Reliable Low Resolution 01-4DM Receivers via Deep Learning

2018-01-01
Balevi, Eren
Andrews, Jeffrey G.
This paper develops novel deep learning-based architectures and design methodologies for an orthogonal frequency division multiplexing (OFDM) receiver under the constraint of one-bit complex quantization. Single bit quantization greatly reduces complexity and power consumption, but makes accurate data detection difficult. This is particularly true for multicarrier waveforms, which have high peak-to-average ratio in the time domain and fragile subcarrier orthogonality in the frequency domain. The severe distortion for one-hit quantization typically results in an error floor even at moderately low signal-to-noise ratio (SNR) such as 5 dB. A neural network-based receiver - specifically, an autoencoder- jointly learns a precoder and decoder for data symbol detection. Since quantization prevents end-to-end training, we propose a two-step sequential training policy for this model. Our proposed design achieves lower bit error rate (BER) in fading than unquantized (full-resolution) OFDM at average SNRs up to 10 dB.
52nd Asilomar Conference on Signals, Systems, and Computers

Suggestions

One-Bit OFDM Receivers via Deep Learning
Balevi, Eren; Andrews, Jeffrey G. (2019-06-01)
This paper develops novel deep learning-based architectures and design methodologies for an orthogonal frequency division multiplexing (OFDM) receiver under the constraint of one-bit complex quantization. Single bit quantization reduces greatly the complexity and power consumption but makes accurate channel estimation and data detection difficult. This is particularly true for multicarrier waveforms that have high peak-to-average power ratio in the time domain and fragile subcarrier orthogonality in the fre...
Compressed Representation of High Dimensional Channels using Deep Generative Networks
Doshi, Akash; Balevi, Eren; Andrews, Jeffrey G. (2020-05-01)
© 2020 IEEE.This paper proposes a novel compressed representation for high dimensional channel matrices obtained by optimization of the input to a deep generative network. Channel estimation using generative networks constrains the reconstructed channel to lie in the range of the generative model, which allows it to outperform conventional channel estimation techniques in the presence of limited number of pilots. It also eliminates the need for explicit knowledge of the sparsifying basis for mmWave multiple...
Efficient Three-Layer Iterative Solutions of Electromagnetic Problems Using the Multilevel Fast Multipole Algorithm
Onol, Can; Ucuncu, Arif; Ergül, Özgür Salih (2017-05-19)
We present a three-layer iterative algorithm for fast and efficient solutions of electromagnetic problems formulated with surface integral equations. The strategy is based on nested iterative solutions employing the multilevel fast multipole algorithm and its approximate forms. We show that the three-layer mechanism significantly reduces solution times, while it requires no additional memory as opposed to algebraic preconditioners. Numerical examples involving three-dimensional scattering problems are prese...
An Efficient Hybrid Beamforming and Channel Acquisition for Wideband mm-Wave Massive MIMO Channels
Kurt, Anıl; Güvensen, Gökhan Muzaffer (2019-01-01)
In this paper, an efficient hybrid beamforming architecture together with a novel spatio-temporal receiver processing is proposed for single-carrier (SC) mm-wave wideband massive MIMO channels in time-domain duplex (TDD) mode. The design of two-stage beamformers is realized by using a virtual sectorization via second-order channel statistics based user grouping. The novel feature of the proposed architecture is that the effect of both inter-group-interference (due to non-orthogonality of virtual angular sec...
Deep learning-based encoder for one-bit quantization
Balevi, Eren; Andrews, Jeffrey G. (2019-12-01)
© 2019 IEEE.This paper proposes a deep learning-based error correction coding for AWGN channels under the constraint of one-bit quantization in receivers. An autoencoder is designed and integrated with a turbo code that acts as an implicit regularization. This implicit regularizer facilitates approaching the Shannon bound for the one-bit quantized AWGN channels even if the autoencoder is trained suboptimally, since one-bit quantization stymies ideal training. Our empirical results show that the proposed cod...
Citation Formats
E. Balevi and J. G. Andrews, “Reliable Low Resolution 01-4DM Receivers via Deep Learning,” presented at the 52nd Asilomar Conference on Signals, Systems, and Computers, California, Amerika Birleşik Devletleri, 2018, Accessed: 00, 2022. [Online]. Available: https://hdl.handle.net/11511/100646.