Wi-Fi Mobile Single Station Localization

The utilization of Wi-Fi-based technology for pervasiveindoor user identification has gained prominence due to its cost-effective nature and compatibility with user devices. For identifyingunique users, previous works proposed capturing the media accesscontrol (MAC) address of the signal emitted from a user’s device,while information elements(IE)-based MAC de-randomization meth-ods were presented to mitigate the impairment caused by randomMAC. However, the IE types of different Wi-Fi devices are notconsistently differentiated, resulting in incorrect identification whenusing IE-based MAC de-randomization methods. In addition, forpervasively locating users, typical Wi-Fi fingerprinting approachesare constrained by the requirement of densely pre-deployed Wi-Fistations, which contradicts the principle of pervasive localization. To address these challenges, we propose the mobilesingle station-based user identification (MS.Id) technique, which leverages Wi-Fi mobile single stations for pervasiveindoor user identification. MS.Id includes mobile single station localization (MSL) and MAC de-randomization based onusers’ spatio-temporal location and IE information (DR.LIE). MSL, a highly pervasive indoor localization solution, may beimplemented on a standard mobile Wi-Fi station without the need for extensive pre-deployment stations. Additionally, acustomized neural network model has been proposed to achieve fine-grained localization accuracy. DR.LIE performs MACde-randomization using a tailor-designed algorithm, named the spatio-temporal location, IE information and clustering-based (LIC) algorithm, to identify users with random MAC addresses. Comprehensive experiments are conducted toevaluate the performance of the proposed MS.Id. Experimental results demonstrate that MS.Id outperforms previous IE-based user identification methods and multi-station localization techniques.