Support vector machine-based blind equalization for high-order QAM with short data length
In this paper, the problem of blind equalization of high-order quadrature amplitude modulation (QAM) signals is tackled by using a batch equalizer based on support vector regression (SVR). A new set of error functions weighted by neighborhood symbol decisions and augmented by generalized power facto...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/164974 |
| _version_ | 1811680622409678848 |
|---|---|
| author | Liu, Xiaobei Guan, Yong Liang Xu, Qiang |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Liu, Xiaobei Guan, Yong Liang Xu, Qiang |
| author_sort | Liu, Xiaobei |
| collection | NTU |
| description | In this paper, the problem of blind equalization of high-order quadrature amplitude modulation (QAM) signals is tackled by using a batch equalizer based on support vector regression (SVR). A new set of error functions weighted by neighborhood symbol decisions and augmented by generalized power factors p and q, are proposed to be used as the penalty terms in SVR, and the optimal values of p and q are determined. In addition, we propose a method to remove the high online computational complexity incurred by the inclusion of neighborhood terms in the new error function. Simulation results show that with about the same complexity, the optimized SVR-NA-SBD-(p,q) attain much lower residual inter-symbol-interference and higher probability of convergence than the best known SVR-MMA, and it needs only about 1400 symbols to achieve a BER of 10^{-4} for 256QAM in a multipath channel. In contrast, the conventional SVR-MMA needs more than 4000 symbols to achieve such BER. |
| first_indexed | 2024-10-01T03:27:59Z |
| format | Journal Article |
| id | ntu-10356/164974 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:27:59Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1649742023-03-09T15:32:26Z Support vector machine-based blind equalization for high-order QAM with short data length Liu, Xiaobei Guan, Yong Liang Xu, Qiang School of Electrical and Electronic Engineering Temasek Laboratories @ NTU Engineering::Electrical and electronic engineering::Wireless communication systems Batch Equalizer Blind Equalization In this paper, the problem of blind equalization of high-order quadrature amplitude modulation (QAM) signals is tackled by using a batch equalizer based on support vector regression (SVR). A new set of error functions weighted by neighborhood symbol decisions and augmented by generalized power factors p and q, are proposed to be used as the penalty terms in SVR, and the optimal values of p and q are determined. In addition, we propose a method to remove the high online computational complexity incurred by the inclusion of neighborhood terms in the new error function. Simulation results show that with about the same complexity, the optimized SVR-NA-SBD-(p,q) attain much lower residual inter-symbol-interference and higher probability of convergence than the best known SVR-MMA, and it needs only about 1400 symbols to achieve a BER of 10^{-4} for 256QAM in a multipath channel. In contrast, the conventional SVR-MMA needs more than 4000 symbols to achieve such BER. Centre for Strategic Infocomm Technologies (MINDEF) Nanyang Technological University Submitted/Accepted version This work was supported by Temasek Laboratories@NTU Signal Research Programme Phase 3 under Grant DSOCL17187. 2023-03-06T08:00:49Z 2023-03-06T08:00:49Z 2021 Journal Article Liu, X., Guan, Y. L. & Xu, Q. (2021). Support vector machine-based blind equalization for high-order QAM with short data length. IEEE Signal Processing Letters, 28, 259-263. https://dx.doi.org/10.1109/LSP.2021.3050928 1070-9908 https://hdl.handle.net/10356/164974 10.1109/LSP.2021.3050928 2-s2.0-85099551577 28 259 263 en DSOCL17187 IEEE Signal Processing Letters © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/ 10.1109/LSP.2021.3050928. application/pdf |
| spellingShingle | Engineering::Electrical and electronic engineering::Wireless communication systems Batch Equalizer Blind Equalization Liu, Xiaobei Guan, Yong Liang Xu, Qiang Support vector machine-based blind equalization for high-order QAM with short data length |
| title | Support vector machine-based blind equalization for high-order QAM with short data length |
| title_full | Support vector machine-based blind equalization for high-order QAM with short data length |
| title_fullStr | Support vector machine-based blind equalization for high-order QAM with short data length |
| title_full_unstemmed | Support vector machine-based blind equalization for high-order QAM with short data length |
| title_short | Support vector machine-based blind equalization for high-order QAM with short data length |
| title_sort | support vector machine based blind equalization for high order qam with short data length |
| topic | Engineering::Electrical and electronic engineering::Wireless communication systems Batch Equalizer Blind Equalization |
| url | https://hdl.handle.net/10356/164974 |
| work_keys_str_mv | AT liuxiaobei supportvectormachinebasedblindequalizationforhighorderqamwithshortdatalength AT guanyongliang supportvectormachinebasedblindequalizationforhighorderqamwithshortdatalength AT xuqiang supportvectormachinebasedblindequalizationforhighorderqamwithshortdatalength |