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

3,626 篇 会议
1,997 篇 期刊文献
68 册 图书

馆藏范围

5,691 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,485 篇 工学
- 2,273 篇 计算机科学与技术...
- 1,837 篇 软件工程
- 739 篇 信息与通信工程
- 595 篇 控制科学与工程
- 478 篇 电气工程
- 444 篇 电子科学与技术（可...
- 397 篇 生物工程
- 324 篇 机械工程
- 283 篇 生物医学工程（可授...
- 245 篇 光学工程
- 218 篇 动力工程及工程热...
- 201 篇 化学工程与技术
- 194 篇 土木工程
- 193 篇 仪器科学与技术
- 170 篇 材料科学与工程（可...
- 147 篇 建筑学
- 147 篇 交通运输工程
1,880 篇 理学
- 884 篇 数学
- 552 篇 物理学
- 451 篇 生物学
- 239 篇 统计学（可授理学、...
- 223 篇 系统科学
- 182 篇 化学
877 篇 管理学
- 622 篇 管理科学与工程(可...
- 328 篇 工商管理
- 289 篇 图书情报与档案管...
302 篇 医学
- 247 篇 临床医学
- 224 篇 基础医学(可授医学...
- 136 篇 公共卫生与预防医...
175 篇 法学
- 157 篇 社会学
118 篇 经济学
102 篇 教育学
59 篇 农学
13 篇 艺术学
8 篇 文学
7 篇 军事学
1 篇 哲学
1 篇 历史学

主题

162 篇 accuracy
127 篇 deep learning
111 篇 machine learning
102 篇 real-time system...
99 篇 computer science
96 篇 computational mo...
93 篇 feature extracti...
91 篇 artificial intel...
89 篇 predictive model...
86 篇 training
76 篇 internet of thin...
76 篇 optimization
75 篇 design engineeri...
74 篇 convolutional ne...
69 篇 computer archite...
68 篇 visualization
66 篇 costs
64 篇 support vector m...
57 篇 neural networks
57 篇 testing

机构

100 篇 school of comput...
74 篇 singapore univer...
56 篇 information syst...
52 篇 the pillar of in...
49 篇 the school of co...
48 篇 pillar of inform...
43 篇 the school of au...
35 篇 school of automa...
31 篇 department of co...
29 篇 shenzhen city ke...
27 篇 school of innova...
26 篇 college of compu...
25 篇 school of comput...
22 篇 college of compu...
22 篇 school of system...
20 篇 information syst...
19 篇 school of comput...
17 篇 college of desig...
16 篇 department of co...
15 篇 school of comput...

作者

120 篇 niyato dusit
110 篇 xiong zehui
57 篇 kang jiawen
40 篇 zehui xiong
38 篇 yuen chau
34 篇 dusit niyato
34 篇 du hongyang
30 篇 quek tony q.s.
30 篇 han zhu
27 篇 zhang yunqing
24 篇 xu minrui
23 篇 shen xuemin
20 篇 rajesh sharma r
20 篇 ji zhen
18 篇 mao shiwen
18 篇 kim dong in
17 篇 zhen ji
17 篇 liu yang
17 篇 li yan
17 篇 quek tony q. s.

语言

5,189 篇 英文
436 篇 其他
50 篇 中文
12 篇 日文
2 篇 朝鲜文
1 篇 德文
1 篇 法文
1 篇 葡萄牙文

检索条件"机构=Computer Science and Design Engineering"

共 5691 条记录，以下是281-290 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：

Transferable Deep Reinforce Learning With Limited Target Data 21

Transferable Deep Reinforce Learning With Limited Target Dat...

引用

21st International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2024

作者： Xiaoqin, Liang Xingyu, Chen Zheng, Wang Wenyi, Xu Shijiao, Han School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Chengdu Aircraft Design and Research Institude Chengdu610091 China School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9798331519254

While there has been significant progress in the application of transfer learning within reinforcement learning, most existing research primarily focuses on online reinforcement learning, with few studies addressing the optimization of offline reinforcement learning. This paper proposes a novel transferable deep reinforcement learning method designed to enhance limited offline samples in the target domain by utilizing online interactive samples from a similar source domain. The method is versatile and can be integrated with any offline reinforcement learning algorithm. To validate its effectiveness, extensive evaluations were conducted across multiple Mujoco environments and D4RL datasets. The results indicate that by employing the proposed method, the algorithm's performance can approach that of using 100% of the target domain data, even when only 10% of the data is available. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Pending Interest Table Control Management with Optimal Forwarder Selection in Named Data Network 1

Pending Interest Table Control Management with Optimal Forwa...

引用

1st IEEE International Conference on Applied Intelligence and Sustainable Computing, ICAISC 2023

作者： Raja Praveen, K.N. Deshpande, Bhargavi Department of Computer Science Engineering Bangalore India ATLAS Skill Tech University ISDI - School of Design & Innovation Mumbai India

ISBN: (纸本)9798350323795

As a result of its usefulness in a variety of contexts, Named Data Networking (NDN) has been a popular topic of study in the last several decades. The Pending Interest Table (PIT) is a crucial part of the NDN that keeps track of all the data included in interest packets. Even if there is no flexible replacement policy, controlling PIT remains a significant problem because of the widespread use of long-term interest. The proposed PIT control system combines the Adaptive Virtual PIT (AVPIT) system, the Smart Threshold Interest Lifetime (STIL) system, as well as the Highest Lifetime Least Request (HLLR) principle. Based on the Interest Satisfaction Ratio (ISR) and the available PIT table capacity, our work chooses the best forwarder to send the packet of interest. Our work uses this method to successfully handle PIT controls via NDN. © 2023 IEEE.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Wow! I Have Tiny Hands: design And Evaluation Of Adaptive Virtual Hands For Small Object Selection Within Arms Length In Dense Virtual Environment

Wow! I Have Tiny Hands: Design And Evaluation Of Adaptive Vi...

引用

Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems, CHI EA 2023

作者： Bhowmick, Shimmila Biswas, Nilotpal Kalita, Pratul Chandra Sorathia, Keyur Department of Design Iit Guwahati Assam Guwahati India Department of Computer Science and Engineering Iit Guwahati Assam Guwahati India

ISBN: (纸本)9781450394222

Object selection is essential to VR applications, but selecting small objects within arms' reach in dense virtual environments can be challenging. We introduce Tiny Hands, which allows reducing the size of the dominant virtual hand in immersive VR to navigate efficiently and accurately select the desired object. This study compares the tiny hands technique with ray casting and pinch-to-select techniques. Our results indicate that the tiny hands technique is significantly faster and more accurate than the other two techniques. It is also significantly easier to use and learn, perceived as natural, playful, and the most preferred technique. Participants appreciated its ability to resize virtual hands for selecting small objects and ease in navigating a dense VE. They also liked its similarity to mouse and cursor-based interactions and flexibility in adjusting hand size according to various object sizes. Participants perceived tiny hands as potentially fatigued for prolonged use and reported a sense of incorrect depth perception when hand sizes are too small. © 2023 Owner/Author.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multi-Scale Convolutional Neural Network with Attention Mechanism for Accurate and Efficient Automated Hematological Diagnostics from Blood Smear 3

Enhanced Multi-Scale Convolutional Neural Network with Atten...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Santosh Kumar, B. Basha, C.H. Hussaian Jini Kumari, M. Pradeep Kumar, S. Sathya, V. Rajaram, K. New Horizon College of Engineering Department of Computer Science and Engineering Bengaluru560103 India Sr University Department of Electrical and Electronics Engineering Warangal506371 India Chennai Institute of Technology Department of Electronics and Communication Engineering Chennai600069 India Rajalakshmi Engineering College Department of Computer Science Design Department Thandalam Chennai602105 India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai600062 India Velalar College of Engineering and Technology Department of Biomedical Engineering Thindal Erode638012 India

ISBN: (纸本)9798331509675

Hematological disorders require accurate and timely diagnosis for effective treatment and patient management. This research develops a new framework that uses deep learning to rapidly identify blood disorders from peripheral blood pictures. Our system uses an AECM and MSCNN combination to diagnose anemia, infections, and leukemia with greater accuracy. The MSCNN captures image details at multiple scales while the AECM detects meaningful areas in blood images which boosts detection results. Our system reached 98.5% total accuracy after validating its performance on public blood smear images. The detection method delivered 97.8% precision and 98.2% recall values during testing. Our diagnostic framework makes blood test results quicker and more affordable while reducing patient labs demands in healthcare environments that face resource constraints. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

PSA-CLNet: Pedestrian Search Method Based on Polarized Self-Attention and COIM Loss 9

PSA-CLNet: Pedestrian Search Method Based on Polarized Self-...

引用

9th International Conference on Virtual Reality, ICVR 2023

作者： Fu, Junjie Liu, Rui Yi, Pengfei Dong, Jing Zhou, Dongsheng Wei, Xiaopeng Dalian University National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian China Dalian University of Technology School of Computer Science and Technology Dalian China

ISBN: (纸本)9798350345810

Pedestrian search is a combined task of pedestrian detection and pedestrian re-identification, i.e., how to find a specific pedestrian in a panoramic picture. However, due to the impact of different imaging conditions and environments, the accuracy of pedestrian search is still low at present, which is difficult to meet the needs of practical applications. To improve the accuracy of pedestrian search, this paper proposes PSA-CLNet pedestrian search method, which integrates polarized self-attention mechanism (PSA) and cosine online instance matching (COIM) loss. Firstly, the channel attention is added to enhance the pedestrian feature information and improve the expression ability of the feature information. Secondly, spatial attention is added to enhance the areas that have more contribution to the pedestrian search task to increase the correlation between the pictures and improve the recognition ability. Meanwhile, this paper proposes a COIM loss based on the online instance matching (OIM) loss. The loss function can enlarge the class distance between pedestrians and background, and reduce the class distance between pedestrians. This could improve the accuracy of pedestrian search algorithm effectively. Finally, this paper uses ResNet as the main backbone network to verify the proposed method. The pedestrian search method proposed in this paper could achieve 96.60% of mAP index and 96.83% of top-1 index in CUHK-SYSU dataset, and achieve 48.78% of mAP index and 88.38% of top-1 index in PRW dataset. © 2023 IEEE.

关键词： COIM loss pedestrian search PSA

来源：评论

学校读者我要写书评

暂无评论

Certificate-Free Aggregate Encryption using Elliptic Curves 1

Certificate-Free Aggregate Encryption using Elliptic Curves

引用

1st IEEE International Conference on Applied Intelligence and Sustainable Computing, ICAISC 2023

作者： Karthick Raghunath, K.M. Krishna, Meena Department of Computer Science Engineering Bangalore India ATLAS Skill Tech University ISDI - School of Design & Innovation Mumbai India

ISBN: (纸本)9798350323795

Having efficient and safe cryptographic techniques for online data exchange is now more important than ever with the rise of the use of cloud computing & the Internet of Things. In a perfect world, those storing data or files online would utilize encryption and provide selected individuals the keys to access such files. with the idea of aggregation, which enables users to decode several kinds of data with an individual key of constant size, is a modern and efficient proposal in this area. For online data sharing, we offer a dynamic key aggregating encryption technique that works on elliptic curve groups and permits dynamic withdrawal of user access rights. We extend this fundamental architecture to a generic two-tiered hierarchical structure that not only effectively permits expansion of data classes but also achieves optimum space and temporal complexity. Finally, we offer an addition to the generalized method that makes it possible to perform encryption and decryption using efficiently computable bilinear pairings. Formal proofs are provided that each scheme is semantically secure. All of the paper's assertions have been verified by actual experiments. © 2023 IEEE.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Alula Effect on Aerodynamic Performance of Small UAVs Wing Configuration 18

Alula Effect on Aerodynamic Performance of Small UAVs Wing C...

引用

18th International engineering Research Conference 2022, EURECA 2022

作者： Eftekhari, Shahrooz Al-Obaidi, Abdulkareem Sh. Mahdi Mari, Tamil Salvi School of Computer Science and Engineering Taylor's University Malaysia School of Architecture Taylor's University Building and Design Malaysia

The application range of small UAVs for civil purposes such as aerial imaging, agricultural pest control and, corps management as well as drone delivery has been increasing throughout recent years. Promising results are observed from recent studies which support the effectiveness of the bio-inspired approach in improving the aerodynamic efficiency of small UAVs. However, very limited studies have investigated the effect of Alula on the aerodynamic performance of wing geometries. This research investigates the effects of employing Alula on the aerodynamic efficiency of the wing to overcome the challenge of small UAVs efficiency degradation. Numerical and experimental investigations are conducted on 6 different Alula configurations. The findings of the investigations shows a reduction in drag for wings and an increase in aerodynamic efficiency by 9% for wings with Alula compared to the conventional wing. It is observed that using Alula configuration helps in delaying flow separation by adding momentum into the flow which resulted in total drag reduction without having a significant effect on the lift. Consequently, the aerodynamic efficiency is increased, and this can be utilized in drone industry to increase the endurance of the flight. © Published under licence by IOP Publishing Ltd.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

An Exploration on Interactive Educational Games for Teaching Primary School Students of Vernacular Medium 9th

An Exploration on Interactive Educational Games for Teaching...

引用

9th International Conference on Research into design, ICoRD 2023

作者： Sarma, Banamita Brahma, Debarshi Kumar Padun, Abhijit Mondal, Anowar Hussain Department of Multimedia Communication and Design CIT Kokrajhar Kokrajhar India Department of Computer Science and Engineering CIT Kokrajhar Kokrajhar India

ISBN: (纸本)9789819902927

The education system is constantly evolving. Teaching has been around since ancient times from Guru–Shishya (apprentice) method to the popularity of books after the invention of the printing press to modern schools with e-learning, and now educational games with AR and VR. Educational games can play an important role on students to make them understand various subjects in a playful manner by coming out of conventional teaching–learning methods. This study explores the implications of educational games for vernacular medium school students and evaluates their improvements. An experiment was carried out in a few vernacular medium schools of Kokrajhar, Assam, where the majority of the students are from the Bodo community who face difficulty in understanding different languages except the Bodo language. A survey conducted among the students outlines the fact that they face such difficulty due to the unavailability of appropriate course contents and study materials in vernacular medium. Hence, to address the issue, an interactive educational game has been designed and developed in three languages—Bodo, English, and Assamese to help students understand their course subjects with fun. Further, the study explores the scope of aligning the educational game with the regular course curriculum of schools to make learning enjoyable and fun. The study further explores the possibility of conducting practical classes in digital mode as well as offering attractive rewards to engage students in their studies. A survey conducted among the students on the educational game gave a strong affirmative response to implement the experiment practically. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Recession Forecasting: Domain-Specific Feature Selection Methodology 1

Recession Forecasting: Domain-Specific Feature Selection Met...

引用

1st International Conference for Women in Computing, InCoWoCo 2024

作者： Katale, Tejaswini Hase, Jayashri Chotrani, Aakash Ozarde, Sakshi Vishwakarma Institute of Technology Department of Computer Engineering Pune India K. K Wagh Institute of Engineering and Research Department of Computer Science and Design Nashik India LDRP Institute of Technology and Research Department of Information Technology Gandhinagar India

ISBN: (纸本)9798331518943

Existing feature selection algorithms often choose features based on their individual importance and consider them as independent entities, which may overlook underlying interrelationships amongst the features. This may result in overfitting because only highly correlated features are selected without considering their collective contribution. Hence it is crucial to take into account both individual feature importance and feature interactions. To mitigate this issue, this research paper proposes a Novel Methodology for Domain Wise feature selection approach which is capable of identifying the interrelationships by focusing on Domain-Wise feature selection. It ensures that correlated and similar features are considered together. It is implemented on a Recession Dataset consisting of 293 observations and 45 features. It groups similar features in 8 domains and further arranges them in descending order of Average Correlation values. For each mini dataset it considers only those data points which are nearest to the mean of that domain and merges all unique observations from these domains and creates a new dataset. Further applying Preprocessing steps - Outlier Elimination, Up sampling and Feature Selection. This paper also discusses how the order of preprocessing can impact the overall result of the evaluation metrics. The efficacy of the algorithm is checked by the accuracy scores of Static Probit Model-98% and Vector Auto Regression-88%. Therefore, by considering both the significance of individual features and the relationships between them the suggested approach successfully addresses the shortcomings of traditional feature selection algorithms. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Quantum Secure Email Communication for Phishing Prevention 7

Quantum Secure Email Communication for Phishing Prevention

引用

7th IEEE Pune Section International Conference, PuneCon 2024

作者： Chandre, Pankaj Sontakke, Palash Patil, Rajkumar Shendkar, Bhagyashree D Dhotre, Dhanraj Vanarote, Viresh Mit Art Design and Technology University Mit School of Computing Department of Computer Science and Engineering Pune India Mit Art Design and Technology University Mit School of Computing Department of Information Technology Pune India

ISBN: (纸本)9798331527822

The rise of sophisticated phishing attacks has necessitated stronger security measures for email communication, especially in sensitive environments. This paper proposes a Quantum Secure Email Communication Framework designed to prevent phishing by integrating Quantum Key Distribution (QKD) with traditional email security mechanisms. The framework leverages quantum keys to encrypt email communication, ensuring that only legitimate users with the correct quantum key can send and receive secure emails. The architecture also incorporates a Phishing Detection Engine that validates email content and sender information using quantum-encrypted keys, alerting users to potential phishing threats. The system operates through the secure exchange of quantum keys between the sender's email server and the user via a QKD Channel, with quantum encryption applied to secure outgoing and incoming emails. In parallel, the phishing detection module analyses all email traffic for signs of malicious activity, using a QKD-based Email Validator to confirm the legitimacy of emails. This hybrid approach ensures both the privacy of communication and the proactive detection of phishing attempts, offering a robust defense mechanism in the increasingly hostile landscape of digital communication. © 2024 IEEE.

关键词： Phishing

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 << < 25 26 27 28 29 30 31 32 33 34 > >>

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：