• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>2016 International Conference on Advanced Robotics and Mechatronics >Comparisons on different sEMG-features with dimension-reduction methods in hand motion recognition
【24h】

Comparisons on different sEMG-features with dimension-reduction methods in hand motion recognition

机译：降维方法在手运动识别中不同sEMG特征的比较

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Hand motion recognition based on surface electromyography (sEMG) has drawn much attention over last decades. Generally, sEMG can be non-invasively measured on the skin, and then different stable features directly relating to hand motion are extracted from the preprocessed sEMG. In order to improve computational efficiency, some dimension-reduction methods, such as PCA, LDA, are always employed to reduce the high-dimensional sEMG-features into a proper low-dimensional space. Afterwards, hand motions can be classified by a trained classification model. The proper sEMG-features and dimension-reduced data are keys for accurately identifying hand motions. This paper provides performance comparisons on different features combining with different dimension-reduction methods.
机译：在过去的几十年中，基于表面肌电图（sEMG）的手势识别已经引起了广泛的关注。通常，可以在皮肤上无创地测量sEMG，然后从预处理的sEMG中提取与手部动作直接相关的不同稳定特征。为了提高计算效率，总是采用某些降维方法（例如PCA，LDA）将高维sEMG特征还原为适当的低维空间。之后，可以通过训练的分类模型对手势进行分类。正确的sEMG功能和降维数据是准确识别手部动作的关键。本文结合不同的降维方法对不同功能进行了性能比较。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号