...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Gait & posture >A topological approach for human movement classification and anticipation
【24h】

A topological approach for human movement classification and anticipation

机译：人类运动分类和预期的拓扑方法

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

The motion capture systems are increasingly used for biomedical purposes. In order to recognize and classify the movements, however whole-body movements using passive markers, generate a huge amount of data. Several works have been realized, with the main idea of using kinematic data as input for independent component analysis (ICA), or machine learning algorithms [1]. These approaches return high accuracy, but remain very sensitive to the noise and to the impact of the morphological difference between subjects. In contrast, we propose to apply a topological data analysis method, based on persistent homology [2], which captures essential features of data in a robust manner [3] that avoids these limitations, before to perform classification using machine-learning methods.
机译：None

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