基于费希尔信息量的轻量化无线感知研究

Research on lightweight wireless sensing based on Fisher information

基于深度网络的无线感知技术需要巨大的计算资源与存储资源,这导致其难以部署在资源有限的无线设备上。针对上述问题,提出使用费希尔信息量来度量感知网络中的冗余并进行裁减。为了验证上述方法的有效性,设计了无线手势识别实验,实验结果表明,提出的方法可在无线手势识别性能下降不超过4%的条件下将网络中的参数量和浮点运算量分别裁减93.2%和94.5%,从而能在资源有限的无线设备上轻量化地实现无线感知。

Wireless sensing technology based on deep network requires huge computing and storage resources,which make it difficult to deploy on wireless devices with limited resources.In order to solve the above problem,this paper proposes using Fisher information to measure the redundancy in wireless sensing network and reduce it.In order to verify the effectiveness of the above method,this paper designs wireless gesture recognition experiment,and the experimental results show that the proposed method can reduce the amount of parameters and floating point operations in the network by 93.2%and 94.5%,respectively,under the condition that the performance of wireless gesture recognition decreases by no more than 4%,so that the wireless sensing can be realized lightweight on wireless devices with limited resources.