[1]马永连*,张登银.基于域自适应网络的跨场景摔倒检测算法研究[J].计算机技术与发展,2023,33(10):86-92.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 014]
　MA Yong-lian*,ZHANG Deng-yin.Cross-scene Fall Detection Algorithm Based on Domain Adaptive Network[J].,2023,33(10):86-92.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 014]

点击复制

基于域自适应网络的跨场景摔倒检测算法研究()

分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

33

期数:

2023年10期

页码:

86-92

栏目:

人工智能

出版日期:

2023-10-10

文章信息/Info

Title:

Cross-scene Fall Detection Algorithm Based on Domain Adaptive Network

文章编号:

1673-629X(2023)10-0086-07

作者:

马永连* ; 张登银

南京邮电大学 物联网学院,江苏 南京 210023

Author(s):

MA Yong-lian* ; ZHANG Deng-yin

School of Internet of Things,Nanjing University of Posts and Telecommunications,Nanjing 210023,China

关键词:

信道状态信息; 摔倒检测; 域自适应网络; 迁移学习; 多核最大均值差异

Keywords:

channel state information; fall detection; domain adaptive network; transfer learning; MK-MMD

分类号:

TP393

DOI:

10. 3969 / j. issn. 1673-629X. 2023. 10. 014

摘要:

目前,基于信道状态信息( Channel State Information,CSI) 的室内摔倒检测( Fall Detection,FD) 系统已被证明拥有巨大潜力,但是,不同室内布局带来的多径效应的差异往往使其无法实现跨场景使用。 因此,该文提出了 DA-Fall( Domain-adaptive Fall) ,通过结合两种自适应策略的域自适应方法来改进未标记噪声信号的泛化,从而提高对目标域的检测精度。在提出的摔倒检测系统中,引入了域鉴别器和域混淆自适应层来进行对抗性训练。 首先,该算法通过引入依赖于相对值的相对鉴别器来优化对抗训练, 从而更好地反映域间差异。 其次, 将基于多核架构的最大均值差异 ( Multiple KernelMaximum Mean Difference,MK-MMD) 作为域对抗损失的正则化项,进一步减小域间的边缘分布距离。 实验分析表明,DA-Fall 取得了比 WiFall,RT-Fall,SignGAN 更好的效果,在原场景与新场景中分别达到了 96. 83% 和 91. 03% 的检测精度。

Abstract:

Indoor Fall Detection ( FD) systems based on Channel State Information ( CSI) have been proved to have great potential,butthe difference in multipath effects?

caused by different indoor layouts often makes it impossible to achieve cross-scene use. Therefore,wepropose DA-Fall ( Domain-Adaptive Fall) ,which combines?

the domain adaptive methods of two adaptive strategies to improve the generalization of unlabeled noise signals, thereby improving the detection accuracy of the target domain. In the proposed fall detectionsystem,a domain discriminator and a domain confusion adaptive layer are introduced for adversarial training. Firstly,?

such algorith　moptimizes adversarial training by introducing a relative discriminator that depends on relative values,so as to better reflect the differencesbetween domains. Secondly,　the Multiple Kernel Maximum Mean Difference ( MK-MMD) based on multi-core architecture is used asthe regularization term of domain adversarial loss to further reduce the edge distribution distance between domains. Experiments show that　DA-Fall achieves better results than Wi-Fall,RT-Fall,

Sign-GAN and other systems. The detection accuracy of 96. 83% and 91. 03%was achieved in the original scene and the new scene, respectively.

常用功能