检索结果-南通市图书馆

Neural network modeling and prediction of HfO2 thin film properties tuned by thermal annealing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High Power Laser Science and Engineering 2024年第2期12卷 79-86页

作者： Min Gao Chaoyi yin Jianda Shao Meiping Zhu School of Microelectronics Shanghai UniversityShanghaiChina Laboratory of Thin Film Optics Key Laboratory of Materials for High Power LaserShanghai Institute of Optics and Fine MechanicsChinese Academy of SciencesShanghaiChina Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of SciencesBeijingChina Hangzhou Institute for Advanced Study University of Chinese Academy of SciencesHangzhouChina

Plasma-enhanced atomic layer deposition (PEALD) is gaining interest in thin films for laser applications, and post-annealing treatments are often used to improve thin film properties. However, research to improve thin film properties is often based on an expensive and time-consuming trial-and-error process. In this study, PEALD-HfO2 thin film samples were deposited and treated under different annealing atmospheres and temperatures. The samples were characterized in terms of their refractive indices, layer thicknesses and O/Hf ratios. The collected data were split into training and validation sets and fed to multiple back-propagation neural networks with different hidden layers to determine the best way to construct the process–performance relationship. The results showed that the three-hidden-layer back-propagation neural network (THL-BPNN) achieved stable and accurate fitting. For the refractive index, layer thickness and O/Hf ratio, the THL-BPNN model achieved accuracy values of 0.99, 0.94 and 0.94, respectively, on the training set and 0.99, 0.91 and 0.90, respectively, on the validation set. The THL-BPNN model was further used to predict the laser-induced damage threshold of PEALD-HfO2 thin films and the properties of the PEALD-SiO2 thin films, both showing high accuracy. This study not only provides quantitative guidance for the improvement of thin film properties but also proposes a general model that can be applied to predict the properties of different types of laser thin films, saving experimental costs for process optimization.

关键词： laser-induced damage threshold laser thin film neural network plasma-enhanced atomic layer deposition

A multiscale differential-algebraic neural network-based method for learning dynamical systems

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

International Journal of Mechanical System Dynamics 2024年第1期4卷 77-87页

作者： yin Huang Jieyu Ding College of Computer Science&Technology Qingdao UniversityQingdaoChina School of Mathematics and Statistics Qingdao UniversityQingdaoChina Center for Computational Mechanics and Engineering Simulation Qingdao UniversityQingdaoChina

The objective of dynamical system learning tasks is to forecast the future behavior of a system by leveraging observed ***,such systems can sometimes exhibit rigidity due to significant variations in component parameters or the presence of slow and fast variables,leading to challenges in *** overcome this limitation,we propose a multiscale differential-algebraic neural network(MDANN)method that utilizes Lagrangian mechanics and incorporates multiscale information for dynamical system *** MDANN method consists of two main components:the Lagrangian mechanics module and the multiscale *** Lagrangian mechanics module embeds the system in Cartesian coordinates,adopts a differential-algebraic equation format,and uses Lagrange multipliers to impose constraints explicitly,simplifying the learning *** multiscale module converts high-frequency components into low-frequency components using radial scaling to learn subprocesses with large differences in *** results demonstrate that the proposed MDANN method effectively improves the learning of dynamical systems under rigid conditions.

关键词： dynamical systems learning multibody system dynamics differential-algebraic equation neural networks multiscale structures

Dynamic Scene Graph Generation of Point Clouds with Structural Representation Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第1期29卷 232-243页

作者： Chao Qi Jianqin yin Zhicheng Zhang Jin Tang School of Artificial Intelligence Beijing University of Posts and TelecommunicationsBeijing 100876China Standard and Metrology Research Institute China Academy of Railway Sciences Corporation LimitedBeijing 100081China

Scene graphs of point clouds help to understand object-level relationships in the 3D *** graph generation methods work on 2D structured data,which cannot be used for the 3D unstructured point cloud *** point-cloud-based methods generate the scene graph with an additional graph structure that needs labor-intensive manual *** address these problems,we explore a method to convert the point clouds into structured data and generate graphs without given ***,we cluster points with similar augmented features into groups and establish their relationships,resulting in an initial structural representation of the point ***,we propose a Dynamic Graph Generation Network(DGGN)to judge the semantic labels of targets of different *** dynamically splits and merges point groups,resulting in a scene graph with high *** show that our methods outperform other baseline *** output reliable graphs describing the object-level relationships without additional manual labeled data.

关键词： scene graph generation structural representation point cloud

Soluble ST2:A Novel Biomarker for Diagnosis and Prognosis of Cardiovascular Disease

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

当代医学科学（英文） 2024年第4期44卷 669-679页

作者： yin FENG Li-qun HE Department of Cardiology Traditional Chinese and Western Medicine Hospital of WuhanTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430030China

The increasing incidence of cardiovascular disease(CVD)is a significant global health concern,affecting millions of individuals each *** diagnosis of acute CVD poses a formidable challenge,as misdiagnosis can significantly decrease patient survival *** biomarkers have played a vital role in the diagnosis and prognosis of CVDs,but they can be influenced by various factors,such as age,sex,and renal *** ST2(sST2)is a novel biomarker that is closely associated with different *** low reference change value makes it suitable for continuous measurement,unaffected by age,kidney function,and other confounding factors,facilitating risk stratification of ***,the combination of sST2 with other biomarkers can enhance diagnostic accuracy and prognostic *** review aims to provide a comprehensive overview of sST2,focusing on its diagnostic and prognostic value as a myocardial marker for different types of CVDs and discussing the current limitations of sST2.

关键词： cardiovascular disease combined biomarker diagnosis and prognosis limitations soluble ST2

High-performance grinding of ceramic matrix composites

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nanotechnology and Precision Engineering 2024年第3期7卷 45-55页

作者： Jingfei yin Jiuhua Xu Honghua Su College of Mechanical and Electrical Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China Department of Technology Center AECC Shenyang Liming Aero-engine Co.Ltd.Shenyang 110043China

Ceramic matrix composites(CMCs)are highly promising materials for the next generation of ***,machining of CMCs suffers from low efﬁciency and poor surfaceﬁnish,which presents an obstacle to their wider *** overcome these problems,this study investigates high-efﬁciency deep grinding of CMCs,focusing on the effects of grinding *** results show that both the sur-face roughness and the depth of subsurface damage(SSD)are insensitive to grinding *** material removal rate can be increased sixfold by increasing the grinding depth,while the surface roughness and SSD depth increase by only about 10%.Moreover,it is found that the behavior of material removal is strongly dependent on grinding *** the grinding depth is increased,ﬁbers are removed in smaller sizes,with theﬁber length in chips being reduced by about 34%.However,too large a grinding depth will result in blockage by chip powder,which leads to a dramatic increase in the ratio of tangential to normal grinding *** study demonstrates that increasing the depth of cut is an effective approach to improve the machining efﬁciency of CMCs,while maintaining a good surfaceﬁ*** provides the basis for the further development of high-performance grinding methods for CMCs,which should facilitate their wider application.

关键词： Ceramic matrix composite Grinding Surfaceﬁnish Subsurface damage Fiber breakage

Learning to optimize:A tutorial for continuous and mixed-integer optimization

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Science China Mathematics 2024年第6期67卷 1191-1262页

作者： Xiaohan Chen Jialin Liu Wotao yin Decision Intelligence Lab Alibaba DAMO AcademyBellevueWA98004USA

Learning to optimize(L2O)stands at the intersection of traditional optimization and machine learning,utilizing the capabilities of machine learning to enhance conventional optimization *** real-world optimization problems frequently share common structures,L2O provides a tool to exploit these structures for better or faster *** tutorial dives deep into L2O techniques,introducing how to accelerate optimization algorithms,promptly estimate the solutions,or even reshape the optimization problem itself,making it more adaptive to real-world *** considering the prerequisites for successful applications of L2O and the structure of the optimization problems at hand,this tutorial provides a comprehensive guide for practitioners and researchers alike.

关键词： AI for mathematics(AI4Math) learning to optimize algorithm unrolling plug-and-play methods differentiable programming machine learning for combinatorial optimization(ML4CO)

Low-Brightness Object Recognition Based on Deep Learning

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第5期79卷 1757-1773页

作者： Shu-yin Chiang Ting-Yu Lin Department of Information and Telecommunications Engineering Ming Chuan UniversityTaoyuan City333Taiwan

This research focuses on addressing the challenges associated with image detection in low-light environments,particularly by applying artificial intelligence techniques to machine vision and object recognition *** primary goal is to tackle issues related to recognizing objects with low brightness *** this study,the Intel RealSense Lidar Camera L515 is used to simultaneously capture color information and 16-bit depth information *** detection scenarios are categorized into normal brightness and low brightness *** the system determines a normal brightness environment,normal brightness images are recognized using deep learning *** low-brightness situations,three methods are proposed for *** first method is the SegmentationwithDepth image(SD)methodwhich involves segmenting the depth image,creating amask from the segmented depth image,mapping the obtained mask onto the true color(RGB)image to obtain a backgroundreduced RGB image,and recognizing the segmented *** second method is theHDVmethod(hue,depth,value)which combines RGB images converted to HSV images(hue,saturation,value)with depth images D to form HDV images for *** third method is the HSD(hue,saturation,depth)method which similarly combines RGB images converted to HSV images with depth images D to form HSD images for *** experimental results,in normal brightness environments,the average recognition rate obtained using image recognition methods is 91%.For low-brightness environments,using the SD method with original images for training and segmented images for recognition achieves an average recognition rate of over 82%.TheHDVmethod achieves an average recognition rate of over 70%,while the HSD method achieves an average recognition rate of over 84%.The HSD method allows for a quick and convenient low-light object recognition *** research outcome can be applied to nighttime surveillance systems or nighttime road safety systems

关键词： Low-brightness depth image image segmentation image recognition HDV HSD

Alternative Method of Constructing Granular Neural Networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 623-650页

作者： Yushan yin Witold Pedrycz Zhiwu Li School of Electro-Mechanical Engineering Xidian UniversityXi’an710071China Department of Electrical and Computer Engineering University of AlbertaEdmontonABT6R 2V4Canada

Utilizing granular computing to enhance artificial neural network architecture, a newtype of network emerges—thegranular neural network (GNN). GNNs offer distinct advantages over their traditional counterparts: The ability toprocess both numerical and granular data, leading to improved interpretability. This paper proposes a novel designmethod for constructing GNNs, drawing inspiration from existing interval-valued neural networks built uponNNNs. However, unlike the proposed algorithm in this work, which employs interval values or triangular fuzzynumbers for connections, existing methods rely on a pre-defined numerical network. This new method utilizesa uniform distribution of information granularity to granulate connections with unknown parameters, resultingin independent GNN structures. To quantify the granularity output of the network, the product of two commonperformance indices is adopted: The coverage of numerical data and the specificity of information *** this combined performance index helps determine the optimal parameters for the network. Finally,the paper presents the complete model construction and validates its feasibility through experiments on datasetsfrom the UCIMachine Learning Repository. The results demonstrate the proposed algorithm’s effectiveness andpromising performance.

关键词： Granular neural network granular connection interval analysis triangular fuzzy numbers particle swarm optimization(PSO)

VKFQ:A Verifiable Keyword Frequency Query Framework with Local Differential Privacy in Blockchain

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第3期78卷 4205-4223页

作者： Youlin Ji Bo yin Ke Gu School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China

With its untameable and traceable properties,blockchain technology has been widely used in the field of data *** to preserve individual privacy while enabling efficient data queries is one of the primary issues with secure data *** this paper,we study verifiable keyword frequency(KF)queries with local differential privacy in *** the numerical and the keyword attributes are present in data objects;the latter are sensitive and require privacy ***,prior studies in blockchain have the problem of trilemma in privacy protection and are unable to handle KF *** propose an efficient framework that protects data owners’privacy on keyword attributes while enabling quick and verifiable query processing for KF *** framework computes an estimate of a keyword’s frequency and is efficient in query time and verification object(VO)size.A utility-optimized local differential privacy technique is used for privacy *** data owner adds noise locally into data based on local differential privacy so that the attacker cannot infer the owner of the keywords while keeping the difference in the probability distribution of the KF within the privacy *** propose the VB-cm tree as the authenticated data structure(ADS).The VB-cm tree combines the Verkle tree and the Count-Min sketch(CM-sketch)to lower the VO size and query *** VB-cm tree uses the vector commitment to verify the query *** fixed-size CM-sketch,which summarizes the frequency of multiple keywords,is used to estimate the KF via hashing *** conduct an extensive evaluation of the proposed *** experimental results show that compared to theMerkle B+tree,the query time is reduced by 52.38%,and the VO size is reduced by more than one order of magnitude.

关键词： Security data sharing blockchain data query privacy protection