Low-Complexity Detection Based on Belief Propagation in a Massive MIMO System

Fukuda, Wataru; Takashi, Abiko; Nishimura, Toshihiko; Ohgane, Takeo; Ogawa, Yasutaka; Ohwatari, Yusuke; Kishiyama, Yoshihisa

doi:10.1109/vtcspring.2013.6692622

Cited by 62 publications

(47 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…MIMO systems can be modeled by a factor graph as in Fig. 1 according to [29]. BP allows observation nodes to transfer belief information with symbol nodes back and forth to iteratively improve the reliability for decision.…”

Section: B Belief Propagation Detectormentioning

confidence: 99%

Improving Massive MIMO Message Passing Detectors With Deep Neural Network

Tan

Sun

et al. 2020

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

In this paper, deep neural network (DNN) is utilized to improve the belief propagation (BP) detection for massive multiple-input multiple-output (MIMO) systems. A neural network architecture suitable for detection task is firstly introduced by unfolding BP algorithms. DNN MIMO detectors are then proposed based on two modified BP detectors, damped BP and maxsum BP. The correction factors in these algorithms are optimized through deep learning techniques, aiming at improved detection performance. Numerical results are presented to demonstrate the performance of the DNN detectors in comparison with various BP modifications. The neural network is trained once and can be used for multiple online detections. The results show that, compared to other state-of-the-art detectors, the DNN detectors can achieve lower bit error rate (BER) with improved robustness against various antenna configurations and channel conditions at the same level of complexity.Index Terms-massive MIMO, deep learning, deep neural network, belief propagation (BP).

show abstract

Section: B Belief Propagation Detectormentioning

confidence: 99%

Improving Massive MIMO Message Passing Detectors With Deep Neural Network

Tan

Sun

et al. 2020

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

show abstract

“…In FG for MIMO channels, the dependency is determined by the channel response with statistically distribution. Therefore, the number of major connections would substantially not become so large with the increase of antennas [14]. As a result, the effective number of critical loops is not that large, which makes BP detection promising for large-scale MIMO systems.…”

Section: A Fg For Mimo Channelsmentioning

confidence: 99%

Improved symbol-based belief propagation detection for large-scale MIMO

Yang

Zhang

Xiao

et al. 2015

2015 IEEE Workshop on Signal Processing Systems (SiPS)

View full text Add to dashboard Cite

In this paper, BP detection based on belief propagation in real domain for large-scale MIMO systems is proposed. Numerical results have shown that, with quadrature phase shift keying (QPSK) modulation, this approach can show 1 dB performance improvement at the BER of 10 −2 , compared to conventional single-edge based BP (SE-BP) in complex domain. Based on the proposed BP detection, its symbol-based variation is also investigated for applications in large-scale MIMO systems with a high-order modulation. This symbol-based method successfully reduces computational complexity by avoiding large dimensional matrix inversion and decomposition. Since the proposed method can also shrink the constellation size, its complexity can be further reduced. Numerical simulation results and complexity comparison have demonstrated that the proposed symbol-based BP detection can show advantages in both performance and complexity compared to existing ones. Therefore, it is suitable for large-scale MIMO system applications, especially for those with high-order modulations.Index Terms-Large-scale MIMO, belief propagation (BP), symbol-based, message passing, iterative detection.

show abstract

“…As in the works of Wang and Giannakis, 21,22 we used a method for generating soft information by means of hard estimates. It is based on the use of a low-complexity hard-output inner massive MIMO detector [23][24][25][26][27] followed by a series of parallel interference cancelations (PICs) and filtering to produce inputs to the MAP detector, which are independent of the number of transmitting antennas. Besides, differently from the mentioned previous work, we do not consider the matrix channel coefficients to be known by the system.…”

Section: Introductionmentioning

confidence: 99%

Low‐complexity soft‐output MIMO uplink detection for large systems iterative detection and decoding

Pereira

Sampaio‐Neto

2018

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Iterative detection and decoding techniques, based on the turbo principle, have been proposed in the literature to achieve near‐capacity on both single‐ and multiple‐antenna fading communication systems. In the multiple‐input–multiple‐output case, when a very large system is considered, one major issue is the overall system complexity. Here, we propose an iterative detection and decoding scheme for the uplink of coded multiple‐input–multiple‐output systems that replaces the exponential complexity maximum a posteriori detector by an approximate maximum a posteriori low‐complexity detector that uses a simple hard‐output inner detector at the first iteration followed by parallel interference cancelation and filtering matched to the channel coefficient matrix that is estimated with the aid of orthogonal pilot transmission. From the second iteration onward, the inner hard‐output detector is replaced by the results from the previous iteration. Simulation results demonstrate that the proposed strategy presents good bit‐error‐rate performance with low computational complexity, measured by the average number of floating‐point operations per message bit.

show abstract

Low-Complexity Detection Based on Belief Propagation in a Massive MIMO System

Cited by 62 publications

References 10 publications

Improving Massive MIMO Message Passing Detectors With Deep Neural Network

Improving Massive MIMO Message Passing Detectors With Deep Neural Network

Improved symbol-based belief propagation detection for large-scale MIMO

Low‐complexity soft‐output MIMO uplink detection for large systems iterative detection and decoding

Contact Info

Product

Resources

About