检索结果-内蒙古大学图书馆

16th International Conference on computer Modeling and Simulation, ICCMS 2024

作者： Pi, Xiaoning Xie, Yulai Zhang, Yang Wang, Xiaohui Ren, Fang School of Computer and Communication Engineering University of Science and Technology Beijing China Hitachi China Research Laboratory China

ISBN: (纸本)9798400717215

In industrial production, visual defect inspection is crucial for ensuring product quality. However, due to difficulties in sample collection during defect inspection, there is often a scarcity of diverse defective samples, leading most data generation methods to fail in generating high-diversity data. Therefore, this paper proposes the Automatic Iterative Diversity Improvement training strategy to improve the diversity of generated data with only a few training samples, which can improve the performance and generalization of downstream tasks. During the training process, given the characteristics of visual defects, we design the Defect Diversity-based Picking and Evaluation to pick up diverse samples and assess the diversity regarding defect location and shape. Experiments show that the method can generate high-diversity defect samples with high quality for industrial defect scenarios even in zero-shot learning tasks. The effectiveness of the generated data is also verified by the down-streaming defect detection task. © 2024 Copyright held by the owner/author(s).

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Energy Oriented Three-Tier Computation Offloading Scheme in Maritime Edge Computing Network

引用

IEEE Transactions on Vehicular technology 2025年第5期74卷 8126-8140页

作者： Zhang, Hongxia Xi, Shiyu Shang, Bodong Zhang, Peiying Wu, Sheng Jiang, Chunxiao Qingdao Institute of Software College of Computer Science and Technology Qingdao266580 China Eastern Institute of Technology Eastern Institute for Advanced Study Ningbo315200 China Beijing University of Posts and Telecommunications School of Information and Communication Engineering Beijing100876 China Tsinghua University Beijing National Research Center for Information Science and Technology Beijing100084 China

With the development of maritime continuing to grow, large-scale maritime wireless devices (MWDs) are being deployed for various maritime applications. The rapid development of maritime Internet of Things (IoT) and growing demand for these applications have led to an increasing number of computation-intensive and resource-sensitive tasks. Considering the limited computing capacity and energy of MWDs, it is challenging to transmit and process massive maritime computing tasks in an energy efficient manner. In this paper, we propose a three-tier maritime edge computing system in which low earth orbit (LEO) satellite and offshore base station (OBS) support to provide communication and computing services for MWDs. The system optimizes association variable, task partitioning, transmission power, and computing resource allocation to reduce system energy consumption under latency constraints. The optimization problem is formulated as a mixed integer non-linear programming (MINLP) optimization problem. We decompose the original problem into four subproblems and design algorithms to solve them. Firstly, the association variable optimization subproblem is solved by slack variable method. Then, we adopt quadratic transformation and design a difference of convex algorithm to solve transmission power optimization subproblem. Further, task partitioning subproblem is solved by obtaining upper and lower bounds of offloading task size by strict deduction, and then solved by the standard convex method. Finally, Lagrangian dual method is utilized to deal with joint computing resource optimization subproblem of LEO satellite and OBS. In simulation results, the proposed algorithm saves 39.3% of system energy consumption compared to benchmark schemes. © 1967-2012 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Learning a Provably Good Wirelength Model for Analytical Placement

Learning a Provably Good Wirelength Model for Analytical Pla...

引用

2023 International Symposium of Electronics Design Automation, ISEDA 2023

作者： Chen, Zhiyang Yao, Hailong Yin, Xia Tsinghua University Department of Computer Science and Technology China School of Computer and Communication Engineering University of Science and Technology Beijing China

ISBN: (纸本)9798350304510

Placement is one of the most critical design stages for very large-scale integrated (VLSI) circuits. Modern VLSI placers usually adopt the analytical placement framework, which formulates placement into a non-linear optimization problem. A key ingredient of analytical placers is the wirelength model. Previous works propose various models to approximate the half-perimeter wirelength (HPWL). However, these models rely on human experiences and may not be fully optimized on realworld designs. In this work, we propose a novel data-driven parameterized wirelength model, which learns the best configuration from placement instances in the training set via Bayesian optimization. Our model is effective and efficient, together with a provable upper bound of the generalization gap. Therefore, the model can generalize to testing data that is unseen during training. Experiments show that our model improves HPWL on average by 1.9% compared with the classic weighted average model on ISPD-2005 benchmarks using DREAMPlace. © 2023 IEEE.

关键词： Nonlinear programming

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of temporal-spatial and time-frequency features for pattern recognition of φ-OTDR

引用

Chinese Optics Letters 2023年第4期21卷 1-8页

作者：孟凡然张文祥刘晓军刘飞周娴 School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China

The phase-sensitive time-domain reflectometer [φ-OTDR] has been popularly used for events detection over a long period of *** this study,the events classification methods based on convolutional neural networks [CNNs] with different features,i.e.,the temporal-spatial features and time-frequency features,are compared and analyzed comprehensively inφ-*** developed CNNs aim at distinguishing three typical events:wind blowing,knocking,and background *** classification accuracy based on temporal-spatial images is higher than that based on time-frequency images[99.49% versus 98.23%).The work here sets a meaningful reference for feature extraction and application in the pattern recognition of φ-OTDR.

关键词： phase-sensitive time-domain reflectometer convolutional neural network temporal-spatial images timefrequency images

来源：评论

学校读者我要写书评

暂无评论

Exploring Dynamics and Hardware Implementation of an Enhanced 5D Hyperchaotic Memristive System Inspired by Sprott-C System

引用

Complex System Modeling and Simulation 2025年第1期5卷 34-45页

作者： Abdulmajeed Abdullah Mohammed Mokbel Fei Yu Yumba Musoya Gracia Bohong Tan Hairong Lin Herbert Ho-Ching Iu School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha 410114China School of Electronic Information Central South UniversityChangsha 410083China School of Electrical Electronic and Computer EngineeringUniversity of Western AustraliaPerth 6009Australia

This paper proposes a novel 5D hyperchaotic memristive system based on the Sprott-C system configuration,which greatly improves the complexity of the system to be used for secure communication and signal processing.A critical aspect of this research work is the introduction of a flux-controlled memristor that exhibits chaotic behavior and dynamic responses of the *** this respect,detailed mathematical modeling and numerical simulations about the stability of the system’s equilibria,bifurcations,and hyperchaotic dynamics were conducted and showed a very wide variety of behaviors of great potential in cryptographic applications and secure data ***,the flexibility and efficiency of the real-time operating environment were demonstrated,and the system was actually implemented on a field-programmable gate array(FPGA)hardware platform.A prototype that confirms the theoretical framework was presented,providing new insights for chaotic systems with practical ***,we conducted National Institute of Standards and technology(NIST)testing on the proposed 5D hyperchaotic memristive system,and the results showed that the system has good randomness.

关键词： Sprott-C system field-programmable gate array(FPGA)implementation hyperchaotic system memristor numerical simulation

来源：评论

学校读者我要写书评

暂无评论

Correction‐enabled reversible data hiding with pixel repetition for high embedding rate and quality preservation

引用

IET Cyber-Systems and Robotics 2024年第3期6卷 49-61页

作者： Mohammad Ali Kawser Hussain Nyeem Md Abdul Wahed School of Transportation Science and Engineering Beihang UniversityBeijingChina Department of Electrical Electronic and Communication Engineering(EECE)Military Institute of Science and Technology(MIST)DhakaBangladesh

A novel correction‐enabled Pixel Repetition(PR)‐based Reversible Data Hiding(RDH)framework,featuring a new embedding scheme is *** proposed RDH scheme uses contextually redundant block pixels,generated via PR,in a two‐phase adaptive embedding process,enhancing both image quality and data embedding ***,each 2×2 block encodes 4 bits of data using new mapping conditions that facilitate seed pixel reconstruction from remaining block pixels and provide additional embedding ***,an innovative post‐embedding error correction technique,based on 2^(k)‐bit error‐correction,minimises post‐embedding distortion,further improving image *** error correction approach augments data embedding robustness,vital for applications like medical imaging,telemedicine,and digital watermarking that requires high embedding capacity with minimum possible *** proposed scheme surpasses existing state‐of‐the‐art methods in embedding ratedistortion performance,validated through subjective and objective ***,statistical analysis,including histogram and fragility testing,confirms the scheme's potential for image authentication across diverse multimedia *** correctionenabled RDH with PR offers enhanced embedding capacity and image quality preservation,making it particularly advantageous for applications requiring robust data hiding while maintaining visual fidelity.

关键词： data assimilation vision

来源：评论

学校读者我要写书评

暂无评论

Skinned Motion Retargeting with Preservation of Body Part Relationships

引用

IEEE Transactions on Visualization and computer Graphics 2024年 PP卷 1-13页

作者： Zhang, Jia-Qi Wang, Miao Zhang, Fu-Cheng Zhang, Fang-Lue State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China School of Engineering and Computer Science Victoria University of Wellington New Zealand

Motion retargeting is an active research area in computer graphics and animation, allowing for the transfer of motion from one character to another, thereby creating diverse animated character data. While this technology has numerous applications in animation, games, and movies, current methods often produce unnatural or semantically inconsistent motion when applied to characters with different shapes or joint counts. This is primarily due to a lack of consideration for the geometric and spatial relationships between the body parts of the source and target characters. To tackle this challenge, we introduce a novel spatially-preserving Skinned Motion Retargeting Network (SMRNet) capable of handling motion retargeting for characters with varying shapes and skeletal structures while maintaining semantic consistency. By learning a hybrid representation of the character's skeleton and shape in a rest pose, SMRNet transfers the rotation and root joint position of the source character's motion to the target character through embedded rest pose feature alignment. Additionally, it incorporates a differentiable loss function to further preserve the spatial consistency of body parts between the source and target. Comprehensive quantitative and qualitative evaluations demonstrate the superiority of our approach over existing alternatives, particularly in preserving spatial relationships more effectively IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Monocular Stereo Learning Based on Hybrid Attention Transformer 2nd

Monocular Stereo Learning Based on Hybrid Attention Transfor...

引用

2nd World Conference on Intelligent and 3D Technologies, WCI3DT 2023

作者： Yang, Jie Chen, Shicong Vu, Vantoi Zheng, Pengfei College of Information and Communication Engineering Harbin Engineering University Harbin China College of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (纸本)9789819970100

Monocular stereo matching estimation network is an important research direction in the field of artificial intelligence. In this paper, a monocular stereo learning network based on Hybrid Attention Transformer for joint estimation of optical flow and depth for monocular sequences is proposed. Firstly, spatial window and channel group attention are used to enhance the ability of the network to extract local and global features, optimizing the learning framework. Secondly, cross attention is used to realize the cross-window connection, which makes the details of image estimation more rich. Finally, we discuss the effect of the two different connection modes of attention in series and parallel on the network estimation tasks. Our experiment results on KITTI datasets show that, compared with the previous methods, our multi-task learning framework has more significant improvements in optical flow and depth. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Enhancement of charging performance of quantum battery via quantum coherence of bath

引用

Chinese Physics B 2023年第1期32卷 161-171页

作者：于文莉张允李海魏广芬韩丽萍田峰邹建 School of Computer Science and Technology Shandong Technology and Business UniversityYantai 264005China School of Information and Electronic Engineering Shandong Technology and Business UniversityYantai 264005China School of Science Tianjin University of TechnologyTianjin 300384China School of Physics Beijing Institute of TechnologyBeijing 100081China

An open quantum battery(QB)model of a single qubit system charging in a coherent auxiliary bath(CAB)consisting of a series of independent coherent ancillae is *** to the collision charging protocol we derive a quantum master equation and obtain the analytical solution of QB in a steady *** find that the full charging capacity(or the maximal extractable work(MEW))of QB,in the weak QB-ancilla coupling limit,is positively correlated with the coherence magnitude of *** with the numerical simulations we compare with the charging properties of QB at finite coupling strength,such as the MEW,average charging power and the charging efficiency,when considering the bath to be a thermal auxiliary bath(TAB)and a CAB,*** find that when the QB with CAB,in the weak coupling regime,is in fully charging,both its capacity and charging efficiency can go beyond its classical counterpart,and they increase with the increase of coherence magnitude of *** addition,the MEW of QB in the regime of relative strong coupling and strong coherent magnitude shows the oscillatory behavior with the charging time increasing,and the first peak value can even be larger than the full charging MEW of *** also leads to a much larger average charging power than that of QB with TAB in a short-time charging *** features suggest that with the help of quantum coherence of CAB it becomes feasible to switch the charging schemes between the long-time slow charging protocol with large capacity and high efficiency and the short-time rapid charging protocol with highly charging power only by adjusting the coupling strength of *** work clearly demonstrates that the quantum coherence of bath can not only serve as the role of“fuel”of QB to be utilized to improve the QB's charging performance but also provide an alternative way to integrate the different charging protocols into a single QB.

关键词： quantum battery quantum coherence maximal extractable work charging power

来源：评论

学校读者我要写书评

暂无评论

Reliability Analysis of Correlated Competitive and Dependent Components Considering Random Isolation Times

引用

computers, Materials & Continua 2023年第9期76卷 2763-2777页

作者： Shuo Cai Tingyu Luo Fei Yu Pradip Kumar Sharma Weizheng Wang Lairong Yin School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China Department of Computing Science University of AberdeenAberdeenUK School of Automotive and Mechanical Engineering Changsha University of Science and TechnologyChangsha410114China

In the Internet of Things(IoT)system,relay communication is widely used to solve the problem of energy loss in long-distance transmission and improve transmission *** Body Sensor Network(BSN)systems,biosensors communicate with receiving devices through relay nodes to improve their limited energy *** the relay node fails,the biosensor can communicate directly with the receiving device by releasing more transmitting ***,if the remaining battery power of the biosensor is insufficient to enable it to communicate directly with the receiving device,the biosensor will be isolated by the ***,a new combinatorial analysis method is proposed to analyze the influence of random isolation time(RIT)on system reliability,and the competition relationship between biosensor isolation and propagation failure is *** approach inherits the advantages of common combinatorial algorithms and provides a new approach to effectively address the impact of RIT on system reliability in IoT systems,which are affected by competing ***,the method is applied to the BSN system,and the effect of RIT on the system reliability is analyzed in detail.

关键词： BSN Internet of Things reliability analysis random isolation time

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：