检索结果-内蒙古大学图书馆

message passing Neural Network Versus message passing algorithm for Cooperative Positioning

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING 2023年第6期9卷 1666-1676页

作者： Tedeschini, Bernardo Camajori Brambilla, Mattia Nicoli, Monica Politecn Milan Dipartimento Elettron Informaz & Bioingn I-20133 Milan Italy Politecn Milan Dipartimento Ingn Gest I-20133 Milan Italy

Cooperative Positioning (CP) relies on a network of connected agents equipped with sensing and communication technologies to improve the positioning performance of standalone solutions. In this paper, we develop a completely data-driven model combining Long Short-Term Memory (LSTM) and message passing Neural Network (MPNN) for CP, where agents estimate their states from inter-agent and ego-agent measurements. The proposed LSTM-MPNN model is derived by exploiting the analogy with the probability-based message passing algorithm (MPA), from which the graph-based structure of the problem and message passing scheme are inherited. In our solution, the LSTM block predicts the motion of the agents, while the MPNN elaborates the node and edge embeddings for an effective inference of the agents' state. We present numerical evidence that our approach can enhance position estimation, while being at the same time an order of magnitude less complex than typical particle-based implementations of MPA for non-linear problems. In particular, the presented LSTM-MPNN model can reduce the error on agents' positioning to one third compared to MPA-based CP, it holds a higher convergence speed and better exploits cooperation among agents.

关键词： message passing Time measurement Task analysis Probability density function Training Sensors Probabilistic logic message passing neural network message passing algorithm belief propagation cooperative positioning LSTM message passing

来源：评论

学校读者我要写书评

暂无评论

Demonstration of Pattern Division Multiple Access With message passing algorithm for Multi-Channel mmWave Uplinks via RoF Mobile Fronthaul

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2020年第21期38卷 5908-5915页

作者： Shen, Shuyi Chen, You-Wei Zhou, Qi Finkelstein, Jeff Chang, Gee-Kung Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30308 USA Cox Commun Atlanta GA 30328 USA

Orthogonal multiple access (OMA) such as orthogonal frequency division multiple access (OFDMA) has been the predominant access technology adopted by the current generation of mobile communication. Representing an evolutionary step in radio access networks, non-orthogonal multiple access (NOMA) is considered to be a promising technology to meet the goals of increased capacity, enhanced flexibility, and reduced latency. Pattern division multiple access (PDMA) is a NOMA scheme using resource-element mapping as the multiple-access signature in the symbol level. This article introduces PDMA in a millimeter-wave (mmWave) radio access system with systematic experimental demonstration. One key advantage of PDMA is that it can facilitate advanced parallel interference cancellation (PIC) in the decoding process. A message passing algorithm (MPA) is developed and implemented in this article to enhance the decoding performance of PDMA. A novel PDMA system integrated with MPA is experimentally demonstrated in a multi-user mmWave radio access system that uses radio-over-fiber (RoF) mobile fronthaul, achieving reduced sensitivity penalty and improved modulation spectral efficiency compared to conventional power-domain NOMA (PD-NOMA) with successive interference cancellation (SIC). Experimental results show that PDMA is capable of supporting disparate channel conditions, adapting to various patterns, and providing improved system flexibility.

关键词： Uplink NOMA Interference Decoding message passing Silicon carbide OFDM message passing algorithm non-orthogonal multiple access pattern division multiplexing access

来源：评论

学校读者我要写书评

暂无评论

message passing localisation algorithm combining BP with VMP for mobile wireless sensor networks

引用

IET COMMUNICATIONS 2017年第7期11卷 1106-1113页

作者： Cui, Jianhua Wang, Zhongyong Zhang, Chuanzong Zhang, Yuanyuan Zhu, Zhengyu Natl Digital Switching Syst Engn & Technol Res Ct Zhengzhou Peoples R China Luoyang Normal Univ Sch Phys & Elect Informat Luoyang Peoples R China Zhengzhou Univ Sch Informat Engn Zhengzhou Peoples R China Aalborg Univ Dept Elect Syst Aalborg Denmark

For large-scale wireless sensor networks (WSNs) with thousands of sensors, cooperative self-localisation is a key task and has caused extensive concerns. In this study, the authors propose a message passing algorithm for cooperative self-localisation of mobile WSNs by using belief propagation (BP) and variational message passing (VMP) on factor graphs. The sensors locate themselves through two steps: a prediction operation accounting for the sensors' mobility and a correction operation accounting for ranging measurements between neighbouring sensors. All the messages for computing and transmitting are restricted to be Gaussian to reduce communication overhead and computational complexity. According to the linear state-transition model and the non-linear ranging model, BP and VMP methods are employed to perform prediction and correction, respectively. Simulation results show that when the standard deviations of the prior distributions is small, the positioning accuracy of the proposed algorithm is comparable with that of sum-product algorithm over a wireless network (SPAWN) with much low communication overhead and computational complexity.

关键词： wireless sensor networks mobile radio sensor placement message passing distance measurement computational complexity graph theory MP localisation algorithm mobile wireless sensor networks large-scale wireless sensor networks cooperative self-localisation message passing algorithm variational MP mobile WSN belief propagation factor graphs sensor localisation sensor mobility ranging measurements communication overhead reduction computational complexity linear state-transition model nonlinear ranging model BP method VMP method positioning accuracy

来源：评论

学校读者我要写书评

暂无评论

A Class of Optimal Structures for Node Computations in message passing algorithms

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2022年第1期68卷 93-104页

作者： He, Xuan Cai, Kui Zhou, Liang Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu 611756 Peoples R China Singapore Univ Technol & Design Math & Technol SMT Cluster Singapore 487372 Singapore Univ Elect Sci & Technol China Natl Key Lab Sci & Technol Commun Chengdu 611731 Peoples R China

Consider the computations at a node in a message passing algorithm. Assume that the node has incoming and outgoing messages x = (x(1), x(2), ..., xn) and y = (y(1), y(2), ..., y(n)), respectively. In this paper, we investigate a class of structures that can be adopted by the node for computing y from x, where each y(j), j = 1, 2,..., n is computed via a binary tree with leaves x excluding x(j). We make three main contributions regarding this class of structures. First, we prove that the minimum complexity of such a structure is 3n - 6, and if a structure has such complexity, its minimum latency is delta + inverted right perpendicularlog(n - 2(delta))inverted left perpendicular with delta = right perpendicularlog(n/2)left perpendicular, where the logarithm always takes base two. Second, we prove that the minimum latency of such a structure is inverted right perpendicularlog(n - 1)inverted left perpendicular, and if a structure has such latency, its minimum complexity is n log(n - 1) when n - 1 is a power of two. Third, given (n, tau) with tau >= inverted right perpendicularlog(n - 1)inverted left perpendicular, we propose a construction for a structure which we conjecture to have the minimum complexity among structures with latencies at most tau. Our construction method runs in O(n(3) log(2) (n)) time, and the obtained structure has complexity at most (generally much smaller than) ninverted right perpendicularlog(n)inverted left perpendicular - 2.

关键词： Binary structure complexity latency lowdensity parity-check (LDPC) code message passing algorithm

来源：评论

学校读者我要写书评

暂无评论

message passing Based Gaussian Mixture Model for DOA Estimation in Complex Noise Scenarios

引用

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 1379-1383页

作者： Guan, Shanwen Lu, Xinhua Li, Ji Luo, Xiaonan Guilin Univ Elect Technol Guangxi Key Lab Image & Graph Intelligent Proc Guilin 541000 Peoples R China Nanyang Inst Technol Sch Informat Engn Nanyang 473000 Peoples R China

Wireless signals are frequently disturbed by complex noise sources, presenting a challenge to traditional direction of arrival (DOA) estimation methods that rely on the assumption of Gaussian noise. To address this issue, this letter proposes an innovative Bayesian DOA estimation approach. This method utilizes Gaussian mixture model (GMM) and Dirichlet process prior to model the density function of complex noise in practical scenarios. Additionally, an efficient combined message passing algorithm is formulated on the factor graph through the use of generalized approximate message passing (GAMP) and mean field (MF) techniques. Simulation results validate the effectiveness of this algorithm.

关键词： Direction of arrival (DOA) estimation factor graph message passing algorithm Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation based on the message passing algorithm in Underlay Cognitive Networks

Resource Allocation based on the Message Passing Algorithm i...

引用

IEEE Wireless Communications and Networking Conference (WCNC)

作者： Mani, Hossein Mokari, Nader Khoshkholgh, Mohamad Ghadir Saeedi, Hamid Tarbiat Modares Univ Tehran Iran Simula Res Lab Lysacer Norway

ISBN: (纸本)9781479930838

A message passing (MP) algorithm for resource allocation (RA) in an Orthogonal Frequency Division Multiple Access (OFDMA) based spectrum sharing system is developed in this paper. We derive optimal power and subcarrier allocations. We further shed light on advantages of the MP algorithm particularly against the dual solution and highlight its suitability in reducing the computational burdens for practical configurations. It is observed that MP algorithm converges only after two iterations compared to 400 required iterations in the dual case. This considerably reduces the corresponding computational time, which in turn results in much lower consumed processing energy. The saved processing energy and time can then be exploited for enhancing the scheduled data rate especially when the number of users is high.

关键词： OFDM modulation cognitive radio frequency division multiple access message passing radio spectrum management MP algorithm message passing algorithm optimal power orthogonal frequency division multiple access OFDMA resource allocation spectrum sharing system subcarrier allocations underlay cognitive networks algorithm design and analysis Computational complexity Convergence Interference Resource management Wireless communication

来源：评论

学校读者我要写书评

暂无评论

Factor Graph Based message passing algorithms for Joint Phase-Noise Estimation and Decoding in OFDM-IM

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 2020年第5期68卷 2906-2921页

作者： Shi, Qiaolin Wu, Nan Wang, Hua Ma, Xiaoli Hanzo, Lajos Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Univ Technol Sydney Fac Engn & Informat Technol Sydney NSW 2007 Australia Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30332 USA Univ Southampton Sch Elect & Comp Sci Southampton SO17 1BJ Hants England

In order to glean benefits from orthogonal frequency division multiplexing combined with index modulation (OFDM-IM) in the presence of strong Phase-Noise (PHN), in this paper, low-complexity joint PHN estimation and decoding methods are developed in the framework of message passing on a factor graph. Both the Wiener process and the truncated discrete cosine transform (DCT) expansion model are considered for approximating the PHN variation. Then based on these a factor graph is constructed for explicitly representing the joint estimation and detection problem. Taking full account of the sparse and structured a priori information arriving from the soft-in soft-out (SISO) decoder of a turbo receiver, a modified generalized approximate message passing (GAMP) algorithm is invoked for decoupling the frequency-domain symbols. In the decoupling step, mean field (MF) approximation is employed for solving the unknown nonlinear transform matrix problem imposed by PHN. Furthermore, merged belief propagation and MF (BP-MF) methods amalgamated both with sequential and parallel message passing schedules are introduced and compared to the proposed GAMP based algorithms in terms of their bit error ratio (BER) vs. complexity. Our simulation results demonstrate the efficiency of the proposed algorithms in the presence of both perfect and imperfect channel state information.

关键词： OFDM message passing Estimation Discrete cosine transforms Complexity theory Receivers Detectors Orthogonal frequency division multiplexing (OFDM) index modulation (IM) phase noise (PHN) discrete cosine transform (DCT) message passing algorithm

来源：评论

学校读者我要写书评

暂无评论

Dancing With Chains: Spaceborne Distributed Multi-User Detection Under Inter-Satellite Link Constraints

引用

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING 2025年第2期19卷 430-446页

作者： Ye, Neng Miao, Sirui Pan, Jianxiong Xiang, Yiyue Mumtaz, Shahid Beijing Inst Technol Beijing 100081 Peoples R China Nottingham Trent Univ Dept Engn Nottingham NG1 4FQ England

Mega constellation, as an extremely large-scale radio access network, faces severe multi-user interference when accommodating ubiquitous access. Distributed multi-user detection (MUD) can utilize the multi-satellite spatial diversities and processing capabilities to alleviate inter-user interference. However, the spaceborne nature makes it seriously chained by inter-satellite link (ISL) constraints including the limited number and the constrained bandwidth of ISL ports. Therefore, this paper proposes an efficient message passing (MP) based distributed MUD framework under stringent ISL constraints. First, the overheads on ISL ports and bandwidth introduced by fully-connected distributed MUD are quantitatively characterized using distributed factor graph (FG) model. On this basis, we propose two ISL-compatible design principles for distributed MUD, i.e., orchestrating message flow (MF) hierarchically among satellites to save ports, and propagating messages selectively to save bandwidth. Specifically, a novel multi-branch tree-like MF orchestration is proposed to forward and aggregate the locally generated detection messages in a partially-connected manner. The relationship between MF structure and overall performance is revealed via EXIT chart and a fairness-aware orchestration algorithm is developed. Further, we introduce a novel squeeze node into the distributed FG, compressing messages and facilitating selective MP under bandwidth constraint. Three criteria are correspondingly proposed to identify the most effective messages for distributed MUD. Our proposed MUD framework is evaluated under practical settings, which demonstrates a reduction of 50% ISL bandwidth costs with less than 1 dB loss in terms of BER compared to the fully-connected MUD, and achieves up to 5 dB gain in BER over the state-of-the-art distributed reception methods.

关键词： Multiuser detection Satellite broadcasting Bandwidth Satellites Topology message passing Faces Aggregates Vectors Stars Distributed multi-user detection graph model inter-satellite link constraints mega-constellation networks message passing algorithm

来源：评论

学校读者我要写书评

暂无评论

A Semi-Analytic algorithm to Estimate Clusters With Loops in Percolation on Real Networks

引用

IEEE ACCESS 2024年 12卷 36074-36082页

作者： Li, Chenguang Fu, Tao Wang, Lian Sun, Ran North China Univ Technol Econ & Management Sch Beijing 100144 Peoples R China Beijing Univ Technol Econ & Management Sch Beijing 100124 Peoples R China North China Inst Aerosp Engn Comp Sch Langfang 065000 Peoples R China

Estimating the percolating cluster fraction is central to many percolation models. For real networks, the total size of clusters with loops can be considered a plausible metric for this fraction. In this paper, we develop a semi-analytic algorithm to estimate clusters with loops for both site and bond percolation via modifying the message passing algorithm. We compared the estimates of the original message passing algorithm and our modified version with simulation results on four real networks. Our findings suggest that our modified algorithm can achieve accuracy for any real network, provided that a sufficient number of possible states following site or bond occupation are selected and analyzed to calculate the final estimate.

关键词： Percolation real network message passing algorithm pseudo-random generation

来源：评论

学校读者我要写书评

暂无评论

Synchronous and Asynchronous HARQ-CC Assisted SCMA Schemes

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 506-510页

作者： Wang, Man Shi, Zheng Li, Yunfei Wu, Xianda Tan, Weiqiang Jinan Univ Sch Intelligent Syst Sci & Engn Zhuhai 519070 Peoples R China Anhui Polytech Univ Dept Elect Engn Wuhu City 241000 Peoples R China South China Normal Univ Sch Elect Sci & Engn Sch Microelect Foshan 528000 Peoples R China Guangzhou Univ Sch Comp Sci & Cyber Engn Guangzhou 510006 Peoples R China

This letter proposes a novel hybrid automatic repeat request with chase combining assisted sparse code multiple access (HARQ-CC-SCMA) scheme. Depending on whether the same superimposed packet is retransmitted, synchronous and asynchronous modes are considered for retransmissions. Moreover, a factor graph aggregation (FGA) method is used for multi-user detection. Specifically, a large-scale factor graph is constructed by combining all the received superimposed signals and message passing algorithm (MPA) is applied to calculate log-likelihood ratio (LLR). Monte Carlo simulations are preformed to show that FGA surpasses bit-level combining (BLC) and HARQ with incremental redundancy (HARQ-IR) in synchronous mode. Moreover, FGA performs better than BLC at high signal-to-noise ratio (SNR) region in asynchronous mode. However, FGA in asynchronous mode is worse than BLC at low SNR, because significant error propagation is induced by the presence of failed messages after the maximum allowable HARQ rounds.

关键词： Decoding Multiuser detection Reliability Signal to noise ratio message passing Encoding Electronic mail Complexity theory Codes Time-frequency analysis Factor graph hybrid automatic repeat request with chase combining (HARQ-CC) log-likelihood ratio message passing algorithm sparse code multiple access (SCMA)

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

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

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：