检索结果-南通市图书馆

Detection and Recognition of Spray Code Numbers on Can Surfaces Based on OCR

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 1109-1128页

作者： Hailong wang Junchao Shi School of Computer Science Zhongyuan University of TechnologyZhengzhou450007China

A two-stage algorithm based on deep learning for the detection and recognition of can bottom spray codes and numbers is proposed to address the problems of small character areas and fast production line speeds in can bottom spray code number *** the coding number detection stage,Differentiable Binarization Network is used as the backbone network,combined with the Attention and Dilation Convolutions Path Aggregation Network feature fusion structure to enhance the model detection *** terms of text recognition,using the Scene Visual Text Recognition coding number recognition network for end-to-end training can alleviate the problem of coding recognition errors caused by image color distortion due to variations in lighting and background *** addition,model pruning and quantization are used to reduce the number ofmodel parameters to meet deployment requirements in resource-constrained environments.A comparative experiment was conducted using the dataset of tank bottom spray code numbers collected on-site,and a transfer experiment was conducted using the dataset of packaging box production *** experimental results show that the algorithm proposed in this study can effectively locate the coding of cans at different positions on the roller conveyor,and can accurately identify the coding numbers at high production line *** Hmean value of the coding number detection is 97.32%,and the accuracy of the coding number recognition is 98.21%.This verifies that the algorithm proposed in this paper has high accuracy in coding number detection and recognition.

关键词： Can coding recognition differentiable binarization network scene visual text recognition model pruning and quantification transport model

Model-based robustness testing for avionics-embedded software

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2013年第3期26卷 730-740页

作者： Yang Shunkun Liu Bin wang Shihai Lu minyan School of Reliability and Systems Engineering Beihang University Science & Technology on Reliability & Environmental Engineering Laboratory

Robustness testing for safety-critical embedded software is still a challenge in its nascent stages. In this paper, we propose a practical methodology and implement an environment by employing model-based robustness testing for embedded software systems. It is a system-level black-box testing approach in which the fault behaviors of embedded software is triggered with the aid of modelbased fault injection by the support of an executable model-driven hardware-in-loop （HIL） testing environment. The prototype implementation of the robustness testing environment based on the proposed approach is experimentally discussed and illustrated by industrial case studies based on several avionics-embedded software systems. The results show that our proposed and implemented robustness testing method and environment are effective to find more bugs, and reduce burdens of testing engineers to enhance efficiency of testing tasks, especially for testing complex embedded systems.

关键词： Embedded software Hardware-in-loop Model-based testing Robustness testing Testing environment

Near-perfect replication on amorphous alloys through active force modulation based on machine learning/neural network parameter prediction

在线全文

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2025年第1期Mechanics & Astronomy) .卷 181-191页

作者： Senkuan Meng Zheng wang Ruisong Zhu Ruijie Liu Jiang Ma Lina Hu Weihua wang Key Laboratory for Liquid-Solid Structural Evolution and Processing of Materials (Ministry of Education) School of Materials Science and Engineering Shandong University College of Mechatronics and Control Engineering Shenzhen University Songshan Lake Materials Laboratory Institute of Physics Chinese Academy of Sciences

As a microforming technique, micro/nano-structural replication possesses advantages of high precision and efficiency. With the remarkable superplasticity in the supercooled liquid region, amorphous alloys or metallic glasses(MGs) are regarded as ideal materials for miniature fabrication. However, due to the intrinsic metastable nature of supercooled liquids, the design of imprinting processes for MGs poses a challenge. In the past, process parameters have largely relied on trial-and-error *** this work, a low-frequency active force modulation system is employed to apply a stable, precise, and real-time feedback stress field for imprinting of MG samples. Low-frequency vibrations can facilitate the filling of microstructures on the template surface by reducing the effective viscosity of the supercooled liquid. With the dataset composed of orthogonal experiments, a machine learning strategy based on back-propagation(BP) neural networks was utilized to construct a 3D parameter space for temperature, stress, and time, and to predict the corresponding filling ratio. Furthermore, the optimal combination of imprinting process parameters was identified, and its filling ratio was experimentally validated to reach as high as 0.94. The near-perfect replication of microstructures confirms the superiority of the active force modulation system and the data-driven strategy of machine learning-assisted parameter design. At the same time, this one-step microforming process provides a new approach to addressing the accuracy-cost trade-off dilemma in precision manufacturing.

关键词： metallic glass amorphous alloy microforming imprinting machine learning

Local-contrastive-learning machine with both generalization and adversarial robustness: A statistical physics analysis

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2025年第1期Mechanics & Astronomy) .卷 109-123页

作者： Mingshan Xie Yuchen wang Haiping Huang PMI Lab School of Physics Sun Yat-sen University Guangdong Provincial Key Laboratory of Magnetoelectric Physics and Devices Sun Yat-sen University

Distinct from human cognitive processing, deep neural networks trained by backpropagation can be easily fooled by adversarial examples. To design a semantically meaningful representation learning, we discard backpropagation, and instead, propose a local contrastive learning, where the representations for the inputs bearing the same label shrink(akin to boson) in hidden layers,while those of different labels repel(akin to fermion). This layer-wise learning is local in nature, being biologically plausible.A statistical mechanics analysis shows that the target fermion-pair-distance is a key parameter. Moreover, the application of this local contrastive learning to MNIST benchmark dataset demonstrates that the adversarial vulnerability of standard perceptron can be greatly mitigated by tuning the target distance, i.e., controlling the geometric separation of prototype manifolds.

关键词： machine learning statistical mechanics adversarial robustness neural networks

高管变更与公司绩效的关系——对股权分置前国有上市公司的实证分析

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

河北经贸大学学报（综合版） 2011年第2期11卷 52-54页

作者：李芳付建全孙红梅王敏彦河北医科大学基础医学院河北石家庄050017 石家庄职业技术学院经济贸易系河北石家庄050081

股权分置改革是解决中国股市非流通股流通问题的一项重要制度改革,为中国内地资本市场所特有。股权分置改革之前,在一股独大的国有企业中,高管变更概率与公司绩效显著负相关;在非一股独大的国有企业中,高管变更概率与公司绩效显著正相关。

关键词：股权分置改革高管变更公司绩效股权结构

Flexible Graphene Field‑Effect Transistors and Their Application in Flexible Biomedical Sensing

在线全文

学校读者我要写书评

暂无评论

Nano-Micro Letters 2025年第2期17卷 252-313页

作者： Mingyuan Sun Shuai wang Yanbo Liang Chao wang Yunhong Zhang Hong Liu Yu Zhang Lin Han Institute of Marine Science and Technology Shandong UniversityQingdao 266237ShandongPeople’s Republic of China State Key Laboratory of Crystal Materials Shandong UniversityJinan 250100ShandongPeople’s Republic of China School of Integrated Circuits Shandong UniversityJinan 250100ShandongPeople’s Republic of China Shandong Engineering Research Center of Biomarker and Artificial Intelligence Application Jinan250100ShandongPeople’s Republic of China

Flexible electronics are transforming our lives by making daily activities more *** to this innovation are field-effect transistors(FETs),valued for their efficient signal processing,nanoscale fabrication,low-power consumption,fast response times,and ***,known for its exceptional mechanical properties,high electron mobility,and biocompatibility,is an ideal material for FET channels and *** combination of graphene and FETs has given rise to flexible graphene field-effect transistors(FGFETs),driving significant advances in flexible electronics and sparked a strong interest in flexible biomedical ***,we first provide a brief overview of the basic structure,operating mechanism,and evaluation parameters of FGFETs,and delve into their material selection and patterning *** ability of FGFETs to sense strains and biomolecular charges opens up diverse application *** specifically analyze the latest strategies for integrating FGFETs into wearable and implantable flexible biomedical sensors,focusing on the key aspects of constructing high-quality flexible biomedical ***,we discuss the current challenges and prospects of FGFETs and their applications in biomedical *** review will provide valuable insights and inspiration for ongoing research to improve the quality of FGFETs and broaden their application prospects in flexible biomedical sensing.

关键词： Flexible Graphene Field-effect transistor Wearable Implantable Biosensor

MixerKT:A Knowledge Tracing Model Based on Pure MLP Architecture

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 485-498页

作者： Jun wang Mingjie wang Zijie Li Ken Chen Jiatian Mei Shu Zhang Key Laboratory of Education Informatization for Nationalities Ministry of EducationYunnan Normal UniversityKunming650000China Yunnan Key Laboratory of Smart Education Yunnan Normal UniversityKunming650000China

In the field of intelligent education,the integration of artificial intelligence,especially deep learning technologies,has garnered significant *** tracing(KT)plays a pivotal role in this field by predicting students’future performance through the analysis of historical interaction data,thereby assisting educators in evaluating knowledgemastery and tailoring instructional *** knowledge tracingmethods,largely based on Recurrent Neural Networks(RNNs)and Transformer models,primarily focus on capturing long-term interaction patterns in sequential ***,these models may neglect crucial short-term dynamics and other relevant *** paper introduces a novel approach to knowledge tracing by leveraging a pure Multilayer Perceptron(MLP)*** proposeMixerKT,a knowledge tracing model based on theHyperMixer framework,which uniquely integrates global and localMixer feature *** architecture enables more effective extraction of both long-terminteraction trends and recent learning behaviors,addressing limitations in currentmodels thatmay overlook these key *** evaluations on twowidely-used datasets,ASSIS Tments2009 and Algebra2005,demonstrate that MixerKT consistently outperforms several state-of-the-art models,including DKT,SAKT,and Separated Self-Attentive Neural Knowledge Tracing(SAINT).Specifically,MixerKT achieves higher prediction accuracy,highlighting its effectiveness in capturing the nuances of learners’knowledge *** results indicate that our model provides a more comprehensive representation of student learning patterns,enhancing the ability to predict future performance with greater precision.

关键词： Knowledge tracing multilayer perceptron channel mixer sequence mixer

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

基于杭州湾区城市群开放度的实测研究

上海城市管理 2020年第5期29卷 36-44页

作者：石坚韧汪妍吕庆文赵秀敏浙江工商大学旅游与城乡规划学院舟山市城市规划设计研究院浙江工商大学艺术设计学院

利用主成分分析法,结合世界三大湾区发展经验和我国目前湾区经济开放格局发展的现状以及优劣势,在现有的经济开放度测算模型和粤港澳大湾区的经济开放度定量研究的基础上,构建环杭州湾区城市群对外开放度定量测算模型,对环杭州湾区城市... 详细信息

利用主成分分析法,结合世界三大湾区发展经验和我国目前湾区经济开放格局发展的现状以及优劣势,在现有的经济开放度测算模型和粤港澳大湾区的经济开放度定量研究的基础上,构建环杭州湾区城市群对外开放度定量测算模型,对环杭州湾区城市群内各城市和总体开放度进行测算比较。测算结果表明,贸易开放度对经济开放度的影响最大,环杭州湾区中,上海、宁波、舟山处于开放度高位,它的开放度发展拥有巨大潜力,但目前其发展还只是处于起步阶段。

关键词：湾区经济开放度环杭州湾区城市群

High-energy-density lithium manganese iron phosphate for lithium-ion batteries: Progresses, challenges, and prospects

在线全文

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2025年第1期100卷 1-17页

作者： Bokun Zhang Xiaoyun wang Shuai wang Yan Li Libo Chen Handong Jiao Zhijing Yu Jiguo Tu State Key Laboratory of Advanced Metallurgy University of Science and Technology Beijing Research Institute for Intelligent Wearable Systems The Hong Kong Polytechnic University Institute of Advanced Structure Technology Beijing Institute of Technology

The soaring demand for smart portable electronics and electric vehicles is propelling the advancements in high-energy–density lithium-ion *** manganese iron phosphate (LiMnxFe1-xPO4) has garnered significant attention as a promising positive electrode material for lithium-ion batteries due to its advantages of low cost,high safety,long cycle life,high voltage,good high-temperature performance,and high energy *** LiMnxFe1-xPO4has made significant breakthroughs in the past few decades,there are still facing great challenges in poor electronic conductivity and Li-ion diffusion,manganese dissolution affecting battery cycling performance,as well as low tap *** review systematically summarizes the reaction mechanisms,various synthesis methods,and electrochemical properties of LiMnxFe1-xPO4to analyze reaction processes accurately and guide material ***,the main challenges currently faced are concluded,and the corresponding various modification strategies are discussed to enhance the reaction kinetics and electrochemical performance of LiMnxFe1-xPO4,including multi-scale particle regulation,heteroatom doping,surface coating,as well as microscopic morphology ***,in view of the current research challenges faced by intrinsic reaction processes,kinetics,and energy storage applications,the promising research directions are *** importantly,it is expected to provide key insights into the development of high-performance and stable LiMnxFe1-xPO4materials,to achieve practical energy storage requirements.

关键词： Semiconductor doping