Abstract
Direction finding and positioning systems based on RF signals are significantly impacted by multipath propagation, particularly in indoor environments. Existing algorithms (e.g MUSIC) perform poorly in resolving Angle of Arrival (AoA) in the presence of multipath or when operating in a weak signal regime. We note that digitally sampled RF frontends allow for the easy analysis of signals, and their delayed components. Low-cost Software-Defined Radio (SDR) modules enable Channel State Information (CSI) extraction across a wide spectrum, motivating the design of an enhanced AoA solution. We propose a Deep Learning approach for deriving AoA from a single snapshot of the SDR multichannel data. We compare
and contrast deep-learning based angle classification and regression models, to estimate up to two AoAs accurately. We have implemented the inference engines on different platforms to extract AoAs in real-time, demonstrating the computational tractability of our approach. To demonstrate the utility of our approach we have collected IQ (In-phase and Quadrature components) samples from a four-element Universal Linear Array (ULA) in various Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) environments, and published the dataset. Our proposed method demonstrates excellent reliability in determining number of impinging signals and realized mean absolute AoA errors less than 2◦.
and contrast deep-learning based angle classification and regression models, to estimate up to two AoAs accurately. We have implemented the inference engines on different platforms to extract AoAs in real-time, demonstrating the computational tractability of our approach. To demonstrate the utility of our approach we have collected IQ (In-phase and Quadrature components) samples from a four-element Universal Linear Array (ULA) in various Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) environments, and published the dataset. Our proposed method demonstrates excellent reliability in determining number of impinging signals and realized mean absolute AoA errors less than 2◦.
Original language | English |
---|---|
Pages (from-to) | 3164-3176 |
Number of pages | 13 |
Journal | IEEE Access |
Volume | 10 |
Early online date | 4 Jan 2022 |
DOIs | |
Publication status | Published - 4 Jan 2022 |
Bibliographical note
Copyright: This work is licensed under a Creative Commons Attribution-Non-Commercial-No Derivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/Funding: This work was supported by the National Institute of Standards and Technology (NIST) via the Pervasive, Accurate, and Reliable Location-based Services for Emergency Responders under Grant 70NANB17H185.
Keywords
- Co-variance matrices
- Multiple signal classification
- Deep learning
- Signal to noise ratio
- Training
- Support vector machines
- Software radio