基于随机配置网络的轻量级人体行为识别模型
作者:
作者单位:

中国矿业大学

作者简介:

通讯作者:

中图分类号:

TP391.4

基金项目:

国家自然科学基金面上项目(61973306); 江苏省自然科学基金优秀青年项目(BK20200086).


A lightweight model for human activity recognition using stochastic configuration networks
Author:
Affiliation:

China University of Mining and Technology

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对基于智能手机的人体行为识别研究中智能手机CPU和存储等资源有限问题, 本文提出基于流形正则化和QR分解的轻量级随机配置网络人体行为识别模型. 首先利用流形正则化解决输入数据被随机映射到SCNs隐含层空间后出现难以预测的非线性分布问题, 以提升模型结构的轻量性. 其次利用QR分解降低输出权值的计算复杂度, 进一步提高模型建模过程的轻量性. 最后基于2种真实的人体行为识别数据集, 评估了所提模型在模型识别精度和轻量性方面的有效性. 实验结果表明, 与SCNs、CNN等相比, 本文所提模型对于人体行为识别问题不仅可以提高识别的精度, 还能有效降低输出权值计算复杂度和提高模型结构的紧致性.

    Abstract:

    Aiming at the problem of limited resources such as smartphone CPU and storage in the research of smartphone-based human activity recognition, this paper proposes a lightweight stochastic configuration network human activity recognition model based on manifold regularization and QR decomposition. Firstly, Manifold Regularization is used to solve the problem of unpredictable nonlinear distribution after the input data are randomly mapped to the hidden layer space of SCNs, so as to improve the lightweight of the model structure. Secondly, QR decomposition is used to reduce the computational complexity of the output weights and further improve the lightweight of the model modeling process. Finally, based on two real human activity data sets, the effectiveness of the proposed model in model recognition accuracy and lightweight is evaluated. Experimental results show that, compared with SCNs, CNN, etc. the proposed model can not only improve the accuracy of activity recognition, but also effectively reduce the calculation complexity of output weights and improve the compactness of the model structure.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-10-14
  • 最后修改日期:2022-01-24
  • 录用日期:2022-01-28
  • 在线发布日期: 2022-03-01
  • 出版日期: