Improved Localization Accuracy Using Machine Learning: Predicting and Refining RSS Measurements

Nguyen, Cam Ly; Georgiou, Orestis; Suppakitpaisarn, Vorapong

doi:10.1109/glocomw.2018.8644270

Cited by 14 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model successfully characterises the propagation environment and accurately describes the loss of signal strength as the signal travels in the test bed environment. The research findings align with the conclusions published byNguyen et al (2018) in their work titled "Improved Localization Accuracy Using Machine Learning: Predicting and Refining RSS Measurements. "CONCLUSIONThe findings of this research hold significant implications for the deployment of an ad hoc WLAN operating at 2.5 GHz within the University of Benin main campus.…”

supporting

confidence: 83%

Pathloss Prediction Model in Wlan Propagation

Ayidu,

Elaigwu

2023

FJS

View full text Add to dashboard Cite

Pathloss propagation in urban, suburban, and rural environments has a significant impact on wireless communication networks. Different propagation models have been developed for network locations. The different terrains are unique in their topological features and environmental factors. Therefore, a propagation model suitable for one terrain may not be suitable for another propagation environment for pathloss prediction. This paper proposes a signal prediction model with an 802.11 b/g wireless local area network (WLAN) infrastructure at 2.4 GHz. The models are backed by extensive received signal strength (RSS) measurements acquired from a free space of the primary field data at the University of Benin, Benin City, Nigeria. The study considered distance based on the received signal strength of an ad hoc network for the development of a propagation model at various distances. The collected data were analysed, and a propagation model for the network terrain was developed from the log normal shadowing model. Graphical comparisons between the average RSS value and the predicted RSS value dependent on the distance were demonstrated to reflect that the proposed model can be used to predict RSS in the given propagation environment. Consequently, the utilization of this model can significantly enhance network planning activities by accurately estimating RSS values, aiding in the identification of optimal access point placement, ensuring seamless coverage, and mitigating potential coverage gaps. The findings of this research offer valuable insights for network engineers and provide a solid foundation for optimizing wireless communication within this unique network environment.

show abstract

supporting

confidence: 83%

Pathloss Prediction Model in Wlan Propagation

Ayidu,

Elaigwu

2023

FJS

View full text Add to dashboard Cite

show abstract

“…It can be inferred from the procedure described above that the performance of the GPR-based RSSI localization algorithm is highly dependent on the accuracy of the covariance matrix model given in eq. (12), which in turn is fundamentally determined by the parameter vector θ. In other words, a core step of the method is to optimally determine θ, given a certain amount of training data.…”

Section: B Location Estimation Via Gprmentioning

confidence: 99%

“…Besides (and partially thanks to) the recent popularity of ML approaches, an increasing trend is to operate with RSSI only, which has the advantage of not requiring the embedding into wireless signals information tailored to the positioning application itself, leading to added flexibility that enables the design of multi-functional systems [10]. Two excellent examples are the work in [11], in which multi-target RSSI localization over a discrete grid is initially estimated via a sparse dictionary updating and a K-means clustering and later refined via dictionary updates; the work in [12], where ML is used to refine the RSSI data itself; and the scheme of [13], where the location of multiple targets are obtained from RSSI values based on a Gaussian process regression (GPR) method.…”

Section: Introductionmentioning

confidence: 99%

Robust Received Signal Strength Indicator (RSSI)-Based Multitarget Localization via Gaussian Process Regression

Führling,

Rou,

de Abreu

et al. 2023

J. Ind. Sea. Pos. Nav.

View full text Add to dashboard Cite

We consider the robust localization, via Gaussian process regression (GPR), of multiple transmitters/targets based on received signal strength indicator (RSSI) data collected by fixed sensors distributed in the environment. For such a scenario and approach, we contribute both with a novel noise robust procedure to train the parameters of the GPR model, which is achieved via a mini-batch stochastic gradient descent (SGD) scheme with gradients given in closed form, and with a pair of corresponding robust marginalization procedures for the estimation of target locations. Simulation results validate the contributions by showing that the proposed methods significantly outperform the best related state-of-the-art (SotA) alternative and approach the performance of a genieaided (GA) scheme.

show abstract

“…This is known as the jamming attack in wireless networks. Jamming is one of the worst attacks due to being easy to launch and hard to detect [11][12][13]. Wireless sensor networks consist of an enormous number of nodes.…”

Section: Introductionmentioning

confidence: 99%

Received Power Based Unmanned Aerial Vehicles (UAVs) Jamming Detection and Nodes Classification Using Machine Learning

Aldosari¹

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

This paper presents a machine-learning method for detecting jamming UAVs and classifying nodes during jamming attacks on Wireless Sensor Networks (WSNs). Jamming is a type of Denial of Service (DoS) attack and intentional interference where a malicious node transmits a high-power signal to increase noise on the receiver side to disrupt the communication channel and reduce performance significantly. To defend and prevent such attacks, the first step is to detect them. The current detection approaches use centralized techniques to detect jamming, where each node collects information and forwards it to the base station. As a result, overhead and communication costs increased. In this work, we present a jamming attack and classify nodes into different categories based on their location to the jammer by employing a single node observer. As a result, we introduced a machine learning model that uses distance ratios and power received as features to detect such attacks. Furthermore, we considered several types of jammers transmitting at different power levels to evaluate the proposed metrics using MATLAB. With a detection accuracy of 99.7% for the k-nearest neighbors (KNN) algorithm and average testing accuracy of 99.9%, the presented solution is capable of efficiently and accurately detecting jamming attacks in wireless sensor networks.

show abstract

Improved Localization Accuracy Using Machine Learning: Predicting and Refining RSS Measurements

Cited by 14 publications

References 15 publications

Pathloss Prediction Model in Wlan Propagation

Pathloss Prediction Model in Wlan Propagation

Robust Received Signal Strength Indicator (RSSI)-Based Multitarget Localization via Gaussian Process Regression

Received Power Based Unmanned Aerial Vehicles (UAVs) Jamming Detection and Nodes Classification Using Machine Learning

Contact Info

Product

Resources

About