DropBlock based bimodal hybrid neural network for wireless communication modulation recognition
As an intermediate step of signal detection and demodulation, automatic modulation recognition played a momentous role in wireless communication system.Aiming at the low recognition accuracy of existing automatic modulation recognition methods, a bimodal hybrid neural network (BHNN) was proposed, wh...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2022-05-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022099/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841529013479145472 |
|---|---|
| author | Yan GAO Jian SHI Shengyu MA Bolin MA Guangxue YUE |
| author_facet | Yan GAO Jian SHI Shengyu MA Bolin MA Guangxue YUE |
| author_sort | Yan GAO |
| collection | DOAJ |
| description | As an intermediate step of signal detection and demodulation, automatic modulation recognition played a momentous role in wireless communication system.Aiming at the low recognition accuracy of existing automatic modulation recognition methods, a bimodal hybrid neural network (BHNN) was proposed, which utilized complementary gain information contained in multiple modes to enrich feature dimensions.The improved residual network was connected in parallel with the bidirectional gated loop unit to construct a bimodal hybrid neural network model, and the spatial and temporal features of the signal were extracted respectively.The DropBlock regularization algorithm was introduced to effectively suppress the influence of over fitting, gradient disappearance and gradient explosion on the recognition accuracy in the process of network training.Using bimodal data input, the spatial and temporal characteristics of signals were fully utilized, and the network depth was reduced through parallel connection.The model convergence was accelerated, and the recognition accuracy of modulated signals was improved.In order to verify the effectiveness of the model, two public datasets were used to simulate the model.The results show that BHNN has high recognition accuracy and strong stability on the two datasets, and the recognition accuracy can reach 89% and 93.63% respectively under high signal-to-noise ratio. |
| format | Article |
| id | doaj-art-59c785bf4c214d16b46347adcb43b00d |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2022-05-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-59c785bf4c214d16b46347adcb43b00d2025-01-15T03:27:06ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012022-05-0138758659810793DropBlock based bimodal hybrid neural network for wireless communication modulation recognitionYan GAOJian SHIShengyu MABolin MAGuangxue YUEAs an intermediate step of signal detection and demodulation, automatic modulation recognition played a momentous role in wireless communication system.Aiming at the low recognition accuracy of existing automatic modulation recognition methods, a bimodal hybrid neural network (BHNN) was proposed, which utilized complementary gain information contained in multiple modes to enrich feature dimensions.The improved residual network was connected in parallel with the bidirectional gated loop unit to construct a bimodal hybrid neural network model, and the spatial and temporal features of the signal were extracted respectively.The DropBlock regularization algorithm was introduced to effectively suppress the influence of over fitting, gradient disappearance and gradient explosion on the recognition accuracy in the process of network training.Using bimodal data input, the spatial and temporal characteristics of signals were fully utilized, and the network depth was reduced through parallel connection.The model convergence was accelerated, and the recognition accuracy of modulated signals was improved.In order to verify the effectiveness of the model, two public datasets were used to simulate the model.The results show that BHNN has high recognition accuracy and strong stability on the two datasets, and the recognition accuracy can reach 89% and 93.63% respectively under high signal-to-noise ratio.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022099/modulation recognitionbimodal hybrid neural networkDropBlock regularizationResNetBiGRU |
| spellingShingle | Yan GAO Jian SHI Shengyu MA Bolin MA Guangxue YUE DropBlock based bimodal hybrid neural network for wireless communication modulation recognition Dianxin kexue modulation recognition bimodal hybrid neural network DropBlock regularization ResNet BiGRU |
| title | DropBlock based bimodal hybrid neural network for wireless communication modulation recognition |
| title_full | DropBlock based bimodal hybrid neural network for wireless communication modulation recognition |
| title_fullStr | DropBlock based bimodal hybrid neural network for wireless communication modulation recognition |
| title_full_unstemmed | DropBlock based bimodal hybrid neural network for wireless communication modulation recognition |
| title_short | DropBlock based bimodal hybrid neural network for wireless communication modulation recognition |
| title_sort | dropblock based bimodal hybrid neural network for wireless communication modulation recognition |
| topic | modulation recognition bimodal hybrid neural network DropBlock regularization ResNet BiGRU |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022099/ |
| work_keys_str_mv | AT yangao dropblockbasedbimodalhybridneuralnetworkforwirelesscommunicationmodulationrecognition AT jianshi dropblockbasedbimodalhybridneuralnetworkforwirelesscommunicationmodulationrecognition AT shengyuma dropblockbasedbimodalhybridneuralnetworkforwirelesscommunicationmodulationrecognition AT bolinma dropblockbasedbimodalhybridneuralnetworkforwirelesscommunicationmodulationrecognition AT guangxueyue dropblockbasedbimodalhybridneuralnetworkforwirelesscommunicationmodulationrecognition |