Integrated Statistical Test of Signal Distributions and Access Point Contributions for Wi-Fi Indoor Localization
Integrated Statistical Test of Signal Distributions and Access Point Contributions for Wi-Fi Indoor Localization
复制标题
DOI：
10.1109/tevc.2021.3085906
复制
发表时间：
2021-05-01
影响因子：
6.8
通讯作者：
He, Wei
中科院分区：
文献类型：
--
作者：
Zhou, Mu;Li, Yaohua;He, Wei
随着Wi-Fi网络的广泛部署，基于接收信号强度（RSS）的Wi-Fi室内定位引起了学术界和工业界的广泛兴趣。目前，大多数当前可用的Wi-Fi室内定位技术集中于提高定位精度。然而，由于室内环境的复杂性，Wi-Fi信号分布的多样性和RSS值的测量误差影响了室内定位系统的鲁棒性。因此，为了解决这一问题，我们设计了一种新的混合假设检验，基于渐近相对效率（ARE）的想法，通过考虑不同的接入点（AP）对Wi-Fi室内定位精度的贡献来利用信号分布。具体而言，首先使用Jarque-Bera（JB）检验对每个参考点（RP）处的Wi-Fi信号分布进行正态性检验，然后应用卡方自动交互检测（CHAID）方法来获得每个AP贡献度。其次，在JB检验对Wi-Fi信号分布的评估的基础上，应用混合Mann-Whitney U和T检验来找到与每个新收集的RSS数据相对应的匹配RP集合。最后，通过使用K-最近邻（KNN）获得目标位置估计，其中每个AP的贡献度被分配为计算过程中的权重，以找到匹配的RP。从大量的实验结果，很明显，所提出的方法可以成功地提高系统的性能，通过实现更高的定位精度和增强的鲁棒性相比，最先进的Wi-Fi室内定位技术。
With the broad deployment of Wi-Fi networks, the Received Signal Strength (RSS) based Wi-Fi indoor localization has attained much interest of both academia and industry. At present, most of the currently available Wi-Fi indoor localization techniques focus on increasing the localization accuracy. However, few of them take into account the diversity of Wi-Fi signal distributions and the measurement error associated with RSS values owing to the complicated indoor environment, which consequently results in the low robustness of indoor localization systems. Thus, with the motivation to tackle this gripping problem, we design a new hybrid hypothesis test based on the idea of Asymptotic Relative Efficiency (ARE), which exploits signal distributions by considering different Access Point (AP) contributions to the Wi-Fi indoor localization accuracy. In concrete terms, first of all, the Jarque-Bera (JB) test is used to perform the normality test on the Wi-Fi signal distribution at each Reference Point (RP), and then the Chi-squared Automatic Interaction Detection (CHAID) approach is applied to obtain each AP contribution degree. Secondly, based on the evaluation of the JB test on the Wi-Fi signal distribution, the hybrid Mann-Whitney U and T test is applied to find the set of matching RPs corresponding to each newly-collected RSS data. Finally, the target location estimate is acquired by using the K-Nearest Neighbor (KNN), where the contribution degree of each AP is assigned as the weight during the calculation to find matching RPs. From the extensive experimental results, it is evident that the proposed approach can successfully improve the system performance by achieving a higher localization accuracy and enhanced robustness when compared with the state-of-the-art Wi-Fi indoor localization techniques.