2019 16th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON) 2019
DOI: 10.1109/sahcn.2019.8824856
|View full text |Cite
|
Sign up to set email alerts
|

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

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 technologie… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
9
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
7
1
1

Relationship

5
4

Authors

Journals

citations
Cited by 25 publications
(9 citation statements)
references
References 12 publications
0
9
0
Order By: Relevance
“…One possible solution to the problem described above is that the GW 1 recognizes the radio technology that interferes and adapts its behavior accordingly [7], [32], [33]. However, this approach is not enough to increase spectrum efficiency as (i) the interfering/interfered technology may not include a mechanism to adapt or coexist, e.g., to change its frequency band to avoid the interference, and (ii) (iii) traffic prioritization can be only based on technology and not on application.…”
Section: B a Tc Framework At Any Layermentioning
confidence: 99%
See 1 more Smart Citation
“…One possible solution to the problem described above is that the GW 1 recognizes the radio technology that interferes and adapts its behavior accordingly [7], [32], [33]. However, this approach is not enough to increase spectrum efficiency as (i) the interfering/interfered technology may not include a mechanism to adapt or coexist, e.g., to change its frequency band to avoid the interference, and (ii) (iii) traffic prioritization can be only based on technology and not on application.…”
Section: B a Tc Framework At Any Layermentioning
confidence: 99%
“…The design of the CNN architecture was based on some of our previous experiences solving classification tasks using raw spectrum data such as in [7], [10], [33], [34], [37], [39]. More precisely, we started with a 2D-CNN architecture that worked well in the task of TR with raw IQ samples (see Fig.…”
Section: DL Models Design and Trainingmentioning
confidence: 99%
“…To compare the performance of the proposed rule-based algorithm with machine learning (ML), we use a convolutional neural network (CNN), of which the architecture is shown in Figure 9. The CNN has shown tremendous performance in various classification problems such as image classification [74], modulation classification [75], and wireless technology classification [76][77][78]. In this work, the CNN is trained with three publicly available fall datasets presented in [79][80][81].…”
Section: Convolutional Neural Network Designmentioning
confidence: 99%
“…In that sense, Cognitive Radio approaches based on deep learning techniques [19], [20] help to detect the technology that is accessing the medium. Hence, different management decisions can be made given that some technologies are more benevolent than others [21].…”
Section: A Motivation For Wi-fi and Lte Coexistence In A Spectrum Mamentioning
confidence: 99%