检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

687 篇 会议
15 册 图书
11 篇 期刊文献

馆藏范围

713 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

490 篇 工学
- 420 篇 计算机科学与技术...
- 198 篇 软件工程
- 91 篇 信息与通信工程
- 84 篇 电气工程
- 54 篇 控制科学与工程
- 32 篇 生物医学工程（可授...
- 30 篇 生物工程
- 21 篇 光学工程
- 19 篇 电子科学与技术（可...
- 13 篇 仪器科学与技术
- 11 篇 化学工程与技术
- 10 篇 材料科学与工程（可...
- 9 篇 机械工程
- 9 篇 安全科学与工程
- 8 篇 环境科学与工程（可...
- 8 篇 网络空间安全
153 篇 理学
- 93 篇 数学
- 35 篇 生物学
- 34 篇 物理学
- 24 篇 统计学（可授理学、...
- 17 篇 化学
- 12 篇 系统科学
75 篇 管理学
- 41 篇 管理科学与工程(可...
- 39 篇 图书情报与档案管...
- 20 篇 工商管理
69 篇 医学
- 64 篇 临床医学
- 21 篇 基础医学(可授医学...
- 10 篇 药学(可授医学、理...
20 篇 法学
- 16 篇 社会学
9 篇 艺术学
8 篇 经济学
- 8 篇 应用经济学
6 篇 农学
1 篇 教育学
1 篇 军事学

主题

106 篇 pattern recognit...
27 篇 feature extracti...
24 篇 machine learning
20 篇 affective comput...
18 篇 cloud computing
17 篇 neural networks
17 篇 data mining
16 篇 pattern matching
16 篇 computer vision
15 篇 deep learning
14 篇 pattern classifi...
14 篇 emotion recognit...
13 篇 support vector m...
13 篇 face recognition
9 篇 object detection
9 篇 task analysis
9 篇 edge computing
9 篇 training
8 篇 classification
8 篇 learning (artifi...

机构

7 篇 university of ch...
5 篇 fujian key labor...
5 篇 school of comput...
4 篇 university of te...
4 篇 bournemouth univ...
4 篇 school of inform...
4 篇 gdynia maritime ...
3 篇 friedrich alexan...
3 篇 department of co...
3 篇 johns hopkins un...
3 篇 univ chinese aca...
3 篇 institute of com...
2 篇 fgan-fom researc...
2 篇 univ mysore dept...
2 篇 univ siegen res ...
2 篇 national laborat...
2 篇 dept. of ict maw...
2 篇 pes univ ctr pat...
2 篇 fuyang normal un...
2 篇 college of compu...

作者

6 篇 wang da-han
6 篇 suen ching y.
5 篇 yang jie
4 篇 ireneusz czarnow...
4 篇 maier andreas
4 篇 alfonso mateos c...
3 篇 chen yiqiang
3 篇 jianhua tao
3 篇 liu cheng-lin
3 篇 fotouhi javad
3 篇 akira notsu
3 篇 seiki ubukata
3 篇 katsuhiro honda
3 篇 navab nassir
3 篇 unberath mathias
3 篇 guo ping
3 篇 pal umapada
3 篇 luo bin
3 篇 shivakumara pala...
2 篇 castelo-branco m...

语言

695 篇 英文
12 篇 其他
10 篇 中文

检索条件"任意字段=Proceedings of the 2019 8th International Conference on Computing and Pattern Recognition"

共 713 条记录，以下是81-90 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Brain-like Combination of Feedforward and Recurrent Network Components Achieves Prototype Extraction and Robust pattern recognition 8th

Brain-like Combination of Feedforward and Recurrent Network ...

引用

8th Annual international conference on Machine Learning, Optimization and Data science (LOD)

作者： Ravichandran, Naresh Balaji Lansner, Anders Herman, Pawel KTH Royal Inst Technol Sch Elect Engn & Comp Sci Div Computat Sci & Technol Stockholm Sweden Stockholm Univ Dept Math Stockholm Sweden KTH Royal Inst Technol Digital Futures Stockholm Sweden

ISBN: (纸本)9783031258909;9783031258916

Associative memory has been a prominent candidate for the computation performed by the massively recurrent neocortical networks. Attractor networks implementing associative memory have offered mechanistic explanation for many cognitive phenomena. However, attractor memory models are typically trained using orthogonal or random patterns to avoid interference between memories, which makes them unfeasible for naturally occurring complex correlated stimuli like images. We approach this problem by combining a recurrent attractor network with a feedforward network that learns distributed representations using an unsupervised Hebbian-Bayesian learning rule. the resulting network model incorporates many known biological properties: unsupervised learning, Hebbian plasticity, sparse distributed activations, sparse connectivity, columnar and laminar cortical architecture, etc. We evaluate the synergistic effects of the feedforward and recurrent network components in complex pattern recognition tasks on the MNIST handwritten digits dataset. We demonstrate that the recurrent attractor component implements associative memory when trained on the feedforward-driven internal (hidden) representations. the associative memory is also shown to perform prototype extraction from the training data and make the representations robust to severely distorted input. We argue that several aspects of the proposed integration of feedforward and recurrent computations are particularly attractive from a machine learning perspective.

关键词： Attractor Associative memory Unsupervised learning Hebbian learning Recurrent networks Feedforward networks Brain-like computing

来源：评论

学校读者我要写书评

暂无评论

KDI-Net: dual-domain mapping network for undersampled magnetic resonance imaging reconstruction

KDI-Net: dual-domain mapping network for undersampled magnet...

引用

2024 international conference on Image, Signal Processing, and pattern recognition, ISPP 2024

作者： Guo, Haiyang Zuo, Zhentao Sun, Dengdi Zhou, Tiangang AHU-IAI AI Joint Laboratory Anhui University Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China State Key Laboratory of Brain and Cognitive Science Institute of Biophysics Chinese Academy of Sciences Beijing100101 China University of Chinese Academy of Sciences Beijing100049 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computing School of Artificial Intelligence Anhui University Hefei230601 China

ISBN: (纸本)9781510680425

Magnetic resonance imaging (MRI) is an imaging technique that provides comprehensive anatomical and functional information on the human body, but prolonged acquisition of fully sampled MRI images causes patient discomfort and motion *** recent years, deep learning (DL) has made significant progress in accelerating MRI image *** present, MRI image reconstruction is concentrated on single domain, but hybrid domain reconstruction has more ***, we propose a hybrid domain reconstruction method based on AUTOMAP-KDI-Net, which divided into three parts: K-Block, D-Block and *** evaluated the performance of our KDI-Net model for MRI image reconstruction using PSNR, RMSE, and SSIM metrics and three reduction factors (2, 3, 4) on two publicly available MRI datasets (the AUTOMAP brain dataset and the Calgary Campinas single-coil brain dataset).the results show that KDI-Net performs better than AUTOMAP and Complex *** to AUTOMAP, KDI-Net basically improved each metric by more than 6%.Compared to Complex AUTOMAP, KDI-Net basically improved by more than 8% on each *** reduction factor 2, the reconstructed MRI image is very close to ground *** specially designed KDI-Net can extract the sparsity from single channel MRI K-space, which achieve 2 folder acceleration. © 2024 SPIE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

An Exploratory Study on the Design of Emergency First Aid Privacy Protection computing System Based on Blockchain 8

An Exploratory Study on the Design of Emergency First Aid Pr...

引用

8th international conference on Business and Industrial Research, ICBIR 2023

作者： Jian, Xiong Parthasarathy, Rajamohan Huang, Bin Wen SEGi University Faculty of Engineering Built Environment and Information Technology Kota Damansara Malaysia Hainan Medical University Faculty of Engineering Built Environment and Information Technology Kota Damansara Malaysia Center Hainan Medical University Faculty of Modern Education Technology Haikou China

ISBN: (纸本)9798350399646

the COVID-19 epidemic at the end of 2019 is a typical global public health event. It has spread to more than 200 countries around the world. In the face of sudden illness, the emergency department is the first choice for most patients, and it is often the first to grasp the basic situation of patients. In the process of processing the data of the emergency big data center, how to ensure the privacy of patients while using medical data reasonably. this paper mainly takes the data of the emergency big data center as the research object. Put important health data on the block chain to ensure that important data remains traceable throughout the process, cannot be tampered with, multi-point maintenance, unified standards, and realize the formation of emergency block chains, and use important health data based on privacy applications, Realize the historical traceability of data usage. At the same time, the calculation process of privacy calculation can also be uploaded to the chain, which can be used for data storage, auxiliary calculation, etc. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Small Object Detection with YOLOv8 Algorithm Enhanced by MobileViTv3 and Wise-IoU 12

Small Object Detection with YOLOv8 Algorithm Enhanced by Mob...

引用

12th international conference on computing and pattern recognition, ICCPR 2023

作者： Wang, Wencheng Liu, Wenxin Shandong Agricultural University Shandong Province Taian Shi China

ISBN: (纸本)9798400707988

Small object detection is an important and challenging task in computer vision, with widespread applications in fields such as remote sensing, autonomous driving, and security. However, due to factors such as small size, indistinct features, and complex backgrounds of small objects, traditional convolutional neural network (CNN)-based object detection algorithms often struggle to effectively detect small objects. To address issues such as insufficient feature extraction, suboptimal anchor box matching, and unbalanced loss functions, an improved YOLOv8 algorithm is proposed. this algorithm enhances the detection accuracy of small objects by adding a lightweight visual transformer, MobileViTv3, which can enhance feature representation capabilities, and a Wise-IoU loss function that adaptively adjusts the ratio of positive and negative samples and regression coefficients. Results show that the improved YOLOv8 algorithm achieves an increase of 2.5%, 2.1%, and 2.9% in precision, recall, and mAP respectively on the public remote sensing dataset VisDrone2019 and 2.4%, 2.7%, and 3.5% on DOTA compared to the original algorithm. It can effectively improve the accuracy of small object detection in complex scenarios while meeting the requirements for detection speed. © 2023 ACM.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Regular Language Prediction from Complete Sample in Grammatical Inference theory – A Literature Survey

Regular Language Prediction from Complete Sample in Grammati...

引用

international conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)

作者： Senthil Kumar.K Nishaanth Balakrishnan Pranav.N Dept. of Computing Technology SRMIST India

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376432

Inferring regular language and the corresponding finite automaton from the given set of samples (both positive and negative) is an important task in grammatical inference theory. the corresponding underlying automaton, viz., Deterministic Finite Automaton, has many applications ranging from lexical analysis of compilers, pattern recognition, image grammar, genetic engineering, etc.

关键词： Surveys Machine learning algorithms Scalability Neural networks Automata Reinforcement learning Inference algorithms Grammar pattern recognition Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Glare-SNet: Unsupervised Glare Suppression Balance Network 27th

Glare-SNet: Unsupervised Glare Suppression Balance Network

引用

27th international conference on pattern recognition, ICPR 2024

作者： Li, Pei Zuo, Chengyu Wei, Wangjuan Pan, Xiaoying Wang, Zhanhao School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an China Shaanxi Key Laboratory of Intelligent Media Computing and interaction Xi’an China Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’an China

ISBN: (纸本)9783031781681

In light of the problems associated with glare and halo effects in low-light images, as well as the inadequacy of existing processing algorithms in handling details, a glare suppression balance network based on unsupervised learning has been designed and implemented in this study. A network that perceives brightness through light decomposition has been proposed, and an illumination learning network has been designed. the idea of integration has been employed to form an unsupervised glare suppression balance network, aiming to tackle the issues of glare and the accompanying halo effects. through objective and subjective evaluations of real images, it has been proven that the method introduced in this paper surpasses other methods in suppressing glare and enhancing the overall quality of low-light images. Furthermore, it has been shown to exhibit good performance and effectiveness in target detection. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

proceedings - 2019 8th IEEE international conference on Cloud computing in Emerging Markets, CCEM 2019

Proceedings - 2019 8th IEEE International Conference on Clou...

引用

8th IEEE international conference on Cloud computing in Emerging Markets, CCEM 2019

ISBN: (纸本)9781728163345

the proceedings contain 16 papers. the topics discussed include: predictive analytics for storage management using time-series forecasting techniques;cache characterization of workloads in a microservice environment;cyber resiliency automation using blockchain;intelligent meters for urban domestic water consumption;outcome classification in cricket using deep learning;deep learning in practice: guidelines for model selection;compressing closed frequent item sets with controlled information loss;hash based integrity verification for vehicular cloud environment;and an efficient two factor authentication scheme providing secure communication in mobile cloud computing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

M-Learning - Before and During COVID-19 8

M-Learning - Before and During COVID-19

引用

8th international conference on Energy Efficiency and Agricultural Engineering, EE and AE 2022

作者： Georgiev, Tsvetozar University of Ruse Department of Computing Ruse Bulgaria

ISBN: (纸本)9781665407090

the report describes a study of the opinion of students from the University of Ruse on their use of mobile learning before and during the COVID-19 pandemic. the research uses the survey methodology and for this purpose an online questionnaire was developed. A total number of 469 students from four academic years were surveyed - two before COVID-19 and two during the pandemic. Of the total number of surveyed students, 143 are in the academic year 2021-2022 and 133 are in the academic year 2020-2021, when most of the education was online. 72 are in the academic year 2019-2020 and 121 are in the academic year 2018-2019. An analysis and comparison of the results of these three academic years was performed. Relevant conclusions about the impact of COVID-19 on the use of mobile learning are made. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

8th international conference on Life System Modeling and Simulation, LSMS 2024 and 8th international conference on Intelligent computing for Sustainable Energy and Environment, ICSEE 2024

8th International Conference on Life System Modeling and Sim...

引用

8th international conference on Life System Modeling and Simulation, LSMS 2024 and 8th international conference on Intelligent computing for Sustainable Energy and Environment, ICSEE 2024

ISBN: (纸本)9789819601875

the proceedings contain 158 papers. the special focus in this conference is on Life System Modeling and Simulation and Intelligent computing for Sustainable Energy and Environment. the topics include: A Method for Evaluating the Operating Health of Wind Turbines Under Wake Effect;toward Next-Generation Buildings: A Review of Renewable Energy Integration and Intelligent Building Energy Management Technologies;improving the Construction of a Multi-modal Underwater Image recognition System for Anomaly Detection in Nuclear Power Plant Cooling Source Areas;A Novel Anti-noise Fault Diagnosis Method for Nuclear Energy Steam Turbine Based on VCformer;Short-Term Photovoltaic Power Forecasting Using Multi-timescale Information Based FFTformer Model;wind Power Forecasting Model Based on Feature Processing and Deep Hybrid Kernel Extreme Learning Machine;optimal User-Side Energy Arbitrage Strategy in Electricity Market with Accurate Battery Model Using Benders Decomposition;a Novel Distributed Economic Dispatch Method for Smart Grid with Time-Varying Feedback Gain;benefits, Barriers, and Human Factors of V2X Implementation – A Brief Review;a General pattern of Permanent Magnet Arrangement for Design Optimization of a Reluctance Magnetic Gear with Enhanced Torque Density for Electric Vehicles;wind Power Scheduling Deviation Compensation Based on Dual-Frequency Pulse Control;a Comprehensive Simulation and Validation of Single Particle Aging Mechanism Model for Lithium-Ion Batteries;semi-supervised State of Health Estimation for Lithium-Ion Batteries via Dynamical Self-encoding;a Reduce-Order Model to Understand the Multiscale Coupling of Battery Electrochemical-thermal Performance;RUL Prediction for Lithium-Ion Batteries Based on Sequence Decomposition and Transformer Networks;An Estimation Method of State of Health of Sodium-Ion Batteries Based on TCN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of histograms of oriented gradients and local binary pattern coefficients for facial emotion recognition 8

Comparative analysis of histograms of oriented gradients and...

引用

8th international conference on computing for Sustainable Global Development, INDIACom 2021

作者： Subudhiray, Swapna Palo, Hemanta Kumar Das, Niva Mohanty, Sachi Nandan Bhubaneswar India College of Engineering Pune Dept. of Computer Engineering Pune India

ISBN: (纸本)9789380544434

this paper examines the human expressive states dependent on facial pictures utilizing a few viable component extraction methods. It reproduces the K-Nearest Neighbor (k-NN) classifier to approve the adequacy of successful capabilities separated from the Local Binary pattern (LBP) and Histograms of Oriented Gradients (HOG) for the said task. An examination of the strategies has been made dependent on the normal acknowledgment precision of the classifiers utilizing the calculation unpredictability as a compromise. the component extraction methods have been approved for their discriminative force under various preparations for testing information division proportions, Kappa Coefficient, and order time. the LBP has outperformed the HOG include extraction strategy with a normal precision of 79.6% yet remains computationally costly. On the contrary, the HOG method has furnished a lower characterization time with a normal precision of 59.3 % as uncovered from our outcomes. © 2021 Bharati Vidyapeeth, New Delhi. Copy Right in Bulk will be transferred to IEEE by Bharati Vidyapeeth.

关键词： Emotion recognition

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共72页 << < 5 6 7 8 9 10 11 12 13 14 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：