Multimodal attention-based deep learning for automatic modulation classification
Wireless Internet of Things (IoT) is widely accepted in data collection and transmission of power system, with the prerequisite that the base station of wireless IoT be compatible with a variety of digital modulation types to meet data transmission requirements of terminals with different modulation...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-12-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2022.1041862/full |
| _version_ | 1797953455428468736 |
|---|---|
| author | Jia Han Zhiyong Yu Jian Yang |
| author_facet | Jia Han Zhiyong Yu Jian Yang |
| author_sort | Jia Han |
| collection | DOAJ |
| description | Wireless Internet of Things (IoT) is widely accepted in data collection and transmission of power system, with the prerequisite that the base station of wireless IoT be compatible with a variety of digital modulation types to meet data transmission requirements of terminals with different modulation modes. As a key technology in wireless IoT communication, Automatic Modulation Classification (AMC) manages resource shortage and improves spectrum utilization efficiency. And for better accuracy and efficiency in the classification of wireless signal modulation, Deep learning (DL) is frequently exploited. It is found in real cases that the signal-to-noise ratio (SNR) of wireless signals received by base station remains low due to complex electromagnetic interference from power equipment, increasing difficulties for accurate AMC. Therefore, inspired by attention mechanism of multi-layer perceptron (MLP), AMC-MLP is introduced herein as a novel AMC method for low SNR signals. Firstly, the sampled I/Q data is converted to constellation diagram, smoothed pseudo Wigner-Ville distribution (SPWVD), and contour diagram of the spectral correlation function (SCF). Secondly, convolution auto-encoder (Conv-AE) is used to denoise and extract image feature vectors. Finally, MLP is employed to fuse multimodal features to classify signals. AMC-MLP model utilizes the characterization advantages of feature images in different modulation modes and boosts the classification accuracy of low SNR signals. Results of simulations on RadioML 2016.10A public dataset prove as well that AMC-MLP provides significantly better classification accuracy of signals in low SNR range than that of other latest deep-learning AMC methods. |
| first_indexed | 2024-04-10T23:03:24Z |
| format | Article |
| id | doaj.art-68ecde1105844dfa87cb4a9d48be1b67 |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-04-10T23:03:24Z |
| publishDate | 2022-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-68ecde1105844dfa87cb4a9d48be1b672023-01-13T17:00:14ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2022-12-011010.3389/fenrg.2022.10418621041862Multimodal attention-based deep learning for automatic modulation classificationJia Han0Zhiyong Yu1Jian Yang2Department of Computer, Rocket Force University of Engineering, Xi’an, Shaanxi, ChinaDepartment of Computer, Rocket Force University of Engineering, Xi’an, Shaanxi, ChinaDepartment of Engineering, Rocket Force University of Engineering, Xi’an, Shaanxi, ChinaWireless Internet of Things (IoT) is widely accepted in data collection and transmission of power system, with the prerequisite that the base station of wireless IoT be compatible with a variety of digital modulation types to meet data transmission requirements of terminals with different modulation modes. As a key technology in wireless IoT communication, Automatic Modulation Classification (AMC) manages resource shortage and improves spectrum utilization efficiency. And for better accuracy and efficiency in the classification of wireless signal modulation, Deep learning (DL) is frequently exploited. It is found in real cases that the signal-to-noise ratio (SNR) of wireless signals received by base station remains low due to complex electromagnetic interference from power equipment, increasing difficulties for accurate AMC. Therefore, inspired by attention mechanism of multi-layer perceptron (MLP), AMC-MLP is introduced herein as a novel AMC method for low SNR signals. Firstly, the sampled I/Q data is converted to constellation diagram, smoothed pseudo Wigner-Ville distribution (SPWVD), and contour diagram of the spectral correlation function (SCF). Secondly, convolution auto-encoder (Conv-AE) is used to denoise and extract image feature vectors. Finally, MLP is employed to fuse multimodal features to classify signals. AMC-MLP model utilizes the characterization advantages of feature images in different modulation modes and boosts the classification accuracy of low SNR signals. Results of simulations on RadioML 2016.10A public dataset prove as well that AMC-MLP provides significantly better classification accuracy of signals in low SNR range than that of other latest deep-learning AMC methods.https://www.frontiersin.org/articles/10.3389/fenrg.2022.1041862/fullInternet of thingsautomatic modulation classificationauto-encoderdeep learningspectrum sensing |
| spellingShingle | Jia Han Zhiyong Yu Jian Yang Multimodal attention-based deep learning for automatic modulation classification Frontiers in Energy Research Internet of things automatic modulation classification auto-encoder deep learning spectrum sensing |
| title | Multimodal attention-based deep learning for automatic modulation classification |
| title_full | Multimodal attention-based deep learning for automatic modulation classification |
| title_fullStr | Multimodal attention-based deep learning for automatic modulation classification |
| title_full_unstemmed | Multimodal attention-based deep learning for automatic modulation classification |
| title_short | Multimodal attention-based deep learning for automatic modulation classification |
| title_sort | multimodal attention based deep learning for automatic modulation classification |
| topic | Internet of things automatic modulation classification auto-encoder deep learning spectrum sensing |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2022.1041862/full |
| work_keys_str_mv | AT jiahan multimodalattentionbaseddeeplearningforautomaticmodulationclassification AT zhiyongyu multimodalattentionbaseddeeplearningforautomaticmodulationclassification AT jianyang multimodalattentionbaseddeeplearningforautomaticmodulationclassification |