Training Deep Filters for Physical-Layer Frame Synchronization
In this paper we demonstrate the application of Fully Convolutional Neural Network (FCN) for Frame Synchronization (FS) in bursty single carrier transmissions, commonly used in wireless sensor networks and Internet of Things (IoT) applications. Our approach shows greatly improved performance compare...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Open Journal of the Communications Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9810523/ |
| _version_ | 1811289226062331904 |
|---|---|
| author | Sarunas Kalade Louise H. Crockett Robert W. Stewart |
| author_facet | Sarunas Kalade Louise H. Crockett Robert W. Stewart |
| author_sort | Sarunas Kalade |
| collection | DOAJ |
| description | In this paper we demonstrate the application of Fully Convolutional Neural Network (FCN) for Frame Synchronization (FS) in bursty single carrier transmissions, commonly used in wireless sensor networks and Internet of Things (IoT) applications. Our approach shows greatly improved performance compared to noncoherent correlation-based methods under carrier phase and frequency offsets, especially for shorter preambles. Using a fully convolutional architecture allows the training of a deep filter, which we believe is more suited to signal processing tasks than more commonly used deep learning architectures with fully connected layers. In terms of deployment within a wider communications system, it could be treated similarly to a typical signal processing filter, which means it can be deployed to inputs of arbitrary length. Additionally, because the proposed model is composed only of convolutional layers, the entire model benefits from the weight sharing property of convolutional filters, and results in a greatly reduced memory footprint compared to that of similar models containing fully connected layers. |
| first_indexed | 2024-04-13T03:51:10Z |
| format | Article |
| id | doaj.art-5affbd4b6e3c4990b9de6f1870fdd4ba |
| institution | Directory Open Access Journal |
| issn | 2644-125X |
| language | English |
| last_indexed | 2024-04-13T03:51:10Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of the Communications Society |
| spelling | doaj.art-5affbd4b6e3c4990b9de6f1870fdd4ba2022-12-22T03:03:49ZengIEEEIEEE Open Journal of the Communications Society2644-125X2022-01-0131063107510.1109/OJCOMS.2022.31859739810523Training Deep Filters for Physical-Layer Frame SynchronizationSarunas Kalade0https://orcid.org/0000-0001-5512-7402Louise H. Crockett1https://orcid.org/0000-0003-4436-0254Robert W. Stewart2https://orcid.org/0000-0002-7779-8597Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, U.K.Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, U.K.Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, U.K.In this paper we demonstrate the application of Fully Convolutional Neural Network (FCN) for Frame Synchronization (FS) in bursty single carrier transmissions, commonly used in wireless sensor networks and Internet of Things (IoT) applications. Our approach shows greatly improved performance compared to noncoherent correlation-based methods under carrier phase and frequency offsets, especially for shorter preambles. Using a fully convolutional architecture allows the training of a deep filter, which we believe is more suited to signal processing tasks than more commonly used deep learning architectures with fully connected layers. In terms of deployment within a wider communications system, it could be treated similarly to a typical signal processing filter, which means it can be deployed to inputs of arbitrary length. Additionally, because the proposed model is composed only of convolutional layers, the entire model benefits from the weight sharing property of convolutional filters, and results in a greatly reduced memory footprint compared to that of similar models containing fully connected layers.https://ieeexplore.ieee.org/document/9810523/Deep learningfully convolutional neural networkframe synchronizationInternet of Things |
| spellingShingle | Sarunas Kalade Louise H. Crockett Robert W. Stewart Training Deep Filters for Physical-Layer Frame Synchronization IEEE Open Journal of the Communications Society Deep learning fully convolutional neural network frame synchronization Internet of Things |
| title | Training Deep Filters for Physical-Layer Frame Synchronization |
| title_full | Training Deep Filters for Physical-Layer Frame Synchronization |
| title_fullStr | Training Deep Filters for Physical-Layer Frame Synchronization |
| title_full_unstemmed | Training Deep Filters for Physical-Layer Frame Synchronization |
| title_short | Training Deep Filters for Physical-Layer Frame Synchronization |
| title_sort | training deep filters for physical layer frame synchronization |
| topic | Deep learning fully convolutional neural network frame synchronization Internet of Things |
| url | https://ieeexplore.ieee.org/document/9810523/ |
| work_keys_str_mv | AT sarunaskalade trainingdeepfiltersforphysicallayerframesynchronization AT louisehcrockett trainingdeepfiltersforphysicallayerframesynchronization AT robertwstewart trainingdeepfiltersforphysicallayerframesynchronization |