DFPhaseFL: a robust device-free passive fingerprinting wireless localization system using CSI phase information
DFPhaseFL: a robust device-free passive fingerprinting wireless localization system using CSI phase information
复制标题
DPhaseFL：使用 CSI 相位信息的强大的无设备被动指纹无线定位系统
DOI：
10.1007/s00521-020-04847-1
复制
发表时间：
2020
影响因子：
6
通讯作者：
Wang Shengyang
中科院分区：
文献类型：
--
作者：
Rao Xinping;Li Zhi;Yang Yanbo;Wang Shengyang
近年来，由于Wi-Fi设备的广泛部署和众多基于位置的服务需求，无设备无源无线室内定位引起了极大的兴趣。在本文中，我们提出了DFPhaseFL，第一个无设备指纹室内定位系统，纯粹使用CSI相位信息。它利用从简单的单个链路中提取的CSI相位信息来估计目标的位置，不需要目标穿戴任何电子设备，也不需要部署大量的接入点和监测设备。在DFPhaseFL中，首先通过Intel WiFi Link 5300无线网络接口卡（IWL 5300 NIC）的三个天线从CSI测量中提取原始CSI相位。然后，应用线性变换和噪声滤波来获取校准后的CSI相位。通过实验观察，我们发现校准CSI相位具有不可预测的特性随着时间的推移。因此，它不能直接用作指纹。为此，提出了一种结合深度神经网络和迁移学习的迁移深度监督神经网络方法，以获得作为指纹的同时具有可迁移性和可区分性的特征表示。然后，DFPhaseFL系统使用SVM算法在线获得目标位置的估计。实验结果表明，DFPhaseFL算法具有较好的估计精度，并且在不重新获取指纹数据库的情况下，能够长时间保持稳定的定位精度。
Device-free passive wireless indoor localization is attracting great interest in recent years due to the widespread deployment of Wi-Fi devices and the numerous location-based services requirements. In this paper, we propose DFPhaseFL, the first device-free fingerprinting indoor localization system that purely uses CSI phase information. It utilizes the CSI phase information extracted from simply a single link to estimate the location of the target, neither requiring the target to wear any electronic equipment nor deploying a large number of access points and monitor devices. In DFPhaseFL, the raw CSI phases are extracted from the CSI measurements through the three antennas of the Intel WiFi Link 5300 wireless Network Interface Card (IWL 5300 NIC) firstly. Then, linear transformation and noise filtering are applied to acquire the calibrated CSI phases. Through experimental observations, we find that the calibrated CSI phase owns an unpredictable characteristic over time. Thus, it cannot be directly applied as a fingerprint. To this end, a transfer deep supervised neural network method combining deep neural network and transfer learning is proposed to obtain feature representations with both transferability and discriminability as fingerprints. Then, the DFPhaseFL system uses the SVM algorithm to obtain the estimation of the target location online. Experiment results demonstrate that the DFPhaseFL owns a better estimation precision compared with the other state of art, and maintain a stable localization accuracy for a long time without reacquiring the fingerprint database.