Development of a Novel Post-processing Algorithm for Myoelectric Pattern Classification
Development of a Novel Post-processing Algorithm for Myoelectric Pattern Classification
复制标题
一种新型肌电模式分类后处理算法的开发
DOI：
10.11239/jsmbe.53.217
复制
发表时间：
2015
影响因子：
--
通讯作者：
粕谷昌宏，加藤龍，横井浩史
中科院分区：
文献类型：
--
作者：
Makizako H;Shimada H;Doi T;Tsutsumimoto K;Hotta R;Nakakubo S;Makino K;Lee S.;粕谷昌宏，加藤龍，横井浩史
本文介绍了一种新的后处理算法的肌电图（EMG）模式分类，用于肌电假手。截肢者难以控制多个自由度，但具有多个自由度的假手越来越多。一般来说，类别数量的增加会降低分类精度。在以往的研究中，人工神经网络已被用于肌电信号模式分类。所提出的后处理算法存储从EMG模式分类算法的分类的时间序列，并运行基于序列模式的第二分类。我们比较了后处理步骤之前和之后的输出精度。在我们的实验中，我们将EMG模式分类算法的训练时间设置为每个类别1 s，并使用三个通道的表面EMG信号。我们选择了7类和9类肌电模式，每隔10 - 20 ms记录一次输出。7类分类器的分类准确率提高了11.5%，9类分类器的分类准确率提高了17.7%。所提出的系统的总体准确率为82.5%，为9类和92.9%，为7类。该方法具有足够高的分类精度和其他特征（肌电通道数量少、训练时间短），适合于假手的实际应用。
This paper describes a novel post-processing algorithm for electromyographic (EMG) pattern classification, for use with myoelectric prosthetic hands. Amputees have difficulties controlling multiple degrees of freedom, but there is an increasing number of prosthetic hands with multiple degrees of freedom. Generally, an increasing number of classes decreases the classification accuracy. Artificial neural networks have been used for EMG pattern classification in previous studies. The proposed post-processing algorithm stores the temporal sequence of classifications from the EMG pattern classification algorithm, and runs a second classification based on the sequential patterns. We compared the accuracy of the output before and after the post-processing step. In our experiment, we set the training time of the EMG pattern classification algorithm to 1 s for each class, and used three channels of surface EMG signals. We selected 7 and 9 classes of EMG patterns, and recorded the output every 10-20ms. The classification accuracy improved by 11.5% with 7 classes, and 17.7% with 9 classes. The overall accuracy of the proposed system was 82.5% for 9 classes and 92.9% for 7 classes. With the adequately high classification accuracy and other features (small number of EMG channels and short training time), the proposed method is potentially suitable for practical use with prosthetic hands.