...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Residuals Science & Technology >Optimization of Haptic Force Feature Based on Feature Weight
【24h】

Optimization of Haptic Force Feature Based on Feature Weight

机译：基于特征权重的触觉力特征优化

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this study, the dynamics feature, morphological feature, and textural feature were extracted and optimized according to the characteristic of haptic force. Subsequently, the coefficient of feature weight is calculated by importance of feature; and the feature optimization based on feature weight (FOFW) is proposed to obtain the optimized feature set (with small correlation and little redundancy). During the data analysis, the experimental results are taken from the ITCSH Gait II database; and the stability of features is investigated by calculating the intraclass correlation coefficient and coefficient of variation. The results indicated that, the accuracy of identity recognition of FOFW could be higher while the number of features was reduced significantly. It is envisioned that the optimized feature set with the weight threshold at 0.06 is suitable for identity recognition.
机译：本研究根据触觉力的特征提取并优化了动力学特征，形态特征和纹理特征。随后，根据特征的重要性计算特征权重系数;提出了基于特征权重（FOFW）的特征优化算法，以得到优化的特征集（相关性小，冗余度低）。在数据分析过程中，实验结果取自ITCSH Gait II数据库。通过计算类内相关系数和变异系数来研究特征的稳定性。结果表明，FOFW的身份识别准确率较高，而特征数量却大大减少。可以设想，权重阈值为0.06的优化特征集适用于身份识别。

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