On automatic identification of upper-limb movements using small-sized training sets of EMG signals

被引：30

作者：

Micera, S ^{[1
]}

Sabatini, AM ^{[1
]}

Dario, P ^{[1
]}

机构：

[1] Scuola Super Sant Anna, ARTS Lab, I-56127 Pisa, Italy

来源：

MEDICAL ENGINEERING & PHYSICS | 2000年 / 22卷 / 08期

关键词：

EMG signal processing; artificial neural networks; fuzzy logic; upper limb biomechanics;

D O I：

10.1016/S1350-4533(00)00069-2

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

We evaluate the performance of a variety of neural and fuzzy networks for discrimination among three planar arm-pointing movements by means of electromyographic (EMG) signals, when learning is based on small-sized training sees. The aim of this work is to underline the importance that the sparse data problem has in designing pattern classifiers with good generalisation properties. The results indicate that one of the proposed fuzzy networks is more robust than the other classifiers when working with small training sets. (C) 2001 IPEM. Published by Elsevier Science Ltd. All rights reserved.

引用

页码：527 / 533

页数：7

共 15 条

[1] A METHOD FOR FUZZY RULES EXTRACTION DIRECTLY FROM NUMERICAL DATA AND ITS APPLICATION TO PATTERN-CLASSIFICATION [J].