摘要
在指纹室内定位中,构建高质量的指纹库是实现高精度定位的前提。针对建库阶段需要在每个参考点上收集足够多的信号样本,耗费大量人力与时间成本的问题,提出一种基于改进的条件深度卷积生成对抗网络的指纹库扩充方法。网络模型将参考点序号作为条件信息,得到对应参考点上的生成样本,利用最小二乘损失函数代替交叉熵损失函数,避免训练过程中容易出现的梯度消失问题。实验验证,该方法能有效增加每个参考点的样本数量,提升了卷积神经网络的训练效果,提高了小样本情况下的定位精度,均方根误差降为0.44 m,定位误差在1 m内的占比为86.98%,误差在2 m内的占比为92.72%。
In fingerprint indoor positioning,constructing a high-quality fingerprint database is a prerequisite for achieving high-precision positioning.Collecting enough signal samples at each reference point during the fingerprint dataset establishment stage usually consumes a lot of manpower and time costs,to solve this problem,this paper proposes a fingerprint database augmentation method based on an improved conditional deep convolutional generative adversarial network.The network model uses the reference point index as conditional information to generate corresponding samples for each reference point.It uses the least squares loss function instead of the cross-entropy loss function to avoid the problem of gradient disappearance that often occurs during training.Experimental results demonstrate that this method can effectively increase the sample size of each reference point,improve the training effect of the convolutional neural network and the positioning accuracy in small sample cases.The root mean square error is reduced to 0.44 meters,and the proportion of positioning errors within 1 meter is 86.98%,while that within 2 meters is 92.72%.
作者
吴雅琴
陈林
侯云峰
Wu Yaqin;Chen Lin;Hou Yunfeng(School of Mechanical Electronic and Information Engineering,China University of Mining and Technology(Beijing),Beijing 100083,China)
出处
《电子测量技术》
北大核心
2023年第24期119-126,共8页
Electronic Measurement Technology
基金
国家自然科学基金重点项目(52130409)
国家重点研发计划项目(2022YFC3004600)资助
关键词
Wi-Fi定位
信道状态信息
指纹库
生成对抗网络
卷积神经网络
Wi-Fi positioning
channel state information
fingerprint database
generative adversarial network
convolutional neural network
作者简介
吴雅琴,教授,主要研究方向为人工智能、物联网技术、信息融合。E-mail:wyqcumt@126.com;陈林,硕士研究生,主要研究方向为物联网技术。E-mail:chenlincumtb@sina.com;侯云峰,硕士研究生,主要研究方向为计算机视觉。E-mail:1762263688@qq.com
