Name
Abstract | ||
|---|---|---|
In this paper, we propose a practical deep neural network for OFDM symbol equalization and demonstrate its advantages in combating large Doppler Shift. In particular, a novel zero-forcing initialized neural architecture named Cascaded Net (CN) is proposed for equalization, where deep trainable network is cascaded behind a zero-forcing preprocessor to prevent the network getting stuck in a saddle point or a local minimum point. In addition, we propose a sliding equalization approach to detect those OFDM symbols with large number of subcarriers. We also evaluate this novel equalizer, as well as the sliding algorithm, using Rayleigh fading channel with large Doppler shift. The numerical results show this novel equalizer can achieve better performance than zero-forcing equalizer and classical ICI cancellation methods in SISO scenario. Thanks to proper training methods, this equalizer is relatively robust to traditional methods when channel estimation is inaccurate or Doppler shift changes. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/VTCFall.2019.8891326 | 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall) |
Keywords | Field | DocType |
zero-forcing initialized neural architecture,OFDM equalizer,Doppler Shift channel,channel estimation,classical ICI cancellation methods,Rayleigh fading channel,sliding algorithm,OFDM symbols,sliding equalization approach,local minimum point,saddle point,deep trainable network,OFDM symbol equalization,deep neural network,deep learning | Frequency domain,Rayleigh fading,Equalization (audio),Computer science,Communication channel,Electronic engineering,Artificial intelligence,Deep learning,Doppler effect,Artificial neural network,Orthogonal frequency-division multiplexing | Conference |
ISSN | ISBN | Citations |
1090-3038 | 978-1-7281-1221-3 | 1 |
PageRank | References | Authors |
0.37 | 8 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Qisheng Huang | 1 | 1 | 0.71 |
| Chunming Zhao | 2 | 671 | 64.30 |
| Ming Jiang | 3 | 198 | 31.08 |
| xiaomin li | 4 | 111 | 6.88 |
| Jing Liang | 5 | 19 | 10.54 |