# Application of Deep Learning to Sphere Decoding for Large MIMO Systems

@article{Nguyen2021ApplicationOD, title={Application of Deep Learning to Sphere Decoding for Large MIMO Systems}, author={Nhan Thanh Nguyen and Kyungchun Lee and Huaiyu DaiIEEE}, journal={IEEE Transactions on Wireless Communications}, year={2021}, volume={20}, pages={6787-6803} }

Although the sphere decoder (SD) is a powerful detector for multiple-input multiple-output (MIMO) systems, it has become computationally prohibitive in massive MIMO systems, where a large number of antennas are employed. To overcome this challenge, we propose fast deep learning (DL)-aided SD (FDL-SD) and fast DL-aided <inline-formula> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula>-best SD (KSD, FDL-KSD) algorithms. Therein, the major application of DL is to generate a highly…

## Figures and Tables from this paper

## 3 Citations

Towards Optimally Efficient Search with Deep Learning for Large-Scale MIMO Systems

- Computer Science, Mathematics
- 2021

Simulation results show that the proposed hyperaccelerated tree search (HATS) algorithm reaches almost the optimal bit error rate (BER) performance in large-scale systems, while the memory size can be bounded, and thereby it is applicable for large- scale systems.

Intelligent Radio Signal Processing: A Survey

- Computer Science, EngineeringIEEE Access
- 2021

This survey covers four intelligent signal processing topics for the wireless physical layer, including modulation classification, signal detection, beamforming, and channel estimation, and presents a brief overview of AI techniques such as machine learning, deep learning, and federated learning.

Machine Learning-based Reconfigurable Intelligent Surface-aided MIMO Systems

- Computer Science, Engineering2021 IEEE 22nd International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)
- 2021

This work proposes a low-complexity unsupervised learning scheme, referred to as learning-phase-shift neural net-work (LPSNet), to efficiently find the solution to the spectral efficiency maximization problem in RIS-aided MIMO systems.

## References

SHOWING 1-10 OF 34 REFERENCES

Learning-Aided Deep Path Prediction for Sphere Decoding in Large MIMO Systems

- Computer Science, EngineeringIEEE Access
- 2020

A novel learning-aided sphere decoding scheme for large multiple-input–multiple-output systems, namely, deep path prediction-based sphere decoding (DPP-SD), which employs a neural network to predict the minimum metrics of the “deep” paths in sub-trees before commencing the tree search in SD.

DNN assisted Sphere Decoder

- Computer Science2019 IEEE International Symposium on Information Theory (ISIT)
- 2019

It is shown through simulation that for high dimensional MIMO systems the number of lattice points highly reduces in the new SD algorithm, which leads to a complexity only 3 times of the MMSE decoder complexity.

Deep Learning-Aided Tabu Search Detection for Large MIMO Systems

- Computer Science, MathematicsIEEE Transactions on Wireless Communications
- 2020

This study proposes a DL-aided TS algorithm, in which the initial solution is approximated by the proposed FS-Net, and achieves approximately 90% complexity reduction for a MIMO system with QPSK with respect to the existing TS algorithms, while maintaining almost the same performance.

Learned Conjugate Gradient Descent Network for Massive MIMO Detection

- Engineering, Computer ScienceICC 2020 - 2020 IEEE International Conference on Communications (ICC)
- 2020

This work considers the use of model-driven deep learning techniques for signal detection in massive multiple-input multiple-output (MIMO) system and proposes a learned conjugate gradient descent network, referred to as LcgNet, which can achieve superior performance over some state-of-the-art MIMO detectors with much lower computational complexity.

Adaptive Neural Signal Detection for Massive MIMO

- Engineering, Computer ScienceIEEE Transactions on Wireless Communications
- 2020

MMNet is a deep learning MIMO detection scheme that significantly outperforms existing approaches on realistic channels with the same or lower computational complexity, and is 4–8dB better overall than a classic linear scheme like the minimum mean square error (MMSE) detector.

Trainable Projected Gradient Detector for Massive Overloaded MIMO Channels: Data-Driven Tuning Approach

- Computer Science, MathematicsIEEE Access
- 2019

The numerical simulations show that the proposed detector achieves a comparable detection performance to those of the existing algorithms for the massively overloaded MIMO channels, e.g., the state-of-the-art IW-SOAV detector, with a lower computation cost.

Deep Learning-Based Sphere Decoding

- Computer Science, EngineeringIEEE Transactions on Wireless Communications
- 2019

The performance achieved by the proposed DL-based sphere decoding algorithm is very close to the optimal maximum likelihood decoding (MLD) over a wide range of signal-to-noise ratios (SNRs), while the computational complexity, compared to existing sphere decoding variants, is significantly reduced.

Algorithm and implementation of the K-best sphere decoding for MIMO detection

- Computer ScienceIEEE Journal on Selected Areas in Communications
- 2006

The implementation results show that it is feasible to achieve near-ML performance and high detection throughput for a 4/spl times/4 16-QAM MIMO system using the proposed algorithms and the VLSI architecture with reasonable complexity.

Deep learning based likelihood ascent search detection algorithm for uplink multiuser Massive MIMO system

- Computer Science2020 International Conference on Computing, Networking and Communications (ICNC)
- 2020

A deep learning based likelihood ascent search (DPLAS) detection algorithm is proposed on the basis of the graphical detection model for uplink multiuser Massive MIMO system that obtains a better BER performance and requires a lower average received SNR than the counterpart algorithms.

A Low-Complexity Detector for Large MIMO Systems and Multicarrier CDMA Systems

- Computer ScienceIEEE Journal on Selected Areas in Communications
- 2008

A low-complexity detector which achieves uncoded near-exponential diversity performance for hundreds of antennas with an average per-bit complexity of just O(NtNr), where Nt and Nr denote the number of transmit and receive antennas, respectively is presented.