检索结果-内蒙古大学图书馆

Deep Transfer Learning for Model-Driven Signal Detection in MIMO-NOMA Systems

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2023年第10期72卷 13039-13054页

作者： Wang, Xiaoming Zhang, Dongcai Chen, Bingcen Liu, Ting Xin, Yuanxue Xu, Youyun Nanjing Univ Posts & Telecommun Sch Commun & Informat Engn Nanjing 210003 Peoples R China Nanjing Univ Informat Sci & Technol Sch Artificial Intelligence Sch Future Technol Nanjing 210044 Peoples R China Hohai Univ Coll Internet Things Engn Changzhou 213022 Jiangsu Peoples R China

In this article, a odel-driven signal detection method with deep transfer learning (DTL) is proposed for downlink multiple-input multiple-output non-orthogonal multiple access (MIMO-NOMA) systems. Specifically, we first introduce some learnable parameters to an unfolded iterative algorithm for MIMO detection and improve it through a preconditioned process to speed up its convergence. Then we combine this modified algorithm with the successive interference cancellation (SIC) structure in NOMA detection to propose our learned preconditioned conjugate gradient descent network with SIC (LPCG-SIC). The proposed network has fewer parameters and lower computational complexity in which only few trainable parameters need to be optimized, and there are only addition and multiplication operations in online detection. Furthermore, to overcome the drawback that most of the existing deep learning-based detectors only focus on signal detection in a given environment and cannot adapt to changes in feature spaces or distributions, we propose a DTL-based detection algorithm and three model-driven transfer strategies for our LPCG-SIC detector to improve the reusability of the trained network. Simulation results show that our proposed method can perform signal detection under multi-user interference and outperforms conventional detectors. The transfer strategies can obtain significant performance gain with lower training cost compared to no-transfer methods.

关键词： Signal detection non-orthogonal multiple access multiple-input multiple-output model-driven deep learning

来源：评论

学校读者我要写书评

暂无评论

Modeling and Optimization of OAM-MIMO Communication Systems With Unaligned Antennas

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 2022年第6期70卷 3682-3694页

作者： Xiong, Xusheng Lou, Hanqiong Ge, Xiaohu Huazhong Univ Sci & Technol Sch Elect Informat & Commun Wuhan 430074 Peoples R China China Int Joint Res Ctr Green Commun & Networking Wuhan 430074 Peoples R China

The orbital angular momentum (OAM) wireless communication technique is emerging as one of potential techniques for the Sixth generation (6G) wireless communication system. The most advantage of OAM wireless communication technique is the natural orthogonality among different OAM states. However, one of the most disadvantages is the crosstalk among different OAM states which is widely caused by the atmospheric turbulence and the misalignment between the transmitting and receiving antennas. Considering the OAM-based multiple-input multiple-output (OAM-MIMO) transmission system with unaligned antennas, a new channel model is proposed for performance analysis. Moreover, the purity and crosstalk models of the OAM-MIMO transmission system with unaligned antennas are derived for the non-Kolmogorov turbulence. Furthermore, the error probability, bit error rate (BER) and capacity models are derived for OAM-MIMO transmission systems with unaligned antennas. To overcome the disadvantage caused by the unaligned antennas and non-Kolmogorov turbulence, a new optimization algorithm of OAM state interval is proposed to improve the capacity of the OAM-MIMO transmission system. Numerical results indicate that the capacity of OAM-MIMO transmission system is improved by the proposed optimization algorithm. Specifically, the capacity increment of the OAM-MIMO transmission system adopting the proposed optimization algorithm is up to 28.7% and 320.3% when the angle of deflection between the transmitting and receiving antennas is -24 dB and -5 dB, respectively.

关键词： Transmitting antennas Receiving antennas Wireless communication Optimization MIMO communication Atmospheric modeling Crosstalk Orbital angular momentum multiple-input multiple-output capacity error probability Laguerre-Gaussian

来源：评论

学校读者我要写书评

暂无评论

A hybrid envelope fluctuations reduction approach using multilayer neural network for MIMO-OFDM signals

引用

WIRELESS NETWORKS 2016年第8期22卷 2705-2712页

作者： Pachori, Khushboo Mishra, Amit Jaypee Univ Engn & Technol Dept Elect & Commun Engn Guna 473226 MP India Thapar Univ Dept Elect & Commun Engn Patiala 147004 Punjab India

One of the major drawback in multi-carrier signals is large envelope fluctuations i.e., high peak-to-average power ratio (PAPR). The objective of this paper is to propose neural network based active gradient project sequence, a computationally efficient hybrid method to reduce PAPR in multiple-input multiple-output orthogonal frequency division multiplexing system without sacrificing BER performance. In this paper, a neural network based trained module of approximate gradient project scheme (AGP-NN) is combined in parallel with partial transmit sequence method. The Levenberg-Marquardt training algorithm is used to train neural network based AGP module. The simulation results show that the proposed technique not only outperforms other conventional techniques but also offers less computational complexity.

关键词： multiple-input multiple-output Levenberg-Marquardt algorithm Partial transmit sequence Approximate gradient project

来源：评论

学校读者我要写书评

暂无评论

Compact MIMO antenna for application to smart glasses using T-shaped ground plane

引用

MICROWAVE AND OPTICAL TECHNOLOGY LETTERS 2018年第8期60卷 2010-2013页

作者： Ryu, Jongin Kim, Hyeongdong Hanyang Univ Dept Elect & Comp Engn Microwave Engn Lab Seoul South Korea

A compact multiple-input multiple-output (MIMO) antenna design for application to smart glasses is proposed in this letter. The proposed MIMO antenna system is comprised of two symmetrical meander antennas operating in the 2.4-GHz wireless local area network band and a T-shaped ground for high isolation. The operation mechanism of the proposed MIMO antennas can be explained using the analysis of a three-port network. Accordingly, the T-shaped ground plane operates as a decoupling structure such that the isolation between antennas can be controlled by tuning the T-shaped ground plane. The reflection coefficient characteristic was measured to be less than -7.5 dB, whereas the isolation obtained was higher than 15 dB. The diversity performance was evaluated using the measured three-dimensional radiation patterns, and the envelope correlation coefficients in the target band were less than 0.1.

关键词： decoupling structure high isolation multiple-input multiple-output

来源：评论

学校读者我要写书评

暂无评论

Error Probability Analysis for Time-Varying Chaos Unitary Matrix-Based Differential MIMO System

引用

IEEE WIRELESS COMMUNICATIONS LETTERS 2022年第7期11卷 1399-1403页

作者： Zhai, Xiaodan Song, Guochao Xiao, Lixia Liu, Guanghua Ishikawa, Naoki Jiang, Tao Huazhong Univ Sci & Technol Wuhan Natl Lab Optoelect Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Res Ctr 6G Mobile Commun Wuhan 430074 Peoples R China China Acad Informat & Commun Technol Mobile Commun Innovat Ctr Beijing 100191 Peoples R China Huazhong Univ Sci & Technol Sch Cyber Sci & Engn Wuhan 430074 Peoples R China Yokohama Natl Univ Fac Engn Yokohama Kanagawa 2408501 Japan

The time-varying (TV) chaos unitary matrix based differential multiple-input multiple-output (D-MIMO) system is capable of achieving beneficial performance gains without channel state information (CSI). To elaborate a little further, the chaos sequence is embedded into the data-carrying matrices by a unique time-varying matrix. By employing differential coding during two adjacent signal blocks, a non-coherent detector can be developed without CSI knowledge. However, its theoretical performance analysis becomes challenging due to its complex construction. To address this issue, the theoretical average bit error probability (ABEP) lower and upper bounds of the TV-D-MIMO system are analyzed using the moment generating function (MGF) over generalized fading channel. The experimental results are shown that the derived ABEP upper and lower bounds are tight with the simulation results, which is helpful for future performance evaluation.

关键词： Chaos Fading channels Time-varying systems MIMO communication Error probability Encoding Indexes multiple-input multiple-output time-varying chaos unitary matrix differential coding chaos sequence average bit error probability

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Precoder in Multi-User MIMO Systems With Imperfect Channel State Information

引用

IEEE WIRELESS COMMUNICATIONS LETTERS 2019年第3期8卷 669-672页

作者： Vaezy, Hossein Omidi, Mohammad Javad Yanikomeroglu, Halim Isfahan Univ Technol Dept Elect & Comp Engn Esfahan *** Iran Carleton Univ Dept Syst & Comp Engn Ottawa ON K1S 5B6 Canada

This letter is on the energy efficient precoder design in multi-user multiple-input multiple-output systems which is also robust with respect to the imperfect channel state information at the transmitters. In other words, we design the precoder matrix associated with each transmitter to maximize the general energy efficiency of the network. We investigate the problem in two conventional cases. The first case considers the statistical characterization for the channel estimation error that leads to a quadratically constrained quadratic program with a semi-closed-form solution. Then, we turn our attention to the case which considers only the uncertainty region for the channel estimation error;this case eventually results in a semi-definite program.

关键词： multiple-input multiple-output precoder general energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Statistically Robust Transceiver Design for Multi-RIS Assisted Multi-User MIMO Systems

引用

IEEE COMMUNICATIONS LETTERS 2022年第6期26卷 1428-1432页

作者： Xu, Kaizhe Gong, Shiqi Cui, Miao Zhang, Guangchi Ma, Shaodan Univ Macau State Key Lab Internet Things Smart City Macau Peoples R China Univ Macau Dept Elect & Comp Engn Macau Peoples R China Guangdong Univ Technol Sch Informat Engn Guangzhou 510006 Peoples R China

In this letter, we investigate the robust transceiver design for a downlink multi-user multiple-input multiple-output (MIMO) system assisted by multiple reconfigurable intelligent surfaces (RISs), where the base station (BS) and multiple users are all equipped with multiple antennas. Different from most previous RIS related works focusing on worst-case performance optimization, which may lead to overly conservative transceiver designs, we assume stochastic channel estimation errors for the considered system, and aim to minimize the average sum mean square error (MSE) of the considered system by jointly optimizing the transmit precoders, the receive equalizers, and the RIS reflecting coefficients. To address the non-convexity of the formulated problem induced by strongly coupled optimization variables, we develop a low-complexity alternating optimization (AO) algorithm to find a locally optimal solution, where the unique optimal solution to each subproblem can be derived in closed-form. Numerical simulations demonstrate the robustness and excellent average sum MSE performance of the proposed AO algorithm compared to the adopted benchmark scheme.

关键词： Channel estimation MIMO communication Transceivers Optimization MISO communication Correlation Robustness Reconfigurable intelligent surface multiple-input multiple-output channel statistics alternating optimization

来源：评论

学校读者我要写书评

暂无评论

ChannelAttention: Utilizing Attention Layers for Accurate Massive MIMO Channel Feedback

引用

IEEE WIRELESS COMMUNICATIONS LETTERS 2021年第5期10卷 1079-1082页

作者： Ji, Dong Jin Cho, Dong-Ho Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon 34141 South Korea

Recently the idea of using deep learning algorithms in massive multiple-input multiple-output channel state information feedback has been studied in great detail. To use the deep-learning-based feedback schemes over the air, they must be able to operate under extremely large antennas. These schemes also need to be verified under a realistic channel model and propagation environment. Thus, we propose ChannelAttention, a deep-learning-based channel state information feedback scheme that utilizes attention layers and residual blocks. Simulations for a 64-by-64 QuaDRiGa channel model based on the 3GPP 38.901 urban microcell scenario show that ChannelAttention surpasses the normalized mean square error and cosine similarity performance of the conventional CsiNet+ scheme across all compression ratio ranges.

关键词： Machine learning for communications deep learning channel feedback multiple-input multiple-output

来源：评论

学校读者我要写书评

暂无评论

BER analysis of BPSK-SIM-based SISO and MIMO FSO systems in strong turbulence with pointing errors

引用

OPTIK 2014年第21期125卷 6413-6417页

作者： Prabu, K. Kumar, D. Sriram Malekian, Reza Natl Inst Technol Dept Elect & Commun Engn Tiruchirappalli 620015 Tamil Nadu India Univ Pretoria Dept Elect Elect & Comp Engn ZA-0002 Pretoria South Africa

Free space optics (FSO) is one of the sprouting technologies in optical communication systems domain. It can be employed as an alternative for the conventional radio frequency (RF) links to work out the current limitations in communication systems. But, the major drawback in FSO communication is the effect of random environment conditions on its performance. In this paper, we analyze the bit error rate (BER) and outage performance of single-input single-output (SISO) and multiple-input multiple-output (MIMO) FSO systems in strong atmospheric turbulence using binary phase shift keying subcarrier intensity modulation (BPSK-SIM) signaling technique. The closed-form expressions are derived and the results are realized in terms of 2D and 3D plots. (C) 2014 Elsevier GmbH. All rights reserved.

关键词： Free space optics Bit error rate Outage probability Single-input single-output multiple-input multiple-output

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Efficient CSI Feedback for THz Band FDD MIMO Systems

引用

IEEE WIRELESS COMMUNICATIONS LETTERS 2024年第2期13卷 343-346页

作者： Ji, Dong Jin Chung, Byung Chang Seoul Natl Univ Sci & Technol Dept Semicond Engn Seoul 01811 South Korea Gyeongsang Natl Univ Dept Intelligence & Commun Engn Tongyeong 53064 South Korea

Machine learning algorithms have been extensively explored for the feedback of multiple-input multiple-output (MIMO) channel state information (CSI) in orthogonal frequency division multiplexing (OFDM) systems. However, their viability in sixth-generation (6G) wireless communication systems, operating in the terahertz (THz) band, remains uncertain. To address this, we propose ChannelTransformer, a transformer-model-based CSI feedback scheme that incorporates multi-head self-attention and a CSI-feedback-aware transformer structure, and a lightweight user equipment (UE) model. Through simulations in the DeepMIMO O1 scenario at 140GHz, ChannelTransformer demonstrates superior performance in terms of normalized mean square error (NMSE) and cosine similarity across various feedback lengths compared to conventional schemes with a much smaller UE model size.

关键词： Transformers Tensors Computational modeling Antenna arrays Computer architecture Receiving antennas 6G mobile communication Machine learning for communications deep learning channel feedback multiple-input multiple-output

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：