Neural Network Architectures for Location Estimation in the Internet of Things

@article{Ihsan2021NeuralNA,
  title={Neural Network Architectures for Location Estimation in the Internet of Things},
  author={Ullah Ihsan and Robert A. Malaney and Shihao Yan},
  journal={ICC 2021 - IEEE International Conference on Communications},
  year={2021},
  pages={1-6}
}
Artificial intelligence (AI) solutions for wireless location estimation are likely to prevail in many real-world scenarios. In this work, we demonstrate for the first time how the Cramer-Rao bound on localization accuracy can facilitate efficient neural-network solutions for wireless location estimation. In particular, we demonstrate how the number of neurons for the network can be intelligently chosen, leading to AI location solutions that are not time-consuming to run and less likely to be… Expand

Figures from this paper

References

SHOWING 1-10 OF 20 REFERENCES
Machine Learning and Location Verification in Vehicular Networks
TLDR
This work introduces a Machine Learning based LVS (ML-LVS) that can adapt itself to changing environments without knowing the channel parameters and demonstrates how this improved performance within the context of vehicular networks can outperform information-theoretic LVSs. Expand
Location Verification for Emerging Wireless Vehicular Networks
TLDR
A neural-network-based LVS (NN-LVS) is designed that can accommodate a priori unknown channel conditions and unknown threat models and shows a performance improvement of 50%, or more, relative to other LVSs under most channel conditions. Expand
Artificial Intelligence and Location Verification in Vehicular Networks
TLDR
This work addresses this critical limitation of a formal information-theoretic Location Verification System by using a Neural Network (NN) showing how such a NN based LVS is capable of efficiently functioning even when the proportions of genuine and malicious users are completely unknown a- priori. Expand
Neighbor-Aided Localization in Vehicular Networks
TLDR
This work addresses the problem of localization in vehicular ad hoc networks by employing a two-stage Bayesian filter to track the vehicle’s position and leading to a robust localization system that is able to provide useful position information even in the absence of GPS data. Expand
Feed Forward Neural Network-Based Sensor Node Localization in Internet of Things
TLDR
A comparison of centroid algorithm and feed forward neural network-based localization has been done and found that the neural network promises better results for higher localization accuracy. Expand
Vehicle localization in VANETs using data fusion and V2V communication
TLDR
This paper introduces a novel approach based on the idea of cooperative localization that incorporates different techniques of localization along with data fusion as well as vehicle-to-vehicle communication, to integrate the available data and cooperatively improve the accuracy of the localization information of the vehicles. Expand
ConFi: Convolutional Neural Networks Based Indoor Wi-Fi Localization Using Channel State Information
TLDR
The ConFi is proposed, the first convolutional neural network (CNN)-based Wi-Fi localization algorithm that addresses localization as a classification problem and addresses it with a five layer CNN that consists of three convolutionAL layers and two fully connected layers. Expand
Relative Positioning Enhancement in VANETs: A Tight Integration Approach
TLDR
A CP method is presented to improve the relative positioning between two vehicles within a VANET, fusing the available low-level Global Positioning System (GPS) data. Expand
Cooperative localization in GNSS-aided VANETs with accurate IR-UWB range measurements
TLDR
A novel 2-step CLoc fusion framework that first selects the “virtual anchor” nodes with the lowest GNSS position uncertainty to mitigate and stop the propagation of the biases, and refines localization accuracy through exhaustive fusion. Expand
Securing Wi-Fi networks with position verification: extended version
  • R. Malaney
  • Computer Science
  • Int. J. Secur. Networks
  • 2007
TLDR
This paper investigates whether Received Signal Strength measurements can identify attempts at network access by malicious nodes exterior to an authorised network perimeter and shows that by referring the residual RSS analysis to a 'claimed position', interior to the authorised perimeter, a robust position-based verification system for secure network access can be developed. Expand
...
1
2
...