检索结果-内蒙古大学图书馆

SL3D-BF: A Real-World Structured Light 3D Dataset with Background-to-Foreground Enhancement

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Li, Yiming Chen, Weikang Li, Zinan Zhang, Chaobo Wang, Xiaohao Gui, Weihua Gao, Wen Liang, Xiaojun Li, Xinghui Tsinghua University Tsinghua Shenzhen International Graduate School Shenzhen518055 China Pengcheng Laboratory Shenzhen518000 China Central South University School of Automation Changsha410083 China Peking University National Engineering Research Center of Visual Technology School of Computer Science Beijing100871 China

Deep-learning-based structured light 3D reconstruction technology (SL3D) provides excellent solutions for intelligent manufacturing. However, the scarcity of real-world datasets covering full-process data and diverse objects hampers the validation of new ideas. Moreover, limited research on dataset construction strategies, such as scene backgrounds and sample distribution, reduces network performance. We investigate the impact of background stability on foreground accuracy (BS-FA) and find a whiteboard background improved foreground prediction accuracy by up to 82% over a black background. Guided by BS-FA, we develop the SL3D-BF, a background-effective SL3D dataset for industrial use, featuring approximately 2,100 scenes with diverse objects like metal/plastic workpieces, plaster sculptures, and standard parts for precise evaluation. It uniquely includes shadow and foreground masks, absent in prior datasets, and offers full-process data from gratings to 3D point clouds, totaling 100,800 gratings. We also establish an initial benchmark for future research by conducting evaluation experiments with advanced methods. Furthermore, we investigate the relationship between the spatial frequency of sample occurrence and the model predictive ability to minimize the time and resource demands of dataset construction. Most importantly, SL3D-BF is also a valuable resource for tasks like depth estimation, defect detection, and semantic segmentation. The dataset is available at: https://***/LiYiMingM/Dataset-SL3D-BF. © 1991-2012 IEEE.

关键词： Industrial research

来源：评论

学校读者我要写书评

暂无评论

A Fault Classification Prediction Model Based on Loose-Type Wavelet Neural Network for Server Health Management

A Fault Classification Prediction Model Based on Loose-Type ...

引用

Cloud Computing, Big Data Applications and Software engineering (CBASE), International Conference on

作者： Yi Wei Yingxiong Nong Zhe Li Jian Pan Zhenyu Yang Xiaoqi Lu Ningjiang Chen China Tobacco Guangxi Industrial Co. Ltd Nanning China School of Computer Electronics and Information Guangxi University Nanning China School of Computer Electronics and Information Guangxi University Guangxi Intelligent Digital Services Research Center of Engineering Technology Key Laboratory of Parallel Distributed and Intelligent Computing (Guangxi University) Nanning China

To prevent the serious impact on production efficiency caused by service interruption, data loss, and other issues resulting from server faults, this paper proposes a server fault prediction model named Wavelet Packet Transform Probabilistic Neural Network(WPT-PNN). WPT-PNN loosely mixes wavelet packet transform and probabilistic neural network to achieve quick fault localization and signal denoising effects. The proposed model is validated using server operational data gathered. The experimental results suggest that the WPT-PNN model can effectively manage the challenges of complicated, non-stationary, and noisy signals in the feature extraction stage and extract signal features reliably. In the fault classification prediction stage, our method improves fault prediction accuracy to 81%, and limits the error range within [-2, 4], better matching the requirements for precise and low false-positive fault prediction in servers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unlocking the power of human milk and infant feeding: Understanding how nutrition and early microbiota interaction shapes health programming

引用

Cell Host and Microbe 2025年第6期33卷 820-835页

作者： Zhernakova, Alexandra Yassour, Moran Hall, Lindsay J. Collado, Maria Carmen Department of Genetics University Medical Center Groningen University of Groningen Groningen Netherlands Department of Microbiology and Molecular Genetics IMRIC Faculty of Medicine The Hebrew University of Jerusalem Jerusalem Israel School of Computer Science and Engineering The Hebrew University of Jerusalem Jerusalem Israel Department of Microbes Infection & Microbiomes School of Infection Inflammation and Immunology College of Medicine & Health University of Birmingham Birmingham United Kingdom Food Microbiome and Health Quadram Institute Bioscience Norwich Research Park Norwich United Kingdom Norwich Medical School University of East Anglia Norwich Research Park Norwich United Kingdom Institute of Agrochemistry and Food Technology- National Research Council (IATA-CSIC) Paterna Valencia Spain

Human milk represents a highly evolved bioactive system that promotes colonization by infant microbial pioneers, supports immune maturation, and fosters infant development. Beyond providing nutrition, human milk contains key bioactive components, such as microbes, metabolites, human milk oligosaccharides, immunoglobulins, lactoferrin, and antimicrobial peptides. These factors influence colonization of the infant gut microbiome and facilitate immune development and metabolic health, with implications for health outcomes and risk of non-communicable diseases. In this review, we highlight the impact of infant feeding, human milk constituents (especially bioactive compounds), and weaning on infant microbial trajectories. By understanding how early-life nutrition influences microbial colonization and nutrient sensing, i.e., “how we feed our microbes,” we can develop targeted interventions and personalized diets to support proper gut maturation and disease prevention from infancy to adulthood, as well as explore the therapeutic potential of human milk bioactives beyond infancy, offering new strategies for disease prevention and treatment. © 2025

关键词： bioactive compounds biotics breastfeeding HMOs human milk infancy microbiome

来源：评论

学校读者我要写书评

暂无评论

Pano-NeRF: Synthesizing High Dynamic Range Novel Views with Geometry from Sparse Low Dynamic Range Panoramic Images

arXiv

引用

arXiv 2023年

作者： Lu, Zhan Zheng, Qian Shi, Boxin Jiang, Xudong School of Electrical and Electronic Engineering Nanyang Technological University Singapore College of Computer Science and Technology Zhejiang University China The State Key Lab of Brain-Machine Intelligence Zhejiang University China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China National Engineering Research Center of Visual Technology School of Computer Science Peking University China

Panoramic imaging research on geometry recovery and High Dynamic Range (HDR) reconstruction becomes a trend with the development of Extended Reality (XR). Neural Radiance Fields (NeRF) provide a promising scene representation for both tasks without requiring extensive prior data. However, in the case of inputting sparse Low Dynamic Range (LDR) panoramic images, NeRF often degrades with under-constrained geometry and is unable to reconstruct HDR radiance from LDR inputs. We observe that the radiance from each pixel in panoramic images can be modeled as both a signal to convey scene lighting information and a light source to illuminate other pixels. Hence, we propose the irradiance fields from sparse LDR panoramic images, which increases the observation counts for faithful geometry recovery and leverages the irradiance-radiance attenuation for HDR reconstruction. Extensive experiments demonstrate that the irradiance fields outperform state-of-the-art methods on both geometry recovery and HDR reconstruction and validate their effectiveness. Furthermore, we show a promising byproduct of spatially-varying lighting estimation. The code is available at https://***/Lu-Zhan/Pano-NeRF. Copyright © 2023, The Authors. All rights reserved.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Model of Switching Power Supply Based on Improved DBN 16

Fault Diagnosis Model of Switching Power Supply Based on Imp...

引用

16th IEEE International Conference on Intelligent Systems and Knowledge engineering, ISKE 2021

作者： Zhou, Lei Yu, Cheng Liu, Hu Li, Xin Li, Fenfen Zhang, Haiyan National-Local Joint Engineering Lab of System Credibility Automatic Verification Huaiyin Institute of Technology huai'An Faculty of Computer and Software Engineering Research Center for Logic and Intelligent Computation Jiangsu China Nanjing University of Technology Nanjing College of Computer Science and Technology Jiangsu211816 China Huaiyin Institute of Technology huai'An Faculty of Chemical Engineering Jiangsu China

ISBN: (纸本)9781665405539

Switching power supply has wide application in various electrical equipment. The failure of high-voltage filter capacitors is the main cause of frequent faults, accounting for more than 60% of switching power supply failures. In order to realize the real-time detection of switching power supply failure without disassembling the power supply, a fault diagnosis model for improving the deep belief network (DTDBN) is proposed. The model uses the data acquisition device to isolate, filter, and collect data on the grid voltage of the switching power supply, judge the failure ratio of the filter capacitor according to the degree of voltage distortion of the power supply. Experimental results show that the proposed fault detection method achieves a 100% recognition rate for the filter capacitor normal state, 50% and 90% state recognition rate is 90%. The superiority of this method for the classification and early warning of power capacitor faults is proved. © 2021 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xiaoke Zhu Danyang Li Xiaopan Chen Fumin Qi Fan Zhang Xiao-Yuan Jing School of Computer and Information Engineering Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng China Department of System Operation National Supercomuting Center in Shenzhen Shenzhen China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer Science Wuhan University Wuhan China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Facial image based kinship verification aims to decide whether there exists kinship between the given facial images. In practice, the cross-generation differences will cause adverse effects on kinship verification, which limits the performance. Therefore, how to mine the implied similarity from facial images with large cross-generation divergence is an important problem in kinship verification, which has not yet been well studied. In view of this, we propose a Similarity Mining via Implicit matching pattern LEarning (SMILE) approach for kinship verification. Specifically, SMILE mainly consists of two modules, including a Semi-coupled Multi-pattern Similarity Learning (SMSL) module and a Cross-Generation Feature Normalization (CGFN) module. The SMSL module is designed to learn multiple semi-coupled matching patterns for mining the implicit facial similarity information from different perspectives. The CGFN module aims to reduce the divergence between facial images of parent and child. Extensive experiments demonstrate that the proposed approach outperforms the existing state-of-the-art methods.

关键词： Pattern matching Similarity learning

来源：评论

学校读者我要写书评

暂无评论

Right Frontal Gamma Transcranial Alternating Current Stimulation Modulates Optimism Biases

引用

Neuroscience Bulletin 2025年第1期41卷 172-176页

作者： Ziqing Yao Jinwen Wei Gan Huang Linling Li Zhen Liang Li Zhang Haiyan Wu Tifei Yuan Zhiguo Zhang Xiaoqing Hu Department of Psychology The State Key Laboratory of Brain and Cognitive SciencesThe University of Hong KongHong KongSARChina School of Biomedical Engineering Medical SchoolShenzhen UniversityShenzhen518060China Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging Shenzhen UniversityShenzhen518060China Centre for Cognitive and Brain Sciences and Department of Psychology University of MacaoMacao SARChina Shanghai Key Laboratory of Psychotic Disorders Brain Health InstituteNational Center for Mental DisordersShanghai Mental Health CenterShanghai Jiaotong University School of MedicineShanghai210109China School of Computer Science and Technology Harbin Institute of TechnologyShenzhen518055China Peng Cheng Laboratory Shenzhen518055China HKU-Shenzhen Institute of Research and Innovation Shenzhen518063China

Dear Editor,People are often optimistic when forecasting the future,such that they believe they are less likely to encounter adverse life *** phenomenon,known as optimism bias,emerges due to preferential encoding and consolidation of desirable over undesirable information[1,2],engaging frontal brain regions such as the anterior cingulate cortex and inferior frontal gyrus[1].An optimism bias is instrumental in supporting mental health:reduction or absence of optimism biases is associated with mood disorders such as depression,characterized by pessimistic thinking about the future[3].This relationship highlights the potential value of interventions that could enhance optimism bias[4].

关键词： ism such likely

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a 5G Security Testbed Based on Zero Trust Architecture

Design and Implementation of a 5G Security Testbed Based on ...

引用

International Conference on Information and Communication technology Convergence (ICTC)

作者： Mahnsuk Yoon Jihun Seo Jonghoon Lee Keuchul Cho Future Mobile Communication Research Center GERI(Gumi Electronics & Information Technology Research Institute) Gumi Korea Department of The Fourth Industrial Revolution & Transport Center for Connected & Automated Driving Research Korea Transport Institute Sejong Korea Cyber Security Research Division ETRI(Electronics and Telecommunications Research Institute) Daejeon Korea School of Computer Secience and Engineering Software Education Center Kyungpook National University Daegu Korea

ISBN: (数字)9798350364637

ISBN: (纸本)9798350364644

This paper presents the design and implementation of a 5G security testbed based on Zero Trust Architecture (ZTA). As 5G networks offer ultra-high speeds, low latency, and massive connectivity, ensuring their security has become a critical challenge, especially with the distributed nature and numerous connected devices. Traditional perimeter-based security models are no longer sufficient. Therefore, Zero Trust Architecture, which continuously verifies and monitors all resources and users regardless of their location, has been proposed as a solution. In this study, we propose a comprehensive security management system by integrating ZTA into a 5G testbed, focusing on real-time monitoring and dynamic policy enforcement using data collected from the Access and Mobility Management Function (AMF) and User Plane Function (UPF). The testbed's effectiveness is demonstrated through the deployment of Nokia's network equipment, allowing the collection and analysis of high-resolution traffic data, which aids in early threat detection and response. The proposed system enhances 5G network security and offers significant potential for application across various industries.

关键词： 5G mobile communication Security management Architecture Network security Real-time systems Threat assessment Zero Trust Security Low latency communication Monitoring

来源：评论

学校读者我要写书评

暂无评论

Embedded propagation graph model for reflection and scattering and its millimeter-wave measurement-based evaluation

IEEE Open Journal of Antennas and Propagation

引用

IEEE Open Journal of Antennas and Propagation 2021年 2卷 191-202页

作者： Liu, Yuan Yin, Xuefeng Ye, Xiaokang He, Yongyu Lee, Juyul College of Electronics and Information Engineering Tongji University Shanghai China Guangdong Communications and Networks Institute Guangzhou China National Computer and Information Technology Practical Education Demonstration Center Tongji University Shanghai200092 China Telecommunication and Media Research Laboratory Electronics and Telecommunications Research Institute Daejeon34129 Korea Republic of

Propagation graph (PG) is a stochastic channel simulation method for scattering propagation. In this article, an embedded-PG (EPG) approach, an extension of conventional PG, is proposed to simulate reflection and scattering multi-path behaviors in wireless channels. In this method, multiple propagation paths are categorized into scattering-path, reflecting-path, and scattering-reflecting mixed paths among reflectors and scatterers. The matrix recursive formula of conventional PG modeling is used to calculate scattering-path, a recursive mathematical transformation is applied to adapt reflecting-path into the recursive formula, and an embedded graph method is used to decompose mixed-path into scattering effects and reflection effects. The proposed simulation approach is validated by comparison with conventional PG and measurement in 39 GHz millimeter-wave (mm-wave) time-variant corridor scenario. Power delay profiles (PDPs) and spatial consistency of multiple paths observed in concatenated-PDPs (CPDPs) obtained by EPG are more consistent with measurement than conventional PG, differences of mean delay and delay spread between simulations and measurement in typical snapshots are within 3 ns and 1.5 ns, respectively. © 2020 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Cyber Warfare Model with Intelligent Predictive Stochastic Networks for Attack-Defend Scenarios on Critical Infrastructures

SSRN

引用

SSRN 2023年

作者： Majeed, Khalid Masood, Zaheer Ghori, Muhammad Rizwan Raja, Muhammad Asif Zahoor Department of Electrical Engineering Capital University of Science and Technology Islamabad Pakistan School of Computer Sciences Universiti Sains Malaysia Penang11800 Malaysia Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan

World is occupied with spies, hackers, hidden digital weapon and in a virtual battlefield cyber warfare could turn every gadget into an armament. The purpose of this study is to develop a novel multi class differential system (Target network, Protected network, Inside attacker and Outside attacker) for cyber war model that imitate the cyber war scenarios on different attack surfaces in the presence of multifarious attack vectors and analysis is presented by stupendous knacks of intelligent predictive stochastic networks (IPSNs). Theoretical convergence analysis through attack free and attack invasion equilibrium in term of basic reproduction number R0 is presentedalong with the global stability of attack free equilibrium points using Lyapunov function. The reference solutions to study the dynamics of all four classes of cyber war model in air-gapped environment are also determined for sundry scenarios via variation in protection strategy parameter ρ, recovery strategy parameter Ε and rate of attack from an outside/inside attacker with implementation of Adams numerical method. The designed IPSNs is constructed by utilizing the multilayer feed-forward networks optimized with Levenberg-Marquardth method. The generated solution data is used in IPSNs as input/targets for train, validate and test samples to calculate the approximate predictive model for each class of nonlinear cyber war system. Exhaustive simulations are performed to determine the accuracy of the proposed model for a sophisticated advance persistent threats attacks, designed to target the critical industrial systems. The outcomes of IPSNs shows good close resemblance with the observed data, while analysis based on mean square error convergence, error histogram and regression index further verify the strength and worth of presented strategy. © 2023, The Authors. All rights reserved.

关键词： Critical infrastructures

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：