Wireless technique classification (WTC) is of crucial importance in Internet of Things for realizing efficient spectrum sharing and interference management. However, the existing deep learning-based methods have low classification accuracy, especially at low SNR levels. In this paper, a multi-scale convolutional neural network framework is proposed for WTC. A multi-scale module is exploited to capture the higher abstraction features. Simulation results demonstrate that our proposed scheme can achieve a better classification performance and a higher convergence speed compared to the state-of-the-art schemes.
%0 Journal Article
%1 Yuan2021multi
%A Yuan, Lu
%A Zhang, Hao
%A Xu, Ming
%A Zhou, Fuhui
%A Wu, Qihui
%D 2021
%I IEEE
%J IEEE Internet of Things Journal
%K Convolution,Convolutional Evolution,Signal Term Things,Long classification,high communication,Wireless convergence convolutional network networks,Internet neural noise of ratio,Training,Wireless speed.,multi-scale technique to
%N c
%P 9--10
%R 10.1109/JIOT.2021.3132652
%T A Multi-Scale CNN Framework for Wireless Technique Classification in Internet of Things
%V 4662
%X Wireless technique classification (WTC) is of crucial importance in Internet of Things for realizing efficient spectrum sharing and interference management. However, the existing deep learning-based methods have low classification accuracy, especially at low SNR levels. In this paper, a multi-scale convolutional neural network framework is proposed for WTC. A multi-scale module is exploited to capture the higher abstraction features. Simulation results demonstrate that our proposed scheme can achieve a better classification performance and a higher convergence speed compared to the state-of-the-art schemes.
@article{Yuan2021multi,
abstract = {Wireless technique classification (WTC) is of crucial importance in Internet of Things for realizing efficient spectrum sharing and interference management. However, the existing deep learning-based methods have low classification accuracy, especially at low SNR levels. In this paper, a multi-scale convolutional neural network framework is proposed for WTC. A multi-scale module is exploited to capture the higher abstraction features. Simulation results demonstrate that our proposed scheme can achieve a better classification performance and a higher convergence speed compared to the state-of-the-art schemes.},
added-at = {2023-02-27T14:12:01.000+0100},
author = {Yuan, Lu and Zhang, Hao and Xu, Ming and Zhou, Fuhui and Wu, Qihui},
biburl = {https://www.bibsonomy.org/bibtex/21f417d2581ca2950f77fae518ca16a59/haozhangcn},
doi = {10.1109/JIOT.2021.3132652},
file = {:F\:/OneDrive - nuaa.edu.cn/mendeley/2021-12-06_wtc.pdf:pdf},
interhash = {7130ea36971e523007130b7d7e7bb446},
intrahash = {1f417d2581ca2950f77fae518ca16a59},
issn = {23274662},
journal = {IEEE Internet of Things Journal},
keywords = {Convolution,Convolutional Evolution,Signal Term Things,Long classification,high communication,Wireless convergence convolutional network networks,Internet neural noise of ratio,Training,Wireless speed.,multi-scale technique to},
number = {c},
pages = {9--10},
publisher = {IEEE},
timestamp = {2023-02-27T14:12:15.000+0100},
title = {{A Multi-Scale CNN Framework for Wireless Technique Classification in Internet of Things}},
volume = 4662,
year = 2021
}