A Data-Driven Approach to Localization for High Frequency Wireless Mobile Networks

Comiter, Marcus; Crouse, Michael B.; Kung, H. T.

doi:10.1109/glocom.2017.8254732

Cited by 16 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comiter et al [55] proposed a data-driven localization approach for narrow beam alignment for mmWave networks. According to real experiments, their methods achieve sub-meter localization accuracy (median squared error) both indoors (0.33-0.37 m) and outdoors (0.76 m).…”

Section: Advances In Positioning Aided By Machine Learningmentioning

confidence: 99%

Positioning in 5G and 6G Networks—A Survey

Mogyorósi

Revisnyei

Pašić

et al. 2022

Sensors

View full text Add to dashboard Cite

Determining the position of ourselves or our assets has always been important to humans. Technology has helped us, from sextants to outdoor global positioning systems, but real-time indoor positioning has been a challenge. Among the various solutions, network-based positioning became an option with the arrival of 5G mobile networks. The new radio technologies, minimized end-to-end latency, specialized control protocols, and booming computation capacities at the network edge offered the opportunity to leverage the overall capabilities of the 5G network for positioning—indoors and outdoors. This paper provides an overview of network-based positioning, from the basics to advanced, state-of-the-art machine-learning-supported solutions. One of the main contributions is the detailed comparison of machine learning techniques used for network-based positioning. Since new requirements are already in place for 6G networks, our paper makes a leap towards positioning with 6G networks. In order to also highlight the practical side of the topic, application examples from different domains are presented with a special focus on industrial and vehicular scenarios.

show abstract

Section: Advances In Positioning Aided By Machine Learningmentioning

confidence: 99%

Positioning in 5G and 6G Networks—A Survey

Mogyorósi

Revisnyei

Pašić

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…For the second category, NN can be applied to estimate parameters of static MIMO channel [123,124,125] and dynamic MIMO channel [126]. A datadriven deep neural network (DNN) approach is proposed in [127] to localize mobile nodes using lower frequency spectrum, and 5G indoor sub-meter accuracy is achieved. Recently, a supervised machine learning approach based on Gaussian process regression is proposed in [128] for distributed localization in massive MIMO systems.…”

Section: Artificial Intelligence Meets 5g Localizationmentioning

confidence: 99%

A survey on 5G massive MIMO localization

Wen

Wymeersch

Peng

et al. 2019

Digital Signal Processing

114

View full text Add to dashboard Cite

show abstract

“…The most important novelty of this paper is considering the worstcase scenario, i.e., a dense indoor environment where establishing LoS links is impossible. On the other hand, due to the complexity of analytical modelling of the multi-path and path-loss effects in indoor environments, the focus has shifted to data-driven approaches such as those based on Deep Neural Networks (DNNs) [24]. Therefore, by considering the effects of multi-path and path-loss on the train dataset, one can eliminate the need for complex and precise analytical models.…”

Section: Introductionmentioning

confidence: 99%

Bluetooth Low Energy and CNN-Based Angle of Arrival Localization in Presence of Rayleigh Fading

Hajiakhondi-Meybodi

Salimibeni

Mohammadi

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Bluetooth Low Energy (BLE) is one of the key technologies empowering the Internet of Things (IoT) for indoor positioning. In this regard, Angle of Arrival (AoA) localization is one of the most reliable techniques because of its low estimation error. BLE-based AoA localization, however, is in its infancy as only recently directionfinding feature is introduced to the BLE specification. Furthermore, AoA-based approaches are prone to noise, multi-path, and path-loss effects. The paper proposes an efficient Convolutional Neural Network (CNN)-based indoor localization framework to tackle these issues specific to BLE-based settings. We consider indoor environments without presence of Line of Sight (LoS) links affected by Additive White Gaussian Noise (AWGN) with different Signal to Noise Ratios (SNRs) and Rayleigh fading channel. Moreover, by assuming a 3-D indoor environment, the destructive effect of the elevation angle of the incident signal is considered on the position estimation. The effectiveness of the proposed CNN-AoA framework is evaluated via an experimental testbed, where In-phase/Quadrature (I/Q) samples, modulated by Gaussian Frequency Shift Keying (GFSK), are collected by four BLE beacons. Simulation results corroborate effectiveness of the proposed CNN-based AoA technique to track mobile agents with high accuracy in the presence of noise and Rayleigh fading channel.

show abstract

A Data-Driven Approach to Localization for High Frequency Wireless Mobile Networks

Cited by 16 publications

References 9 publications

Positioning in 5G and 6G Networks—A Survey

Positioning in 5G and 6G Networks—A Survey

A survey on 5G massive MIMO localization

Bluetooth Low Energy and CNN-Based Angle of Arrival Localization in Presence of Rayleigh Fading

Contact Info

Product

Resources

About