ELM‐based timing synchronization for OFDM systems by exploiting computer‐aided training strategy
Abstract Due to the implementation bottleneck of training data collection in realistic wireless communications systems, supervised learning‐based timing synchronization (TS) is challenged by the incompleteness of training data. To tackle this bottleneck, the computer‐aided approach is extended, with...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-09-01
|
| Series: | IET Communications |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cmu2.12655 |
| _version_ | 1797729171348127744 |
|---|---|
| author | Mintao Zhang Shuhai Tang Chaojin Qing Na Yang Xi Cai Jiafan Wang |
| author_facet | Mintao Zhang Shuhai Tang Chaojin Qing Na Yang Xi Cai Jiafan Wang |
| author_sort | Mintao Zhang |
| collection | DOAJ |
| description | Abstract Due to the implementation bottleneck of training data collection in realistic wireless communications systems, supervised learning‐based timing synchronization (TS) is challenged by the incompleteness of training data. To tackle this bottleneck, the computer‐aided approach is extended, with which the local device can generate the training data instead of generating learning labels from the received samples collected in realistic systems, and then construct an extreme learning machine (ELM)‐based TS network in orthogonal frequency division multiplexing (OFDM) systems. Specifically, by leveraging the rough information of channel impulse responses (CIRs), i.e. root‐mean‐square (r.m.s) delay, the loose constraint‐based and flexible constraint‐based training strategies are proposed for the learning‐label design against the maximum multi‐path delay. The underlying mechanism is to improve the completeness of multi‐path delays that may appear in the realistic wireless channels and thus increase the statistical efficiency of the designed TS learner. By this means, the proposed ELM‐based TS network can alleviate the degradation of generalization performance. Numerical results reveal the robustness and generalization of the proposed scheme against varying parameters. |
| first_indexed | 2024-03-12T11:25:10Z |
| format | Article |
| id | doaj.art-70640fd1be6e4bdd8b686e76999b3689 |
| institution | Directory Open Access Journal |
| issn | 1751-8628 1751-8636 |
| language | English |
| last_indexed | 2024-03-12T11:25:10Z |
| publishDate | 2023-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Communications |
| spelling | doaj.art-70640fd1be6e4bdd8b686e76999b36892023-09-01T09:09:12ZengWileyIET Communications1751-86281751-86362023-09-0117151806181910.1049/cmu2.12655ELM‐based timing synchronization for OFDM systems by exploiting computer‐aided training strategyMintao Zhang0Shuhai Tang1Chaojin Qing2Na Yang3Xi Cai4Jiafan Wang5School of Electrical Engineering and Electronic Information Xihua University ChengduChinaSchool of Electrical Engineering and Electronic Information Xihua University ChengduChinaSchool of Electrical Engineering and Electronic Information Xihua University ChengduChinaSchool of Electrical Engineering and Electronic Information Xihua University ChengduChinaSchool of Electrical Engineering and Electronic Information Xihua University ChengduChinaSchool of Electrical Engineering and Electronic Information Xihua University ChengduChinaAbstract Due to the implementation bottleneck of training data collection in realistic wireless communications systems, supervised learning‐based timing synchronization (TS) is challenged by the incompleteness of training data. To tackle this bottleneck, the computer‐aided approach is extended, with which the local device can generate the training data instead of generating learning labels from the received samples collected in realistic systems, and then construct an extreme learning machine (ELM)‐based TS network in orthogonal frequency division multiplexing (OFDM) systems. Specifically, by leveraging the rough information of channel impulse responses (CIRs), i.e. root‐mean‐square (r.m.s) delay, the loose constraint‐based and flexible constraint‐based training strategies are proposed for the learning‐label design against the maximum multi‐path delay. The underlying mechanism is to improve the completeness of multi‐path delays that may appear in the realistic wireless channels and thus increase the statistical efficiency of the designed TS learner. By this means, the proposed ELM‐based TS network can alleviate the degradation of generalization performance. Numerical results reveal the robustness and generalization of the proposed scheme against varying parameters.https://doi.org/10.1049/cmu2.12655learning (artificial intelligence)OFDM modulationsynchronisation |
| spellingShingle | Mintao Zhang Shuhai Tang Chaojin Qing Na Yang Xi Cai Jiafan Wang ELM‐based timing synchronization for OFDM systems by exploiting computer‐aided training strategy IET Communications learning (artificial intelligence) OFDM modulation synchronisation |
| title | ELM‐based timing synchronization for OFDM systems by exploiting computer‐aided training strategy |
| title_full | ELM‐based timing synchronization for OFDM systems by exploiting computer‐aided training strategy |
| title_fullStr | ELM‐based timing synchronization for OFDM systems by exploiting computer‐aided training strategy |
| title_full_unstemmed | ELM‐based timing synchronization for OFDM systems by exploiting computer‐aided training strategy |
| title_short | ELM‐based timing synchronization for OFDM systems by exploiting computer‐aided training strategy |
| title_sort | elm based timing synchronization for ofdm systems by exploiting computer aided training strategy |
| topic | learning (artificial intelligence) OFDM modulation synchronisation |
| url | https://doi.org/10.1049/cmu2.12655 |
| work_keys_str_mv | AT mintaozhang elmbasedtimingsynchronizationforofdmsystemsbyexploitingcomputeraidedtrainingstrategy AT shuhaitang elmbasedtimingsynchronizationforofdmsystemsbyexploitingcomputeraidedtrainingstrategy AT chaojinqing elmbasedtimingsynchronizationforofdmsystemsbyexploitingcomputeraidedtrainingstrategy AT nayang elmbasedtimingsynchronizationforofdmsystemsbyexploitingcomputeraidedtrainingstrategy AT xicai elmbasedtimingsynchronizationforofdmsystemsbyexploitingcomputeraidedtrainingstrategy AT jiafanwang elmbasedtimingsynchronizationforofdmsystemsbyexploitingcomputeraidedtrainingstrategy |