Yiqing Zhang

Dr. Yiqing Zhang

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 August 2020 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
JSJianyong Sun
Jianyong Sun
YZYiqing Zhang
Yiqing Zhang
JXJiang Xue
Jiang Xue
ZXZongben Xu
Zongben Xu
This paper proposes a novel learning to learn method, called learning to learn iterative search algorithm (LISA), for signal detection in a multi-input multi-output (MIMO) system. The idea is to regard the signal detection problem as a decision making problem over tree. The goal is to learn the optimal decision policy. In LISA, deep neural networks are used as parameterized policy function. Through training, optimal parameters of the neural networks are learned and thus optimal policy can be approximated. Different neural network-based architectures are used for fixed and varying channel models, respectively. LISA provides soft decisions and does not require any information about the additive white Gaussian noise. Simulation results show that LISA 1) obtains near maximum likelihood detection performance in both fixed and varying channel models under QPSK modulation; 2) achieves significantly better bit error rate (BER) performance than classical detectors and recently proposed deep/machine learning based detectors at various modulations and signal to noise (SNR) ratios both under i.i.d and correlated Rayleigh fading channels in the simulation experiments; 3) is robust to MIMO detection problems with imperfect channel state information; and 4) generalizes very well against channel correlation and SNRs.

9 September 2022 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
YZYiqing Zhang
Yiqing Zhang
JSJianyong Sun
Jianyong Sun
JXJiang Xue
Jiang Xue
GLGeoffrey Ye Li
Geoffrey Ye Li
XZXu Zongben
Xu Zongben
To overcome the influence of channel estimation error on signal detection, this paper presents a model-driven deep learning method for joint channel estimation and signal detection in multiple-input multiple-output (MIMO) wireless communication systems. To improve the robustness of the method, we use the Student's t -distribution to model the environment noise, and model the joint problem probabilistically by taking the channel state information (CSI) as a latent variable, then derive a generalized expectation maximization (GEM) algorithm to fit the model. In GEM, the expectation step is used for robust CSI estimation while the maximization step detects the transmitted signal with the estimated CSI. To reduce the computational complexity of GEM, we unfold it into a deep neural network. The network contains only a few trainable parameters, which is easy to train and has low space complexity. Based on our experimental results, we find that the proposed GEM algorithm outperforms a variety of signal detection algorithms which take the CSI estimation and signal detection as independent modules. Further, we find empirically that the proposed GEM network outperforms state-of-the-art deep learning based joint channel estimation and signal detection methods and has a good generalization ability against the number of antennas, the modulation mode, the level of signal-to-noise ratio and channel correlation.

28 August 2023 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
YZYiqing Zhang
Yiqing Zhang
JSJianyong Sun
Jianyong Sun
JXJiang Xue
Jiang Xue
LHLinxi Han
Linxi Han
XZXu Zongben
Xu Zongben
The condition number of the channel matrix greatly affects the performance of existing signal detectors in a multiple-input multiple-output (MIMO) system. When the channel matrix is ill-conditioned, existing sub-optimal and optimal detectors exhibit poor performances. In our early work, we have proposed a learning to learn iterative search algorithm (LISA), in which the MIMO detection problem is modeled as a decision problem over tree. The performance of LISA is close to the maximum likelihood detector (MLD) in some scenarios, but degenerates when the MIMO channel is with large condition number. In this paper, we propose to remedy this problem by incorporating a precoding scheme at the transmitter side to reduce the condition number of the channel matrix. Furthermore, we improve LISA by adding a parallel signal recovery module which is named I-LISA. Extensive experimental results show that incorporating the precoding scheme improves not only the performance of LISA, but also existing signal detectors including MLD. Extensive experimental results show that I-LISA with the proposed precoding scheme achieves better performance than MLD for QPSK and 16QAM, and for 64QAM at low signal-to-noise ratio (SNR) regimes.

17 December 2024 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
YZYiqing Zhang
Yiqing Zhang
JSJianyong Sun
Jianyong Sun
JXJiang Xue
Jiang Xue
XZXu Zongben
Xu Zongben
For the signal detection problem in a multiple-input multiple-output (MIMO) system, it has been demonstrated that deep learning can improve the detection accuracy and/or reduce the complexity of traditional detection algorithms under the assumption that the channel scenario remains the same in training and test. However, this assumption is not appropriate since the communication environment in practice is constantly changing. As a result, the performance of deep-learning-based detection methods will degrade significantly due to their lack of generalization ability. To address this problem, we model the channel scenario adaptation problem as a multi-scenario learning task and propose two schemes to improve the adaptability of model-driven detection network to cross-channel scenarios. For the case where the test channel scenario has been seen in the training stage, a hypernetwork is introduced to the deep-learning-based iterative soft thresholding algorithm (DISTA) to generate a personalized set of network parameters for each channel scenario, which is named hyperDISTA. Experimental results show that hyperDISTA trained in multiple channel scenarios can not only adapt to each seen channel scenario but also outperform existing deep-learning-based detectors trained in the single channel scenario at high signal-to-noise ratio (SNR) regimes. For the case where the test channel scenario is unseen in the training stage, we propose to retrain the hyperDISTA in a semi-supervised manner. Experimental results show that the retrained hyperDISTA achieves a performance that is comparable to that of the maximum likelihood detection algorithm (MLD).

21 October 2025 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
JGJianhua Guo
Jianhua Guo
RLRunhua Li
Runhua Li
GLGuanzhang Liu
Guanzhang Liu
ZHZhengyang Hu
Zhengyang Hu
YZYiqing Zhang
Yiqing Zhang
XZXu Zongben
Xu Zongben
The architectural design of the air interface plays a critical role in wireless communications, embedding crucial functionality to guarantee both efficiency and robustness. Physical layer algorithms often face performance challenges in real-world scenarios owing to the basic assumptions of Gaussian noise, channel model linearity, and functional separation. This paper explores intelligent air interface (IAI) algorithms for multiple-input multiple-output (MIMO) systems to overcome the limitations of these assumptions. The physical layer link is restructured as a composite of various functions and framed as a mathematical optimization problem aimed at maximizing transmission rates, solved through optimization sub-problems for each function using specialized neural networks. Additionally, this paper presents the intelligent modulation and demodulation network (IMD-Net) with an adaptive adjustment sub-network, joint channel feedback and prediction network (CFP-Net), and GEM-Net for joint channel estimation and signal detection, using an unfolded generalized expectation maximization algorithm. Simulation results indicate that the proposed algorithms surpass traditional linear methods and the independent deep learning (DL) based methods in various scenarios and configurations.

15 October 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JZJiayi Zhang
Jiayi Zhang
YZYiqing Zhang
Yiqing Zhang
GHGuangrui Huang
Guangrui Huang
To alleviate the computational burden of signal detection in uplink massive MIMO systems, the distributed baseband processing architecture has been developed. However, the quality of local channel state information (CSI) and received signal may vary considerably across different distributed units (DUs), and the information exchange among DUs is constrained by different interconnection topologies, making efficient distributed MIMO signal detection challenging. In this paper, we propose a distributed deep-unfolding detector based on the deep iterative shrinkage-thresholding algorithm (DISTA). In each layer of the proposed distributed DISTA network, every DU performs DISTA-based local signal detection in parallel using its own received signal and CSI, and the resulting local detection results are then exchanged and aggregated among DUs. For inter-DU information aggregation, a layer-wise learnable cooperation weight matrix is introduced to combine local detection results from different DUs, with its parameters optimized through end-to-end training under heterogeneous local observation conditions. Meanwhile, a topology mask is incorporated to enforce communication constraints imposed by various DU interconnection topologies. To improve the robustness of the proposed distributed DISTA network to different signal-to-noise ratio (SNR) levels, we further make the empirically determined momentum coefficient learnable and apply a weight-decay regularization to it in the training stage. Simulation results demonstrate that under heterogeneous SNR conditions, the proposed method outperforms the centralized MMSE detector in the low-to-medium SNR range (1–7 dB), while also maintaining robust detection performance with different numbers of DUs and interconnection topologies.