scholarly journals Sequential Geometric Approach for Device-Free Localization with Outlier Link Rejection

2015 ◽  
Vol 2015 ◽  
pp. 1-8 ◽  
Author(s):  
Wendong Xiao ◽  
Biao Song
Keyword(s):  
Error Detection ◽  
Clustering Algorithm ◽  
Target Location ◽  
Geometric Approach ◽  
Wireless Channel ◽  
Location Estimation ◽  
Wireless Transmitters ◽  
Localization Accuracy ◽  
Radio Tomographic Imaging ◽  
Device Free

Device-free localization (DFL) is an emerging technique for estimating the location of the target that does not attach any electronic equipment. Wireless devices are needed to perform as transmitters or receivers. The location of the target is estimated by detecting the changes of the received signal strength (RSS) measurements of the wireless links formed by wireless transmitters and receivers. Due to the uncertainty of the wireless channel, certain links may be polluted seriously, resulting in error detection. In this paper, we propose a novel sequential geometric approach with outlier link rejection (SGOLR) for DFL. It consists of three sequential strategies, including (1) affected link identification by differential RSS detection; (2) outlier link rejection via clustering algorithm by intersection of link (IoL) calculation from the affected links; and (3) density based IoL selection and target location estimation from the remained IoLs. Experimental results show that SGOLR is robust to the fluctuation of the wireless signals with superior localization accuracy compared with the existing Radio Tomographic Imaging (RTI) approach.

scholarly journals Device-Free Localization and Identification Using Sub-GHz Passive Radio Mapping

2020 ◽  
Vol 10 (18) ◽  
pp. 6183
Author(s):  
Stijn Denis ◽  
Abdil Kaya ◽  
Rafael Berkvens ◽  
Maarten Weyn
Keyword(s):  
Target Location ◽  
The Other ◽  
Identification Accuracy ◽  
Body Type ◽  
Localization Accuracy ◽  
Rf Communication ◽  
Distance Minimization ◽  
Rudimentary Form ◽  
Device Free ◽  
The Impact

The research domain of device-free localization (DFL) is centered on the study of localization techniques which do not require targets to wear any kind of device. Passive radio mapping or passive fingerprinting is an example of a training-based DFL technique which uses the impact of a human target on radio frequency (RF) communication between stationary nodes to perform localization. We describe a set of experiments performed in a 42 m2 empty office environment in which we installed a RF network with nodes communicating on the 433 MHz and 868 MHz bands. We attempted to locate a single stationary human target based solely on signal strength measurements and did so for six different participants using two different fingerprinting methods. One method was based on Euclidean distance minimization while the other made use of a naive Bayesian classifier. We investigated the impact of frequency band, number of nodes and target body type on localization accuracy. Results indicated that a root mean square error of 48 cm could be obtained with only four nodes, provided that the data from both frequency bands was combined. Additionally, we investigated the potential of these fingerprinting approaches to distinguish between targets based on body type and perform a rudimentary form of passive identification. Accuracy rates for identification could vary significantly depending on target location, with results ranging from 0.07 to 0.75 in the exact same environment. However, the experiment participant with the lowest height and weight could be distinguished from the other participants in over 90% of cases.

DAFI

2021 ◽  
Vol 5 (4) ◽  
pp. 1-21
Author(s):  
Hang Li ◽  
Xi Chen ◽  
Ju Wang ◽  
Di Wu ◽  
Xue Liu
Keyword(s):  
Indoor Localization ◽  
Domain Adaptation ◽  
Target Domain ◽  
Localization Accuracy ◽  
Source Domain ◽  
Fine Grained ◽  
Time Signals ◽  
Environmental Variations ◽  
Device Free ◽  
Localization Approach

WiFi-based Device-free Passive (DfP) indoor localization systems liberate their users from carrying dedicated sensors or smartphones, and thus provide a non-intrusive and pleasant experience. Although existing fingerprint-based systems achieve sub-meter-level localization accuracy by training location classifiers/regressors on WiFi signal fingerprints, they are usually vulnerable to small variations in an environment. A daily change, e.g., displacement of a chair, may cause a big inconsistency between the recorded fingerprints and the real-time signals, leading to significant localization errors. In this paper, we introduce a Domain Adaptation WiFi (DAFI) localization approach to address the problem. DAFI formulates this fingerprint inconsistency issue as a domain adaptation problem, where the original environment is the source domain and the changed environment is the target domain. Directly applying existing domain adaptation methods to our specific problem is challenging, since it is generally hard to distinguish the variations in the different WiFi domains (i.e., signal changes caused by different environmental variations). DAFI embraces the following techniques to tackle this challenge. 1) DAFI aligns both marginal and conditional distributions of features in different domains. 2) Inside the target domain, DAFI squeezes the marginal distribution of every class to be more concentrated at its center. 3) Between two domains, DAFI conducts fine-grained alignment by forcing every target-domain class to better align with its source-domain counterpart. By doing these, DAFI outperforms the state of the art by up to 14.2% in real-world experiments.

An Accurate, Robust and Low Dimensionality Deep Learning Localization Approach in DM-MIMO Systems Based on RSS

2021 ◽  
Author(s):  
Seyedeh Samira Moosavi ◽  
Paul Fortier
Keyword(s):  
Massive Mimo ◽  
Clustering Algorithm ◽  
Mean Squared Error ◽  
Mimo Systems ◽  
Principal Component ◽  
Base Station ◽  
Location Estimation ◽  
Similar Data ◽  
High Coverage ◽  
Single Antenna

Abstract Currently, localization in distributed massive MIMO (DM-MIMO) systems based on the fingerprinting (FP) approach has attracted great interest. However, this method suffers from severe multipath and signal degradation such that its accuracy is deteriorated in complex propagation environments, which results in variable received signal strength (RSS). Therefore, providing robust and accurate localization is the goal of this work. In this paper, we propose an FP-based approach to improve the accuracy of localization by reducing the noise and the dimensions of the RSS data. In the proposed approach, the fingerprints rely solely on the RSS from the single-antenna MT collected at each of the receive antenna elements of the massive MIMO base station. After creating a radio map, principal component analysis (PCA) is performed to reduce the noise and redundancy. PCA reduces the data dimension which leads to the selection of the appropriate antennas and reduces complexity. A clustering algorithm based on K-means and affinity propagation clustering (APC) is employed to divide the whole area into several regions which improves positioning precision and reduces complexity and latency. Finally, in order to have high precise localization estimation, all similar data in each cluster are modeled using a well-designed deep neural network (DNN) regression. Simulation results show that the proposed scheme improves positioning accuracy significantly. This approach has high coverage and improves average root-mean-squared error (RMSE) performance to a few meters, which is expected in 5G and beyond networks. Consequently, it also proves the superiority of the proposed method over the previous location estimation schemes.

scholarly journals Deep Learning for Fingerprint Localization in Indoor and Outdoor Environments

2020 ◽  
Vol 9 (4) ◽  
pp. 267 ◽  
Author(s):  
Da Li ◽  
Yingke Lei ◽  
Xin Li ◽  
Haichuan Zhang
Keyword(s):  
Magnetic Field ◽  
Deep Learning ◽  
Clustering Algorithm ◽  
Fingerprint Image ◽  
Density Peak ◽  
Localization Accuracy ◽  
Localization System ◽  
Outdoor Environments ◽  
Indoor And Outdoor Environments ◽  
Indoor And Outdoor

Wi-Fi and magnetic field fingerprinting-based localization have gained increased attention owing to their satisfactory accuracy and global availability. The common signal-based fingerprint localization deteriorates due to well-known signal fluctuations. In this paper, we proposed a Wi-Fi and magnetic field-based localization system based on deep learning. Owing to the low discernibility of magnetic field strength (MFS) in large areas, the unsupervised learning density peak clustering algorithm based on the comparison distance (CDPC) algorithm is first used to pick up several center points of MFS as the geotagged features to assist localization. Considering the state-of-the-art application of deep learning in image classification, we design a location fingerprint image using Wi-Fi and magnetic field fingerprints for localization. Localization is casted in a proposed deep residual network (Resnet) that is capable of learning key features from a massive fingerprint image database. To further enhance localization accuracy, by leveraging the prior information of the pre-trained Resnet coarse localizer, an MLP-based transfer learning fine localizer is introduced to fine-tune the coarse localizer. Additionally, we dynamically adjusted the learning rate (LR) and adopted several data enhancement methods to increase the robustness of our localization system. Experimental results show that the proposed system leads to satisfactory localization performance both in indoor and outdoor environments.

scholarly journals Research on RSS Data Optimization and DFL Localization for Non-Empty Environments

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4419
Author(s):  
Wenyu Mao ◽  
Rongxuan Shen ◽  
Ke Wang ◽  
Guoliang Gong ◽  
Yi Xiao ◽  
...  
Keyword(s):  
Target Location ◽  
Learning Model ◽  
Random Disturbance ◽  
Wavelet Filtering ◽  
Localization Accuracy ◽  
Generalization Ability ◽  
Localization Model ◽  
Random Disturbances ◽  
Shadowing Effect ◽  
A New Technique

Device-free localization (DFL) is a new technique which can estimate the target location through analyzing the shadowing effect on surrounding radio frequency (RF) links. In a relatively complex environment, the influences of random disturbance and the multipath effect are more serious. There are kinds of noises and disturbances in the received signal strength (RSS) data of RF links and the data itself can even be distorted, which will seriously affect the DFL accuracy. Most of the common filtering methods adopted in DFL field are not targeted and the filtering effects are unstable. This paper researches the characteristics of RSS data with random disturbances and proposes two-dimensional double correlation (TDDC) distributed wavelet filtering. It can filter out the random disturbances and noise while preserving the RSS fluctuations which are helpful for the DFL, thus improving the quality of RSS data and localization accuracy. Furthermore, RSS variation rules for the links are different in complex environments and hence, it is difficult for the collected training samples to cover all possible patterns. Therefore, a single machine learning model with poor generalization ability finds it difficult to achieve ideal localization results. In this paper, the Adaboost.M2 ensemble learning model based on the Gini decision tree (GDTE) is proposed to improve the generalization ability for unknown patterns. Extensive experiments performed in two different drawing rooms demonstrate that the TDDC distributed wavelet filtering and the GDTE localization model have obvious advantages compared with other methods. The localization accuracy rates of 87% and 95% can be achieved respectively in the two environments.

scholarly journals Compressive Sensing Based Radio Tomographic Imaging with Spatial Diversity

Sensors ◽  
2019 ◽  
Vol 19 (3) ◽  
pp. 439 ◽  
Author(s):  
Shengxin Xu ◽  
Heng Liu ◽  
Fei Gao ◽  
Zhenghuan Wang
Keyword(s):  
Multipath Fading ◽  
Spatial Diversity ◽  
Tomographic Imaging ◽  
Link Quality ◽  
Small Scale ◽  
Reconstruction Method ◽  
Indoor Environments ◽  
Localization Accuracy ◽  
Measurement Variation ◽  
Radio Tomographic Imaging

Radio tomographic imaging (RTI) has emerged as a promising device-free localization technology for locating the targets with no devices attached. RTI deduces the location information from the reconstructed attenuation image characterizing target-induced spatial loss of radio frequency measurements in the sensing area. In cluttered indoor environments, RF measurements of wireless links are corrupted by multipath effects and thus less robust to achieve a high localization accuracy for RTI. This paper proposes to improve the quality of measurements by using spatial diversity. The key insight is that, with multiple antennae equipped, due to small-scale multipath fading, RF measurement variation of each antenna pair behaves differently. Therefore, spatial diversity can provide more reliable and strong measurements in terms of link quality. Moreover, to estimate the location from the image more precisely and make the image more identifiable, we propose using a new reconstruction regularization linearly combining the sparsity and correlation inherent in the image. The proposed reconstruction method can remarkably reduce the image noise and enhance the imaging accuracy especially in the case of a few available measurements. Indoor experimental results demonstrate that compared to existing RTI improvement methods, our RTI solution can reduce the root-mean-square localization error at least 47% while also improving the imaging performance.

scholarly journals Wideband Channel Modeling for mm-Wave inside Trains for 5G-Related Applications

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Juan Moreno García-Loygorri ◽  
César Briso-Rodríguez ◽  
Israel Arnedo ◽  
César Calvo ◽  
Miguel A. G. Laso ◽  
...  
Keyword(s):  
Clustering Algorithm ◽  
Path Loss ◽  
Channel Modeling ◽  
Wireless Channel ◽  
Full Description ◽  
Model Parameters ◽  
Time Of Arrival ◽  
Traffic Demand ◽  
Automatic Clustering ◽  
Wideband Channel

Passenger trains and especially metro trains have been identified as one of the key scenarios for 5G deployments. The wireless channel inside a train car is reported in the frequency range between 26.5 GHz and 40 GHz. These bands have received a lot of interest for high-density scenarios with a high-traffic demand, two of the most relevant aspects of a 5G network. In this paper we provide a full description of the wideband channel estimating Power-Delay Profiles (PDP), Saleh-Valenzuela model parameters, time-of-arrival (TOA) ranging, and path-loss results. Moreover, the performance of an automatic clustering algorithm is evaluated. The results show a remarkable degree of coherence and general conclusions are obtained.

Sign in / Sign up

Export Citation Format

Share Document