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

1,579 篇 会议
83 册 图书
16 篇 期刊文献

馆藏范围

1,678 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,040 篇 工学
- 870 篇 计算机科学与技术...
- 465 篇 软件工程
- 226 篇 信息与通信工程
- 185 篇 电气工程
- 100 篇 生物工程
- 98 篇 生物医学工程（可授...
- 84 篇 控制科学与工程
- 63 篇 光学工程
- 35 篇 机械工程
- 34 篇 电子科学与技术（可...
- 24 篇 仪器科学与技术
- 23 篇 化学工程与技术
- 21 篇 建筑学
- 21 篇 土木工程
- 20 篇 材料科学与工程（可...
- 20 篇 安全科学与工程
- 20 篇 网络空间安全
352 篇 理学
- 174 篇 数学
- 114 篇 生物学
- 89 篇 物理学
- 52 篇 统计学（可授理学、...
- 35 篇 系统科学
- 21 篇 化学
173 篇 管理学
- 91 篇 图书情报与档案管...
- 87 篇 管理科学与工程(可...
- 44 篇 工商管理
113 篇 医学
- 91 篇 临床医学
- 61 篇 基础医学(可授医学...
- 34 篇 药学(可授医学、理...
33 篇 法学
- 26 篇 社会学
17 篇 教育学
12 篇 经济学
8 篇 农学
3 篇 军事学
3 篇 艺术学
2 篇 文学

主题

237 篇 pattern recognit...
79 篇 cloud computing
74 篇 artificial intel...
71 篇 training
57 篇 feature extracti...
55 篇 neural networks
52 篇 machine learning
50 篇 deep learning
40 篇 computer archite...
36 篇 data mining
34 篇 computer imaging...
33 篇 pattern matching
33 篇 computer vision
32 篇 semantics
29 篇 image segmentati...
28 篇 computational mo...
28 篇 image recognitio...
28 篇 image processing...
27 篇 information syst...
26 篇 edge computing

机构

15 篇 school of comput...
12 篇 university of ch...
9 篇 school of comput...
8 篇 inria nancy gran...
8 篇 national center ...
8 篇 icube université...
8 篇 fujian key labor...
8 篇 erasmus mc - uni...
8 篇 tencent jarvis l...
8 篇 university of ba...
7 篇 college of intel...
6 篇 univ chinese aca...
6 篇 institute of ima...
6 篇 department of co...
6 篇 the 54th researc...
6 篇 school of artifi...
6 篇 dipartimento di ...
6 篇 dipartimento di ...
6 篇 computational sc...
6 篇 institute of com...

作者

13 篇 tan chew lim
12 篇 wang da-han
11 篇 yang jie
8 篇 stéphane cotin
8 篇 yefeng zheng
8 篇 chew lim tan
8 篇 philippe c. catt...
8 篇 marleen de bruij...
8 篇 stefanie speidel
8 篇 caroline essert
8 篇 nicolas padoy
7 篇 maier andreas
7 篇 yang yang
7 篇 hancock edwin r.
7 篇 rita cucchiara
7 篇 alberto del bimb...
6 篇 hugo jair escala...
6 篇 tao mei
6 篇 lu shijian
6 篇 marco bertini

语言

1,669 篇 英文
7 篇 其他
3 篇 中文

检索条件"任意字段=2021 10th International Conference on Computing and Pattern Recognition"

共 1678 条记录，以下是1551-1560 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：

Attention as Activation

Attention as Activation

引用

international conference on pattern recognition

作者： Yimian Dai Stefan Oehmcke Fabian Gieseke Yiquan Wu Kobus Barnard College of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics Nanjing China University of Copenhagen Copenhagen Denmark University of Münster Münster Germany University of Arizona Tucson AZ USA

ISBN: (纸本)9781728188089;9781728188096

Activation functions and attention mechanisms are typically treated as having different purposes and have evolved differently. However, both concepts can be formulated as a nonlinear gating function. Inspired by their similarity, we propose a novel type of activation units called attentional activation (ATAC) units as a unification of activation functions and attention mechanisms. In particular, we propose a local channel attention module for the simultaneous non-linear activation and element-wise feature refinement, which locally aggregates point-wise cross-channel feature contexts. By replacing the well-known rectified linear units by such ATAC units in convolutional networks, we can construct fully attentional networks that perform significantly better with a modest number of additional parameters. We conducted detailed ablation studies on the ATAC units using several host networks with varying network depths to empirically verify the effectiveness and efficiency of the units. Furthermore, we compared the performance of the ATAC units against existing activation functions as well as other attention mechanisms on the CIFAR-10, CIFAR-100, and ImageNet datasets. Our experimental results show that networks constructed with the proposed ATAC units generally yield performance gains over their competitors given a comparable number of parameters.

关键词： Aggregates Performance gain pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Converting Java Source Code for Programming Education Support Tool pgtracer

Converting Java Source Code for Programming Education Suppor...

引用

IIAI international conference on Advanced Applied Informatics (IIAIAAI)

作者： Masateru Kishikawa Tetsuro Kakeshita Computing Division Saga University Saga Japan

ISBN: (纸本)9781665424219

We have proposed a programming education support tool pgtracer for effective programming education. Pgtracer utilizes source codes and trace tables that represent execution results of the source code and creates programming exercises by defining blanks in some of them. the difficulty level of the exercises can be freely adjusted since the fill-in-the-blanks in the programs and trace tables can be defined freely. Furthermore, we can realize learning analytics by collecting the data of students' response process. In this paper, we extend pgtracer to incorporate Java for the effective education of object-oriented programming. We convert Java programs into an XML format that can be processed by pgtracer to effectively teach object-oriented programming using Java. By expressing the source code in XML format, it becomes possible to create flexible fill-in-the-blank questions. For this purpose, we utilize JavaCC to create an XML generator, which implements a program for each syntactic rule of the Java grammar to convert the source code into the specified XML format. the XML generator is implemented by combining these programs.

关键词： Java Codes Education XML Syntactics Generators Grammar

来源：评论

学校读者我要写书评

暂无评论

Joint Face Alignment and 3D Face Reconstruction with Efficient Convolution Neural Networks

Joint Face Alignment and 3D Face Reconstruction with Efficie...

引用

international conference on pattern recognition

作者： Keqiang Li Huaiyu Wu Xiuqin Shang Zhen Shen Gang Xiong Xisong Dong Bin Hu Fei-Yue Wang School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

3D face reconstruction from a single 2D facial image is a challenging and concerned problem. Recent methods based on CNN typically aim to learn parameters of 3D Morphable Model (3DMM) from 2D images to render face alignment and 3D face reconstruction. Most algorithms are designed for faces with small, medium yaw angles, which is extremely challenging to align faces in large poses. At the same time, they are not efficient usually. the main challenge is that it takes time to determine the parameters accurately. In order to address this challenge with the goal of improving performance, this paper proposes a novel and efficient end-to-end framework. We design an efficient and lightweight network model combined with Depthwise Separable Convolution and Muti-scale Representation, Lightweight Attention Mechanism, named Mobile-FRNet. Simultaneously, different loss functions are used to constrain and optimize 3DMM parameters and 3D vertices during training to improve the performance of the network. Meanwhile, extensive experiments on the challenging datasets show that our method significantly improves the accuracy of face alignment and 3D face reconstruction. Model parameters and complexity of our method are also improved greatly.

关键词： Training Solid modeling three-dimensional displays Convolution Face recognition Neural networks Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Early Prediction of Complex Business Processes Using Association Rule Based Mining 4th

Early Prediction of Complex Business Processes Using Associ...

引用

4th international conference on Recent Trends in Image Processing and pattern recognition, RTIP2R 2021

作者： Khan, Naveed Tariq, Zeeshan Ali, Aftab McClean, Sally Taylor, Paul Nauck, Detlef School of Computing Ulster University JordanstownBT37 0QB United Kingdom Applied Research BT Ipswich United Kingdom

ISBN: (纸本)9783031070044

Complex business processes are challenging and hard to analyse. the objective here is to enhance delivery of processes in terms of improving quality of service and customer satisfaction. therefore, an automated process prediction system is desirable to monitor and evaluate complex business processes and forecast process outcome during execution time. the analysis of such processes would help domain experts to make in-time decisions to improve the process. the in-time response greatly effects the quality of service and customer satisfaction. therefore, in this paper, the early process prediction framework using Classification Based on Association rules (CBA) has been proposed to predict outcomes for such incomplete processes. the essential part of the proposed system is to extract association rules from the process data up to a certain point in time (i.e. the cut-off time) at which the prediction needs to be made;in an live process this would usually be the current time. the CBA algorithm generates rules with user specified support and confidence which are then utilised for early process prediction. the experimental results based on real business process data are presented for on-time and delayed processes. the proposed early process prediction system is evaluated using different metrics such as accuracy, precision, recall and the F-measure. Moreover, the proposed system is also compared with our prior published work in terms of accuracy, recall and F-measure. the analysis shows that the performance of proposed system outperforms schemes in the literature. © 2022, Springer Nature Switzerland AG.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Stacked Dark COVID-Net: A Multi-class Multi-label Classification Approach for Diagnosing COVID-19 Using Chest X-Ray Images 4th

Stacked Dark COVID-Net: A Multi-class Multi-label Classifica...

引用

4th international conference on Recent Trends in Image Processing and pattern recognition, RTIP2R 2021

作者： Anila Glory, H. Meghana, S. Kesav Kumar, J.S. Shankar Sriram, V.S. School of Computing SASTRA Deemed University Tamil Nadu Thanjavur613401 India

ISBN: (纸本)9783031070044

Most challenging yet, the need of the hour is accurate diagnosis of COVID-19, as the Coronavirus cases are increasing drastically day-by-day. Ceaseless efforts by the researchers and innovators have led to the development of several diagnostic models based on Deep Learning for effective diagnosis of COVID-19. However, the Deep Learning techniques that have been developed so far, fail to address major challenges such as overfitting, stability, computation overhead due to the usage of the massive volume of parameters and problems associated with the multi-class classification. Also in the medical perspective, researchers often suffer to identify the infinitesimal difference that exists in the radiographic images among the several lung diseases which makes the decision-making process difficult. thus, to curb the crisis and to provide promising solutions & expertise for accurate diagnosis, this paper presents a novel lightweight multi-class multi-label COVID-19 detection model to assist physicians with greater ease to fight against this pandemic situation. Radiographic images are pre-processed using Contrast Limited Adaptive Histogram Equalization (CLAHE) and classified using novel Stacked Dark COVID-Net. the proposed model is validated using chest X-ray images and the results confirm the efficacy of the proposed model in terms of classification accuracy, sensitivity, specificity and stability. © 2022, Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Temporal Analysis for the Identification of Extreme Rainfall Events Recorded in Uruguay Over a 30-Year Period (1991–2021)

Temporal Analysis for the Identification of Extreme Rainfall...

引用

pattern recognition Systems (ICPRS), international conference on

作者： Luana Frias-Telesca Nelcy N. Atehortua-Sanchez Fernando Pasini Artificial Intelligence Applications Group - ARIA Universidad Tecnológica de Uruguay Durazno Uruguay

Uruguay is a country susceptible to extreme events (heavy rainfall or drought) due to the large variation in rainfall. the identification of extreme events at a regional scale is essential since the impact due to climate change could become devastating and extended. Significant changes in climate trends make it difficult to predict extreme events. In this study, the variability of precipitation from 1991 to 2021 was analyzed at five meteorological stations of the National Institute of Agricultural Research (INIA). the data used are publicly available in open sources. the statistical analysis of the accumulated precipitation at each station shows that the stations of Tacuarembó and Salto Grande, located in the country's northern region, have a higher annual accumulated precipitation. Due to the nature of the precipitation records, a classical decomposition was performed to analyze the time series, revealing better results for the additive model and showing the seasonality in the data. this information is used to describe the behavior of the precipitation records with the possibility of making projections of the extreme events identified. the decomposition results revealed the presence of extreme events, such as heavy rainfall and prolonged periods of drought. For heavy rain events, the maximum rainfall values were determined for each station and the return periods were calculated using the Gumbel probability. the Salto Grande station is the station with the highest seasonal precipitation records for spring, summer and fall for a return period of 10 years.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Hand Motion pattern recognition Using Deep Learning Network Algorithms 2020

EEG-Based Hand Motion Pattern Recognition Using Deep Learnin...

引用

Proceedings of the 2020 9th international conference on computing and pattern recognition

作者： Yongyu Jiang Christine Chen Xiaodong Zhang Wei Zhou Chaoyang Chen Stephen Lemos Xi'an Jiaotong University Xi'an China Department of Computer Science University of Michigan at Ann Arbor Ann Arbor Michigan USA Ximen University Xiamen China Department of Biomedical Engineering Wayne State University Detroit Michigan USA Orthopedic Surgery and Sports Medicine DMC Detroit MI USA

ISBN: (纸本)9781450387835

EEG signals contain information of limb motion patterns that are difficult to be extracted using conventional methods. the purpose of this study was to determine the feasibility of novel machine learning algorithms in extraction of hand motion intents from EEG. In this paper, 3 hand motion patterns (hand opening, closing, resting) were recognized using the filter bank common spatial pattern (FBCSP) method. the spatial filtering method and the CNN classifier were used to decode and classify the EEG signals. 15 healthy subjects' EEG datasets were used. Results demonstrated that the average correct rate of motion pattern recognition was 83.61%. the performance of these algorithms was validated using off-line computer-controlled robotic hand system, the average accuracy of a subject was 77.32%, and the average time of the system recognition action was 28.4ms. this study demonstrated that hand motion pattern recognition can be extracted from EEG signals and can be utilized by brain computer interface (BCI) to trajectory control a robotic hand motion.

关键词： pattern recognition electroencephalography (eeg) signal processing hand motion convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Opposition-based Grey Wolf Optimization Approaches for Feature Selection

Opposition-based Grey Wolf Optimization Approaches for Featu...

引用

international conference on Intelligent System and Knowledge Engineering, ISKE

作者： Zhi Cao Hongmei Chen School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China

ISBN: (纸本)9781665405546

Feature selection is an approach to select the important and key feature subset from a large number of redundant features, which can effectively reduce the computational cost and storage cost in the data processing process. therefore, feature selection is widely used in data mining and pattern recognition. the grey Wolf optimization algorithm can solve the problem of feature selection by simulating the predation behavior of gray wolves to obtain the optimal feature subset step by step. In this paper, we propose an opposition based learning grey Wolf optimization algorithm(OGWO), which uses opposition-based learning to initialize and update the population to improve the exploration ability of the population. In order to avoid the local optimum, a nonlinear parameter adjustment strategy is used to update the important parameters of the grey Wolf optimization algorithm. Experiments on 12 datasets demonstrate the effectiveness of the proposed method. Experimental results show that OGWO has better classification performance compared with other swarm intelligence algorithms.

关键词： Knowledge engineering Sociology Packaging Feature extraction Data processing Classification algorithms Statistics

来源：评论

学校读者我要写书评

暂无评论

Gas Discrimination & Quantification using Sensor Array with 3D Convolution Regression Dual Network

Gas Discrimination & Quantification using Sensor Array with ...

引用

IEEE international Workshop on Intelligent Data Acquisition and Advanced computing Systems: Technology and Applications

作者： Vishakha Pareek Santanu Chaudhury Sanjay Singh CSIR - Central Electronics Engineering Research Institute Pilani India Academy of Scientific and Innovative Research (AcSIR) Ghaziabad India Indian Institute of Technology Delhi India

ISBN: (纸本)9781665426060

Smart sensor system design requires intelligent data processing, which analyzes raw time-series sensor data to efficiently and precisely discriminate and quantify target gases. the work presented here utilizes the response of twin gas sensor arrays for gases such as ethanol, ethylene, methane, and carbon monoxide to discriminate and quantify the target gases. We propose a 3D convolution neural-based regression dual network (3D-CNRDN) for both gas quantification and discrimination. the spatiotemporal correlation of sensor array responses inspired us to design the deep neural network for the gas concentration estimation model. the sensor array set is spatially correlated, and all the twin array responses are temporally related. 3D-CNRDN uses raw time-series gas sensor array data. the data is fed to the network as the 3D pattern, which contains 2D spatial information varying with third dimension time to recognize patterns that eventually predict the concentration. the model evaluation shows that the proposed methods are an effective technique for gas quantification and identification with $\text{RMSE}=0.3179$ and classification accuracy 94.37%. Furthermore, the proposed method outperforms and provides higher discrimination accuracy and lower RMSE than other machine learning and deep learning methods.

关键词： Deep learning Gases three-dimensional displays Convolution Neural networks Spatiotemporal phenomena pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Earliest-Arrival Route: A Global Optimized Communication for Networked Control Systems 8th

Earliest-Arrival Route: A Global Optimized Communication for...

引用

8th EAI international conference on Advancement of Science and Technology, ICAST 2020

作者： Rajan, M. Sundar Arunkumar, J.R. Anusuya, R. Mesfin, Abraham Faculty of Electrical and Computer Engineering Arbaminch University Arba Minch Ethiopia Faculty of Computing and Software Engineering Arbaminch University Arba Minch Ethiopia

ISBN: (纸本)9783030806200

As per the present switched system theorem, data package-drop ratio decides the strength of NCSs. through the focal point principle to offer small data package-drop ratio for dispersed NCS under parameter transmission environment, the communication improvement issue is described from universal transmission aspect. Initially, system stimulated break is illustrated function associated with time can be calculated using auto-regressive-moving-average (ARMA) pattern, and the upcoming break is forecasted by the obtained break samples. Subsequently, the widespread referred shortest route of time dependent network(SPTDN) algorithm is described and enhanced by means of introducing waiting-time previous to data packages are dispatched to subsequent unit in a route, in order to get quickly coming time than SPTDN. Subsequently, the concept of earliest-arrival time (EAT) is suggested to calculate the excellence of transmission route, the connected EAT algorithm is intended to look for upcoming EAT and the equivalent route since universal system vigorously. Advantage from the active EAT route, data packages reach at target as early as feasible, it reduces data package-drop ratio. therefore, EAT route make sure the steadiness of shared NCSs from the opinion of worldwide system. At last, the experiment demonstrates the strength and efficiency of the suggested method. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Networked control systems

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168页 << < 152 153 154 155 156 157 158 159 160 161 > >>

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：