Bayesian Device-Free Localization and Tracking in a Binary RF Sensor Network

Abstract

Received-signal-strength-based (RSS-based) device-free localization (DFL) is a promising technique since it is able to localize the person without attaching any electronic device. This technology requires measuring the RSS of all links in the network constituted by several radio frequency (RF) sensors. It is an energy-intensive task, especially when the RF sensors work in traditional work mode, in which the sensors directly send raw RSS measurements of all links to a base station (BS). The traditional work mode is unfavorable for the power constrained RF sensors because the amount of data delivery increases dramatically as the number of sensors grows. In this paper, we propose a binary work mode in which RF sensors send the link states instead of raw RSS measurements to the BS, which remarkably reduces the amount of data delivery. Moreover, we develop two localization methods for the binary work mode which corresponds to stationary and moving target, respectively. The first localization method is formulated based on grid-based maximum likelihood (GML), which is able to achieve global optimum with low online computational complexity. The second localization method, however, uses particle filter (PF) to track the target when constant snapshots of link stats are available. Real experiments in two different kinds of environments were conducted to evaluate the proposed methods. Experimental results show that the localization and tracking performance under the binary work mode is comparable to the those in traditional work mode while the energy efficiency improves considerably.

A Survey on Detection, Tracking and Identification in Radio Frequency-Based Device-Free Localization

“…In order to avoid this problem, several model-based tracking techniques have been proposed which do not include any imaging. Many of the approaches we will describe in the following paragraphs can be classified as ‘Bayesian DFL’ [88]. Entities are tracked directly without any intermediary imaging phase based on a model that describes the RSS-values as the result of the locations of these entities.…”

“…As can be gleaned from the name, the entire focus of this methodology was energy efficiency and they managed to obtain an energy decrease of up to 69% with meter-level multi-tracking localization accuracy when compared to implementations of the RTI, SCPL, and RASS-algorithms. Energy-efficiency was the main focus of the Bayesian DFL approach described in [88] as well. In this paper, the authors did not implement CS-based techniques, however.…”

A Novel Passive Tracking Scheme Exploiting Geometric and Intercept Theorems

“…The LOSL-based approach has received more and more attention. In Reference [ 16 ], the monitoring area in the WSNs is divided into grids, according to maps of the shadowed and non-shadowed links, and the feasible and infeasible grids are distinguished. Finally, the Bayesian grid approach is used to determine the device-free target positioning information.…”

“…Moreover, a kidnapped person or a child cannot use any wireless devices. The targets under such circumstances are defined as device-free targets, and capturing the position information of device-free targets is termed as a passive tracking problem, also known as device-free localization [ 1 , 2 , 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 ].…”

A systematic literature review of machine learning applications in IoT

“… Principal component analysis (PCA): PCA blackuces the dimension of a large collection of factors to a much smaller number that almost perfectly captures the data from the initial significant set. At the detector or cluster head level, PCA is used in IoT systems to blackuce data size 36,40 K‐means clustering: used to group or categorize various pieces of data into groups or clusters 41 .…”