Abstract | ||
---|---|---|
Accurate Time of Arrival (TOA) estimation has many use cases, including 5G initial access and localization. However, due to multipath propagation and noise, the correlation-based TOA estimation may not be accurate. In this paper, a deep learning based framework is proposed for preamble detection and TOA estimation without the need of knowing the transmit waveform. Extensive simulations on both synthetic data and real measured data show that the proposed method improves prediction accuracy by about three times while keeping the same computational complexity in comparison to the correlation method. It also provides 1000x computational reduction compared to the template matching method without loss of accuracy. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/GLOBECOM38437.2019.9013265 | GLOBECOM |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Haoran Sun | 1 | 53 | 4.14 |
Aliye Özge Kaya | 2 | 0 | 0.34 |
Mike Macdonald | 3 | 0 | 0.34 |
Harish Viswanathan | 4 | 477 | 68.86 |
Mingyi Hong | 5 | 1533 | 91.29 |