Performance Analysis of Convolutional Neural Networks with Different Window Functions for Automatic Modulation Classification

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F25547526%3A_____%2F22%3AN0000002" target="_blank" >RIV/25547526:_____/22:N0000002 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9952750" target="_blank" >https://ieeexplore.ieee.org/document/9952750</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICTC55196.2022.9952750" target="_blank" >10.1109/ICTC55196.2022.9952750</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Performance Analysis of Convolutional Neural Networks with Different Window Functions for Automatic Modulation Classification

Popis výsledku v původním jazyce

Automatic modulation classification is one of the main tasks for developing information security and radio signal surveillance systems. It is also becoming increasingly significant for spectrum monitoring, management, and secure communications. Recently, deep learning models have been widely applied in many fields due to their outstanding feature extraction and classification accuracy. In this paper, the automatic modulation classification performance of several deep convolutional neural networks (CNN) is analyzed on the Fast Fourier Transform (FFT) based signal spectrum and the Short Time Fourier Transform (STFT) based signal spectrogram. By using ResNet18 and MobileNet cross-combined with FFT and STFT input data, the simulation shows that the STFT data provides a higher AMC accuracy than that of FFT data. On the same STFT data, the ResNet18 model outperforms three other models (SqueezeNet, GoogleNet, and MobileNet) in classifying 26 modulation types under the influence of five levels of fading noise with SNRs from −20 dB to +18 dB. Besides, the impact of different window functions in STFT is also investigated. Numerical results indicate that the considered window functions cause an insignificant difference in the AMC accuracy.

Název v anglickém jazyce

Performance Analysis of Convolutional Neural Networks with Different Window Functions for Automatic Modulation Classification

Popis výsledku anglicky

Automatic modulation classification is one of the main tasks for developing information security and radio signal surveillance systems. It is also becoming increasingly significant for spectrum monitoring, management, and secure communications. Recently, deep learning models have been widely applied in many fields due to their outstanding feature extraction and classification accuracy. In this paper, the automatic modulation classification performance of several deep convolutional neural networks (CNN) is analyzed on the Fast Fourier Transform (FFT) based signal spectrum and the Short Time Fourier Transform (STFT) based signal spectrogram. By using ResNet18 and MobileNet cross-combined with FFT and STFT input data, the simulation shows that the STFT data provides a higher AMC accuracy than that of FFT data. On the same STFT data, the ResNet18 model outperforms three other models (SqueezeNet, GoogleNet, and MobileNet) in classifying 26 modulation types under the influence of five levels of fading noise with SNRs from −20 dB to +18 dB. Besides, the impact of different window functions in STFT is also investigated. Numerical results indicate that the considered window functions cause an insignificant difference in the AMC accuracy.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20202 - Communication engineering and systems

Projekt

<a href="/cs/project/TM02000035" target="_blank" >TM02000035: Pokroková klasifikace signálů (NEOCLASSIG) pro radio-průzkumné systémy</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

C - Předmět řešení projektu podléhá obchodnímu tajemství (§ 504 Občanského zákoníku), ale název projektu, cíle projektu a u ukončeného nebo zastaveného projektu zhodnocení výsledku řešení projektu (údaje P03, P04, P15, P19, P29, PN8) dodané do CEP, jsou upraveny tak, aby byly zveřejnitelné.

Název statě ve sborníku

Performance Analysis of Convolutional Neural Networks with Different Window Functions for Automatic Modulation Classification

ISBN

978-1-6654-9940-8

ISSN

2162-1233

e-ISSN

2162-1241

Počet stran výsledku

5

Strana od-do

153 - 157

Název nakladatele

IEEE

Místo vydání

Jeju Island, Republic of Korea

Místo konání akce

Jeju Island, Republic of Korea

Datum konání akce

1. 1. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—