parameters during the operation phase. Initially, the decoder parameters are estimated during a training phase. During the normal operation, the parameters of the algorithm are updated in a semi-supervised manner based on a movement model. The results presented here, obtained from a single amputee subject, suggest that the approach of this paper improves long-term performance of the decoders over the current state-of-the-art with statistical significance.