Demo Abstract: Identification of LPWAN Technologies using Convolutional Neural Networks

Shahid, Adnan; Fontaine, Jaron; Haxhibeqiri, Jetmir; Saelens, Martijn; Khan, Zaheer; Moerman, Ingrid; Poorter, Eli De

doi:10.1109/infcomw.2019.8845259

Cited by 2 publications

(4 citation statements)

References 4 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can conclude that time domain features are sufficient in most scenarios where the signal is clear and high above the noise floor. Finally, compared to related research [9] [8], the model retains and even surpasses classification accuracy (98.9% and 99.8% compared to 95% and 97% in IQ mode), even with reduced complexity for embedded platforms.…”

Section: Resultsmentioning

confidence: 71%

“…This causes the model to recognize features with a higher confidence in the FFT mode compared to the IQ mode. Again, compared to other related research [9] [8] the proposed small CNN achieves comparable performance, if not higher, caused by optimizations to the model. Similar to the conclusion in section V-A, we observe a higher accuracy for high SNR scenarios (> 10 dB) in IQ mode for the 867 MHz signals and a negligible difference for the 864 MHz signals.…”

Section: B Robustness To Noisementioning

confidence: 68%

See 1 more Smart Citation

Multi-band sub-GHz technology recognition on NVIDIA’s Jetson Nano

Fontaine

Shahid

Elsas

et al. 2020

2020 IEEE 92nd Vehicular Technology Conference (VTC2020-Fall)

Self Cite

View full text Add to dashboard Cite

Low power wide area networks support the success of long range Internet of things applications such as agriculture, security, smart cities and homes. This enormous popularity, however, breeds new challenging problems as the wireless spectrum gets saturated which increases the probability of collisions and performance degradation. To this end, smart spectrum decisions are needed and will be supported by wireless technology recognition to allow the networks to dynamically adapt to the ever changing environment where fair coexistence with other wireless technologies becomes essential. In contrast to existing research that assesses technology recognition using machine learning on powerful graphics processing units, this work aims to propose a deep learning solution using convolutional neural networks, cheap software defined radios and efficient embedded platforms such as NVIDIA's Jetson Nano. More specifically, this paper presents low complexity near-real time multi-band sub-GHz technology recognition and supports a wide variety of technologies using multiple settings. Results show accuracies around 99%, which are comparable with state of the art solutions, while the classification time on a NVIDIA Jetson Nano remains small and offers real-time execution. These results will enable smart spectrum management without the need of expensive and high power consuming hardware. Index Terms-Sub-GHz, deep learning, Software-defined radio, low-cost devices I. INTRODUCTION The Internet of things (IoT) paradigm has grown exponentially in the past decade and continues this trend into the foreseeable future. At the beginning of 2020, IoT Analytics estimated that 9.5 billion devices are connected to the Internet and forecasts a growth of 28 billion devices by 2025 [1]. This is due to the proliferation of various IoT application areas such as security, tracking, agriculture, smart metering, smart cities and smart homes. To accommodate commercial deployment of such large number of devices, recently a number of IoT technologies were developed which are called low power wide area networks (LPWANs). These technologies offer very long communication ranges allowing to connect a large number of devices using limited infrastructure cost (e.g. by installing a small number of gateways). Example technologies include Sigfox, LoRA, IEEE 802.11ah, IEEE 802.11g, Dash7, Weightless, etc. These technologies operate in unlicensed sub-GHz band, typically 868 MHz in Europe and 915 MHz in North America. These radio frequencies offer good object penetration performance and can be used for a long range of communication, i.e., up to 15 km (for LoRa) [2]. However, due to

show abstract

Section: Resultsmentioning

confidence: 71%

Section: B Robustness To Noisementioning

confidence: 68%

Multi-band sub-GHz technology recognition on NVIDIA’s Jetson Nano

Fontaine

Shahid

Elsas

et al. 2020

2020 IEEE 92nd Vehicular Technology Conference (VTC2020-Fall)

Self Cite

View full text Add to dashboard Cite

show abstract

“…According to the best of our knowledge, classification of LPWAN technologies in sub-GHz unlicensed bands using DL has not been investigated so far. This work is an extension of our recently accepted demo paper [15] where we demonstrate classification of different signal classes of Sigfox, LoRA, IEEE 802.15.4g and Noise. Following are the extensions of our work: a) detailed description of the spectrum manager framework, b) inclusion of the interference signal class, and c) detailed analysis of the two CNN classifiers in different channel conditions per each signal class.…”

Section: Related Workmentioning

confidence: 88%

“…In addition, the Institute of Electrical and Electronics Engineers (IEEE) has also proposed an amendment for IEEE 802.15.4, i.e., IEEE 802. 15.4g, which finds its applications in smart in unlicensed sub-GHz bands, typically 868 MHz in Europe and 915 MHz in North America. In this work, we focus on the operation of the three technologies in Europe, where a duty cycle limitation of 1% is imposed.…”

Section: Introductionmentioning

confidence: 99%

A Convolutional Neural Network Approach for Classification of LPWAN Technologies: Sigfox, LoRA and IEEE 802.15.4g

Shahid

Fontaine

Camelo

et al. 2019

2019 16th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON)

Self Cite

View full text Add to dashboard Cite

This paper presents a Convolutional Neural Network (CNN) approach for classification of low power wide area network (LPWAN) technologies such as Sigfox, LoRA and IEEE 802.15.4g. Since the technologies operate in unlicensed sub-GHz bands, their transmissions can interfere with each other and significantly degrade their performance. This situation further intensifies when the network density increases which will be the case of future LPWANs. In this regard, it becomes essential to classify coexisting technologies so that the impact of interference can be minimized by making optimal spectrum decisions. State-of-the-art technology classification approaches use signal processing approaches for solving the task. However, such techniques are not scalable and require domain-expertise knowledge for developing new rules for each new technology. On the contrary, we present a CNN approach for classification which requires limited domain-expertise knowledge, and it can be scalable to any number of wireless technologies. We present and compare two CNN based classifiers named CNN based on in-phase and quadrature (IQ) and CNN based on Fast Fourier Transform (FFT). The results illustrate that CNN based on IQ achieves classification accuracy close to 97% similar to CNN based on FFT and thus, avoiding the need for performing FFT.

show abstract

Demo Abstract: Identification of LPWAN Technologies using Convolutional Neural Networks

Cited by 2 publications

References 4 publications

Multi-band sub-GHz technology recognition on NVIDIA’s Jetson Nano

Multi-band sub-GHz technology recognition on NVIDIA’s Jetson Nano

A Convolutional Neural Network Approach for Classification of LPWAN Technologies: Sigfox, LoRA and IEEE 802.15.4g

Contact Info

Product

Resources

About