Advanced search
2 files | 40.41 MB Add to list
Author
Organization
Abstract
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.
Keywords
Convolutional Neural Networks, technology classification, interference, spectrum manager, coexistence

Downloads

  • 7586 i.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 20.21 MB
  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 20.21 MB

Citation

Please use this url to cite or link to this publication:

MLA
Shahid, Adnan, et al. “A Convolutional Neural Network Approach for Classification of LPWAN Technologies : Sigfox, LoRA and IEEE 802.15.4g.” 2019 16TH ANNUAL IEEE INTERNATIONAL CONFERENCE ON SENSING, COMMUNICATION, AND NETWORKING (SECON), IEEE, 2019, pp. 1–8, doi:10.1109/sahcn.2019.8824856.
APA
Shahid, A., Fontaine, J., Camelo, M., Haxhibeqiri, J., Saelens, M., Khan, Z., … De Poorter, E. (2019). A convolutional neural network approach for classification of LPWAN technologies : Sigfox, LoRA and IEEE 802.15.4g. 2019 16TH ANNUAL IEEE INTERNATIONAL CONFERENCE ON SENSING, COMMUNICATION, AND NETWORKING (SECON), 1–8. https://doi.org/10.1109/sahcn.2019.8824856
Chicago author-date
Shahid, Adnan, Jaron Fontaine, Miguel Camelo, Jetmir Haxhibeqiri, Martijn Saelens, Zaheer Khan, Ingrid Moerman, and Eli De Poorter. 2019. “A Convolutional Neural Network Approach for Classification of LPWAN Technologies : Sigfox, LoRA and IEEE 802.15.4g.” In 2019 16TH ANNUAL IEEE INTERNATIONAL CONFERENCE ON SENSING, COMMUNICATION, AND NETWORKING (SECON), 1–8. IEEE. https://doi.org/10.1109/sahcn.2019.8824856.
Chicago author-date (all authors)
Shahid, Adnan, Jaron Fontaine, Miguel Camelo, Jetmir Haxhibeqiri, Martijn Saelens, Zaheer Khan, Ingrid Moerman, and Eli De Poorter. 2019. “A Convolutional Neural Network Approach for Classification of LPWAN Technologies : Sigfox, LoRA and IEEE 802.15.4g.” In 2019 16TH ANNUAL IEEE INTERNATIONAL CONFERENCE ON SENSING, COMMUNICATION, AND NETWORKING (SECON), 1–8. IEEE. doi:10.1109/sahcn.2019.8824856.
Vancouver
1.
Shahid A, Fontaine J, Camelo M, Haxhibeqiri J, Saelens M, Khan Z, et al. A convolutional neural network approach for classification of LPWAN technologies : Sigfox, LoRA and IEEE 802.15.4g. In: 2019 16TH ANNUAL IEEE INTERNATIONAL CONFERENCE ON SENSING, COMMUNICATION, AND NETWORKING (SECON). IEEE; 2019. p. 1–8.
IEEE
[1]
A. Shahid et al., “A convolutional neural network approach for classification of LPWAN technologies : Sigfox, LoRA and IEEE 802.15.4g,” in 2019 16TH ANNUAL IEEE INTERNATIONAL CONFERENCE ON SENSING, COMMUNICATION, AND NETWORKING (SECON), Boston, MA, 2019, pp. 1–8.
@inproceedings{8637794,
  abstract     = {{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.}},
  author       = {{Shahid, Adnan and Fontaine, Jaron and Camelo, Miguel and Haxhibeqiri, Jetmir and Saelens, Martijn and Khan, Zaheer and Moerman, Ingrid and De Poorter, Eli}},
  booktitle    = {{2019 16TH ANNUAL IEEE INTERNATIONAL CONFERENCE ON SENSING, COMMUNICATION, AND NETWORKING (SECON)}},
  isbn         = {{9781728112077}},
  issn         = {{2473-0440}},
  keywords     = {{Convolutional Neural Networks,technology classification,interference,spectrum  manager,coexistence}},
  language     = {{eng}},
  location     = {{Boston, MA}},
  pages        = {{1--8}},
  publisher    = {{IEEE}},
  title        = {{A convolutional neural network approach for classification of LPWAN technologies : Sigfox, LoRA and IEEE 802.15.4g}},
  url          = {{http://doi.org/10.1109/sahcn.2019.8824856}},
  year         = {{2019}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: