Mingjin Wang

Mingjin Wang

Auto-generated profile, based on publicly available information

Mingjin Wang

Department of Automation, Institute for Artificial Intelligence, and Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
12 August 2019 in IEEE Journal of Selected Topics in Signal Processing
Verified
Journal Article
Open access
MWMingjin Wang
Mingjin Wang
FGFeifei Gao
Feifei Gao
SJShi Jin
Shi Jin
HLHai Lin
Hai Lin
In the past ten years, there have been tremendous research progresses on massive MIMO systems, most of which stand from the communications viewpoint. A new trend of investigating massive MIMO, especially for the sparse scenario like millimeter wave (mmWave) transmission, is to re-build the transceiver design from array signal processing viewpoint that could deeply exploit the large half-wavelength array and provide enhanced performances in many aspects. For example, the high dimensional channel could be decomposed into small amount of physical parameters, e.g., amount of physical parameters, e.g., angle of arrival (AoA), multi-path delay, and Doppler shift, etc. As a consequence, transceiver techniques like synchronization, channel estimation, beamforming, precoding, multi-user access, etc., can be re-shaped with these physical parameters, as opposed to those with channel state information (CSI). Interestingly, parameters like AoA and multi-path are frequency insensitive and thus can be used to guide the downlink transmission from uplink training even for FDD systems. Moreover, some phenomena of massive MIMO that were vaguely revealed previously can be better explained now with array signal processing viewpoint, e.g., the beam squint effect. In all, the target of this paper is to present an overview of recent progress on merging array signal processing into massive MIMO communications as well as its promising future directions.

28 November 2019 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
MWMingjin Wang
Mingjin Wang
FGFeifei Gao
Feifei Gao
NSNir Shlezinger
Nir Shlezinger
MFMark F. Flanagan
Mark F. Flanagan
YEYonina C. Eldar
Yonina C. Eldar
Multiple-input multiple-output (MIMO) millimeter wave (mmWave) communication is a key technology for next generation wireless networks. One of the consequences of utilizing a large number of antennas with an increased bandwidth is that array steering vectors vary among different subcarriers. Due to this effect, known as beam squint, the conventional channel model is no longer applicable for mmWave massive MIMO systems. In this paper, we study channel estimation under the resulting non-standard model. To that aim, we first analyze the beam squint effect from an array signal processing perspective, resulting in a model which sheds light on the angle-delay sparsity of mmWave transmission. We next design a compressive sensing based channel estimation algorithm which utilizes the shift-invariant block-sparsity of this channel model. The proposed algorithm jointly computes the off-grid angles, the off-grid delays, and the complex gains of the multi-path channel. We show that the newly proposed scheme reflects the mmWave channel more accurately and results in improved performance compared to traditional approaches. We then demonstrate how this approach can be applied to recover both the uplink as well as the downlink channel in frequency division duplex (FDD) systems, by exploiting the angle-delay reciprocity of mmWave channels.

8 June 2022 in IEEE Journal on Selected Areas in Communications
Verified
Journal Article
Closed access
YYYuwen Yang
Yuwen Yang
FGFeifei Gao
Feifei Gao
MWMingjin Wang
Mingjin Wang
JXJiang Xue
Jiang Xue
XZXu Zongben
Xu Zongben
Achieving adequate precision in deep learning based communications often requires large network architectures, which results into unacceptable time delay and power consumption. This paper introduces the dynamic neural network (DyNN) into the design of wireless communications systems. DyNN allocates different samples with computation resources on demand by preforming dynamic inferences, thereby reducing the redundant computational cost and enhancing the network efficiency. We design a dynamic depth architecture that allows samples to adaptively skip layers with various dynamic strategies, from which we further develop a c onfidence criterion based d ynamic i mproved DetNet (CD-IDetNet) and a p olicy network based d ynamic i mproved DetNet (PD-IDetNet) for multiple-input multiple-output (MIMO) detection. Specifically, in CD-IDetNet, a confidence criterion is adopted to control samples exiting early, while in PD-IDetNet, policy networks are trained by reinforcement learning to selectively skip layers for varying samples. Simulation results demonstrate that CD-IDetNet and PD-IDetNet detectors can respectively reduce 17.4% and 31.1% computational costs while preserving the full accuracy of IDetNet. Desirable tradeoffs between accuracy and computational complexity can be further achieved by fine-tuning the hyper-parameters of CD-IDetNet and PD-IDetNet. Moreover, over-the-air (OTA) tests are conducted to validate the effectiveness of the proposed detectors in practical systems.

24 January 2025 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
HLHongyao Li
Hongyao Li
MWMingjin Wang
Mingjin Wang
RHRunyu Han
Runyu Han
NWNing Wang
Ning Wang
HWHuihui Wu
Huihui Wu
FGFeifei Gao
Feifei Gao
In this paper, we study the deep learning (DL) based channel extrapolation problem and conduct the over-the-air (OTA) antenna extrapolation and frequency channel interpolation test for the 3rd generation partnership project (3GPP) long-term evolution (LTE) time-division duplex (TDD)-like orthogonal frequency division multiplexing (OFDM) massive MIMO prototype.We first present measurement campaigns using universal software radio peripherals (USRP) at 3.5 GHz, where the base station (BS) is composed of a 64-element antenna array. A DL-based antenna extrapolation network is then designed to approximate the inner deterministic function among antennas from the attained channel data within the “training” pilots. We present an antenna selection network (ASN) that can select a limited number of antennas for the best extrapolation, which outperforms the uniform antenna selection in terms of channel reconstruction and signal detection. We also design a deep residual neural network for channel interpolation. The performance of the extrapolated channel is evaluated in terms of normalized mean squared error (NMSE) in comparison to the measured channels on all antenna ports or the full pilot-aided channels in all OFDM subcarriers. Experimental results show that ASN can reduce an average of 87.5% antenna ports and maintain channel estimation NMSE by 10-2 when compared to 3GPP channel estimation protocols.

1 November 2017 in Journal of Mathematical Analysis and Applications
Verified
Journal Article
Closed access
MWMingjin Wang
Mingjin Wang

16 March 2017 in Infinite Dimensional Analysis, Quantum Probability and Related Topics
Verified
Journal Article
Closed access
MWMingjin Wang
Mingjin Wang