检索结果-南通市图书馆

learning feature alignment and dual correlation for few‐shot image classification

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第2期9卷 303-318页

作者： Xilang Huang Seon han Choi Department of Electronic and Electrical Engineering Ewha Womans UniversitySeoulSouth Korea Graduate Program in Smart Factory Ewha Womans UniversitySeoulSouth Korea

Few‐shot image classification is the task of classifying novel classes using extremely limited labelled *** perform classification using the limited samples,one solution is to learn the feature alignment(FA)information between the labelled and unlabelled sample *** FA methods use the feature mean as the class prototype and calculate the correlation between prototype and unlabelled features to learn an alignment ***,mean prototypes tend to degenerate informative features because spatial features at the same position may not be equally important for the final classification,leading to inaccurate correlation ***,the authors propose an effective intraclass FA strategy that aggregates semantically similar spatial features from an adaptive reference prototype in low‐dimensional feature space to obtain an informative prototype feature map for precise correlation ***,a dual correlation module to learn the hard and soft correlations was developed by the *** module combines the correlation information between the prototype and unlabelled features in both the original and learnable feature spaces,aiming to produce a comprehensive cross‐correlation between the prototypes and unlabelled *** both FA and cross‐attention modules,our model can maintain informative class features and capture important shared features for *** results on three few‐shot classification benchmarks show that the proposed method outperformed related methods and resulted in a 3%performance boost in the 1‐shot setting by inserting the proposed module into the related methods.

关键词： image classification machine learning metric learning

Reactor field reconstruction from sparse and movable sensors using Voronoi tessellation-assisted convolutional 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

Nuclear Science and Techniques 2024年第5期35卷 173-185页

作者： He-Lin Gong han Li Dunhui Xiao Sibo Cheng Paris Elite Institute of Technology Shanghai Jiao Tong UniversityShanghai 200240China School of Mathematical Sciences Tongji UniversityShanghai 200092China Department of Computing Data Science InstituteImperial College LondonLondon SW72AZUK

The aging of operational reactors leads to increased mechanical vibrations in the reactor *** vibration of the incore sensors near their nominal locations is a new problem for neutronic field *** field-reconstruction methods fail to handle spatially moving *** this study,we propose a Voronoi tessellation technique in combination with convolutional neural networks to handle this *** from movable in-core sensors were projected onto the same global field structure using Voronoi tessellation,holding the magnitude and location information of the *** convolutional neural networks were used to learn maps from observations to the global *** proposed method reconstructed multi-physics fields(including fast flux,thermal flux,and power rate)using observations from a single field(such as thermal flux).Numerical tests based on the IAEA benchmark demonstrated the potential of the proposed method in practical engineering applications,particularly within an amplitude of 5 cm around the nominal locations,which led to average relative errors below 5% and 10% in the L_(2) and L_(∞)norms,respectively.

关键词： Voronoi tessellation Field reconstruction Nuclear reactors Reactor physics On-line monitoring

Implicit policy constraint for offline reinforcement learning

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第4期9卷 973-981页

作者： Zhiyong Peng Yadong Liu Changlin han Zongtan Zhou National University of Defense Technology ChangshaChina

Offline reinforcement learning(RL)aims to learn policies entirely from passively collected datasets,making it a data‐driven decision *** of the main challenges in offline RL is the distribution shift problem,which causes the algorithm to visit out‐of‐distribution(OOD)*** distribution shift can be mitigated by constraining the divergence between the target policy and the behaviour ***,this method can overly constrain the target policy and impair the algorithm's performance,as it does not directly distinguish between in‐distribution and OOD *** addition,it is difficult to learn and represent multi‐modal behaviour policy when the datasets are collected by several different behaviour *** overcome these drawbacks,the au-thors address the distribution shift problem by implicit policy constraints with energy‐based models(EBMs)rather than explicitly modelling the behaviour *** EBM is powerful for representing complex multi‐modal distributions as well as the ability to distinguish in‐distribution samples and *** results show that their method significantly outperforms the explicit policy constraint method and other *** addition,the learnt energy model can be used to indicate OOD visits and alert the possible failure.

关键词： artificial intelligence artificial neural network learning(artificial intelligence) planning(artificial intelligence)

Visual Semantic Segmentation Based on Few/Zero-Shot learning:An Overview

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第5期11卷 1106-1126页

作者： Wenqi Ren Yang Tang Qiyu Sun Chaoqiang Zhao Qing-Long han Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of EducationEast China University of Science and TechnologyShanghai 200237China National Key Laboratory of Air-Based Information Perception and Fusion Aviation Industry Corporation of ChinaLuoyang 471000China School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourne VIC 3122Australia

Visual semantic segmentation aims at separating a visual sample into diverse blocks with specific semantic attributes and identifying the category for each block,and it plays a crucial role in environmental *** learning-based visual semantic segmentation approaches count heavily on largescale training data with dense annotations and consistently fail to estimate accurate semantic labels for unseen *** obstruction spurs a craze for studying visual semantic segmentation with the assistance of few/zero-shot *** emergence and rapid progress of few/zero-shot visual semantic segmentation make it possible to learn unseen categories from a few labeled or even zero-labeled samples,which advances the extension to practical ***,this paper focuses on the recently published few/zero-shot visual semantic segmentation methods varying from 2D to 3D space and explores the commonalities and discrepancies of technical settlements under different segmentation ***,the preliminaries on few/zeroshot visual semantic segmentation,including the problem definitions,typical datasets,and technical remedies,are briefly reviewed and ***,three typical instantiations are involved to uncover the interactions of few/zero-shot learning with visual semantic segmentation,including image semantic segmentation,video object segmentation,and 3D ***,the future challenges of few/zero-shot visual semantic segmentation are discussed.

关键词： Visual segmentation separating

Nonlinear Registration of Brain Magnetic Resonance Images with Cross Constraints of Intensity and Structure

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 2295-2313页

作者： han Zhou HongtaoXu Xinyue Chang Wei Zhang Heng Dong Digital Fujian Research Institute of Big Data forAgriculture and Forestry Fujian Agriculture and Forestry UniversityFuzhou350002China College of Computer and Information Science Fujian Agriculture and Forestry UniversityFuzhou350002China

Many deep learning-based registration methods rely on a single-stream encoder-decoder network for computing deformation fields between 3D ***,these methods often lack constraint information and overlook semantic consistency,limiting their *** address these issues,we present a novel approach for medical image registration called theDual-VoxelMorph,featuring a dual-channel cross-constraint *** innovative network utilizes both intensity and segmentation images,which share identical semantic information and feature *** encoder-decoder structures calculate deformation fields for intensity and segmentation images,as generated by the dual-channel cross-constraint *** design facilitates bidirectional communication between grayscale and segmentation information,enabling the model to better learn the corresponding grayscale and segmentation details of the same anatomical *** ensure semantic and directional consistency,we introduce constraints and apply the cosine similarity function to enhance semantic *** on four public datasets demonstrates superior performance compared to the baselinemethod,achieving Dice scores of 79.9%,64.5%,69.9%,and 63.5%for OASIS-1,OASIS-3,LPBA40,and ADNI,respectively.

关键词： Medical image registration cross constraint semantic consistency directional consistency dual-channel

Application of chitosan-based nanoparticles in skin wound healing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Asian Journal of Pharmaceutical Sciences 2022年第3期17卷 299-332页

作者： Hooi Leong Loo Bey Hing Goh learn-han lee Lay Hong Chuah School of Pharmacy Monash University MalaysiaSelangor 47500Malaysia Biofunctional Molecule Exploratory Research Group School of PharmacyMonash University MalaysiaSelangor 47500Malaysia College of Pharmaceutical Sciences Zhejiang UniversityHangzhou 310058China Novel Bacteria and Drug Discovery(NBDD)Research Group Microbiome and Bioresource Research StrengthJeffrey Cheah School of Medicine and Health SciencesMonash University MalaysiaSelangor 47500Malaysia

The rising prevalence of impaired wound healing and the consequential healthcare burdens have gained increased attention over recent *** has prompted research into the development of novel wound dressings with augmented wound healing ***(NP)-based delivery systems have become attractive candidates in constructing such wound dressings due to their various favourable *** non-toxicity,biocompatibility and bioactivity of chitosan(CS)-based NPs make them ideal candidates for wound *** review focusses on the application of CS-based NP systems for use in wound *** overview of the wound healing process was presented,followed by discussion on the properties and suitability of CS and its NPs in wound *** wound healing mechanisms exerted by CS-based NPs were then critically analysed and discussed in sections,namely haemostasis,infection prevention,inflammatory response,oxidative stress,angiogenesis,collagen deposition,and wound closure *** results of the studieswere thoroughly reviewed,and contradicting findings were identified and *** on the literature,the gap in research and future prospects in this research area were identified and *** evidence shows that CS-based NPs possess superior wound healing effects either used on their own,or as drug delivery vehicles to encapsulate wound healing *** is concluded that great opportunities and potentials exist surrounding the use of CSNPs in wound healing.

关键词： Biopolymer Chitosan nanoparticle Nanotechnology Wound dressing Wound healing

Weakly supervised point cloud segmentation via deep morphological semantic information embedding

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第3期9卷 695-708页

作者： Wenhao Xue Yang Yang Lei Li Zhongling Huang Xinggang Wang Junwei han Dingwen Zhang School of Automation Northwestern Polytechnical UniversityXi'anChina Institute of Mechanical and Electrical Engineering BeijingChina School of Electronic Information and Communications Huazhong University of Science and TechnologyWuhanChina

Segmenting the semantic regions of point clouds is a crucial step for intelligent agents to understand 3D *** supervised point cloud segmentation is highly desirable because entirely labelling point clouds is highly time-consuming and *** the low-costing labelling of 3D point clouds,the scene-level label is one of the most effortless label ***,due to the limitation of classifier discriminative capability and the orderless and structurless nature of the point cloud data,existing scene-level method is hard to transfer the semantic information,which usually leads to the under-activated or over-activated *** this end,a local semantic embedding network is introduced to learn local structural patterns and semantic ***,the proposed network contains graph convolution-based dilation and erosion embedding modules to implement‘inside-out’and‘outside-in’semantic information dissemination ***,the proposed weakly supervised learning framework could achieve the mutual propagation of semantic information in the foreground and *** experiments on the widely used ScanNet benchmark demonstrate the superior capacity of the proposed approach when compared to the current alternatives and baseline models.

关键词： artificial intelligence computer vision deep learning

Fructose promotes pyoluteorin biosynthesis via the CbrAB-CrcZ-Hfq/Crc pathway in the biocontrol strain Pseudomonas PA1201

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Synthetic and Systems Biotechnology 2023年第4期8卷 618-628页

作者： Ying Cui Kai Song Zi-Jing Jin learn-han lee Chitti Thawai Ya-Wen He State Key Laboratory of Microbial Metabolism Joint International Research Laboratory of Metabolic and Developmental SciencesSchool of Life Sciences and BiotechnologyShanghai Jiao Tong UniversityShanghai200240China Novel Bacteria and Drug Discovery Research Group(NBDD) Microbiome and Bioresource Research Strength(MBRS)Jeffrey Cheah School of Medicine and Health SciencesMonash University MalaysiaBandar SunwaySelangor Darul Ehsan47500Malaysia Department of Biology Faculty of ScienceKing Mongkut’s Institute of Technology LadkrabangBangkok10520Thailand

Biocontrol strain Pseudomonas PA1201 produces pyoluteorin(Plt),which is an antimicrobial secondary *** represents a promising candidate pesticide due to its broad-spectrum antifungal and antibacterial *** PA1201 contains a complete genetic cluster for Plt biosynthesis,it fails to produce detectable level of Plt when grown in media typically used for Pseudomonas *** this study,minimum medium(MM)was found to favor Plt *** the medium M,which contains all the salts of MM medium except for mannitol,as a basal medium,we compared 10 carbon sources for their ability to promote Plt ***,mannitol,and glycerol promoted Plt biosynthesis,with fructose being the most effective carbon *** or succinic acid had no significant effect on Plt biosynthesis,but effectively antagonized fructose-dependent synthesis of ***-lacZ fusion reporter strains demonstrated that fructose acted through activation of the pltLABCDEFG(pltL)operon but had no effect on other genes of plt gene cluster;glucose or succinic acid antagonized fructose-dependent pltL ***,fructose-mediated Plt synthesis involved carbon catabolism *** two-component system CbrA/CbrB and small RNA catabolite repression control Z(crcZ)were essential for fructose-induced Plt *** small RNA binding protein Hfq and Crc negatively regulated fructose-induced *** together,this study provides a new model of fructose-dependent Plt production in PA1201 that can help improve Plt yield by biosynthetic approaches.

关键词： Pseudomonas Biocontrol Pyoluteorin Fructose Carbon catabolism repression

A Study on the Utilization of Applied Linguistics in Contemporary English Teaching

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Contemporary Educational Research 2024年第4期8卷 126-131页

作者： han Li Qingdao Huanghai College Qingdao 266555Shandong ProvinceChina

In the context of globalization,the importance of teaching English as a common language in the world becomes increasingly *** Linguistics belongs to one of the sub-disciplines of linguistics,which plays an important role in contemporary English *** knowledge of applied linguistics can help students learn the grammar,semantics,vocabulary,writing,and other contents in English,deepen their knowledge and understanding of English,and enhance the effectiveness of English *** paper mainly describes the important role played by English linguistics in English teaching and focuses on its utilization strategies in the hope of providing references on this topic.

关键词： Applied linguistics English teaching Utilization strategy