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

13,295 篇 会议
487 篇 期刊文献
182 册 图书
5 篇 学位论文

馆藏范围

13,969 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

8,285 篇 工学
- 6,655 篇 计算机科学与技术...
- 4,099 篇 软件工程
- 1,482 篇 信息与通信工程
- 1,090 篇 生物工程
- 937 篇 电气工程
- 878 篇 控制科学与工程
- 834 篇 生物医学工程（可授...
- 547 篇 机械工程
- 531 篇 化学工程与技术
- 470 篇 力学（可授工学、理...
- 446 篇 光学工程
- 427 篇 电子科学与技术（可...
- 396 篇 动力工程及工程热...
- 391 篇 材料科学与工程（可...
- 214 篇 土木工程
- 214 篇 安全科学与工程
4,306 篇 理学
- 2,495 篇 数学
- 1,173 篇 生物学
- 1,107 篇 物理学
- 665 篇 统计学（可授理学、...
- 533 篇 化学
- 402 篇 系统科学
1,561 篇 管理学
- 848 篇 图书情报与档案管...
- 782 篇 管理科学与工程(可...
- 456 篇 工商管理
676 篇 医学
- 578 篇 临床医学
- 527 篇 基础医学(可授医学...
- 331 篇 药学(可授医学、理...
310 篇 法学
- 266 篇 社会学
237 篇 教育学
- 231 篇 教育学
168 篇 经济学
128 篇 农学
100 篇 文学
15 篇 军事学
7 篇 艺术学
1 篇 哲学
1 篇 历史学

主题

2,426 篇 computational mo...
555 篇 training
490 篇 task analysis
450 篇 machine learning
421 篇 artificial intel...
418 篇 feature extracti...
403 篇 data models
395 篇 computational in...
382 篇 predictive model...
363 篇 deep learning
340 篇 neural networks
303 篇 scientific compu...
288 篇 optimization
244 篇 analytical model...
237 篇 computational co...
234 篇 computational fl...
234 篇 computer archite...
232 篇 computational ef...
219 篇 semantics
214 篇 mathematical mod...

机构

48 篇 computer science...
36 篇 school of artifi...
35 篇 university of ch...
34 篇 university of sc...
33 篇 univ chinese aca...
28 篇 faculty of infor...
24 篇 tsinghua univers...
22 篇 university of el...
22 篇 peng cheng labor...
21 篇 college of intel...
20 篇 department of co...
19 篇 school of comput...
19 篇 school of comput...
19 篇 college of compu...
19 篇 school of comput...
19 篇 harbin institute...
18 篇 school of automa...
18 篇 department of co...
18 篇 beijing key labo...
17 篇 department of co...

作者

21 篇 sun maosong
21 篇 liu zhiyuan
19 篇 mahmoud mohammed
18 篇 huang minlie
17 篇 wang lei
17 篇 chen yubo
16 篇 haungs a.
15 篇 fritz a.
15 篇 liu yang
14 篇 fürst p.
14 篇 bourbeau e.
14 篇 halve l.
14 篇 gonzalez j.g.
14 篇 iglesias andres
14 篇 de clercq c.
14 篇 böttcher j.
14 篇 ha minh m.
14 篇 günther c.
14 篇 glauch t.
14 篇 delaunay j.j.

语言

13,228 篇 英文
681 篇 其他
74 篇 中文
1 篇 俄文

检索条件"任意字段=2020 International Conference on Computational Science and Computational Intelligence, CSCI 2020"

共 13969 条记录，以下是31-40 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-Inspired Visual Odometry: Balancing Speed and Interpretability through a System of Systems Approach

Brain-Inspired Visual Odometry: Balancing Speed and Interpre...

引用

international conference on computational science and computational intelligence (csci)

作者： Tabrizi, Habib Boloorchi Crick, Christopher Oklahoma State Univ Stillwater OK 74078 USA

ISBN: (纸本)9798350361513;9798350372304

In this study, we address the critical challenge of balancing speed and accuracy while maintaining interpretabfity in visual odometry (VO) systems, a pivotal aspect in the field of autonomous navigation and robotics. Traditional VO systems often face a trade-off between computational speed and the precision of pose estimation. To tackle this issue, we introduce an innovative system that synergistically combines traditional VO methods with a specifically tailored fully connected network (FCN). Our system is unique in its approach to handle each degree of freedom independently within the FCN, placing a strong emphasis on causal inference to enhance interpretability. This allows for a detailed and accurate assessment of relative pose error (RPE) across various degrees of freedom, providing a more comprehensive understanding of parameter variations and movement dynamics in different environments. Notably, our system demonstrates a remarkable improvement in processing speed without compromising accuracy. In certain scenarios, it achieves up to a 5% reduction in Root Mean Square Error (RMSE), showcasing its ability to effectively bridge the gap between speed and accuracy that has long been a limitation in VO research. This advancement represents a significant step forward in developing more efficient and reliable VO systems, with wide-ranging applications in real-time navigation and robotic systems.

关键词： Explainable Artificial intelligence Interpretable Visual Odometry Visual Odometry

来源：评论

学校读者我要写书评

暂无评论

Tokenization of Digital Assets for Ethical and Equitable Model Training in an AI-based Proctoring Application

Tokenization of Digital Assets for Ethical and Equitable Mod...

引用

international conference on computational science and computational intelligence (csci)

作者： Boscovic, Dragan Khullar, Kashish Oguri, Pooja Bharathi Pandey, Pratyush Eghbali, Mandi Olsen, Mike Dordevic, Milan Arizona State Univ Sch Comp & Augmented Intelligence Fulton Sch Engn Tempe AZ 85004 USA Arizona State Univ Econ Dept WP Carey Business Sch Tempe AZ USA Proctorio Inc Scottsdale AZ USA

ISBN: (纸本)9798350361513;9798350372304

The COVID-19 pandemic catalyzed a significant shift in education towards online learning and remote examination processes. AI-based proctoring tools emerged to maintain exam integrity but raised ethical, bias, and privacy concerns. This paper proposes a blockchain-driven architecture to address these issues. Our approach incentivizes genuine data collection through blockchainpowered crowdsourcing, rewarding contributors with crypto tokens. It ensures decentralization by using a voting system to validate labels given by annotators for user images, with winners also receiving tokens. Emphasizing user privacy, our model enables users to retract image access, triggering server image removal and model retraining. To enhance accessibility, our trained models are available as a service through layered APIs accessed via crypto tokens. This proposed architecture aims to reconcile the challenges of online proctoring while prioritizing ethics, fairness, data reliability, and inclusivity.

关键词： proctoring ethics academic integrity machine learning model training crowdsourcing blockchain tokenomics model as a service

来源：评论

学校读者我要写书评

暂无评论

Generative & Responsible AI LLMs use in Differential Governance

Generative & Responsible AI LLMs use in Differential Governa...

引用

international conference on computational science and computational intelligence (csci)

作者： Mhammad, Atif Farid Agarwal, Ram Columbo, Tony Vigorito, Jess Global Technol Solut Alta Loma CA 91701 USA

ISBN: (纸本)9798350361513;9798350372304

Generative AI techniques are widely used to extract valuable insights from data, which can be used to expand into new markets or save money by changing existing structures. However, there is a lack of innovation in the compliance area of financial transactional platforms, which can lead to money laundering. Standard Generative AI algorithms, specifically the use of Responsible AI within the realm of LLMs, have the potential to build robust detection systems to apply differential governance to capture money laundering transactions. Additionally, refined AI predictions can be used to improve the response time of compliance users in deciding whether a transaction is suspicious. This paper focuses on using Generative AI algorithms, anomaly detection, and network analysis to detect suspicious transactions and improve the overall risk rating assessment using hypothetical dataset. In this research we have proposed differential governance, oversight, controls and procedures incorporating generative AI, starting with differential privacy assisting financial institutions in detecting fraud while still upholding customer privacy rights and regulatory obligations. But it requires deliberate effort to implement it responsibly.

关键词： financial intelligence responsible AI network analysis anomaly detection fraud prevention

来源：评论

学校读者我要写书评

暂无评论

Steganalysis of Medical Radiographs For Radiographic Machine Identification

Steganalysis of Medical Radiographs For Radiographic Machine...

引用

international conference on computational science and computational intelligence (csci)

作者： Mohammadi, Farid Ghareh Sebro, Rotmie Mayo Clin Dept Radiol Ctr Augmented Intelligence Jacksonville FL 32224 USA

ISBN: (纸本)9798350361513;9798350372304

Large online databases with radiographs from different institutions are being increasingly used in biomedical research consortiums. Radiographs from one machine at a single site may he suboptimal or corrupted. Steganalysis can he used to quality assurance of radiographs. Here, we use a deep learning framework 14 source identification of radiographs by predicting the exact radiographic machine (manufacturer and model) using a single rich model. A convolutional neural network architecture is applied to extract high-level contentfree features, and three fully connected neural network layers are used to predict the radiographic machine source of the radiographs. Potential change in pixel information in medical images can be detected using steganalysis. Steganalysis contributes to maintaining trust in medical systems and ensures the accurate diagnosis and treatment of patients. Patients with cervical (n=2028 patients;3905 radiographs) and chest (n=1499 patients;2725 radiographs) radiographs obtained at Mayo Clinic from 01/01/2010 to 12/31/2021 were analyzed. Data was randomly split by patient into training/validation (n=80%) and test (n=20%) datasets respectively. The accuracy in the test dataset was 99.50% (AUC=99.72%) and 96.86% (AUC=98.23%) for cervical and chest radiographic machine identification respectively.

关键词： Deep Learning Machine Learning Radiographs Medical Imaging Source Identification

来源：评论

学校读者我要写书评

暂无评论

THE RISKS AND VULNERABILITIES OF ARTIFICIAL intelligence USAGE IN INFORMATION SECURITY

THE RISKS AND VULNERABILITIES OF ARTIFICIAL INTELLIGENCE USA...

引用

international conference on computational science and computational intelligence (csci)

作者： Mahmoud, Mohammed Univ Jamestown Dept Comp Sci Jamestown ND 58405 USA

ISBN: (数字)9798350361513

ISBN: (纸本)9798350361513;9798350372304

In this paper we will discuss Artificial intelligence, as well as the advantages and challenges it presents with information security. Artificial intelligence is a transformative force that impacts our daily lives in various forms and technologies. This paper looks at the complex relationship between Artificial intelligence and information systems security. The first section explores the fundamental concepts of AI and its unassuming integration into our everyday lives, shedding light on the ever-present existence of AI-based solutions. By inspecting the differences between risks and vulnerabilities, the paper makes clear the importance of separating between these terms and proceeds to identify potential threats to server security. The remaining part of the paper investigates data mining as an integral aspect of AI's functionality, emphasizing the importance of robust security measures to maintain security against data breaches. Furthermore, it reveals the diverse attack routes targeting AI systems and highlights the pivotal role of security in mitigating manipulation and attacks. By offering insights into strategies for avoiding vulnerabilities while harnessing the power of AI, this paper emphasizes the paramount importance of privacy in the context of At-driven data collection and utilization. Finally, it presents guidelines for businesses to implement monitoring procedures that safeguard against risks, ensuring that AI technologies remain a benefit rather than a liability in the realm of information security. This comprehensive exploration underscores the pivotal role of AI in modern society and the imperative to secure its applications for the benefit of all.

关键词： Artificial intelligence (AI) information security risks vulnerabilities threats security cybersecurity data mining data breaches attack privacy

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence - Enabled Deep Learning Model for Diabetes Prediction Using Deep Belief Network with Bayesian Optimization

Artificial Intelligence - Enabled Deep Learning Model for Di...

引用

international conference on computational science and computational intelligence (csci)

作者： Akinsola, Jide Ebenezer Taiwo Ajagbe, Sunday Adeola Olajubu, Emmanuel Ajayi Lawal, Azeezat Oluwayemisi Aderounmu, Ganiyu Adesola Adigun, Matthew Olusegun First Tech Univ Dept Comp Sci Ibadan Nigeria First Tech Univ Dept Comp & Ind Engn Ibadan Nigeria Obafemi Awolowo Univ Dept Comp Sci & Engn Ife Nigeria Univ Zululand Dept Comp Sci Kwa Dlangezwa South Africa

ISBN: (纸本)9798350361513;9798350372304

Diabetes is one of the major health issues that affect more than 10.5 percent of the adult population across the globe. This study applied deep learning techniques of deep belief network (DBN), long short-term memory (LSTM) and recurrent neural network (RNN) with Bayesian optimization on a diabetes dataset to forecast patients with diabetes. A splitting ratio of 80:20 was used for model performance evaluation. DBN model had the lowest mean absolute error in comparison to the other two models with 95.79% accuracy, 0.0331 mean absolute error, 0.0709 mean squared error, 0.1204 loss function, 0.9458 precision, 0.1819 RAISE, and 0.5307 recall. The results from this study validate that the DBN model can be used on a larger dataset to reduce variance and model overfitting, thereby achieving a better accuracy score.

关键词： bayesian optimization deep belief network deep learning diabetes recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

SOCIALBERT a Transformer based Model Used for Detection of Social Engineering Characteristics

SOCIALBERT a Transformer based Model Used for Detection of S...

引用

international conference on computational science and computational intelligence (csci)

作者： Abobor, Michael Josyula, Darsana P. Bowie State Univ Dept Comp Sci Bowie MD 20715 USA

ISBN: (纸本)9798350361513;9798350372304

Security threats have escalated in recent years based on social engineering attacks. In these attacks, bad actors target organizations, businesses, and private individuals by luring them into clicking on a link either in a text message, email message, or a document. Social Engineering is the act of using psychological tricks to gain the trust of humans leading to the release of sensitive information which can be used for various nefarious activities by the bad actors. These types of attacks have proven to be the genesis of most of the malicious attacks launched against both physical and virtual IT systems by tricking humans into allowing these attacks. It is scarce to find widely established machine learning techniques specifically designed for identifying social engineering features in messages. To help tackle this problem, this research paper aims to explore the detection of social engineering tactics in text messages by fine-tuning a pre-trained Machine Learning Transformer model, BERT to produce our model called SOCIALBERT. SOCIALBERT (Social Engineering Detection Bert) achieves a 97.55 percent accuracy as compared to DistilBERT, Bert-Base multilingual, and Naive Bayes Models which achieved 55.40 percent, 60.23 percent, and 95.58 percent accuracies respectfully.

关键词： Transformer Artificial intelligence Machine Learning Social Engineering Cyberattack

来源：评论

学校读者我要写书评

暂无评论

An evaluation of tiered machine learning framework to predict science achievement among Singapore students

An evaluation of tiered machine learning framework to predic...

引用

international conference on computational science and computational intelligence (csci)

作者： Nguyen, Khanh Linh Mayberry, Ta'Rhonda Lui, Yang Khine, Myint Swe Pallipuram, Vivek K. Univ Pacific Sch Engn & Comp Sci Stockton CA 95211 USA Shanghai Maritime Univ Shanghai Peoples R China Curtin Univ Bentley WA Australia

ISBN: (纸本)9798350361513;9798350372304

There is a significant interest in the education community to use machine learning (ML) techniques to model students' achievement as a function of non-cognitive factors. In this research, we present a tiered machine learning framework designed for educators to apply ML and classify student achievement.. The framework comprises three components including SMOTE balancer, a council of selectors, and a suite of learners. The SMOTE balancer removes any data imbalances, thereby reducing ML bias. The council of selectors collectively voles to elect the top three features for effective model training. The suite of classifiers comprises popular ML models that train using the selected features. The suite of classifiers also includes a combiner, which uses ML performance metrics and users' analysis preferences to select an effective model for classification. Using the Trends in international Mathematics and science study (TIMSS) data on Singapore students, we evaluate the framework and achieve up-to-par prediction results, despite the low correlation between the dependent variable and features. Our goal is to offer educators an easy-to-use ML framework that assists with the analysis of large education data.

关键词： machine learning classification information mining education data analysis education multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Realtime Sign Language Recognition Using Computer Vision and AI

Realtime Sign Language Recognition Using Computer Vision and...

引用

international conference on computational science and computational intelligence (csci)

作者： Serrano, Gabriel Kwak, Daehan Kean Univ Dept Comp Sci & Technol Union NJ 07083 USA

ISBN: (纸本)9798350361513;9798350372304

Promoting inclusive communication is essential and sign language plays a crucial role in achieving this goal. In this research, a system is developed capable of making it easier for those who primarily communicate through sign language to interact with those who are unable or may not be knowledgeable in the language. This has the potential to help bridge the communication gap between those who arc fluent in sign language, and those who may be struggling to learn or are not knowledgeable. In its current state, our system is capable of recognizing two forms of sign language, namely: American Sign Language and British Sign Language. The system also is capable of performing facial expression analysis to account for nonverbal inflections expressed by the user. These tasks are accomplished by making use of computer vision provided by the OpenCV Python library. It also uses various machine learning models and the MediaPipe library. We explore two approaches for sign language recognition: contour-based recognition and landmark-based recognition. Additionally, facial landmarks for facial expression analysis are investigated which can be used to detect expressions and inflections from a user's face alone. The next steps of this research will consist of working with more complex words and phrases and investigating gesture recognition.

关键词： Sign Language Facial Expression Image Recognition Computer Vision Artificial intelligence (Al) Machine Learning (ML)

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence in Cybersecurity: A Dual-Nature Technology

Artificial Intelligence in Cybersecurity: A Dual-Nature Tech...

引用

international conference on computational science and computational intelligence (csci)

作者： Yarali, Abdulrahman Rodocker, Evan Gora, Christie Murray State Univ Sch Engn Murray KY 42071 USA Univ Cumberlands Comp Informat Scinece Williamsburg VA USA

ISBN: (纸本)9798350361513;9798350372304

Artificial intelligence (AI) is undoubtedly one of the most promising information age developments. AI has emerged as a transformative technology, reshaping various sectors, including cybersecurity. As digital threats evolve in complexity and scale with a higher potential for vulnerabilities, traditional cybersecurity measures often need help to keep pace. With its ability to learn and adapt, AI offers promising solutions to these challenges. Traditional cybersecurity measures, which often rely on predefined rules and signatures, must be equipped to manage novel threats. AI presents a promising alternative with its ability to learn from data and adapt to the latest information. However, integrating AI into cybersecurity has its challenges when cyber adversaries use it as an AI-powered Cyber-attack tool to their advantage in a threat landscape that is constantly evolving. This paper discusses the future trends in self-learning AI technology to combat novel threats and new attack techniques. The paper reviews how cybersecurity frameworks can mitigate the exploitation of AI systems, making them safe and reliable by taking precautions and suitability-testing steps before implementation. We will draw on various sources, providing a balanced and in-depth perspective on the rise of AI as a dual-nature technology and its applications and challenges in the ever-expanding attack surface in cyberspace. The goal is not only to inform but also to provoke thought and discussion on the implications of AI for the future of cybersecurity.

关键词： Artificial intelligence Cybersecurity Technologies Applications Policy Regulations

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 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：