Automatic Modulation Classification: Convolutional Deep Learning Neural Networks Approaches
This study proposes robust convolutional neural network (CNN)-based automatic modulation classification (AMC) techniques. Traditional AMCs may be classified into two types: those that rely on ML (maximum likelihood-based AMCs) and those that rely on features. Numerous studies have been conducted on...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10244007/ |
| _version_ | 1797685350926123008 |
|---|---|
| author | Hany S. Hussein Mohamed Hassan Essai Ali Mohammed Ismeil Mohamed N. Shaaban Mona Lotfy Mohamed Hany A. Atallah |
| author_facet | Hany S. Hussein Mohamed Hassan Essai Ali Mohammed Ismeil Mohamed N. Shaaban Mona Lotfy Mohamed Hany A. Atallah |
| author_sort | Hany S. Hussein |
| collection | DOAJ |
| description | This study proposes robust convolutional neural network (CNN)-based automatic modulation classification (AMC) techniques. Traditional AMCs may be classified into two types: those that rely on ML (maximum likelihood-based AMCs) and those that rely on features. Numerous studies have been conducted on feature-based automatic modulation classification techniques. The current feature-based AMCs lack generalization capability and frequently target a small group of modulation techniques. The current paper develops three different CNN-based AMCs, each with a different classification layer (CL). The adopted classification layers are mean absolute error-based CL, a sum of squared errors-based CL, and crossentropy-based CL. The developed techniques can classify the received signals without feature extraction, where they can learn the features from the transmitted signals automatically during the offline training process, thus eliminating the necessity for feature extraction. A comparison study was done for the proposed CNN-based AMCs with three optimization algorithms at two signal-to-noise ratios. The proposed AMCs attain a true classification accuracy of up to 100% depending on the optimizer and loss function-base CL. |
| first_indexed | 2024-03-12T00:43:53Z |
| format | Article |
| id | doaj.art-2585819c3a824d7dac0f9ae0a27d73cb |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T00:43:53Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2585819c3a824d7dac0f9ae0a27d73cb2023-09-14T23:00:54ZengIEEEIEEE Access2169-35362023-01-0111986959870510.1109/ACCESS.2023.331339310244007Automatic Modulation Classification: Convolutional Deep Learning Neural Networks ApproachesHany S. Hussein0https://orcid.org/0000-0002-4929-0702Mohamed Hassan Essai Ali1https://orcid.org/0000-0002-0929-7053Mohammed Ismeil2https://orcid.org/0000-0002-9885-8501Mohamed N. Shaaban3https://orcid.org/0000-0003-3075-325XMona Lotfy Mohamed4Hany A. Atallah5https://orcid.org/0000-0001-5541-2326Electrical Engineering Department, Faculty of Engineering, King Khalid University, Abha, Saudi ArabiaElectrical Engineering Department, Faculty of Engineering, Al-Azhar University, Qena, EgyptElectrical Engineering Department, Faculty of Engineering, King Khalid University, Abha, Saudi ArabiaElectrical Engineering Department, Faculty of Engineering, Al-Azhar University, Qena, EgyptElectrical Engineering Department, International Maritime Science Academy, Hurghada, EgyptElectrical Engineering Department, Faculty of Engineering, South Valley University, Qena, EgyptThis study proposes robust convolutional neural network (CNN)-based automatic modulation classification (AMC) techniques. Traditional AMCs may be classified into two types: those that rely on ML (maximum likelihood-based AMCs) and those that rely on features. Numerous studies have been conducted on feature-based automatic modulation classification techniques. The current feature-based AMCs lack generalization capability and frequently target a small group of modulation techniques. The current paper develops three different CNN-based AMCs, each with a different classification layer (CL). The adopted classification layers are mean absolute error-based CL, a sum of squared errors-based CL, and crossentropy-based CL. The developed techniques can classify the received signals without feature extraction, where they can learn the features from the transmitted signals automatically during the offline training process, thus eliminating the necessity for feature extraction. A comparison study was done for the proposed CNN-based AMCs with three optimization algorithms at two signal-to-noise ratios. The proposed AMCs attain a true classification accuracy of up to 100% depending on the optimizer and loss function-base CL.https://ieeexplore.ieee.org/document/10244007/Modulation classificationdeep learningconvolutional neural networkwireless signal |
| spellingShingle | Hany S. Hussein Mohamed Hassan Essai Ali Mohammed Ismeil Mohamed N. Shaaban Mona Lotfy Mohamed Hany A. Atallah Automatic Modulation Classification: Convolutional Deep Learning Neural Networks Approaches IEEE Access Modulation classification deep learning convolutional neural network wireless signal |
| title | Automatic Modulation Classification: Convolutional Deep Learning Neural Networks Approaches |
| title_full | Automatic Modulation Classification: Convolutional Deep Learning Neural Networks Approaches |
| title_fullStr | Automatic Modulation Classification: Convolutional Deep Learning Neural Networks Approaches |
| title_full_unstemmed | Automatic Modulation Classification: Convolutional Deep Learning Neural Networks Approaches |
| title_short | Automatic Modulation Classification: Convolutional Deep Learning Neural Networks Approaches |
| title_sort | automatic modulation classification convolutional deep learning neural networks approaches |
| topic | Modulation classification deep learning convolutional neural network wireless signal |
| url | https://ieeexplore.ieee.org/document/10244007/ |
| work_keys_str_mv | AT hanyshussein automaticmodulationclassificationconvolutionaldeeplearningneuralnetworksapproaches AT mohamedhassanessaiali automaticmodulationclassificationconvolutionaldeeplearningneuralnetworksapproaches AT mohammedismeil automaticmodulationclassificationconvolutionaldeeplearningneuralnetworksapproaches AT mohamednshaaban automaticmodulationclassificationconvolutionaldeeplearningneuralnetworksapproaches AT monalotfymohamed automaticmodulationclassificationconvolutionaldeeplearningneuralnetworksapproaches AT hanyaatallah automaticmodulationclassificationconvolutionaldeeplearningneuralnetworksapproaches |