Electromagnetic signal modulation recognition technology based on lightweight deep neural network
In response to the trend that in the 6th generation wireless (6G) era,mobile communications and artificial intelligence will be closely integrated,and a huge number of edge intelligent signal processing nodes will be deployed,an efficient and intelligent electromagnetic signal recognition model was...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2020-11-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2020237/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850095833017483264 |
|---|---|
| author | Sicheng ZHANG Yun LIN Ya TU Shiwen Mao |
| author_facet | Sicheng ZHANG Yun LIN Ya TU Shiwen Mao |
| author_sort | Sicheng ZHANG |
| collection | DOAJ |
| description | In response to the trend that in the 6th generation wireless (6G) era,mobile communications and artificial intelligence will be closely integrated,and a huge number of edge intelligent signal processing nodes will be deployed,an efficient and intelligent electromagnetic signal recognition model was proposed,which could be deployed on resource-constrained edge devices.The constellation diagram of electromagnetic signal was firstly drawn to visualize electromagnetic signal as a two-dimensional image,and color the constellation diagram according to the normalized point density to achieve feature enhancement.Then,a binary deep neural network was adopted to recognize the colored constellation diagrams.It was shown that the approach can guarantee a high recognition accuracy,which significantly reduced the model storage and calculation costs.For verification,the proposed approach was applied to the problem of electromagnetic signal modulation recognition.The experiment uses eight commonly used digital modulation signals and selects additive white Gaussian noise as the channel environment.The experimental results show that the scheme can achieve a comprehensive recognition rate of 96.1% under the noise condition of -6～6 dB,while the size of the network model is only 166 KB.Further,the execution time,when executed on a Raspberry Pi 4B,is only 290 ms.Compared to a full-precision network of the same scale,the accuracy is increased by 0.6%,the model is reduced to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML"> <mfrac> <mtext>1</mtext> <mrow> <mtext>26</mtext><mo>.</mo><mtext>16</mtext></mrow> </mfrac> </math></inline-formula>,and the running time is reduced to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML"> <mfrac> <mtext>1</mtext> <mrow> <mn>2.37</mn></mrow> </mfrac> </math></inline-formula>. |
| format | Article |
| id | doaj-art-8810d80d54274d73b4e849d094ec5095 |
| institution | DOAJ |
| issn | 1000-436X |
| language | zho |
| publishDate | 2020-11-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-8810d80d54274d73b4e849d094ec50952025-08-20T02:41:21ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2020-11-0141122159738338Electromagnetic signal modulation recognition technology based on lightweight deep neural networkSicheng ZHANGYun LINYa TUShiwen MaoIn response to the trend that in the 6th generation wireless (6G) era,mobile communications and artificial intelligence will be closely integrated,and a huge number of edge intelligent signal processing nodes will be deployed,an efficient and intelligent electromagnetic signal recognition model was proposed,which could be deployed on resource-constrained edge devices.The constellation diagram of electromagnetic signal was firstly drawn to visualize electromagnetic signal as a two-dimensional image,and color the constellation diagram according to the normalized point density to achieve feature enhancement.Then,a binary deep neural network was adopted to recognize the colored constellation diagrams.It was shown that the approach can guarantee a high recognition accuracy,which significantly reduced the model storage and calculation costs.For verification,the proposed approach was applied to the problem of electromagnetic signal modulation recognition.The experiment uses eight commonly used digital modulation signals and selects additive white Gaussian noise as the channel environment.The experimental results show that the scheme can achieve a comprehensive recognition rate of 96.1% under the noise condition of -6～6 dB,while the size of the network model is only 166 KB.Further,the execution time,when executed on a Raspberry Pi 4B,is only 290 ms.Compared to a full-precision network of the same scale,the accuracy is increased by 0.6%,the model is reduced to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML"> <mfrac> <mtext>1</mtext> <mrow> <mtext>26</mtext><mo>.</mo><mtext>16</mtext></mrow> </mfrac> </math></inline-formula>,and the running time is reduced to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML"> <mfrac> <mtext>1</mtext> <mrow> <mn>2.37</mn></mrow> </mfrac> </math></inline-formula>.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2020237/6Gedge intelligenceelectromagnetic signal modulation recognitionimage visualizationbinary deep neur-al network |
| spellingShingle | Sicheng ZHANG Yun LIN Ya TU Shiwen Mao Electromagnetic signal modulation recognition technology based on lightweight deep neural network Tongxin xuebao 6G edge intelligence electromagnetic signal modulation recognition image visualization binary deep neur-al network |
| title | Electromagnetic signal modulation recognition technology based on lightweight deep neural network |
| title_full | Electromagnetic signal modulation recognition technology based on lightweight deep neural network |
| title_fullStr | Electromagnetic signal modulation recognition technology based on lightweight deep neural network |
| title_full_unstemmed | Electromagnetic signal modulation recognition technology based on lightweight deep neural network |
| title_short | Electromagnetic signal modulation recognition technology based on lightweight deep neural network |
| title_sort | electromagnetic signal modulation recognition technology based on lightweight deep neural network |
| topic | 6G edge intelligence electromagnetic signal modulation recognition image visualization binary deep neur-al network |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2020237/ |
| work_keys_str_mv | AT sichengzhang electromagneticsignalmodulationrecognitiontechnologybasedonlightweightdeepneuralnetwork AT yunlin electromagneticsignalmodulationrecognitiontechnologybasedonlightweightdeepneuralnetwork AT yatu electromagneticsignalmodulationrecognitiontechnologybasedonlightweightdeepneuralnetwork AT shiwenmao electromagneticsignalmodulationrecognitiontechnologybasedonlightweightdeepneuralnetwork |