Deep Learning Based Preamble Detection and TOA Estimation

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.

[1]  G.B. Giannakis,et al.  Localization via ultra-wideband radios: a look at positioning aspects for future sensor networks , 2005, IEEE Signal Processing Magazine.

[2]  Carlos Fernandez-Granda,et al.  Deconvolution of Point Sources: A Sampling Theorem and Robustness Guarantees , 2017, Communications on Pure and Applied Mathematics.

[3]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[4]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[5]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[6]  Daniel George,et al.  Deep Neural Networks to Enable Real-time Multimessenger Astrophysics , 2016, ArXiv.

[7]  R. Tibshirani,et al.  Least angle regression , 2004, math/0406456.

[8]  Alexander M. Haimovich,et al.  High Precision TOA-based Direct Localization of Multiple Sources in Multipath , 2015, ArXiv.

[9]  Songtao Lu,et al.  A multipath mitigation algorithm in Global Navigation Satellite Systems arrays using Independent Component Analysis , 2010, 2010 IEEE International Conference on Wireless Communications, Networking and Information Security.

[10]  Mingyi Hong,et al.  Limited Feedback Double Directional Massive MIMO Channel Estimation: From Low-Rank Modeling to Deep Learning , 2018, 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[12]  Geoffrey Ye Li,et al.  Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems , 2017, IEEE Wireless Communications Letters.

[13]  Jakob Hoydis,et al.  An Introduction to Deep Learning for the Physical Layer , 2017, IEEE Transactions on Cognitive Communications and Networking.

[14]  N. Sidiropoulos,et al.  Learning to Optimize: Training Deep Neural Networks for Interference Management , 2017, IEEE Transactions on Signal Processing.

[15]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[16]  Songtao Lu,et al.  A Wideband Space Time Statistical Model for Characterization of Satellite Communication Channel in Dense Multipath Environment , 2010, 2010 IEEE 71st Vehicular Technology Conference.