DeepSIC: Deep Soft Interference Cancellation for Multiuser MIMO Detection

@article{Shlezinger2021DeepSICDS,
  title={DeepSIC: Deep Soft Interference Cancellation for Multiuser MIMO Detection},
  author={Nir Shlezinger and Rong Fu and Yonina C. Eldar},
  journal={IEEE Transactions on Wireless Communications},
  year={2021},
  volume={20},
  pages={1349-1362}
}
Digital receivers are required to recover the transmitted symbols from their observed channel output. In multiuser multiple-input multiple-output (MIMO) setups, where multiple symbols are simultaneously transmitted, accurate symbol detection is challenging. A family of algorithms capable of reliably recovering multiple symbols is based on interference cancellation. However, these methods assume that the channel is linear, a model which does not reflect many relevant channels, as well as require… 
[PDF] Semantic Reader
50 Citations
Highly Influential Citations
4
Background Citations
15
Methods Citations
24

Figures from this paper

50 Citations

Data-Driven Symbol Detection Via Model-Based Machine Learning

This work presents a data-driven framework to symbol detection design that combines machine learning (ML) and model-based algorithms that only replaces the channel-model-based computations with dedicated neural networks that can be trained from a small amount of data, while keeping the general algorithm intact.

ViterbiNet: A Deep Learning Based Viterbi Algorithm for Symbol Detection

ViterbiNet, which is a data-driven symbol detector that does not require channel state information (CSI), is obtained by integrating deep neural networks (DNNs) into the Viterbi algorithm and demonstrates the conceptual benefit of designing communication systems that integrate DNNs into established algorithms.

Data-Driven Factor Graphs for Deep Symbol Detection

The results indicate that by utilizing ML tools to learn factor graphs from labeled data, one can implement a broad range of model-based algorithms, which traditionally require full knowledge of the underlying statistics, in a data-driven fashion.

UPR: A Model-Driven Architecture for Deep Phase Retrieval

This paper proposes a hybrid model-based data-driven deep architecture, referred to as Unfolded Phase Retrieval (UPR), that shows potential in improving the performance of the state-of-the-art phase retrieval algorithms.

Deep Learning-Based Decoding and AP Selection for Radio Stripe Network

The proposed DNN Based Parallel Decoding in Radio Stripe (DNNBPDRS) framework not only improves Symbol Error Rate (SER) performance when compared to counterparts but is also proved to be comparatively far lesser computational complex.

DNN-based distributed sequential uplink processing in cell-free massive MIMO based on radio stripes

This study proposes DNN ‐ based distributed sequential uplink processing for detecting symbols in the uplink of CFMMRS network architecture and Simulation results show that the proposed algorithm outperforms the traditional iterative soft interference cancellation ‹ based detection method.

Deep Learning Based Successive Interference Cancellation for the Non-Orthogonal Downlink

A deep learning-aided SIC detector termed SICNet is proposed, which replaces the interference cancellation blocks of SIC by deep neural networks (DNNs), which reliably detects the superimposed symbols in the downlink of non-orthogonal systems while being less sensitive to CSI uncertainty than its model-based counterpart.

Jointly Learned Symbol Detection and Signal Reflection in RIS-Aided Multi-user MIMO Systems

A Machine Learning (ML) approach is proposed to jointly design the multi-antenna receiver and configure the RIS reflection coefficients and demonstrate the capability of the proposed approach to provide reliable communications in non-linear channel conditions corrupted by Gaussian noise.

CSI-Free Geometric Symbol Detection via Semi-Supervised Learning and Ensemble Learning

This work employs both semi-supervised learning and ensemble learning to design a flexible parallelizable approach to symbol detection and proves theoretically that the proposed algorithms can arbitrarily approach the performance of the MLD algorithm with perfect CSI.

MetaSSD: Meta-Learned Self-Supervised Detection

A meta-learning-based self-supervised symbol detector named MetaSSD is proposed, which helps the model adapt to a new channel environment based on experience with various meta-training environments, and help the model to use relatively less supervision than the previously suggested learning-based detectors.

References

SHOWING 1-10 OF 58 REFERENCES

Iterative (turbo) soft interference cancellation and decoding for coded CDMA

Simulation results demonstrate that the proposed low complexity iterative receivers structure for interference suppression and decoding offers significant performance gain over the traditional noniterative receiver structure.

Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems

The proposed deep learning-based approach to handle wireless OFDM channels in an end-to-end manner is more robust than conventional methods when fewer training pilots are used, the cyclic prefix is omitted, and nonlinear clipping noise exists.

Model-Driven Deep Learning for Joint MIMO Channel Estimation and Signal Detection

The model-driven DL based JCESD scheme significantly improves the performance of the corresponding traditional iterative detector and the signal detector exhibits superior robustness to signal-to-noise ratio (SNR) and channel correlation mismatches.

Multistage detection in asynchronous code-division multiple-access communications

A multiuser detection strategy for coherent demodulation in an asynchronous code-division multiple-access system is proposed and analyzed, showing that the two-stage receiver is particularly well suited for near-far situations, approaching performance of single-user communications as the interfering signals become stronger.

One-Bit OFDM Receivers via Deep Learning

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 and proposes a two-step sequential training policy for this model.

On the Spectral Efficiency of Noncooperative Uplink Massive MIMO Systems

This paper characterize the spectral efficiency of massive MIMO when the BSs are allowed to jointly decode the received signals, and considers four schemes for treating the interference, and derives the achievable average ergodic rates for both finite and asymptotic number of antennas for each scheme.

A Model-Driven Deep Learning Network for MIMO Detection

Numerical results show that the proposed approach can improve the performance of the iterative algorithm significantly under Rayleigh and correlated MIMO channels.

Asymptotic Task-Based Quantization With Application to Massive MIMO

This paper focuses on the task of recovering a desired signal statistically related to the high-dimensional input, and analyzes two quantization approaches, and considers vector quantization, which is typically computationally infeasible, and the optimal performance achievable with this approach.

Iterative soft interference cancellation for multiple antenna systems

Simulations results show that an SNR gain of about 3 to 5 dB can be obtained by the proposed soft cancellation scheme, which is derived from the maximum a posteriori (MAP) criterion.

Brain-Inspired Wireless Communications: Where Reservoir Computing Meets MIMO-OFDM

Simulation results for the uncoded bit error rate of nonlinear MIMO-OFDM systems show that the introduced scheme outperforms conventional symbol detection methods.
...