Joint range extension and localization for low‐power wide‐area network

Mahfoudi, Mohamed Naoufal; Sivadoss, Gayatri; Korachi, Othmane Bensouda; Turletti, Thierry; Dabbous, Walid

doi:10.1002/itl2.120

Cited by 7 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used intermittent LoRa beacons at 0.5Hz as the vendor signal, which transmits a narrow-band signal at 868M Hz in the EU. The benefits are threefold: (1) excellent range in multipath environments; (2) highly configurable air time, transmitting power, and payload [36]; (3) free licensing in the Industrial, Scientific and Medical (ISM) band. We used KerberosSDR as the receiver for data collection thanks to its low cost and simplified synchronization steps.…”

Section: Dataset Compositionmentioning

confidence: 99%

DeepAoANet: Learning Angle of Arrival From Software Defined Radios With Deep Neural Networks

Dai

Tran

et al. 2022

IEEE Access

View full text Add to dashboard Cite

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 Angle-of-Arrival (AoA) solution. We propose a Deep Learning approach to 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 Light-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 • .

show abstract

Section: Dataset Compositionmentioning

confidence: 99%

DeepAoANet: Learning Angle of Arrival From Software Defined Radios With Deep Neural Networks

Dai

Tran

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Other work has considered diversity techniques to improve IoT technologies. In [3] Snipe is introduced, which is an IoT system deploying two antennas to coherently combine the received signals at the gateway. Spatial diversity is exploited in [4] by coherently combining weak signals of different gateways in the cloud.…”

Section: Towards Massive and Reliable Iot: The Potential Of Multiple Antenna Systemsmentioning

confidence: 99%

Experimental Exploration of Unlicensed Sub-GHz Massive MIMO for Massive Internet-of-Things

Callebaut

Gunnarsson

Guevara

et al. 2021

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

IoT networks are getting overcrowded following the vast increase in number of Internet-of-Things (IoT) devices and connections. Networks can be extended with more gateways, increasing the number of supported devices. However, as investigated in this work, massive MIMO has the potential to increase the number of simultaneous connections and moreover lower the energy expenditure of these devices. We present a study of the channel characteristics of massive MIMO in the narrowband unlicensed sub-GHz band. The goal is to support IoT applications with strict requirements in terms of number of devices, power consumption, and reliability. The assessment is based on experimental measurements using both a uniform linear and a rectangular array. Our study demonstrates and validates the advantages of deploying massive MIMO gateways to serve IoT nodes. While the results are general, here we specifically focus on static nodes. The array gain and channel hardening effect yield opportunities to lower the transmit power of IoT nodes while also increasing reliability. The exploration confirms that exploiting large arrays brings great opportunities to connect a massive number of IoT devices by separating the nodes in the spatial domain. In addition, we give an outlook on how static IoT nodes could be scheduled based on partial channel state information.

show abstract

“…As the measurements were done in summer, the presence of foliage on the trees has a non-negligible effect on the collected channels. Both the 3 Due to an unforeseen software issue, only the first 31 antennas were usable. measurement data 4 and the processing scripts 5 are available in open-source.…”

Section: Towards Massive and Reliable Iot: The Potential Of Multiple ...mentioning

confidence: 99%

Experimental Exploration of Unlicensed Sub-GHz Massive MIMO for Massive Internet-of-Things

Callebaut¹,

Gunnarsson²,

Guevara³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Joint range extension and localization for low‐power wide‐area network

Cited by 7 publications

References 10 publications

DeepAoANet: Learning Angle of Arrival From Software Defined Radios With Deep Neural Networks

DeepAoANet: Learning Angle of Arrival From Software Defined Radios With Deep Neural Networks

Experimental Exploration of Unlicensed Sub-GHz Massive MIMO for Massive Internet-of-Things

Experimental Exploration of Unlicensed Sub-GHz Massive MIMO for Massive Internet-of-Things

Contact Info

Product

Resources

About