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

20,422 篇 会议
3,768 篇 期刊文献
263 册 图书

馆藏范围

24,453 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

15,068 篇 工学
- 10,749 篇 计算机科学与技术...
- 8,998 篇 软件工程
- 3,749 篇 信息与通信工程
- 2,428 篇 控制科学与工程
- 1,761 篇 电子科学与技术（可...
- 1,759 篇 电气工程
- 1,491 篇 生物工程
- 1,279 篇 生物医学工程（可授...
- 1,021 篇 光学工程
- 1,015 篇 机械工程
- 807 篇 仪器科学与技术
- 748 篇 动力工程及工程热...
- 730 篇 化学工程与技术
- 604 篇 安全科学与工程
- 511 篇 交通运输工程
- 457 篇 建筑学
7,848 篇 理学
- 4,352 篇 数学
- 2,089 篇 物理学
- 1,659 篇 生物学
- 1,375 篇 统计学（可授理学、...
- 939 篇 系统科学
- 749 篇 化学
3,984 篇 管理学
- 2,368 篇 管理科学与工程(可...
- 1,854 篇 图书情报与档案管...
- 1,295 篇 工商管理
1,038 篇 医学
- 891 篇 临床医学
- 838 篇 基础医学(可授医学...
- 536 篇 药学(可授医学、理...
696 篇 法学
- 560 篇 社会学
455 篇 经济学
- 454 篇 应用经济学
371 篇 教育学
323 篇 农学
92 篇 文学
59 篇 军事学
31 篇 艺术学
6 篇 哲学
4 篇 历史学

主题

662 篇 accuracy
480 篇 feature extracti...
473 篇 computational mo...
464 篇 deep learning
420 篇 computer science
341 篇 training
337 篇 support vector m...
295 篇 internet of thin...
266 篇 machine learning
259 篇 computer archite...
256 篇 predictive model...
252 篇 real-time system...
230 篇 optimization
211 篇 data mining
210 篇 routing
206 篇 artificial intel...
203 篇 neural networks
194 篇 reliability
190 篇 convolutional ne...
183 篇 image segmentati...

机构

83 篇 north-west unive...
83 篇 institut univers...
81 篇 infn sezione di ...
81 篇 national centre ...
80 篇 université de st...
79 篇 tno technical sc...
79 篇 dept. of compute...
76 篇 infn sezione di ...
71 篇 nikhef national ...
66 篇 università di ca...
62 篇 university würzb...
52 篇 school of automa...
51 篇 leiden universit...
50 篇 dept. of compute...
44 篇 university moham...
43 篇 in2p3 lpc campus...
42 篇 infn lnf via enr...
42 篇 university of jo...
40 篇 dept. of compute...
39 篇 university of gr...

作者

94 篇 ardid m.
93 篇 ferrara g.
90 篇 kalekin o.
89 篇 díaz a.f.
88 篇 boumaaza j.
88 篇 coleiro a.
87 篇 calvo d.
82 篇 gal t.
82 篇 bozza c.
81 篇 chen a.
77 篇 huang f.
75 篇 gozzini s.r.
75 篇 dallier r.
69 篇 anguita m.
63 篇 kulikovskiy v.
62 篇 enzenhöfer a.
59 篇 celli s.
56 篇 boettcher m.
53 篇 dornic d.
50 篇 aly z.

语言

21,843 篇 英文
2,277 篇 其他
219 篇 中文
107 篇 日文
9 篇 朝鲜文
4 篇 斯洛文尼亚文
3 篇 德文
1 篇 法文

检索条件"机构=Dept. of Computer Science and Systems Technology"

共 24453 条记录，以下是91-100 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：

Effect of Varied Datasets on Training of a Segmentation Model Used in Visual Navigation

Effect of Varied Datasets on Training of a Segmentation Mode...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Wada, Marin Adachi, Miho Miyamoto, Ryusuke Graduate School of Science and Technology Dept. of Computer Science Japan Meiji University School of Science and Technology Dept. of Computer Science Kawasaki Japan

ISBN: (纸本)9798350324457

A visual navigation method based on results of semantic segmentation showed interesting results in previous researches. The most significant problem of the method is that the moving performance is affected by the segmentation accuracy, which strongly depends on the training data even though SOTA methods are adopted. To create high-quality dataset for this application without huge human efforts, the authors tries to generate datasets for semantic segmentation from a 3D scanned data composed of colored point clouds. In this study, we investigate what kinds of variations are effective to construct a classifier: variation of augmentation considering shadows, shooting angles, and shooting locations. Experimental results using actual images for evaluation and generated dataset for training captured at the course of Tsukuba Challenge, which is the famous competition for autonomous moving robots in Japan, showed that adding shadows in training datasets improved the mIoU but random changes to the shooting angle and location did not always work well. By the result, it is shown that augmentation considering the characteristic of the target environment becomes important for practical use. © 2023 IEEE.

关键词： 3D scanned data dataset generation semantic segmentation visual navigation

来源：评论

学校读者我要写书评

暂无评论

Personalized Movie Recommendation Based on User Preferences Using Optimized Sequential Transformer Model

Personalized Movie Recommendation Based on User Preferences ...

引用

2024 International Conference on Artificial Intelligence and Emerging technology, Global AI Summit 2024

作者： Ravikumar, R.N. Jain, Sanjay Sarkar, Manash Amity University Rajasthan Dept. of Computer Science and Engineering Jaipur India Atria Institute of Technology Dept. of Computer Science and Engineering Banglore India

ISBN: (纸本)9798350379716

This study explores the application of a Transformer based model to the 'MovieLens 1M' and 'MovieLens 10M' datasets provided by GroupLens, which includes one million and ten movie ratings. The Transformer model, known for its proficiency in handling sequence-to-sequence tasks, employs multi-head self-attention mechanisms and position-wise feed-forward networks. Our implementation, developed in PyTorch, benefits from its capacity for automatic differentiation and GPU acceleration, which significantly enhances the training efficiency. The model underwent rigorous hyperparameter tuning and optimization to adapt optimally to the characteristics of the dataset. Performance evaluation using the Normalized Discounted Cumulative Gain (NDCG) metric demonstrates that the Transformer model substantially outperforms a conventional popular recommendation system across various top-K rankings. Specifically, for the MovieLens 1M dataset, the Transformer model achieved NDCG scores of 0.0455, 0.0805, 0.0995, and 0.1273 at top 1, 3, 5, and 10, respectively. Comparatively, the popular recommendation system scored 0.0023, 0.0044, 0.0061, and 0.0091 at these same rankings. This trend of superior performance by the Transformer model is also consistent across the MovieLens 10M dataset, further confirming its effectiveness in ranking highly relevant items at the top of the list. Also, to address quality and utility of recommendations, MAP, Precision, Recall, F1 Score, Coverage and Serendipity metrics evaluated. These results underscore the effectiveness of Transformer models in extracting and leveraging complex patterns in sequence data, demonstrating a clear superiority over traditional methods in recommendation systems. This study highlights the potential of deep learning architectures to revolutionize fields reliant on understanding user preferences and sequential data interactions. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Towards a Real Vehicular Data Cloud 11

Towards a Real Vehicular Data Cloud

引用

11th IEEE International Conference on Software Defined systems, SDS 2024

作者： Cardel, Victor S. Zisner, Philipp Rettore, Paulo H. L. Sevenich, Peter Santos, Bruno P. Federal University of Bahia Dept. of Computer Science Brazil Fraunhofer FKIE Dept. of Communication Systems Bonn Germany

ISBN: (纸本)9798331518325

Intelligent Transportation systems (ITSs) increasingly rely on cloud computing to gather and process vehicular data, enabling the development of adaptable transportation solutions. However, the availability of such data is often limited by privacy, security, and commercial concerns, challenging the open research in ITS. Existing datasets rarely include both intra-vehicular data (created from or inside the vehicle) and extra-vehicular data (created from surrounding sources) or provide flexible scenarios for data extraction. This paper introduces a methodology to collect and publish ITS data, including intra and extra-vehicular sensor data. A quantitative analysis was conducted as part of the data characterization to show the associated data challenges. Moreover, the dataset collected is freely accessible, allowing innovation in ITS research and application development. © 2024 IEEE.

关键词： Big-data Data Fusion Intelligent Transportation systems Vehicular Cloud Computing

来源：评论

学校读者我要写书评

暂无评论

Sub Event Relation Classification for Amharic Texts Using Deep Learning Approach

Sub Event Relation Classification for Amharic Texts Using De...

引用

2024 International Conference on Information and Communication technology for Development for Africa, ICT4DA 2024

作者： Desta, Abinet Bizuayehu Abetw, Abebe Alemu Werku, Kebad Nigussie Asfaw, Nega Agmas Belachew, Habtamu Molla Alemu, Wubie Belay Debark University Dept. Information Technology Debark Ethiopia University of Gondar Dept. Computer Science Gondar Ethiopia Woldia University Dept. Computer Science Woldia Ethiopia

ISBN: (纸本)9798331527792

This research focuses on the challenge of Sub-event Relation Classification (SERC) in Amharic text, with the objective of identifying relationships between event triggers or mentions in sentences. The aim is to predict sub-event relationships in Amharic sentences, benefiting applications such as information extraction, question answering, and document summarization. Amharic text requires a lot of effort to manually identify event relationships, and there isn't yet a model that specializes in extracting event relationships from Amharic language. Deep learning techniques, particularly LSTM and BiLSTM, are used in this work to categorize the relation type between event pairs in unstructured Amharic text in order to address this difficulty. The models are trained and assessed using a dataset of 6622 manually annotated Amharic texts. Experimental results showcase the effectiveness of the BiLSTM model, achieving a high accuracy of 93% for Amharic sub-event relation classification. The findings of this research hold significant implications for natural language processing applications in Amharic and other languages. Moreover, the developed model can be extended to other languages, making it a valuable contribution to the field of natural language processing. © 2024 IEEE.

关键词： Amharic Sub-event Relation Classification (A-SERC) Bidirectional Long Short-Term Memory (BiLSTM) Deep Learning (DL) Long Short-Term Memory (LSTM) Natural Language Processing (NLP) Word2Vec

来源：评论

学校读者我要写书评

暂无评论

TARG: A Reference-Free, Lossless, Customized General-Purpose Encoder for Genome Sequence in Raw, FASTA, or Multi-FASTA Formats 4

TARG: A Reference-Free, Lossless, Customized General-Purpose...

引用

4th International Conference on computer, Communication, Control and Information technology, C3IT 2024

作者： Roy, Subhankar Ghosh, Partha Mukhopadhyay, Anirban Academy of Technology Dept. of Computer Science and Engg. Hooghly India University of Kalyani Dept. of Computer Science and Engg. Nadia India

ISBN: (纸本)9798350389128

The ability to efficiently encode and store vast amounts of genome sequence data is paramount for various analytical and computational tasks. General-purpose compressors fail to efficiently compress genome sequences, primarily due to the highly repetitive nature of genomic data, the complexity and variability of genomes across organisms, the large size of genome sequences, the limitations of standard compression algorithms, and the absence of optimization for genomic data patterns. This article addresses this challenge through the development of a reference-free, lossless, customized general-purpose encoder for genome sequences in raw, FASTA (FAST-ALL), or multi-FASTA formats. The proposed encoder offers a versatile solution that can handle diverse genome datasets without relying on preexisting reference sequences, ensuring compatibility with emerging genome sequencing technologies. We tested and evaluated the encoder thoroughly to show that it works well and is reliable. We looked at compression ratios, compression and decompression speeds, memory, and how well it recreated the original genome sequences. This encoder not only addresses the pressing need for efficient data storage and transmission in genomics but also paves the way for further advancements in genome analysis and interpretation. Unlike other algorithms, the proposed method, TARG (Two-bit coding encoded using ASCII with Run length encoding followed by General-purpose encoding), does not depend on time-consuming parameter settings. Based on experiments, the average compression ratio of TARG on 10 benchmark genome datasets is 4.33, while the current state-of-the-art general-purpose algorithms gzip, bzip2, zstd, and bsc have respective averages of 3.26, 3.51, 4.21, and 4.28. © 2024 IEEE.

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

Unveiling Insights: Vision-Based Data Mining Analysis of Webpages in Transition from HTML 3 to HTML 5 5

Unveiling Insights: Vision-Based Data Mining Analysis of Web...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Chaudhary, Meena Pooja Chandwani, Gunjan Manav Rachna University Dept. of Computer Science and Technology Faridabad India Galgotias University Dept. of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350383522

Deep web material is accessed with web database requests, and returned information is packaged into dynamically generated web pages known as deep Web pages. Due to their intricate structure, it is tedious task to retrieve organized data from deep web pages. A great many approaches to address this problem are yet to be proposed, but all of them have inherent drawbacks because they are based on the website and the programming language. The contents of Sites are always shown for users to search daily, like the common two-dimensional media. This motivates us to search for an alternative way to extract deep Web information, by using some interesting popular visual features from deep Webpages, to address the limitations of past works. A novel blog vision approach is proposed in this paper to overcome these issues. This technique uses visual features in deep web pages specifically to conduct deep web data extraction. This paper also recommends a new appraisal measure to capture the required human activity to make maximum mining. The proposed methodology is highly efficient in the deep network data extraction, according to our studies with a large set of web-based data bases. © 2024 IEEE.

关键词： Data mining HTML 3 HTML5 Vision based technique Web Content Mining

来源：评论

学校读者我要写书评

暂无评论

The Impact of Compiler Warnings on Code Quality in C++ Projects 32

The Impact of Compiler Warnings on Code Quality in C++ Proje...

引用

32nd IEEE/ACM International Conference on Program Comprehension, ICPC 2024

作者： Johansson, Albin Holmberg, Carl Neto, Francisco G. De Oliveira Leitner, Philipp Chalmers University of Technology Dept. of Computer Science and Engineering Gothenburg Sweden Chalmers - University of Gothenburg Dept. of Computer Science and Engineering Gothenburg Sweden

ISBN: (纸本)9798400705861

Modern compilers often offer a variety of warning flags, which developers can enable to get feedback on code that, while syntactically correct, may be problematic. In the case of C++, one example of such 'correct but problematic' code is code that leads to undefined behavior (UB). The usage of compiler warnings has long been suspected as a way to decrease bugs and increase code quality. However, empirical evidence that supports this hypothesis is rare. In this study, we present evidence from a study of 127 open source C++ projects. We categorize their usage of compiler warnings into five groups based on which warning flags are being used, and analyse the relationship between compiler warnings and five quality metrics (bugs, critical issues, vulnerabilities, code smells, and technical debt) using Bayesian analysis. We conclude that, in general, compiler warnings indeed correlate with, and potentially cause, higher code quality, with the clearest impact being on the number of critical issues in a project. Using stricter warning flags expectantly correlates with higher code quality in our study objects. However, there are substantial differences between projects, which we attribute to the project's individual development culture. That is, while warnings matter, other factors such as quality culture, are likely to be even more important to source code quality. © 2024 ACM.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Quantum Convolutional Neural Networks for Student Facial Expression Identifcation and Mode Assessments 4

Leveraging Deep Quantum Convolutional Neural Networks for St...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information systems, ICUIS 2024

作者： Hossain, Javed Alam, Md. Nur Akib, Mohammad Yasin Nur Kogoya, Krisdahim Nanjing University of Information Science and Technology Dept. of Artificial Intelligence Nanjing China Nanjing University of Information Science and Technology Dept. of Computer Science and Technology Nanjing China

ISBN: (纸本)9798331529635

The incorporation of modern technologies into education has transformed how learning is seen and assessed, with a rising emphasis on understanding student behavior using facial expression recognition (FER). Recognizing students' emotional and cognitive states can provide vital insights into their engagement and learning styles, allowing teachers to adjust their teaching tactics in real time. Traditional machine learning algorithms have been used to solve this problem, but they frequently struggle with the complexity of facial expressions and big datasets, resulting in limitations in accuracy and processing efficiency. This study explores the potential of quantum computing in addressing these challenges through the development of a Deep Quantum Convolutional Neural Network (QCNN) architecture. By combining the advanced image processing capabilities of convolutional neural networks (CNNs) with the computational power of quantum features such as superposition and entanglement, we aim to enhance the detection of facial expressions that reflect students' engagement, concentration, frustration, and satisfaction. Finally, the result demonstrates a classification accuracy of 91.58 © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based Digital Forensic Data for Unbreakable Trust and Security

Blockchain Based Digital Forensic Data for Unbreakable Trust...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Imrankhan, M. Viji, M. Sathishkumar, R. Gnanaprakash, T. Roshan, R. Karthik Saravanan, G. Manakula Vinayagar Institute of Technology Dept. of Cse Puducherry India Sri Manakula Vinayagar Engineering College Dept. of Computer Science and Business Systems Puducherry India

ISBN: (纸本)9798331510022

This can be one of the most magnificent advantages realized from applying blockchain technology in a forensic investigation context, namely, a transformative approach to address challenges embedded within legal and criminal justice systems. For example, smart contracts, being self-executing agreements with the automated inclusion of predefined rules, may even automate and secure the process of tracking evidence, managing chain of custody, and access control. This smart contract will ensure that forensic operations are transparent and of sound integrity. Every transaction and action performed on the blockchain is recorded there, instantaneously bringing down tampering to the lowest possibility and any chance for human mistakes. Regarding decentralized nature and cryptography-based security combined with immutability, blockchain is a technology known to have safeguards over sensitive data. Once recorded on the blockchain, the information thereupon becomes completely un-changeable, assuring the reliability and authenticity of evidence. This will be especially important in the management of an unforgeable chain of custody and in ensuring that forensic evidence remains unchanged and can be relied on with integrity throughout the court process.[6] Critical data can then be maintained tamper-proof for management and storage by developing Ethereum-based smart contracts on Remix IDE using Solidity.[15]Each transaction will be time-stamped and safely logged on the Ethereum blockchain, thus developing an unchallenged ledger that makes any investigation that much more trustworthy. In a nutshell, the application of blockchain in forensic activities builds greater control and efficiencies, reduces possible errors and conflicts, and provides transparency, integrity, and an unchangeable, permanent record for forensic processes. The invention thereby significantly upgrades the general integrity and confidence in legal and criminal justice inquiries. © 2024 IEEE.

关键词： Ethereum

来源：评论

学校读者我要写书评

暂无评论

Active Element Arrangement and Prediction Model for Channel Estimation in IRS-Assisted systems

Active Element Arrangement and Prediction Model for Channel ...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Tsuchiya, Yoshihiko Suga, Norisato Uruma, Kazunori Fujisawa, Masaya Tokyo University of Science Dept. of Information and Computer Technology Tokyo Japan Shibaura Institute of Technology Dept. of Information and Communication Engineering Tokyo Japan Kogakuin University Dept. of Computer Science Tokyo Japan

ISBN: (纸本)9798350350821

Intelligent reflecting surfaces (IRS) that can dynamically control the phase of radio waves and reflect them are attracting attention to realize non line-of-sight communication in the high-frequency band. Channel state information (CSI) is estimated to properly control the phase, however the overhead of the estimation reduces communication efficiency. To reduce the overhead, IRS systems with active elements that perform channel estimation are considered. One approach treats the partial CSI obtained from the active elements as an image and utilizes a super-resolution technique to predict the entire CSI. However, because the active elements are arranged in grid, prediction is difficult when the active elements spacing and the CSI fluctuation period match. In this study, we propose a new arrangement that gathers the active elements in the center of the IRS. Furthermore, we regard prediction as an image-inpainting problem that recovers missing pixels from known pixel values, and we propose applying the U-Net to solve this problem. Numerical experiments show that the proposed method outperforms conventional methods in prediction accuracy and spectral efficiency. © 2024 IEEE.

关键词： Channel estimation

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 << < 6 7 8 9 10 11 12 13 14 15 > >>

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：