Improving Recognition of Sub-GHz LPWANs: A Deep Learning Approach With the UPC-LPWAN-1 Dataset

Deep neural networks (DNNs) have emerged as an effective technique for modulation/system recognition but rely heavily on representative datasets. This paper introduces the "UPC-LPWAN-1" dataset, a comprehensive collection of 40 Sub-GHz LPWAN transmission modes acquired using real hardware....

Full description

Saved in:
Bibliographic Details
Published in:IEEE open journal of the Communications Society 2024, Vol.5, p.6635-6654
Main Authors: Maya-Olalla, Edgar, Garcia-Lozano, Mario, Perez-Diaz-de-Cerio, David, Ruiz-Boque, Silvia
Format: Article
Language:English
Subjects:
Accuracy
Artificial neural networks
Convolutional neural networks
Datasets
Deep learning
Frequency modulation
Hardware
LoRa
low power wide area networks (LPWAN)
Low-power wide area networks
LPWAN dataset
Machine learning
Modulation
modulation recognition
Neural networks
Performance degradation
Recognition
Signal to noise ratio
spectrum sensing
sub-GHz ISM band
system classification
Wireless fidelity
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep neural networks (DNNs) have emerged as an effective technique for modulation/system recognition but rely heavily on representative datasets. This paper introduces the "UPC-LPWAN-1" dataset, a comprehensive collection of 40 Sub-GHz LPWAN transmission modes acquired using real hardware. Publicly available to the scientific community, this dataset includes raw and pre-processed samples across different Signal-to-Noise Ratios (SNRs) and features multi-carrier modulations, which are typically underrepresented in existing datasets. The variability in studies using different neural network architectures and small, unrepresentative datasets complicates research comparisons. To address this, this paper compares seven proposed architectures using UPC-LPWAN-1, providing a standardized evaluation. To further enhance accuracy, we propose four new convolutional neural network (CNN) architectures adapted to four forms of signal representation. Our results demonstrate that while some existing models perform well under high SNR conditions, their performance degrades significantly in low SNR environments. The proposed spectrogram-based CNN consistently outperforms other models, achieving a classification accuracy of 99.71% at SNR = 0 dB, above 90% at SNR =−10 dB, and above 70% at SNR =−15 dB, while still being able to differentiate between systems.
ISSN:2644-125X
2644-125X
DOI:10.1109/OJCOMS.2024.3480856