检索结果-内蒙古大学图书馆

Controlled-source electromagnetic noise attenuation via a deep convolutional neural network and high-quality sounding curve screening mechanism

引用

Geophysics 2025年第3期90卷 WA125-WA140页

作者： Liu, Yecheng Li, Diquan Li, Jin Zhang, Xian Central South University Monitoring Ministry of Education Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Changsha China Hunan Provincial Key Laboratory of Non-ferrous Resources and Geological Hazard Detection Changsha China Central South University School of Geoscience and Info-physics Changsha China Hunan Normal University College of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha China Hunan University of Finance and Economics School of Information Technology and Management Hunan Provincial Key Laboratory of Finance & Economics Big Data Science and Technology Changsha China

Strong noise is one of the biggest challenges in controlled-source electromagnetic (CSEM) exploration, which severely affects the quality of the recorded signal. We develop a novel and effective CSEM noise attenuation method that integrates a deep convolutional neural network (DCNN) with a high-quality sounding curve screening mechanism. This method first uses a DCNN to learn the large-scale noise characteristics of CSEM measured data and build a DCNN denoising model for attenuating the noise. Because some impulse noise remains after DCNN denoising, the high-quality sounding curve screening mechanism is innovatively applied to optimize the DCNN denoised data. The core of this method is the smoothness value (SV), which quantitatively evaluates the smoothness of the sounding curve (apparent resistivity curve). In effect, the mechanism segments the overall DCNN denoised data and calculates the corresponding sounding curve and its SV for each segment. The highest-quality sounding curve can be screened out by comparing the SVs of all curves as well as obtaining the highest-quality data segment present in the overall DCNN denoised data. Finally, our method is validated with synthetic and field data, demonstrating its feasibility and effectiveness in attenuating large-scale CSEM noise. The quality of CSEM data, which is heavily affected by noise, is significantly improved after processing by our method. © 2025 Society of Exploration Geophysicists. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Kernel Bayesian tensor ring decomposition for multiway data recovery

引用

Neural Networks 2025年 189卷 107500页

作者： Huang, Zhenhao Zhou, Guoxu Qiu, Yuning Chen, Xinqi Zhao, Qibin School of Automation Guangdong University of Technology Guangzhou510006 China Key Laboratory of Intelligent Detection and the Internet of Things in Manufacturing Ministry of Education Guangdong University of Technology Guangzhou510006 China RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong Key Laboratory of IoT Information Technology Guangdong University of Technology Guangzhou510006 China 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou510006 China

Tensor ring (TR) decomposition has emerged as the prevailing method for tensor completion. Earlier approaches have situated TR decomposition within a probabilistic framework, yielding satisfactory outcomes. However, these methods ignore side information or are inherently incapable of leveraging it. In response to this challenge, we propose a variational inference-based kernel Bayesian TR (VKBTR) method that integrates side information, low-rankness, and sparse learning. By incorporating kernel matrices into the TR factors, we can effectively leverage the intrinsic properties of the data (e.g., the smoothness in images and videos) to improve performance across different tasks. Additionally, by introducing a sparsity-inducing hierarchical prior on the latent factors, the proposed method enables automatic selection of the TR rank. Leveraging the variational inference algorithm enables us to achieve the update of posterior parameters effectively. Extensive experiments conducted on synthetic data, color images, face images, and color video data have shown that, with the assistance of side information, VKBTR significantly improves performance in completion tasks compared to other state-of-the-art methods. © 2025 Elsevier Ltd

关键词： Variational techniques

来源：评论

学校读者我要写书评

暂无评论

Solo Adaptation for Distributed Synchronization With Application to Event-Triggered Linear Multi-Agent Systems

引用

IEEE Transactions on Automatic Control 2025年第6期70卷 4225-4232页

作者： Chen, Ci Zheng, Zhiyang Lewis, Frank L. Xie, Kan Xie, Shengli Guangdong University of Technology Guangdong Provincial Key Laboratory of Intelligent Systems and Optimization Integration Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education School of Automation Guangzhou510006 China Guangdong University of Technology School of Automation Guangdong Guangzhou510006 China The University of Texas at Arlington UTA Research Institute Fort Worth76118 United States Guangdong University of Technology 111 Center for Intelligent Batch Manufacturing Based on IoT Technology School of Automation Guangzhou China Guangdong University of Technology Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing Ministry of Education School of Automation Guangzhou510006 China

We study a solo adaptation-based protocol design problem for distributed synchronization of event-triggered linear multi-agent systems (MAS) over general directed graphs. We show that a solo adaptive gain, a locally static control gain matrix, and a distributed state measurement are sufficient for obtaining adaptive distributed synchronization of linear MAS over directed graphs without any prior knowledge of the global communication network. We then extend the solo adaptation structure to formulate an event-triggered synchronization control protocol. The main feature of our result is that the time for triggering a subsequent event is now computed using the distributed event-triggered state measurement, rather than the continuous-time state measurement. © 1963-2012 IEEE.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Super-Sparse-Sampling High-Resolution Photoacoustic Microscopy Boosted by Generative Diffusion Priors

SSRN

引用

SSRN 2025年

作者： Chen, Yanhan Cao, Yubin Liu, Guolin Wang, Yiguang Cao, Siyi Yuan, Weiliang Lian, Teng Liu, Qiegen Song, Xianlin School of Information Engineering Nanchang University Nanchang330031 China Jiluan Academy Nanchang University Nanchang330031 China Jiangxi Provincial Key Laboratory of Advanced Signal Processing and Intelligent Communications Nanchang University Nanchang330031 China Jiangxi Provincial Engineering Research Center for Intelligent Medical Information Detection and Internet of Things Nanchang University Nanchang330031 China

Photoacoustic Microscopy (PAM) is a non-invasive hybrid biomedical imaging technology that combines the advantages of optics and acoustics to provide high-resolution biological tissue information at the submicron scale. Conventional PAM suffers from slow imaging speeds during high-resolution imaging due to the limitations of the laser pulse repetition rate. Although extending the sampling step size (i.e., sparse sampling) can enhance imaging speed and alleviate data collection demands, it might compromise image quality by causing distortions or the loss of fine details. This study presents an enhanced method based on the mean-reverting diffusion model for sparse-sampling high-resolution reconstruction in PAM to address the problem. The model captures prior knowledge of the data distribution by simulating the degradation process from a fully-sampled image to a sparsely-sampled image contaminated with Gaussian noise (mean state). The learned prior is then utilized to iteratively reconstruct a fully-sampled image from the sparsely-sampled one. The results indicate that the IR-SDE method achieves high-resolution sparse-sampling reconstruction for mouse in vivo blood vessel experimental data compared with the Richardson-Lucy deconvolution method (RL Deconv) and CycleGAN method. Under super-sparse sampling (sampling ratios of about 0.4%), the IR-SDE method reaches an SSIM of 0.742 and a PSNR of 24.22 dB using only about 0.4% of the fully-sampled pixels, improving 0.597 (~412%) in SSIM and 11.51 dB (~91%) in PSNR, compared to U-Net method. Even in the case of reconstructing sparsely-sampled PAM images obtained from real-world scenarios without prior training or extensive trainable data, the proposed method still demonstrates satisfactory reconstruction performance. The proposed method is anticipated to improve reconstruction speed and imaging speed, achieving highresolution reconstruction at super-sparse sampling. © 2025, The Authors. All rights reserved.

关键词： Photoacoustic microscopy

来源：评论

学校读者我要写书评

暂无评论

Artificial Immune detection for Network Intrusion Data Based on Quantitative Matching Method

引用

Computers, Materials & Continua 2024年第2期78卷 2361-2389页

作者： CaiMing Liu Yan Zhang Zhihui Hu Chunming Xie School of Electronic Information and Artificial Intelligence Leshan Normal UniversityLeshan614000China Intelligent Network Security Detection and Evaluation Laboratory Leshan Normal UniversityLeshan614000China Internet Natural Language Intelligent Processing Key Laboratory of Education Department of Sichuan Province Leshan Normal UniversityLeshan614000China

Artificial immune detection can be used to detect network intrusions in an adaptive approach and proper matching methods can improve the accuracy of immune detection *** paper proposes an artificial immune detection model for network intrusion data based on a quantitative matching *** proposed model defines the detection process by using network data and decimal values to express features and artificial immune mechanisms are simulated to define immune ***,to improve the accuracy of similarity calculation,a quantitative matching method is *** model uses mathematical methods to train and evolve immune elements,increasing the diversity of immune recognition and allowing for the successful detection of unknown *** proposed model’s objective is to accurately identify known intrusions and expand the identification of unknown intrusions through signature detection and immune detection,overcoming the disadvantages of traditional *** experiment results show that the proposed model can detect intrusions *** has a detection rate of more than 99.6%on average and a false alarm rate of 0.0264%.It outperforms existing immune intrusion detection methods in terms of comprehensive detection performance.

关键词： Immune detection network intrusion network data signature detection quantitative matching method

来源：评论

学校读者我要写书评

暂无评论

Grain condition inspection: one improved grey wolf algorithm for nodes deployment optimization combining with path planning of multi-inspection robots

引用

Soft Computing 2024年第20期28卷 11971-11986页

作者： Zhu, Chunhua Zhang, Jilong Yang, Jing Key Laboratory of Grain Information Processing and Control Ministry of Education Henan University of Technology Henan Zhengzhou450001 China Henan Key Laboratory of Grain Photoelectric Detection and Control Henan University of Technology Henan Zhengzhou450001 China Henan Engineering Laboratory of Grain Condition Intelligent Detection and Application Henan University of Technology Henan Zhengzhou450001 China

Grain inspection robots can detect abnormal information such as grain insects and impurities on the grain surface by deploying detection nodes, it has a significant for the safety of grain storage. Generally, the grey wolf optimization (GWO) algorithm has significant advantages such as fewer control parameters and easy implementation, is one of the commonly employed approaches aiming to solve the problem in many fields. However, the traditional GWO has the shortcomings such as poor population initialization diversity, slow convergence speed and easily fall into local optimal values, it is difficult to solve deployment of inspection nodes problem in the grain surface. In this study, an improved Latin Hypercube grey wolf optimization (LH-GWO) is presented to overcome the disadvantages of the traditional GWO algorithm in solving inspection node deployment problem. The LH-GWO algorithm contains two novel mechanisms which are the Latin Hypercube Sampling population initialization and an improved nonlinear convergence factor. Moreover, a grain surface boundary inspection nodes deployment strategy is proposed to optimize the location of nodes at the boundary. For verifying the effectiveness of the proposed LH-GWO, comparing with six commonly used algorithms based on benchmark functions experiment and coverage rate experiment. The experimental results demonstrate the merits of LH-GWO in terms of convergence speed, optimization accuracy and area coverage. Finally, the optimal inspection nodes are divided into three inspection regional areas by k-means algorithm clustering, and in each inspection regional area, the optimal inspection path of each robot is determined by solving the travel salesman problem (TSP). © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

A Low Complexity Beam Selection Method for MmWave Massive MIMO Systems

A Low Complexity Beam Selection Method for MmWave Massive MI...

引用

2023 International Conference on Ubiquitous Communication, Ucom 2023

作者： Zhu, Chunhua Ji, Qinwen Guo, Xinying Henan University of Technology The Key Laboratory of Grain Information Processing and Control The Henan Key Laboratory of Grain Photoelectric Detection and Control Zhengzhou China Henan University of Technology Henan Engineering Laboratory of Grain Condition Intelligent Detection and Application Zhengzhou China

ISBN: (纸本)9798350340433

The levels of inter-user interference (IUI) usually vary due to the different geographical locations of users, but, most existing beam selection methods apply the same beam selection criteria for all users, which is detrimental to maintain an attractive trade-off between complexity and system performance. Considering the discrepancy of IUI comprehensively, a low complexity beam selection method for millimeter-wave massive multiple-input multiple-output (MIMO) systems is proposed. Firstly, a candidate beam set (CBS) is constructed in light of the sparsity and power distribution of the beamspace channel, thereby all users are classified into non-interfering users (NIUs), low-interference users (LIUs) and high-interference users (HIUs). For NIUs, the beams with large power are selected from CBS under the magnitude maximization (MM) criterion;for LIUs, a novel MM criterion with a tabu list is designed, which can effectively tackle the drawback of assigning shared beams in traditional MM;for HIUs, the incremental algorithm based on the sum-rate maximization criterion is developed to find the optimal beams from CBS. Simulation results validate that the proposed method can achieve almost the same sum-rate performance as the existing methods with the lower computational complexity. © 2023 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Control Policy Learning Design for Vehicle Urban Positioning via BeiDou Navigation

引用

Journal of Systems Science & Complexity 2024年第1期37卷 114-135页

作者： QIN Yahang ZHANG Chengye CHEN Ci XIE Shengli LEWIS Frank L School of Automation Guangdong University of TechnologyGuangzhou 510006China Guangdong Key Laboratory of IoT Information Technology Guangzhou 510006China. Center for Intelligent Batch Manufacturing Based on IoT Technology Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing Ministry of EducationGuangzhou 510006China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou 510006China Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China. UTA Research Institute The University of Texas at ArlingtonFort WorthTX 76019USA

This paper presents a learning-based control policy design for point-to-point vehicle positioning in the urban environment via BeiDou *** navigating in urban canyons,the multipath effect is a kind of interference that causes the navigation signal to drift and thus imposes severe impacts on vehicle localization due to the reflection and diffraction of the BeiDou ***,the authors formulated the navigation control system with unknown vehicle dynamics into an optimal control-seeking problem through a linear discrete-time system,and the point-to-point localization control is modeled and handled by leveraging off-policy reinforcement learning for feedback *** proposed learning-based design guarantees optimality with prescribed performance and also stabilizes the closed-loop navigation system,without the full knowledge of the vehicle *** is seen that the proposed method can withstand the impact of the multipath effect while satisfying the prescribed convergence rate.A case study demonstrates that the proposed algorithms effectively drive the vehicle to a desired setpoint under the multipath effect introduced by actual experiments of BeiDou navigation in the urban environment.

关键词： BeiDou navigation multipath effect prescribed convergence rate reinforcement learning urban localization.

来源：评论

学校读者我要写书评

暂无评论

Recognition of Group Activities Using Complex Wavelet Domain Based Cayley-Klein Metric Learning

引用

Journal of Beijing Institute of Technology 2018年第4期27卷 592-603页

作者： Gensheng Hu Min Li Dong Liang Mingzhu Wan Wenxia Bao Key Laboratory of Intelligent Computing and Signal Processing Ministry of EducationAnhui University Hefei 230039China School of Electronics and Information Engineering Anhui UniversityHefei 230601 China School of Information Science and Technology Fudan UniversityShanghai 200433China Anhui Key Laboratory of Polarization Imaging Detection Technology Hefei 230031China

A group activity recognition algorithm is proposed to improve the recognition accuracy in video surveillance by using complex wavelet domain based Cayley-Klein metric ***-sampled dual-tree complex wavelet packet transform(NS-DTCWPT)is used to decompose the human images in videos into multi-scale and *** improved local binary pattern(ILBP)and an inner-distance shape context(IDSC)combined with bag-of-words model is adopted to extract the decomposed high and low frequency coefficient *** extracted coefficient features of the training samples are used to optimize Cayley-Klein metric matrix by solving a nonlinear optimization *** group activities in videos are recognized by using the method of feature extraction and Cayley-Klein metric *** results on behave video set,group activity video set,and self-built video set show that the proposed algorithm has higher recognition accuracy than the existing algorithms.

关键词： video surveillance group activity recognition non-sampled dual-tree complex wavelet packet transform(NS-DTCWPT) Cayley-Klein metric learning

来源：评论

学校读者我要写书评

暂无评论

UWB SAR image segmentation algorithm based on polynomial analysis of statistical distribution 6

UWB SAR image segmentation algorithm based on polynomial ana...

引用

6th Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2019

作者： Yuming, Wang Tian, Jin Chaopeng, Luo College of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computhing and Language Information Processing Science and Technology on Near-Surface Detection Laboratory Hunan Normal University Changsha China College of Electronic Science and Technology Science and Technology on Near-Surface Detection Laboratory National University of Defense Technology Changsha China Science and Technology on Near-Surface Detection Laboratory Wuxi214035 China

ISBN: (纸本)9781728129129

Aimed at the segmentation problem of ultrawideband synthetic aperture radar (UWB SAR) image, a novel algorithm based on polynomial analysis of statistical distribution is proposed in this letter. Firstly, we estimate the probability density function (PDF) for each pixel via sparse decomposition of which the dictionary consists of orthogonal polynomials (OP). Secondly, the weighting coefficients of corresponding OP are used to segment image using their maximum value. The experimental results validate the efficiency of this algorithm. © 2019 IEEE.

关键词： Synthetic aperture radar

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：