On-line supervising mechanism for learning data in surface electromyogram motion classifiers
On-line supervising mechanism for learning data in surface electromyogram motion classifiers
复制标题
表面肌电运动分类器学习数据的在线监督机制
DOI：
10.1002/scj.10245
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
Y. Kakazu
中科院分区：
文献类型：
--
作者：
D. Nishikawa;Wenwei Yu;H. Yokoi;Y. Kakazu
本文提出了一种机制，监督学习数据集的分类从肌电图前臂运动。监控机制包括自动数据添加和自动数据删除过程。它还包含与我们以前的算法相同的手动数据添加。自动添加和消除过程都根据分类器输出的连续性来评估分类的成功或失败。这些过程假设一个人在一定的时间间隔内不能改变他的运动。在实验中，一个系统与监督机制嵌入分类前臂运动从两个通道的肌电图。首先，本文通过与六种设置（包括缺乏监督模式）的比较，表明所提出的机制是有效的。接下来，通过传感器移动测试验证了系统能够适应操作员特性的改变，在该测试中，我们在操作员的培训后移动一个传感器。从实验结果中，它的结论是，该机制可以调整生成的决策边界，提高分类能力，此外是能够跟踪随着时间的变化的运营商的特性。© 2002 Wiley Periodicals，Inc. Syst Comp Jpn，33（14）：1-11，2002;在线发表于Wiley InterScience（www.interscience.wiley.com）。DOI 10.1002/scj.10245
This paper proposes a mechanism that supervises the learning data set for the classification from electromyogram to forearm motion. The supervising mechanism contains automatic data addition and automatic data elimination processes. It also contains manual data addition that is the same as our former algorithm. Both the automatic addition and elimination processes evaluate success or failure of classification from the continuity of the classifier's outputs. These processes assume that a person cannot change his motion within a certain interval. In experiments, a system with the supervising mechanism embedded classifies ten forearm motions from two channels of the electromyogram. First, this paper makes it clear that the proposed mechanism is effective by comparison with six settings, including the absence of a supervising pattern. Next, it is verified that the system can adapt to alteration of the operator's characteristics by a sensor-shifting test in which we move one sensor after the operator's training. From the experimental results, it is concluded that the proposed mechanism can adjust the generated decision boundaries for improvement of classification ability, and in addition is capable of tracking the alteration of the operator's characteristics through time. © 2002 Wiley Periodicals, Inc. Syst Comp Jpn, 33(14): 1–11, 2002; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10245