Serial and parallel convolutional neural network schemes for NFDM signals
Abstract Two conceptual convolutional neural network (CNN) schemes are proposed, developed and analysed for directly decoding nonlinear frequency division multiplexing (NFDM) signals with hardware implementation taken into consideration. A serial network scheme with a small network size is designed...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-05-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-12141-4 |
| _version_ | 1818206813378576384 |
|---|---|
| author | Wen Qi Zhang Terence H. Chan Shahraam Afshar Vahid |
| author_facet | Wen Qi Zhang Terence H. Chan Shahraam Afshar Vahid |
| author_sort | Wen Qi Zhang |
| collection | DOAJ |
| description | Abstract Two conceptual convolutional neural network (CNN) schemes are proposed, developed and analysed for directly decoding nonlinear frequency division multiplexing (NFDM) signals with hardware implementation taken into consideration. A serial network scheme with a small network size is designed for small user applications, and a parallel network scheme with high speed is designed for places such as data centres. The work aimed at showing the potential of using CNN for practical NFDM-based fibre optic communication. In the numerical demonstrations, the serial network only occupies 0.5 MB of memory space while the parallel network occupies 128 MB of memory but allows parallel computing. Both network schemes were trained with simulated data and reached more than 99.9% accuracy. |
| first_indexed | 2024-12-12T04:18:59Z |
| format | Article |
| id | doaj.art-26043fa1369547ee8f0b2fc892ba5872 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-12T04:18:59Z |
| publishDate | 2022-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-26043fa1369547ee8f0b2fc892ba58722022-12-22T00:38:22ZengNature PortfolioScientific Reports2045-23222022-05-0112111210.1038/s41598-022-12141-4Serial and parallel convolutional neural network schemes for NFDM signalsWen Qi Zhang0Terence H. Chan1Shahraam Afshar Vahid2Laser Physics and Photonic Devices Laboratories, STEM, University of South AustraliaInstitute for Telecommunications Research, University of South AustraliaLaser Physics and Photonic Devices Laboratories, STEM, University of South AustraliaAbstract Two conceptual convolutional neural network (CNN) schemes are proposed, developed and analysed for directly decoding nonlinear frequency division multiplexing (NFDM) signals with hardware implementation taken into consideration. A serial network scheme with a small network size is designed for small user applications, and a parallel network scheme with high speed is designed for places such as data centres. The work aimed at showing the potential of using CNN for practical NFDM-based fibre optic communication. In the numerical demonstrations, the serial network only occupies 0.5 MB of memory space while the parallel network occupies 128 MB of memory but allows parallel computing. Both network schemes were trained with simulated data and reached more than 99.9% accuracy.https://doi.org/10.1038/s41598-022-12141-4 |
| spellingShingle | Wen Qi Zhang Terence H. Chan Shahraam Afshar Vahid Serial and parallel convolutional neural network schemes for NFDM signals Scientific Reports |
| title | Serial and parallel convolutional neural network schemes for NFDM signals |
| title_full | Serial and parallel convolutional neural network schemes for NFDM signals |
| title_fullStr | Serial and parallel convolutional neural network schemes for NFDM signals |
| title_full_unstemmed | Serial and parallel convolutional neural network schemes for NFDM signals |
| title_short | Serial and parallel convolutional neural network schemes for NFDM signals |
| title_sort | serial and parallel convolutional neural network schemes for nfdm signals |
| url | https://doi.org/10.1038/s41598-022-12141-4 |
| work_keys_str_mv | AT wenqizhang serialandparallelconvolutionalneuralnetworkschemesfornfdmsignals AT terencehchan serialandparallelconvolutionalneuralnetworkschemesfornfdmsignals AT shahraamafsharvahid serialandparallelconvolutionalneuralnetworkschemesfornfdmsignals |