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

8,608 篇 会议
1,297 册 图书

馆藏范围

9,905 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

8,123 篇 工学
- 7,165 篇 计算机科学与技术...
- 1,833 篇 软件工程
- 1,501 篇 信息与通信工程
- 1,000 篇 控制科学与工程
- 561 篇 机械工程
- 491 篇 生物工程
- 355 篇 生物医学工程（可授...
- 183 篇 网络空间安全
- 181 篇 电气工程
- 162 篇 光学工程
- 149 篇 化学工程与技术
- 140 篇 安全科学与工程
- 137 篇 电子科学与技术（可...
- 131 篇 交通运输工程
- 129 篇 动力工程及工程热...
1,492 篇 理学
- 853 篇 数学
- 513 篇 生物学
- 256 篇 物理学
- 250 篇 统计学（可授理学、...
- 141 篇 系统科学
- 130 篇 化学
1,099 篇 教育学
- 1,099 篇 教育学
862 篇 管理学
- 544 篇 管理科学与工程(可...
- 369 篇 工商管理
- 300 篇 图书情报与档案管...
310 篇 医学
- 306 篇 临床医学
- 304 篇 基础医学(可授医学...
- 184 篇 药学(可授医学、理...
- 146 篇 公共卫生与预防医...
157 篇 法学
124 篇 经济学
- 124 篇 应用经济学
113 篇 农学
10 篇 军事学
1 篇 文学

主题

983 篇 computational in...
847 篇 artificial intel...
564 篇 machine learning
386 篇 deep learning
239 篇 communications e...
220 篇 data engineering
154 篇 cyber-physical s...
151 篇 professional com...
145 篇 internet of thin...
107 篇 blockchain
100 篇 big data
96 篇 iot
90 篇 higher education
87 篇 industry 4.0
87 篇 control, robotic...
84 篇 natural language...
83 篇 education
78 篇 covid-19
78 篇 signal, image an...
69 篇 object detection

机构

66 篇 global knowledge...
33 篇 faculty of scien...
23 篇 ukrainian engn p...
23 篇 iseg universidad...
22 篇 univ tecnol peru...
21 篇 inesc tec porto
18 篇 bauman moscow st...
18 篇 saga university ...
18 篇 univ esan lima p...
18 篇 univ salerno dep...
17 篇 moroccan society...
17 篇 univ politecn sa...
16 篇 cti global
16 篇 aristotle univ t...
16 篇 middlesex univer...
16 篇 department of in...
15 篇 silesian tech un...
14 篇 rabat morocco
14 篇 reshetnev siberi...
14 篇 kaliningrad stat...

作者

82 篇 amit joshi
53 篇 kohei arai
28 篇 janusz kacprzyk
27 篇 álvaro rocha
26 篇 ajith abraham
23 篇 rhalem wajih
22 篇 prajapat shaligr...
22 篇 leonard barolli
21 篇 abhishek swaroop
20 篇 ticona wilfredo
20 篇 kumar tarun
19 篇 anu bajaj
19 篇 nilanjan dey
18 篇 radek silhavy
18 篇 xin-she yang
17 篇 nugent chris
17 篇 valentina emilia...
15 篇 bahaaeddin alare...
15 篇 qjidaa hassan
14 篇 tomonobu senjyu

语言

7,572 篇 英文
2,315 篇 其他
18 篇 中文

检索条件"丛书名=Lecture Notes in Networks and Systems"

共 9905 条记录，以下是3521-3530 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：

Using Ensemble Convolutional Neural Network to Detect Deepfakes Using Periocular Data

Using Ensemble Convolutional Neural Network to Detect Deepfa...

引用

Intelligent systems Conference (IntelliSys)

作者： Johnson, David Yuan, Xiaohong Roy, Kaushik North Carolina Agr & Technol State Univ Greensboro NC 27411 USA

ISBN: (纸本)9783031477232;9783031477249

Deepfakes are manipulated or altered images, or video, that are created using deep learning models with high levels of photorealism. A popular method of deepfake creation is using convolutional neural networks (CNN). Deepfakes created using CNN comparatively show high qualities of realism, yet oftentimes leave artifacts and distortions in the generated media that can be detected using machine learning and deep learning algorithms. In recent years, there has been an influx of periocular image and video data because of the increased usage of face masks. By wearing masks, much of what is used for facial recognition is hidden, leaving only the periocular region visible to an observer. This loss of vital information leads to easier misidentification of media, allowing deepfakes to less likely be identified as fake. In this work, feature extraction methods, such as Scale-Invariant Feature Transform (SIFT), Histogram of Oriented Gradients (HOG), and CNN, are used to train an ensemble deep learning model to detect deepfakes in videos on a frame-by-frame level based on the periocular region. Our proposed model is able to distinguish original and manipulated images with averaged accuracy of 98.9 percent, which is an improvement to previous works by combining SIFT and HOG for deepfake detection in convolutional neural networks.

关键词： Deepfake detection CNN Deep neural network Computer vision Scale invariant feature transform Histogram of oriented gradients

来源：评论

学校读者我要写书评

暂无评论

Investigating the Robustness of Sliding Mode Control Applied to NPC Rectifier-Based Smart Transformer 4th

Investigating the Robustness of Sliding Mode Control Applied...

引用

4th International Conference on Digital Technologies and Applications (ICDTA)

作者： Helali, Hiba Khedher, Adel Univ Sousse LATIS Lab Adv Technol & Intelligent Syst Ecole Natl Ingenieurs Sousse Sousse 4023 Tunisia

ISBN: (纸本)9783031686498;9783031686504

In recent years, the Smart Transformer (ST), defined as an advanced type of power electronic transformer incorporating sophisticated communication and control systems, has received increasing attention in the power distribution system. Its power circuit is a combination of High Frequency (HF) transformers and power electronic converters. In power distribution systems, the three-stage ST topology comprising a medium voltage AC-DC power stage, a HF DC-DC power stage, and a low voltage DC-AC power stage, is selected as the most appropriate due to the availability of DC buses on the medium and low voltage sides. However, it has a low efficiency as multiple power converters are integrated. To enhance the performance of this topology, an ST model comprising a 3-level Neutral Point Clamp (NPC) rectifier, a dual active bridge power electronic converter, and a 3-phase inverter is proposed in this manuscript. To optimize the performance of the studied ST model, the sliding-mode controller is implemented at the NPC rectifier and the 3-phase inverter, while the soft-switching technology is used for the dual active bridge converter. Furthermore, several simulations under disturbed operating modes, including voltage flicker, overvoltage, voltage sag, and parametric variations, are performed to demonstrate the good performance of the ST model under study and the great robustness of the proposed control strategy.

关键词： Smart transformer neutral point clamp rectifier 3-phase inverter dual active bridge converter sliding mode controller

来源：评论

学校读者我要写书评

暂无评论

Emails Classification: Comparing Statistics, Machine-Learning, Deep-Learning, and ChatGPT Prompting Techniques 9th

Emails Classification: Comparing Statistics, Machine-Learnin...

引用

9th International Congress on Information and Communication Technology (ICICT)

作者： Turon, Pablo Cuadros, Montse Grande, Alicia Lopez, David Basque Res & Technol Alliance BRTA Vicomtech Fdn Mikeletegi Pasealekua 57 Donostia San Sebastian 20009 Spain LIS Data Solut Santander Spain

ISBN: (纸本)9789819732883;9789819732890

The automatic classification of emails in a real scenario is very helpful for administration purposes and focuses human attention on solving tasks instead of organizing them. This paper presents a study of the applicability of a wide variety of approaches to the problem of this automatic email classification. For this purpose, we have conducted a wide set of experiments using traditional classification methods such as Support Vector Machines (SVM), distinct Large Language Models (LLMs), and prompting techniques applied to ChatGPT to tackle the classification problem. Thus, a set of labeled email conversations from LIS DATA Solutions have been studied, pre-processed, and prepared in order to be used by the different classification techniques. The results show that, surprisingly, traditional approaches beat more robust solutions for this task.

关键词： Text classification LLMS NLP ChatGPT IA

来源：评论

学校读者我要写书评

暂无评论

Development of an Artificial Intelligence-Based Application to Predict Air Quality and Environmental Comfort from Design Parameters in New Buildings 9th

Development of an Artificial Intelligence-Based Application ...

引用

9th International Congress on Information and Communication Technology (ICICT)

作者： Moreno, Silvia Villarreal, Reynaldo Saavedra, John Vega-Sampayo, Yolanda Chamorro-Solano, Sindy Espejo, Carlos A. Rivera, Jaidid Daza, Yaneth Univ Simon Bolivar Barranquilla Colombia Bioteckta SAS Bogota Colombia SENA Bogota Colombia

ISBN: (纸本)9789819733019;9789819733026

In this paper, the development of an AI-based application to predict levels of environmental comfort and air quality in new buildings from the design stage is presented. The objective of this approach is to improve construction quality and reduce their environmental impact. This project uses as knowledge base the experience of the enterprise Bioteckta, a bioclimatics consulting firm, and is funded and supported by the Colombian Ministry of Science (MINCIENCIAS) and the National Learning Service (SENA). The research is divided into three key stages: predictive model optimization, software development, and validation. As a result, a predictive model and a Web application were obtained. A model was generated using 18 design parameters as input variables. In the initial model assessment, an accuracy of 91% was obtained, which then was improved to 100% with machine learning techniques (decision trees). This model was then integrated into a practical and user-friendly Web platform, and a coherence with the base model of 99.7% was obtained, with only one case getting a different result from the optimized base model. These results indicate that the model and Web platform are reliable and can be used to predict environmental comfort in new buildings in a simple and practical way.

关键词： Bioclimatics Artificial intelligence Machine learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fuzzy Controller for Ballbot with Complex Uncertainties 7th

Adaptive Fuzzy Controller for Ballbot with Complex Uncertain...

引用

7th International Conference on Green Technology and Sustainable Development

作者： Van-Truong Nguyen Dai-Nhan Duong Hong-Son Nguyen Tien-Dung Hoang Tuan-Linh Nguyen Hanoi Univ Ind Sch Mech & Automot Engn Hanoi Vietnam Hanoi Univ Ind Dept Sci & Technol Hanoi Vietnam

ISBN: (纸本)9783031761966;9783031761973

The present study introduces an adaptive fuzzy controller designed specifically for a ballbot system that incorporates uncertainties. The suggested methodology involves the construction of an adaptive fuzzy controller that aims to acquire the desirable characteristics of rapid response, finite-time convergence, and avoidance of singularities. The adaptive fuzzy controller's parameters are continuously changed in order to effectively mitigate uncertainty and decrease errors. The Lyapunov synthesis method ensures the stability of the ballbot system. Ultimately, a series of simulations are performed in order to showcase the efficacy of the adaptive fuzzy controller in comparison to the fuzzy logic controller.

关键词： Adaptive fuzzy control Lyapunov ballbot uncertainty

来源：评论

学校读者我要写书评

暂无评论

An Anomaly Detection Framework for IIoT-Based Smart Farming systems

An Anomaly Detection Framework for IIoT-Based Smart Farming ...

引用

Computing Conference

作者： Noor, Muaaz Sithungu, Siphesihle Lebea, Khutso Univ Johannesburg ZA-2006 Johannesburg South Africa

ISBN: (纸本)9783031622755;9783031622731;9783031622724

The advent of Industrial Internet of Things (IIoT) technologies has revolutionized agriculture, ushering in a new era of precision and efficiency. Enabled by the IIoT, intelligent farming systems possess the capacity to greatly enhance crop productivity, preserve resources, and guarantee the health of crops and livestock. However, to harness the full potential of these systems, real-time anomaly detection is crucial, enabling farmers to rectify deviations from the norm and optimize their agricultural practices. This paper introduces a theoretical anomaly detection framework tailored specifically for IIoT in agriculture, with a particular focus on smart farming and irrigation systems. In order to address the unique challenges faced within the agricultural domain;this paper investigates the architectural elements and methodology of an "Anomaly Detection Framework for Smart Farming systems Using IIoT". The paper then explores the transformative impact of IIoT on agriculture, using real-life examples and literature to demonstrate its revolutionary influence. We evaluate the framework in multiple dimensions, including anomaly detection performance, incident response effectiveness, adaptability to changing conditions, scalability, and cost-efficiency. Effective implementation in real-world agricultural contexts necessitates collaboration with stakeholders, extensive training, continual monitoring, and continuous development based on feedback and evolving agricultural practices. This paper presents a theoretical Anomaly Detection Framework for IIoT in Agriculture, offering a valuable theoretical tool for addressing agricultural challenges and promoting sustainability in farming operations. It emphasizes the transformational potential of IIoT in modern agriculture, paving the way for data-driven decision-making and the advancement of smart farming practices.

关键词： IIoT (Industrial Internet of Things) Agriculture Smart farming Anomaly detection framework

来源：评论

学校读者我要写书评

暂无评论

Particle Swarm Optimization for Tuning PID Parameters to Control General systems

Particle Swarm Optimization for Tuning PID Parameters to Con...

引用

Intelligent systems Conference

作者： Gruber, Lukas Buchi, Roland Zurich Univ Appl Sci Sch Engn Winterthur Switzerland

ISBN: (纸本)9783031664304;9783031664311

The PID controller is a control system that is widely used in control engineering. PID stands for Proportional-Integral-Derivative, representing the three components of the controller. The controller can be used for various systems, from temperature control in heating devices to speed regulation of motors in robotics. The art lies in selecting the three parameters of the PID controller so that the system shows the desired control behaviour. This work investigates how Particle Swarm Optimization (PSO), an algorithm from the field of artificial intelligence, is capable of efficiently finding suitable control parameters for a PT3 system and a 2nd order-overshooting system. An analysis of the parameters found using PSO was conducted, which were assessed according to the Integrated Time Absolute Error (ITAE) criterion. These parameters are compared with those from previous studies to validate the reliability of PSO. For both systems examined, 300 simulations were carried out, the results of the simulations serve as a database for evaluation. The approach includes a detailed classification of the studied systems, an analysis of their transfer functions, and a discussion of the computational aspects of the ITAE criterion. Additionally, the operation of the PSO algorithm is explained. It discusses how the PSO algorithm was implemented and how the results were stored and evaluated. The evaluations show that PSO can find very precise parameters in a short time. The found parameters led to better control of the studied systems compared with traditional methods.

关键词： PID PSO ITAE 2nd order-overshooting systems PT3 systems

来源：评论

学校读者我要写书评

暂无评论

A Comparative Assessment of Wrappers and Filters for Detecting Cyber Intrusions 12th

A Comparative Assessment of Wrappers and Filters for Detecti...

引用

12th World Conference on Information systems and Technologies (WorldCIST)

作者： Zouhri, Houssam Idri, Ali Mohammed VI Polytech Univ Ben Guerir Morocco Mohammed V Univ Software Project Management Res Team ENSIAS Rabat Morocco

ISBN: (纸本)9783031602207;9783031602214

The high number of features in network traffic data might overload intrusion detection systems (IDSs) and resulted in overfitting. Furthermore, duplicated, and unnecessary features may restrict an IDS's ability to learn and infer. Generally, feature selection methods can alleviate this issue. It is a data preprocessing step that can be applied before the classification phase and aims to improve classifier performance and interpretability by selecting only a few highly informative features. The present study aims at assessing the effects of four filters (Consistency-based subset selection, Pearson correlation, Double Input Symmetric Relevance and Chi2);and four wrappers (Boruta, BorutaShap, Recursive Feature Elimination, and Genetic Algorithm) on the classification effectiveness of four models: Random Forest, Multilayer Perceptron, eXtreme Gradient Boosting and Support Vector Machines using CICIDS2018 dataset. The findings suggested that combining ensemble models with RFE and CON techniques can effectively reduce the number of attributes without impacting the outcomes of classification.

关键词： Intrusion detection systems Feature selection Filters Wrappers

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Forensic Occupancy Detection in IoT Environments 12th

Machine Learning for Forensic Occupancy Detection in IoT Env...

引用

12th World Conference on Information systems and Technologies (WorldCIST)

作者： Deconto, Guilherme Dall'Agnol Zorzo, Avelino Francisco Dalalana, Daniel Bertoglio Oliveira, Edson, Jr. Lunardi, Roben Castagna Pontificia Univ Catolica Rio Grande do Sul Porto Alegre RS Brazil Univ Estadual Maringa Maringa Parana Brazil Fed Inst Educ Sci & Technol Rio Grande do Sul Porto Alegre RS Brazil

ISBN: (纸本)9783031602146;9783031602153

The adoption of the Internet of Things (IoT) has brought many advantages, but it also presents challenges for the field of Digital Forensics. The heterogeneity of the data directly affects the investigative process in scenarios involving IoT applications. Through the analysis of a comprehensive and heterogeneous dataset collected from IoT devices, this study analyzes the use of machine learning algorithms to detect specific patterns to estimate the number of people in physical environments involving IoT devices. In this work, we discuss the use of Machine Learning approaches to enhance criminal investigations based on data collected from IoT environments. The experimental evaluation not only showcases the potential enhancement of Digital Forensics through the utilization of IoT data but also serves to emphasize the effectiveness of machine learning-based approaches in these environments.

关键词： Internet of Things Digital Forensics Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Scratch-Based Exergame-Educational Approach in Teaching the Course "Physical Education" for IT-Specialties 21st

Scratch-Based Exergame-Educational Approach in Teaching the ...

引用

21st International Conference on Smart Technologies and Education (STE) on Smart Technologies for a Sustainable Future

作者： Blazhko, Oleksandr Podhorna, Viktoriia Kokotieieva, Anastasiia Bashavets, Nataliia Odessa Polytech Natl Univ Dept Informat Syst Odesa Ukraine Odessa Polytech Natl Univ Dept Phys Educ & Sports Odesa Ukraine South Ukrainian Natl Pedag Univ Odesa Ukraine

ISBN: (纸本)9783031618901;9783031618918

I's proposed the approach of computer game control of human movements in sport computer games in order to increase the level of physical activity of stu-dents in online classes, which takes into account the initial knowledge of the spe-cialized disciplines of the curriculum. The approach is based on an open-access repository of computer programs created in the Scratch-based block language (47 games for 28 summer sports, 16 games for 10 winter sports), Scratch programs for human motion recognition based on the PoseNet neural network, which allow changing the principle of controlling game characters through the keyboard and mouse. The approach uses static gestures - unchanging position of the human body with fixed relationships of its various parts to each other, dynamic gesture - sequential transition in time between two static gestures and Scratch-block descriptions of recognition of gestures.

关键词： ExerGame motion recognition Scratch

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 << < 349 350 351 352 353 354 355 356 357 358 > >>

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：