1D-Concatenate based channel estimation DNN model optimization method
In order to improve the channel estimation accuracy of DNN model in wireless communication, a DNN model optimization method based on 1D-Concatenate was proposed.In this method, Concatenate performs one-dimensional data transformation, the DNN model was introduced by hopping connection, the gradient...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2023-04-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023097/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530802363432960 |
|---|---|
| author | Min LU Zehao QIN Zhihui CHEN Min ZHANG Guangxue YUE |
| author_facet | Min LU Zehao QIN Zhihui CHEN Min ZHANG Guangxue YUE |
| author_sort | Min LU |
| collection | DOAJ |
| description | In order to improve the channel estimation accuracy of DNN model in wireless communication, a DNN model optimization method based on 1D-Concatenate was proposed.In this method, Concatenate performs one-dimensional data transformation, the DNN model was introduced by hopping connection, the gradient disappearance problem was suppressed, and 1D-Concatenate was used to restore the data features lost during network training to improve the accuracy of DNN channel estimation.In order to verify the effectiveness of the optimization method, a typical DNN-based wireless communication channel estimation model was selected for comparative simulation experiments.Experimental results show that the estimated gain of the existing DNN model can be increased by 77.10% by the proposed optimization method, and the channel gain can be increased by up to 3 dB under high signal-to-noise ratio.This optimization method can effectively improve the channel estimation accuracy of DNN model in wireless communication, especially the improvement effect is significant under high signal-to-noise ratio. |
| format | Article |
| id | doaj-art-09a81dfc64744039b877d3c5f12cba8e |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2023-04-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-09a81dfc64744039b877d3c5f12cba8e2025-01-15T02:58:48ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012023-04-01397186595688021D-Concatenate based channel estimation DNN model optimization methodMin LUZehao QINZhihui CHENMin ZHANGGuangxue YUEIn order to improve the channel estimation accuracy of DNN model in wireless communication, a DNN model optimization method based on 1D-Concatenate was proposed.In this method, Concatenate performs one-dimensional data transformation, the DNN model was introduced by hopping connection, the gradient disappearance problem was suppressed, and 1D-Concatenate was used to restore the data features lost during network training to improve the accuracy of DNN channel estimation.In order to verify the effectiveness of the optimization method, a typical DNN-based wireless communication channel estimation model was selected for comparative simulation experiments.Experimental results show that the estimated gain of the existing DNN model can be increased by 77.10% by the proposed optimization method, and the channel gain can be increased by up to 3 dB under high signal-to-noise ratio.This optimization method can effectively improve the channel estimation accuracy of DNN model in wireless communication, especially the improvement effect is significant under high signal-to-noise ratio.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023097/channel estimationdeep neural networkConcatenate dimension conversiondata feature recovery |
| spellingShingle | Min LU Zehao QIN Zhihui CHEN Min ZHANG Guangxue YUE 1D-Concatenate based channel estimation DNN model optimization method Dianxin kexue channel estimation deep neural network Concatenate dimension conversion data feature recovery |
| title | 1D-Concatenate based channel estimation DNN model optimization method |
| title_full | 1D-Concatenate based channel estimation DNN model optimization method |
| title_fullStr | 1D-Concatenate based channel estimation DNN model optimization method |
| title_full_unstemmed | 1D-Concatenate based channel estimation DNN model optimization method |
| title_short | 1D-Concatenate based channel estimation DNN model optimization method |
| title_sort | 1d concatenate based channel estimation dnn model optimization method |
| topic | channel estimation deep neural network Concatenate dimension conversion data feature recovery |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023097/ |
| work_keys_str_mv | AT minlu 1dconcatenatebasedchannelestimationdnnmodeloptimizationmethod AT zehaoqin 1dconcatenatebasedchannelestimationdnnmodeloptimizationmethod AT zhihuichen 1dconcatenatebasedchannelestimationdnnmodeloptimizationmethod AT minzhang 1dconcatenatebasedchannelestimationdnnmodeloptimizationmethod AT guangxueyue 1dconcatenatebasedchannelestimationdnnmodeloptimizationmethod |