期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到351篇文章
< 1 2 … 18 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
A residual-based message passing algorithm for constraint satisfaction problems 认领 引用 被引量：3
1
作者 Chun-Yan Zhao Yan-Rong Fu Jin-Hua Zhao 《Communications in Theoretical Physics》 SCIE CAS CSCD 2022年第3期77-86,共10页
Message passing algorithms,whose iterative nature captures complicated interactions among interconnected variables in complex systems and extracts information from the fixed point of iterated messages,provide a powerf... Message passing algorithms,whose iterative nature captures complicated interactions among interconnected variables in complex systems and extracts information from the fixed point of iterated messages,provide a powerful toolkit in tackling hard computational tasks in optimization,inference,and learning problems.In the context of constraint satisfaction problems(CSPs),when a control parameter(such as constraint density)is tuned,multiple threshold phenomena emerge,signaling fundamental structural transitions in their solution space.Finding solutions around these transition points is exceedingly challenging for algorithm design,where message passing algorithms suffer from a large message fiuctuation far from convergence.Here we introduce a residual-based updating step into message passing algorithms,in which messages with large variation between consecutive steps are given high priority in the updating process.For the specific example of model RB(revised B),a typical prototype of random CSPs with growing domains,we show that our algorithm improves the convergence of message updating and increases the success probability in finding solutions around the satisfiability threshold with a low computational cost.Our approach to message passing algorithms should be of value for exploring their power in developing algorithms to find ground-state solutions and understand the detailed structure of solution space of hard optimization problems. 展开更多
关键词 constraint satisfaction problems model RB message passing algorithms residuals of messages
暂未订购 下载PDF
强震动记录滤波截止频率选择的人工智能替代算法研究 认领 引用
2
作者 郭文轩 任叶飞 +4 位作者 姚鑫鑫 岸田忠大 王宏伟 刘也 温瑞智 《地球物理学报》 SCIE EI CAS CSCD 北大核心 2026年第8期3663-3678,共16页
强震记录是地震工程和地震学研究必不可少的基础资料,但普遍存在的噪声问题影响了强震记录的准确性和可用性.高通滤波是常用的去噪方法,其关键是高通滤波截止频率(fHP)的合理选取.本文构建了基于人工智能的fHP自动选取模型,利用中国与欧... 强震记录是地震工程和地震学研究必不可少的基础资料,但普遍存在的噪声问题影响了强震记录的准确性和可用性.高通滤波是常用的去噪方法,其关键是高通滤波截止频率(fHP)的合理选取.本文构建了基于人工智能的fHP自动选取模型,利用中国与欧洲ESM强震动数据库中不含永久位移的记录,提取多种记录特征,构建联合特征向量,并采用八种典型分类模型开展训练与对比分析.在此基础上,结合预测标签对fHP进行拟合,确定最优截止频率值.结果表明,随机森林(RF)模型在两个数据集上的综合表现最优,fHP预测相关系数分别为0.899和0.925,残差分布集中,展现出良好的精度与稳定性.通过多模型评估与跨数据集验证,进一步确认了多特征联合优化在提升模型准确性与泛化能力方面的有效性.与传统方法Guo 2025和R-S 2023对比,RF模型在预测性能和适应性方面均具有显著优势.研究结果表明,基于人工智能的fHp选取方法,尤其是RF模型可显著提升强震动数据的预处理效率和质量,为地震动记录的自动化处理提供了可靠技术路径. 展开更多
关键词 强震动记录 滤波 高通滤波器截止频率 自动处理 随机森林算法
暂未订购 下载PDF
基于深度强化学习的站所一体化下动走线通过能力适应性评估方法研究 认领 引用
3
作者 陈韬 徐梦婷 潘金山 《铁道学报》 EI CAS CSCD 北大核心 2026年第3期16-27,共12页
随着高速铁路车站和动车所规模进一步扩大,存在动车所动走线通过能力在实际运用中难以达到设计值,不适应终到、始发列车高峰时段高速铁路车站行车需求的情况,主要原因是设计时缺乏高速铁路车站、动走线、动车所三个子系统一体化下的能... 随着高速铁路车站和动车所规模进一步扩大,存在动车所动走线通过能力在实际运用中难以达到设计值,不适应终到、始发列车高峰时段高速铁路车站行车需求的情况,主要原因是设计时缺乏高速铁路车站、动走线、动车所三个子系统一体化下的能力适应性检算。以高峰时段内尽可能达到高速铁路车站需要接发列车数为目标,采用深度强化学习方法,构建站所一体化场景下动走线通过能力适应性评估模型。模型中嵌入列车运行约束检测模块,设计MAAC多智能体强化学习求解算法,最终生成站所一体化协调作业计划,实现动走线通过能力与高速铁路车站行车作业需求的适应性判定。经某实际站所系统案例验证,模型与算法具备合理性,为大规模站所动走线设计及运用优化提供理论支撑。 展开更多
关键词 站所一体化 动走线通过能力 适应性评估 深度强化学习 MAAC算法
暂未订购 下载PDF
基于超螺旋滑模算法的欠驱动无人艇轨迹跟踪控制 认领 引用
4
作者 师光飞 刘伟 龚成林 《船海工程》 北大核心 2026年第3期99-107,共9页
针对欠驱动无人艇的轨迹跟踪控制问题,提出一种基于超螺旋趋近率的干扰观测器补偿动态面滑模控制方法。根据无人艇的期望轨迹和实际状态信息设计轨迹跟踪误差,进一步融合非线性反步法的虚拟设计原理,以纵向速度和横向速度为虚拟控制量... 针对欠驱动无人艇的轨迹跟踪控制问题,提出一种基于超螺旋趋近率的干扰观测器补偿动态面滑模控制方法。根据无人艇的期望轨迹和实际状态信息设计轨迹跟踪误差,进一步融合非线性反步法的虚拟设计原理,以纵向速度和横向速度为虚拟控制量进行虚拟控制律设计;为避免虚拟纵/横向速度求导带来的复杂数学运算问题,融合一阶低通滤波器设计逼近函数以趋近虚拟纵/横速度,基于微分跟踪器对横向速度求导进行平滑处理,避免控制前期出现剧烈的抖振现象,设计具有指数稳定性的轨迹跟踪滑模控制律;设计超螺旋算法趋近率替换符号函数,进一步增强控制效果,并采用干扰观测器对复杂海洋干扰进行观测和补偿,以确保实现高精度的轨迹跟踪。采用Lyapunov稳定性理论证明所设计的控制算法全局一致稳定;通过多组计算机仿真实验结果验证了所提出的欠驱动无人艇轨迹跟踪控制算法的有效性、稳定性和优越性。 展开更多
关键词 欠驱动无人艇 超螺旋算法 轨迹跟踪 滑模控制 一阶低通滤波器
暂未订购 下载PDF
Speech Enhancement Based on Approximate Message Passing 认领 引用 被引量：2
5
作者 Chao Li Ting Jiang Sheng Wu 《China Communications》 SCIE CSCD 2020年第8期187-198,共12页
To overcome the limitations of conventional speech enhancement methods, such as inaccurate voice activity detector(VAD) and noise estimation, a novel speech enhancement algorithm based on the approximate message passi... To overcome the limitations of conventional speech enhancement methods, such as inaccurate voice activity detector(VAD) and noise estimation, a novel speech enhancement algorithm based on the approximate message passing(AMP) is adopted. AMP exploits the difference between speech and noise sparsity to remove or mute the noise from the corrupted speech. The AMP algorithm is adopted to reconstruct the clean speech efficiently for speech enhancement. More specifically, the prior probability distribution of speech sparsity coefficient is characterized by Gaussian-model, and the hyper-parameters of the prior model are excellently learned by expectation maximization(EM) algorithm. We utilize the k-nearest neighbor(k-NN) algorithm to learn the sparsity with the fact that the speech coefficients between adjacent frames are correlated. In addition, computational simulations are used to validate the proposed algorithm, which achieves better speech enhancement performance than other four baseline methods-Wiener filtering, subspace pursuit(SP), distributed sparsity adaptive matching pursuit(DSAMP), and expectation-maximization Gaussian-model approximate message passing(EM-GAMP) under different compression ratios and a wide range of signal to noise ratios(SNRs). 展开更多
关键词 speech enhancement approximate message passing Gaussian model expectation maximization algorithm
暂未订购 下载PDF
A low-complexity AMP detection algorithm with deep neural network for massive mimo systems 认领 引用 被引量：1
6
作者 Zufan Zhang Yang Li +1 位作者 Xiaoqin Yan Zonghua Ouyang 《Digital Communications and Networks》 SCIE CSCD 2024年第5期1375-1386,共12页
Signal detection plays an essential role in massive Multiple-Input Multiple-Output(MIMO)systems.However,existing detection methods have not yet made a good tradeoff between Bit Error Rate(BER)and computational complex... Signal detection plays an essential role in massive Multiple-Input Multiple-Output(MIMO)systems.However,existing detection methods have not yet made a good tradeoff between Bit Error Rate(BER)and computational complexity,resulting in slow convergence or high complexity.To address this issue,a low-complexity Approximate Message Passing(AMP)detection algorithm with Deep Neural Network(DNN)(denoted as AMP-DNN)is investigated in this paper.Firstly,an efficient AMP detection algorithm is derived by scalarizing the simplification of Belief Propagation(BP)algorithm.Secondly,by unfolding the obtained AMP detection algorithm,a DNN is specifically designed for the optimal performance gain.For the proposed AMP-DNN,the number of trainable parameters is only related to that of layers,regardless of modulation scheme,antenna number and matrix calculation,thus facilitating fast and stable training of the network.In addition,the AMP-DNN can detect different channels under the same distribution with only one training.The superior performance of the AMP-DNN is also verified by theoretical analysis and experiments.It is found that the proposed algorithm enables the reduction of BER without signal prior information,especially in the spatially correlated channel,and has a lower computational complexity compared with existing state-of-the-art methods. 展开更多
关键词 Massive MIMO system Approximate message passing(AMP)detection algorithm Deep neural network(DNN) Bit error rate(BER) Low-complexity
暂未订购 下载PDF
基于流向控制的消息传递协作定位算法 认领 引用
7
作者 俞文彦 李浩宇 +1 位作者 李有明 李博辉 《西安电子科技大学学报》 EI CAS CSCD 北大核心 2026年第3期44-61,共18页
针对移动目标节点的协作定位问题,联合到达时间和多普勒频移测量提出一种基于流向控制的后验线性化消息传递算法。首先构建所有目标节点位置-速度的联合后验分布,并设计相应因子图;然后采用后验线性化方法实现测量模型的伪线性化;接着... 针对移动目标节点的协作定位问题,联合到达时间和多普勒频移测量提出一种基于流向控制的后验线性化消息传递算法。首先构建所有目标节点位置-速度的联合后验分布,并设计相应因子图;然后采用后验线性化方法实现测量模型的伪线性化;接着设计节点分类机制以控制因子图中的消息流向,从而抑制不准确消息的传递,降低其造成的定位误差和计算开销;最后通过迭代消息传递和置信度更新完成全部目标节点的位置和速度估计。仿真结果表明,在测量噪声为1的条件下,当目标节点在第一个时刻开始运动时,所提算法的位置估计误差在1.5 m内的概率达到95%,而两种对比算法分别为62%和20%。同时,所提算法的速度估计误差在0.2 m/s内的概率达到99%,两种对比算法分别为72%和84%。此外,所提算法的运行时间较两种对比算法分别缩短约27%和34%。 展开更多
关键词 协作定位 消息传递算法 因子图 到达时间 多普勒频移
暂未订购 下载PDF
Multi-Deme Parallel FGAs-Based Algorithm for Multitarget Tracking 认领 引用 被引量：1
8
作者 刘虎 朱力立 张焕春 《Journal of Electronic Science and Technology of China》 2006年第1期12-17,共6页
For data association in multisensor and multitarget tracking, a novel parallel algorithm is developed to improve the efficiency and real-time performance of FGAs-based algorithm. One Cluster of Workstation （COW） wit... For data association in multisensor and multitarget tracking, a novel parallel algorithm is developed to improve the efficiency and real-time performance of FGAs-based algorithm. One Cluster of Workstation （COW） with Message Passing Interface （MPI） is built. The proposed Multi-Deme Parallel FGA （MDPFGA） is run on the platform. A serial of special MDPFGAs are used to determine the static and the dynamic solutions of generalized m-best S-D assignment problem respectively, as well as target states estimation in track management. Such an assignment-based parallel algorithm is demonstrated on simulated passive sensor track formation and maintenance problem. While illustrating the feasibility of the proposed algorithm in multisensor multitarget tracking, simulation results indicate that the MDPFGAs-based algorithm has greater efficiency and speed than the FGAs-based algorithm. 展开更多
关键词 multitarget tracking multi-deme Fuzzy Genetic Algorithm （FGA） parallelization Message Passing Interface （MPI）
暂未订购 下载PDF
面向大规模LEO卫星网络的深度图强化学习路由算法 认领 引用
9
作者 黄思博 杨明川 张祯昊 《光电工程》 CAS CSCD 北大核心 2026年第6期166-185,共20页
大规模低地球轨道(LEO)卫星网络路由技术面临着网络拓扑动态变化导致的路由传输性能不佳、算法模型可扩展性不足等关键挑战。为此,利用改进的消息传递神经网络(MPNN)和深度Q网络(DQN),本文提出了一种基于MPNN和DQN的大规模LEO卫星网络... 大规模低地球轨道(LEO)卫星网络路由技术面临着网络拓扑动态变化导致的路由传输性能不佳、算法模型可扩展性不足等关键挑战。为此,利用改进的消息传递神经网络(MPNN)和深度Q网络(DQN),本文提出了一种基于MPNN和DQN的大规模LEO卫星网络路由算法(MDSR)。其中,改进的MPNN模块提取网络中卫星和星间链路的状态特征,DQN模块基于这些特征实现路由决策。MDSR算法在极轨道大规模LEO卫星网络上训练并测试。结果表明,训练时MDSR模型的收敛速度和初始奖励均优于未改进MPNN模型。测试时MDSR的平均丢包率比其他强化学习算法降低约48%,比Dijkstra最短路径(DSP)算法降低约35%;平均端到端时延比DSP、Q学习(Q-learning)、DQN和深度确定性策略性梯度(DDPG)算法分别降低了约20.5%、7.9%、2.7%和5.4%;平均吞吐量比DSP、Q-learning、DQN和DDPG分别提升了约21.7%、7.6%、5%和1.2%。同时,MDSR无需额外训练即可适应不同星座网络构型,具备较强的拓扑泛化能力。 展开更多
关键词 大规模低地球轨道卫星网络 路由算法 消息传递神经网络 深度Q网络
暂未订购 下载PDF
UAMP-Based Delay-Doppler Channel Estimation for OTFS Systems 认领 引用 被引量：5
10
作者 Zhongjie Li Weijie Yuan +2 位作者 Qinghua Guo Nan Wu Ji Zhang 《China Communications》 SCIE CSCD 2023年第10期70-84,共15页
Orthogonal time frequency space(OTFS)technique,which modulates data symbols in the delay-Doppler(DD)domain,presents a potential solution for supporting reliable information transmission in highmobility vehicular netwo... Orthogonal time frequency space(OTFS)technique,which modulates data symbols in the delay-Doppler(DD)domain,presents a potential solution for supporting reliable information transmission in highmobility vehicular networks.In this paper,we study the issues of DD channel estimation for OTFS in the presence of fractional Doppler.We first propose a channel estimation algorithm with both low complexity and high accuracy based on the unitary approximate message passing(UAMP),which exploits the structured sparsity of the effective DD domain channel using hidden Markov model(HMM).The empirical state evolution(SE)analysis is then leveraged to predict the performance of our proposed algorithm.To refine the hyperparameters in the proposed algorithm,we derive the update criterion for the hyperparameters through the expectation-maximization(EM)algorithm.Finally,Our simulation results demonstrate that our proposed algorithm can achieve a significant gain over various baseline schemes. 展开更多
关键词 orthogonal time frequency space(OTFS) channel estimation hidden Markov model(HMM) unitary approximate message passing(UAMP)
暂未订购 下载PDF
UAMP-Based Delay-Doppler Channel Estimation for OTFS Systems 认领 引用
11
作者 Li Zhongjie Yuan Weijie +2 位作者 Guo Qinghua Wu Nan Zhang Ji 《China Communications》 SCIE CSCD 2024年第10期1-15,共15页
Orthogonal time frequency space(OTFS)technique, which modulates data symbols in the delayDoppler(DD) domain, presents a potential solution for supporting reliable information transmission in highmobility vehicular net... Orthogonal time frequency space(OTFS)technique, which modulates data symbols in the delayDoppler(DD) domain, presents a potential solution for supporting reliable information transmission in highmobility vehicular networks. In this paper, we study the issues of DD channel estimation for OTFS in the presence of fractional Doppler. We first propose a channel estimation algorithm with both low complexity and high accuracy based on the unitary approximate message passing(UAMP), which exploits the structured sparsity of the effective DD domain channel using hidden Markov model(HMM). The empirical state evolution(SE) analysis is then leveraged to predict the performance of our proposed algorithm. To refine the hyperparameters in the proposed algorithm,we derive the update criterion for the hyperparameters through the expectation-maximization(EM) algorithm. Finally, Our simulation results demonstrate that our proposed algorithm can achieve a significant gain over various baseline schemes. 展开更多
关键词 channel estimation hidden Markov model(HMM) orthogonal time frequency space(OTFS) unitary approximate message passing(UAMP)
暂未订购 下载PDF
Message Passing Based Detection for Orthogonal Time Frequency Space Modulation 认领 引用
12
作者 YUAN Zhengdao LIU Fei +1 位作者 GUO Qinghua WANG Zhongyong 《ZTE Communications》 2021年第4期34-44,共11页
The orthogonal time frequency space(OTFS)modulation has emerged as a promis⁃ing modulation scheme for wireless communications in high-mobility scenarios.An efficient detector is of paramount importance to harvesting t... The orthogonal time frequency space(OTFS)modulation has emerged as a promis⁃ing modulation scheme for wireless communications in high-mobility scenarios.An efficient detector is of paramount importance to harvesting the time and frequency diversities promised by OTFS.Recently,some message passing based detectors have been developed by exploiting the features of the OTFS channel matrices.In this paper,we provide an overview of some re⁃cent message passing based OTFS detectors,compare their performance,and shed some light on potential research on the design of message passing based OTFS receivers. 展开更多
关键词 OTFS detection message passing belief propagation approximate message pass⁃ing(AMP) unitary AMP(UAMP)
暂未订购 下载PDF
QIM digital watermarkingbased on LDPC code and messagepassingunder scalingattacks 认领 引用
13
作者 崔鑫 颜斌 +1 位作者 贾霞 王亚菲 《Journal of Measurement Science and Instrumentation》 CAS 2014年第1期37-40,共4页
Watermarking system based on quantization index modulation （QIM） is increasingly popular in high payload applications,but it is inherently fragile against amplitude scaling attacks.In order to resist desynchronizati... Watermarking system based on quantization index modulation （QIM） is increasingly popular in high payload applications,but it is inherently fragile against amplitude scaling attacks.In order to resist desynchronization attacks of QIM digital watermarking,a low density parity check （LDPC） code-aided QIM watermarking algorithm is proposed,and the performance of QIM watermarking system can be improved by incorporating LDPC code with message passing estimation/detection framework.Using the theory of iterative estimation and decoding,the watermark signal is decoded by the proposed algorithm through iterative estimation of amplitude scaling parameters and decoding of watermark.The performance of the proposed algorithm is closer to the dirty paper Shannon limit than that of repetition code aided algorithm when the algorithm is attacked by the additive white Gaussian noise.For constant amplitude scaling attacks,the proposed algorithm can obtain the accurate estimation of amplitude scaling parameters.The simulation result shows that the algorithm can obtain similar performance compared to the algorithm without desynchronization. 展开更多
关键词 digital watermarking quantization index modulation （QIM） message passing algorithm based on factor graph low density parity check （LDPC） code amplitude scaling attack
暂未订购 下载PDF
Pre-process algorithm for satellite laser ranging data based on curve recognition from points cloud 认领 引用
14
作者 Liu Yanyu Zhao Dongming Wu Shan 《Geodesy and Geodynamics》 2012年第2期53-59,共7页
The satellite laser ranging （SLR） data quality from the COMPASS was analyzed, and the difference between curve recognition in computer vision and pre-process of SLR data finally proposed a new algorithm for SLR was ... The satellite laser ranging （SLR） data quality from the COMPASS was analyzed, and the difference between curve recognition in computer vision and pre-process of SLR data finally proposed a new algorithm for SLR was discussed data based on curve recognition from points cloud is proposed. The results obtained by the new algorithm are 85 % （or even higher） consistent with that of the screen displaying method, furthermore, the new method can process SLR data automatically, which makes it possible to be used in the development of the COMPASS navigation system. 展开更多
关键词 satellite laser ranging （SLR） curve recognition points cloud pre-process algorithm COM- PASS screen displaying
暂未订购 下载PDF
Index Modulation Aided OTFS for SCMA System 认领 引用
15
作者 He Chunlin Xiao Lixia +3 位作者 Li Shuo Liu Weidan Xiao Pei Jiang Tao 《China Communications》 SCIE EI CSCD 2025年第8期19-28,共10页
In this paper,an index modulation(IM)aided uplink orthogonal time frequency space modulation(OTFS)structure for sparse code multiple access(SCMA)is proposed.To be more specific,the information bits are firstly partiti... In this paper,an index modulation(IM)aided uplink orthogonal time frequency space modulation(OTFS)structure for sparse code multiple access(SCMA)is proposed.To be more specific,the information bits are firstly partitioned for transmit antenna(TA)selection and sparse codeword mapping,respectively.Subsequently,the codewords deployed on the 2-dimensional(2D)delay-Doppler(DD)plane are transmitted by the selected TA,and the superimposed signals are jointly detected at the receiver.Furthermore,a low-complexity zero-embedded expectation propagation(ZE-EP)detector is conceived,where the codebooks are extended with zero vectors to reflect the silent indices.The simulation results demonstrate that the proposed IM-OTFS-SCMA system is capable of providing significant performance gain over the OTFS-SCMA counterpart. 展开更多
关键词 expectation propagation algorithm index modulation message passing algorithm OTFS SCMA
暂未订购 下载PDF
极弱电网下并网逆变器自适应改进前馈策略 认领 引用 被引量：1
16
作者 赵铁英 田培建 +2 位作者 李俊然 黄志远 祁昱昂 《电力科学与技术学报》 CAS CSCD 北大核心 2025年第4期269-281,共13页
在极弱电网条件下,并网逆变器引入网压比例前馈控制策略来提升低频段幅值增益并抑制电网背景谐波干扰。但当电网阻抗参数增大时,系统的相位裕度会显著下降,出现失稳现象。对此,提出一种极弱电网下并网逆变器自适应改进前馈策略。先基于... 在极弱电网条件下,并网逆变器引入网压比例前馈控制策略来提升低频段幅值增益并抑制电网背景谐波干扰。但当电网阻抗参数增大时,系统的相位裕度会显著下降,出现失稳现象。对此,提出一种极弱电网下并网逆变器自适应改进前馈策略。先基于阻抗特性分析方法,分析系统相位裕度恶化的内在机理,提出在前馈通道上串联二阶低通滤波器来提高系统的相位裕度,并尽可能保留其在低频的增益效果的方法;再提出采用在线阻抗检测技术与结合遗传优化算法的自适应参数设计方法,提高参数设计效率,进而提高并网逆变器在极弱电网环境下的鲁棒性;最后,通过仿真与试验验证所提方法的可行性与有效性。 展开更多
关键词 极弱电网 二阶低通滤波器 并网逆变器 遗传优化算法 自适应参数设计
暂未订购 下载PDF
基于深度残差网络的多层多道焊缝识别 认领 引用 被引量：2
17
作者 何俊杰 王传睿 王天琪 《天津工业大学学报》 CAS 北大核心 2025年第1期91-96,共6页
为保证焊缝跟踪的精度并将激光条纹从强弧光、飞溅中分离出来,提出了一种基于深度残差(SRNU)网络的激光条纹分割算法。该算法是将带有弧光的图像送入SRNU模型,对内嵌于Resunet网络的编码层部分进行改进,添加SE模块和分组残差模块,对多... 为保证焊缝跟踪的精度并将激光条纹从强弧光、飞溅中分离出来,提出了一种基于深度残差(SRNU)网络的激光条纹分割算法。该算法是将带有弧光的图像送入SRNU模型,对内嵌于Resunet网络的编码层部分进行改进,添加SE模块和分组残差模块,对多层级特征信息进行提取和解析。结果表明:所提算法与Resunet算法相比,平均交并比、精确率、召回率与F1分数分别提升了0.79%、1.38%、0.50%和0.91%,说明该方法有较好的鲁棒性且具有较强的抗干扰能力,在复杂工况下也能将激光条纹从强弧光、飞溅中分离出来。 展开更多
关键词 结构光视觉传感器 深度学习 多层多道焊缝 焊缝识别 深度残差 激光条纹分割算法
暂未订购 下载PDF
可满足性问题研究进展 认领 引用
18
作者 赵星宇 王晓峰 +2 位作者 庞立超 杨易 杨澜 《计算机应用与软件》 北大核心 2025年第10期13-23,52,共11页
可满足性问题是一种NP完全问题,被广泛运用于人工智能和机器学习等研究方面。基于近年来对可满足性问题的研究,对可满足性问题的定义与因子图的特征进行介绍;从可满足性问题的结构特征入手,分类介绍相变、树宽与树分解、结构熵等;将求... 可满足性问题是一种NP完全问题,被广泛运用于人工智能和机器学习等研究方面。基于近年来对可满足性问题的研究,对可满足性问题的定义与因子图的特征进行介绍;从可满足性问题的结构特征入手,分类介绍相变、树宽与树分解、结构熵等;将求解算法分为四类(完备性算法、信息传播算法、局部搜索算法和智能优化算法)分别进行归纳;分析可满足性问题的各类实际应用;对可满足性问题研究的发展趋势进行展望与总结。 展开更多
关键词 可满足性问题 结构特征 局部搜索算法 信息传播算法
暂未订购 下载PDF
Combined UAMP and MF Message Passing Algorithm for Multi-Target Wideband DOA Estimation with Dirichlet Process Prior 认领 引用
19
作者 Shanwen Guan Xinhua Lu +2 位作者 Ji Li Rushi Lan Xiaonan Luo 《Tsinghua Science and Technology》 SCIE EI CAS CSCD 2024年第4期1069-1081,共13页
When estimating the direction of arrival (DOA) of wideband signals from multiple sources, the performance of sparse Bayesian methods is influenced by the frequency bands occupied by signals in different directions. Th... When estimating the direction of arrival (DOA) of wideband signals from multiple sources, the performance of sparse Bayesian methods is influenced by the frequency bands occupied by signals in different directions. This is particularly true when multiple signal frequency bands overlap. Message passing algorithms (MPA) with Dirichlet process (DP) prior can be employed in a sparse Bayesian learning (SBL) framework with high precision. However, existing methods suffer from either high complexity or low precision. To address this, we propose a low-complexity DOA estimation algorithm based on a factor graph. This approach introduces two strong constraints via a stretching transformation of the factor graph. The first constraint separates the observation from the DP prior, enabling the application of the unitary approximate message passing (UAMP) algorithm for simplified inference and mitigation of divergence issues. The second constraint compensates for the deviation in estimation angle caused by the grid mismatch problem. Compared to state-of-the-art algorithms, our proposed method offers higher estimation accuracy and lower complexity. 展开更多
关键词 wideband direction of arrival(DOA)estimation sparse Bayesian learning(SBL) unitary approximate message passing(UAMP)algorithm Dirichlet process(DP)
暂未订购 下载PDF
卫星物联网中基于状态位置信息的低复杂度SCMA多用户检测算法 认领 引用
20
作者 甄立 王嘉浩 +1 位作者 何华 卢光跃 《物联网学报》 2025年第1期71-81,共11页
卫星物联网是6G实现万物智联的关键所在,而其频谱资源和星上载荷的双重受限性,给海量用户的接入效能提升带来严峻挑战。针对稀疏码多址接入(SCMA,sparse code multiple access)星载接收机多用户检测效率低下问题,考虑迭代过程中码字发... 卫星物联网是6G实现万物智联的关键所在,而其频谱资源和星上载荷的双重受限性,给海量用户的接入效能提升带来严峻挑战。针对稀疏码多址接入(SCMA,sparse code multiple access)星载接收机多用户检测效率低下问题,考虑迭代过程中码字发送概率的差异性,提出一种基于状态位置信息的对数域消息传递算法(SPI-Log-MPA,state position information based log message passing algorithm)。该算法根据用户码字状态位置的变化情况,在迭代检测过程中通过减少不可靠码字、提前对稳定用户进行解码、设立奖惩机制对非稳定用户进行解码等措施,显著提升了检测效率。在此基础上,对阶段设置与状态位置信息矩阵两方面进行优化,提出两阶段的改进算法,进一步加快了收敛速度。复杂度分析与仿真结果表明,所提算法在保证误码率性能的前提下具有更低的计算复杂度。 展开更多
关键词 卫星物联网 稀疏码多址接入 多用户检测 消息传递算法 状态位置信息
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 18 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈