Abstract | ||
---|---|---|
To combat the inter-symbol interference (ISI) and the inter-block interference (IBI) caused by multi-path fading in orthogonal frequency-division multiplexing (OFDM) systems, it is usually recommended employing a cyclic prefix (CP) with length equal to the channel order. In some practical cases, however, the channel order is not exactly known. Looking for a balance between a full-sized CP and its absence, we investigate the redundancy issues and propose a minimum redundancy OFDM receiver using deep-learning (DL) tools. In this way, we can benefit from an improved reception performance, when compared with CP-free case, and also a better spectrum utilization when compared with the CP-OFDM case. Moreover, compared with the CP-free case, improved performance can be obtained even when the channel order is not available. Simulation results indicate that a good BER level can be achieved and the proposed technique can also be applied in other DL-based receivers. |
Year | DOI | Venue |
---|---|---|
2020 | 10.23919/Eusipco47968.2020.9287725 | 28TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2020) |
Keywords | DocType | ISSN |
deep-learning, channel-estimation, symbol-detection, OFDM, minimum-redundancy | Conference | 2076-1465 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marcele O. K. Mendonca | 1 | 3 | 2.06 |
Paulo S. R. Diniz | 2 | 247 | 38.72 |