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

4,580 篇 会议
572 篇 期刊文献
10 篇 学位论文
5 册 图书
1 篇 科技报告

馆藏范围

5,168 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,665 篇 工学
- 2,216 篇 计算机科学与技术...
- 1,445 篇 软件工程
- 576 篇 电气工程
- 365 篇 控制科学与工程
- 332 篇 信息与通信工程
- 258 篇 机械工程
- 248 篇 石油与天然气工程
- 215 篇 化学工程与技术
- 204 篇 生物医学工程（可授...
- 195 篇 生物工程
- 188 篇 仪器科学与技术
- 175 篇 土木工程
- 163 篇 光学工程
- 157 篇 建筑学
- 151 篇 动力工程及工程热...
- 132 篇 材料科学与工程（可...
- 124 篇 电子科学与技术（可...
- 122 篇 航空宇航科学与技...
1,589 篇 理学
- 601 篇 物理学
- 420 篇 数学
- 313 篇 地球物理学
- 270 篇 地质学
- 221 篇 生物学
- 203 篇 统计学（可授理学、...
- 191 篇 化学
- 120 篇 系统科学
659 篇 管理学
- 420 篇 管理科学与工程(可...
- 267 篇 图书情报与档案管...
- 173 篇 工商管理
400 篇 医学
- 307 篇 临床医学
92 篇 法学
86 篇 农学
68 篇 教育学
59 篇 经济学
30 篇 文学
12 篇 艺术学
4 篇 军事学
1 篇 历史学

主题

664 篇 visualization
382 篇 data visualizati...
242 篇 visual analytics
170 篇 data mining
149 篇 data analysis
135 篇 feature extracti...
101 篇 data models
93 篇 deep learning
92 篇 image color anal...
90 篇 task analysis
88 篇 training
81 篇 accuracy
79 篇 computational mo...
72 篇 analytical model...
71 篇 big data
66 篇 machine learning
62 篇 cameras
57 篇 predictive model...
57 篇 semantics
56 篇 convolutional ne...

机构

17 篇 center for space...
17 篇 nagoya universit...
17 篇 department of el...
16 篇 infn sezione di ...
16 篇 department of ph...
16 篇 quantum ict adva...
16 篇 department of ph...
16 篇 department of ph...
15 篇 vrvis res ctr au...
15 篇 institute of spa...
15 篇 faculty of scien...
15 篇 infn sezione di ...
15 篇 institute of par...
15 篇 national institu...
15 篇 via madonna del ...
15 篇 department of as...
15 篇 faculty of engin...
14 篇 univ konstanz co...
14 篇 waseda research ...
14 篇 jem utilization ...

作者

22 篇 asano k.
18 篇 schreck tobias
18 篇 cherry m.l.
18 篇 krizmanic j.f.
17 篇 tamura t.
17 篇 bruno a.
17 篇 kawakubo y.
17 篇 katayose y.
17 篇 binns w.r.
17 篇 castellini g.
17 篇 israel m.h.
17 篇 uchihori y.
17 篇 ebisawa k.
17 篇 yoshida a.
17 篇 bongi m.
17 篇 bigongiari g.
17 篇 shiomi a.
17 篇 collazuol g.
17 篇 nakahira s.
17 篇 ozawa s.

语言

4,725 篇 英文
234 篇 其他
161 篇 俄文
48 篇 中文
3 篇 乌克兰文
2 篇 德文
1 篇 法文
1 篇 葡萄牙文

检索条件"任意字段=Conference on Visual Data Exploration and Analysis V"

共 5168 条记录，以下是961-970 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：

Securing Intelligent vehicular Networks Using AI-Driven Federated Learning

Securing Intelligent Vehicular Networks Using AI-Driven Fede...

引用

International conference on Computer and Communications Technologies (ICCCT)

作者： N Shivaanivarsha J Swetha vL Ram Lashmi G S Yaswanth Rao Department of Electronics and Communication Engineering Sri Sairam Engineering College Chennai India

ISBN: (数字)9798331537579

ISBN: (纸本)9798331537586

analysis of Detour Index in Graph Joins and Special Graph Structures vehicular networks are crucial for modern transportation safety and efficiency. However, in adverse weather conditions such as fog, reduced visibility severely disrupts vehicle-to-vehicle (v2v) communication, increasing the risk of chain accidents. Traditional centralized approaches for managing vehicular communication suffer from high latency, limited scalability, and data privacy concerns, making them unsuitable for real-time decision-making in dynamic environments. To address these challenges, this project proposes a Federated Learning Framework for Securing vehicular Networks Using AI, enabling decentralized, privacy-preserving, and real-time threat detection in vehicular networks. The proposed system leverages Artificial Intelligence (AI) and Federated Learning (FL) to enhance situational awareness and predict collision risks. A deep learning-based object detection model, utilizing the YOLO algorithm, identifies obstacles, vehicles, and hazardous conditions in low-visibility environments. Edge detection techniques further improve visual clarity and detection accuracy. Federated Learning enables vehicles to collaboratively train AI models on local data without sharing raw information, ensuring data privacy and adaptability to real-world scenarios. Secure vehicle-to-vehicle (v2v) communication enhances decision-making speed, reducing latency in critical situations. By integrating AI-driven predictive analysis, federated learning, and decentralized data processing, this system significantly improves vehicular safety in challenging weather conditions. It ensures real-time hazard detection, reduces the likelihood of chain accidents, enhances data privacy, and scales effectively for large vehicular networks. This innovation marks a critical step toward intelligent, autonomous, and resilient transportation systems in smart cities.

关键词： YOLO data privacy Federated learning Image edge detection Decision making vehicular ad hoc networks Transportation Real-time systems Artificial intelligence Meteorology

来源：评论

学校读者我要写书评

暂无评论

Gesturemap: Supporting visual analytics and quantitative analysis of motion elicitation data by learning 2d embeddings 21

Gesturemap: Supporting visual analytics and quantitative ana...

引用

2021 CHI conference on Human Factors in Computing Systems: Making Waves, Combining Strengths, CHI 2021

作者： Dang, Hai Buschek, Daniel Research Group Hci + Ai Department of Computer Science University of Bayreuth Bayreuth Germany

ISBN: (纸本)9781450380966

This paper presents GestureMap, a visual analytics tool for gesture elicitation which directly visualises the space of gestures. Concretely, a variational Autoencoder embeds gestures recorded as 3D skeletons on an interactive 2D map. GestureMap further integrates three computational capabilities to connect exploration to quantitative measures: Leveraging DTW Barycenter Averaging (DBA), we compute average gestures to 1) represent gesture groups at a glance;2) compute a new consensus measure (variance around average gesture);and 3) cluster gestures with *** evaluate GestureMap and its concepts with eight experts and an in-depth analysis of published data. Our findings show how GestureMap facilitates exploring large datasets and helps researchers to gain a visual understanding of elicited gesture spaces. It further opens new directions, such as comparing elicitations across *** discuss implications for elicitation studies and research, and opportunities to extend our approach to additional tasks in gesture elicitation. © 2021 ACM.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Lip Reading with 3D Convolutional and Bidirectional LSTM Networks on the GRID Corpus

Lip Reading with 3D Convolutional and Bidirectional LSTM Net...

引用

Network, Multimedia and Information Technology (NMITCON) International conference on

作者： B S Prashanth M v Manoj Kumar B H Puneetha R Lohith v Darshan Gowda v Chandan H R Sneha Department of Information Science & Engineering Nitte Meenakshi Institute of Technology Bangalore Karnataka India Department of Computer Science and Business Systems Bapuji Institute of Engineering and Technology Davanagere Karnataka India

ISBN: (数字)9798350372892

ISBN: (纸本)9798350372908

In recent years, the application of artificial intelligence has revolutionized the field of lip reading by enabling the development of sophisticated models capable of accurately interpreting lip movements from video data. This work presents a novel deep learning approach to lip reading, focused on decoding spoken text from video sequences of lip movements. Traditional lip reading methods involve separate stages for visual feature design and prediction. The proposed system utilizes an endto-end deep learning model to directly map video frames to text transcriptions, leveraging 3D convolutional neural networks and bidirectional Long Short-Term Memory. By analyzing visual cues from lipmotions, the system can interpret speech, improving accessibility for individuals with hearing impairments and enabling communication in noisy environments. Compared to existing lip reading techniques, the deep learning model achieves superior performance on benchmark datasets, demonstrating its effectiveness in this challenging task. The model has achieved a character error rate of 1.54% and a word error rate of 7.96% on the best model.

关键词： Deep learning Solid modeling Adaptation models visualization Three-dimensional displays Attention mechanisms Error analysis Lips Feature extraction data models

来源：评论

学校读者我要写书评

暂无评论

A virtual 3D City Model for Urban Planning and Decision-Making - The East Jerusalem Case 22nd

A Virtual 3D City Model for Urban Planning and Decision-Maki...

引用

22nd International conference on Computational Science and its Applications (ICCSA)

作者： Fricke, Andreas Doellner, Juergen Asche, Hartmut Univ Potsdam Digital Engn Fac Hasso Plattner Inst Prof Dr Helmert Str 2-3 D-14482 Potsdam Germany

ISBN: (纸本)9783031104503;9783031104497

This contribution presents an approach for generating and modelling spatially referenced, multi-dimensional urban models from remote sensing data for regions where no reliable reference data are available. The focus is on a modular service-oriented process chain covering the entire process from data acquisition to effective web-based visualization, addressing raw data, preprocessing, management, spatial analyses, visualisation and applications. The use case, investigated in the framework of a EU-funded multidisciplinary R+D project, is the cityspace of East Jerusalem (about 190 about 190 sqkm). Due to the controversial geopolitical situation, usable and high-resolution reference data of the complex, granular urban fabric is unavailable. Hence very high-resolution stereo aerial images (571 pcs. 'a 10 cm GSD) were acquired and photogram-metrically processed to build a high-resolution 3D reference point cloud. Corresponding semantic data from various sources and household surveys (3,500 pcs.) specially conducted were integrated into the data and managed within a unified, fully-referenced 3D database (opensource). The resulting virtual urban 3D model includes functionalities for geospatial exploration and analysis, allowing spatio-temporal applications, such as land use/management, social/technical infrastructure, or tourism for documentation, information, education as well as decision-making. It addresses both the local civil society and, through specific functions, urban planners and decision makers. analysis and interaction functionalities are provided in a user-oriented and application-related framework, taking into account effective visualisation (cartographic and visual gestalt principles). The independent spatial reference of a multiscale grid is used for spatial analyses and visualisation purposes. The generic construction of the dedicated virtual cityspace allows for the transferability of results.

关键词： Service-oriented workflow Lack of reference data virtual multi-dimensional model

来源：评论

学校读者我要写书评

暂无评论

Fog Computing in IoT: Architecture and Applications

Fog Computing in IoT: Architecture and Applications

引用

International conference on Science Technology Engineering and Management (ICONSTEM)

作者： Anurag vijay Agrawal Shashi Gowridurga A Suresh Balakrishnan T Anwar Ahamed Shaikh Kalaipriya v Department of Electronics and Communication Engineering J. P. Institute of Engineering and Technology Meerut Uttar Pradesh India Department of Computer Application CCS University Meerut Department of Computer Science and Engineering Velammal Institute Of Technology Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Thandalam Tamil Nadu India Department of Computer Science and Engineering KoneruLakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of Computer Science and Engineering RMK College of Engineering and Technology Puduvoyal Tamil Nadu India

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

This exploration paper explores the paradigm of Fog Computing as a transformative armature in the Internet of effects(IoT) geography. Fog Computing represents a decentralized approach, positioning computing coffers closer to the edge of the network, thereby addressing quiescence, bandwidth, and data sequestration challenges current in traditional polycentric IoT infrastructures. The paper provides an in-depth analysis of Fog Computing's armature, expounding its crucial factors similar to fog bumps, middleware, and edge bias. likewise, it investigates the different operations of Fog Computing in IoT, ranging from realtime data analytics, effective resource operation, to enhanced security and sequestration measures. By bridging the gap between edge bias and centralised pall waiters, Fog Computing emerges as a vital result, fostering the elaboration of scalable, effective, and responsive IoT ecosystems. This exploration contributes precious perceptivity to the architectural nuances and practical operations, paving the way for the integration of Fog Computing as a foundation in the ever-expanding realm of IoT technologies.

关键词： Geography data analysis Ecosystems Mathematics Distance measurement Internet Security

来源：评论

学校读者我要写书评

暂无评论

THE SPATIAL data INFRASTRUCTURE OF AN URBAN DIGITAL TWIN IN THE BUILDING ENERGY DOMAIN USING OGC STANDARDS 17

THE SPATIAL DATA INFRASTRUCTURE OF AN URBAN DIGITAL TWIN IN ...

引用

17th 3D GeoInfo conference

作者： Santhanavanich, T. Padsala, R. Wurstle, P. Coors, v. Univ Appl Sci Stuttgart Ctr Geodesy & Geoinformat Schellingstr 24 D-70174 Stuttgart Germany

As the world has more urbanized, cities need to assess and manage their building energy performances in order to achieve energy-reduction goals. The urban digital twins (UDT) offer promising solutions to this demand by providing valuable insights with qualitative and quantitative information about the building environment. The urban building energy data is not only measured from the equipped sensor devices but can also be simulated based on the analysis software. In this research, we aim to explore the development of the spatial data infrastructure (SDI) for managing building energy in the UDT application by employing the Open Geospatial Consortium (OGC) standards which increases the data usability and efficiency. In our concept SDI, the big data in the UDT application is managed with the OGC specifications as follows: OGC SensorThings API (STA) for data with Spatio-temporal characteristics, OGC API 3D Geovolumes for 3D geospatial content delivery, OGC CityGML for virtual 3D city models, OGC API Features, Web Feature Service (WFS), and Web Map Service (WMS) for other 2D geospatial contents. This concept enables broad interoperability between multiple data layers and client applications. As a proof of concept, we developed the UDT application called with a highly visual and intuitive user interface using the proposed SDI concept as a part of the EnSysLE project in the study area of three regions in Germany: Ludwigsburg, Dithmarschen, and Ilm-Kreis. The proposed concept can be expanded to other UDT domains and on a larger scale in future work.

关键词： Urban Digital Twin Spatial data Infrastructure Building Energy Open Geospatial Consortium 3D City Model

来源：评论

学校读者我要写书评

暂无评论

data Augmentation for Multivariate Time Series Classification: An Experimental Study

Data Augmentation for Multivariate Time Series Classificatio...

引用

International conference on data Engineering Workshops

作者： Romain Ilbert Thai v. Hoang Zonghua Zhang Huawei Paris Research Center and LIPADE Paris France TH Consulting Paris France CRSC R&D Institute Group Co. Ltd. Beijing China

ISBN: (数字)9798350384031

ISBN: (纸本)9798350384048

Our study investigates the impact of data augmentation on the performance of multivariate time series models, focusing on datasets from the UCR archive. Despite the limited size of these datasets, we achieved classification accuracy improvements in 10 out of 13 datasets using the ROCKET and InceptionTime models. This highlights the essential role of sufficient data in training effective models, paralleling the advancements seen in computer vision. Our work delves into adapting and applying existing methods in innovative ways to the domain of multivariate time series classification. Our comprehensive exploration of these techniques sets a new standard for addressing data scarcity in time series analysis, emphasizing that diverse augmentation strategies are crucial for unlocking the potential of both traditional and deep learning models. Moreover, by meticulously analyzing and applying a variety of augmentation techniques, we demonstrate that strategic data enrichment can enhance model accuracy. This not only establishes a benchmark for future research in time series analysis but also underscores the importance of adopting varied augmentation approaches to improve model performance in the face of limited data availability.

关键词： Training Analytical models Rockets Computer vision Adaptation models Accuracy Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Deployment of Compressed MobileNet v3 on iMX RT 1060

Deployment of Compressed MobileNet V3 on iMX RT 1060

引用

IEEE International IOT, Electronics and Mechatronics conference (IEMTRONICS)

作者： Prasad, Kavyashree S. P. El-Sharkawy, Mohamed Purdue Sch Engn & Technol Dept Elect & Comp Engn IOT Collab IUPUI Indianapolis IN 46202 USA

ISBN: (纸本)9781665440677

Deep Neural Networks (DNN) are prominent in most applications today. From self-driving cars, sentiment analysis, surveillance systems, and robotics, they have been used extensively. Among DNNs, Convolutional Neural Networks (CNN) have achieved massive success in computer vision applications as the human visual system inspires their architecture. However, striving to achieve higher accuracies, CNN complexity, parameters, and layers were increased, which led to a drastic surge in their size, making their deployment challenging. Over the years, many researchers have proposed various techniques to alleviate this issue-one of them being Design Space exploration (DSE) to minimize size and computation with little compromise to accuracy. MobileNet v3 is one such architecture designed to achieve good accuracy while being mindful of resources. It produces an accuracy of 88.93% on CIFAR-10 with a size of 15.3MB. This paper further reduces its size to 2.3MB while boosting its accuracy to 89.13% using DSE techniques. It is then deployed into NXP's *** RT1060 Advanced Driver Assistance System (ADAS) platform.

关键词： MobileNet v3 Convolution Neural Networks Depthwise Pointwise Depthwise blocks Compressed MobileNet v3 CIFAR-10 Design space exploration Tensor Flow i.MX RT 1060

来源：评论

学校读者我要写书评

暂无评论

Privacy Protection of Wireless Sensor Networks from the Perspective of Big data 2

Privacy Protection of Wireless Sensor Networks from the Pers...

引用

2nd IEEE International conference on Advanced Technologies in Intelligent Control, Environment, Computing and Communication Engineering, ICATIECE 2022

作者： Mu, Wenjing Hefei Technology College Anhui Hefei230000 China

ISBN: (纸本)9781665493963

With the advent of the era of big data, the relevant technical standards of wireless sensor networks are becoming more and more perfect, so the information security of wireless sensor networks will also attract increasing attention. Because once the information secret of the wireless sensor network is leaked, it will bring huge damage to the entire Internet environment, and even cause the entire Internet to collapse. As a result, the privacy security problem in sensor networks has become an urgent problem to be solved. This paper aims to study the privacy protection of wireless sensor networks from the perspective of big data. Taking data privacy protection as an example, it proposes based on the analysis of the characteristics of wireless sensor networks, the application fields of wireless sensors, the classification of data aggregation technologies, and the CPDA scheme. An improved data privacy protection scheme is proposed, and simulation experiments are carried out on it. The experimental results show that the privacy of the method used in this paper is better than that of the CPDA method, and the probability of the lock being exposed increases, and its privacy is better than that of CPDA. © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of Classifiers in the Single-Trial vEP Classification of Human Cerebral Cortex 4

Comparative Analysis of Classifiers in the Single-Trial VEP ...

引用

4th International conference "Neurotechnologies and Neurointerfaces", CNN 2022

作者： Sergeeva, Maria Moiseeva, Ksenia Kuznetsov, Andrey Shabakaeva, Dilyara Petrova, Anastasia Khivintseva, Elena Research Institute of Neuroscience Fsbei He Samara State Medical University of the Ministry of Healthcare of Russia Samara Russia Department of Neurology and Neurosurgery Fsbei He Samara State Medical University of the Ministry of Healthcare of Russia Samara Russia

ISBN: (数字)9781665463294

ISBN: (纸本)9781665463294

EEG-based brain-computer interface (BCl) advancement necessitates the application of efficient signal processing methods. One of the methods relies on the use of a single visual evoked response (vEPs). This is a challenging endeavor, though, necessitating a mix of many signal processing algorithms, particularly blind source separation (Blind Source Separation), machine learning, and a number of others. The findings of comparing various classifiers in the job of identifying single vEPs are presented in the current study. The work made use of EEG data that was made public. © 2022 IEEE.

关键词： Brain computer interface

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500页 << < 93 94 95 96 97 98 99 100 101 102 > >>

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：