Fingerprinting-Based Indoor Localization With Commercial MMWave WiFi: A Deep Learning Approach

Abstract

Existing fingerprint-based indoor localization uses either fine-grained channel state information (CSI) from the physical layer or coarse-grained received signal strength indicator (RSSI) measurements. In this paper, we propose to use a mid-grained intermediate-level channel measurement-spatial beam signal-to-noise ratios (SNRs) that are inherently available and defined in the IEEE 802.11ad/ay standardsto construct the fingerprinting database. These intermediate channel measurements are further utilized by a deep learning approach for multiple purposes: 1) location-only classification; 2) simultaneous locationand-orientation classification; and 3) direct coordinate estimation. Furthermore, the effectiveness of the framework is thoroughly validated by an in-house experimental platform consisting of 3 access points using commercial-off-the-shelf millimeter-wave WiFi routers. The results show a 100% accuracy if the location is only interested, about 99% for simultaneous location-and-orientations classification, and an averaged root mean-square error (RMSE) of 11.1 cm and an average median error of 9.5 cm for direct coordinate estimate, greater than 2-fold improvements over the RMSE of 28.7 cm and median error of 23.6 cm for RSSI-like single SNR-based localization.

CSI2Image: Image Reconstruction From Channel State Information Using Generative Adversarial Networks

“…Several studies have already shown the possibility of extracting physical space information from radio waves using wireless sensing. This has been applied for various purposes, including device localization [3]- [7], [22]- [29], device-free user localization [8], [9], [23], [30]- [32], gesture recognition [10], [11], [33], [34], device-free motion tracking [12], [35], [36], RF imaging [37]- [39], crowdedness estimation [40], activity recognition [13], [14], respiratory monitoring [15], [41], heart rate monitoring [41], material sensing [16], [42], soil sensing [17], keystroke recognition [18], emotion recognition [19], in-body device localization [43], object state change detection [20], touch sensing [44], device proximity detection [45], device orientation tracking [46], and human detection through walls [38], [47], [48]. While these studies have explored new possibilities using an application-specific approach, the present work is unique in that it attempts to construct a general-purpose wireless sensing technique.…”

Indoor Large-Scale MIMO-Based RSSI Localization with Low-Complexity RFID Infrastructure

“…Another direction to enhance RSSI localization is to use pattern matching and fingerprinting based methods for reducing the influence of range measurement errors [ 17 , 19 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 37 , 38 , 39 , 40 , 41 ]. The LANDMARC indoor localization system is presented in [ 22 ] as a pattern matching method to enhance the overall accuracy of locating objects using some reference tags.…”

“…Even fingerprint methods offer higher accuracy and better robustness, they require more cost in the facility and more complexity, which does not meet IoT expectations [ 4 ]. The work in [ 41 ] proposes to use mid-grained intermediate-level channel measurements that are provided by the IEEE 802.11ad/ay standards to construct the fingerprinting database.…”

An Accurate and Real-Time Commercial Indoor Localization System in LTE Networks

“…For UE localization scene, localization methods running in Google Maps, Amap or other navigation applications (Apps), are mainly initiated by UE. With the authorization of UE, the localization module in these Apps can access various data, such as Global Navigation Satellite Systems (GNSS) data [9], motion sensor data [10], image sensor data [12], [12], Wi-Fi data [13]- [15] and Base Station signal data [16]- [19], to provide high-accuracy location services for UEs, and the location accuracy is usually better than 5 meters. However, CSP MDT Localization Scene is different.…”