A Wi-Fi-Based Passive Indoor Positioning System via Entropy-Enhanced Deployment of Wi-Fi Sniffers

Abstract

This study presents a Wi-Fi-based passive indoor positioning system (IPS) that does not require active collaboration from the user or additional interfaces on the device-under-test (DUT). To maximise the accuracy of the IPS, the optimal deployment of Wi-Fi Sniffers in the area of interest is crucial. A modified Genetic Algorithm (GA) with an entropy-enhanced objective function is proposed to optimize the deployment. These Wi-Fi Sniffers are used to scan and collect the DUT’s Wi-Fi received signal strength indicators (RSSIs) as Wi-Fi fingerprints, which are then mapped to reference points (RPs) in the physical world. The positioning algorithm utilises a weighted k-nearest neighbourhood (WKNN) method. Automated data collection of RSSI on each RP is achieved using a surveying robot for the Wi-Fi 2.4 GHz and 5 GHz bands. The preliminary results show that using only 20 Wi-Fi Sniffers as features for model training, the offline positioning accuracy is 2.2 m in terms of root mean squared error (RMSE). A proof-of-concept real-time online passive IPS is implemented to show that it is possible to detect the online presence of DUTs and obtain their RSSIs as online fingerprints to estimate their position.

Free device location independent WiFi‐based localisation using received signal strength indicator and channel state information

“…where H represents the transpose operation, Hl and ∠Hl are the amplitude and phase of the l-th subcarrier respectively. Generally, the continuous raw CSI data of the l-th subcarrier is collected, and the length of sliding time window is set as m given by Equation (7).…”

“…The interest in RSSI-based localisation has significantly increased among academic and industrial communities due to the convenience of obtaining RSSI from any commercial WiFi device without requiring additional hardware or devices [8]. In addition, the utilisation of CSI and RSS for localisation has become promising due to the MIMO enhancement of WiFi, which is obtained from the medium access control and physical layers of WiFi networks [7].…”

“…The primary objective of WiFi‐based localisation is to discern the spatial coordinates of human subjects by leveraging variations in the propagation of WiFi signals, which is influenced by various physical phenomena, including absorption, scattering, diffraction, and reflection, as the signals propagate through the environment. These mechanisms and characteristics of the wireless signals are used to estimate the position of the human subject relative to one or more reference points in the indoor or outdoor environment [7]. The interest in RSSI‐based localisation has significantly increased among academic and industrial communities due to the convenience of obtaining RSSI from any commercial WiFi device without requiring additional hardware or devices [8].…”

A Review: Current Trend of Immersive Technologies for Indoor Navigation and the Algorithms

“…Various technologies can be utilized for indoor positioning, including but not limited to Wi-Fi (Chan et al, 2023), Bluetooth (Babakhani et al, 2021), radio frequency identification (Chumkamon et al, 2008), ZigBee (Dong et al, 2018), ultra-wideband (Sarkar et al, 2021), and a geomagnetic field (Yeh et al, 2020). These technologies require specific equipment, resulting in a high implementation cost.…”

A Pseudo-Satellite Fingerprint Localization Method Based on Discriminative Deep Belief Networks

“…In some complex indoor environments, such as airport terminals, sports stadiums, shopping malls, supermarkets, libraries, and underground car parks, high-precision location services are essential for personnel management and vehicle navigation. Therefore, indoor positioning technology has become a focal point for research both domestically and internationally [2,3]. Currently, indoor positioning techniques mainly include 5G positioning [4,5], Wi-Fi fingerprint Remote Sens.…”