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

2,247 篇 会议
492 篇 期刊文献
40 册 图书

馆藏范围

2,779 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,738 篇 工学
- 1,276 篇 计算机科学与技术...
- 1,065 篇 软件工程
- 497 篇 信息与通信工程
- 253 篇 控制科学与工程
- 218 篇 生物医学工程（可授...
- 210 篇 电气工程
- 208 篇 生物工程
- 194 篇 电子科学与技术（可...
- 133 篇 光学工程
- 95 篇 仪器科学与技术
- 93 篇 机械工程
- 92 篇 动力工程及工程热...
- 64 篇 建筑学
- 64 篇 化学工程与技术
- 63 篇 交通运输工程
- 61 篇 安全科学与工程
895 篇 理学
- 444 篇 数学
- 241 篇 物理学
- 219 篇 生物学
- 143 篇 统计学（可授理学、...
- 104 篇 系统科学
- 75 篇 化学
455 篇 管理学
- 261 篇 管理科学与工程(可...
- 215 篇 图书情报与档案管...
- 149 篇 工商管理
172 篇 医学
- 151 篇 临床医学
- 141 篇 基础医学(可授医学...
- 98 篇 药学(可授医学、理...
85 篇 教育学
- 84 篇 教育学
84 篇 法学
- 70 篇 社会学
46 篇 经济学
45 篇 农学
13 篇 文学
5 篇 军事学
3 篇 艺术学

主题

76 篇 accuracy
64 篇 training
61 篇 computational mo...
47 篇 feature extracti...
42 篇 deep learning
42 篇 artificial intel...
41 篇 real-time system...
38 篇 predictive model...
37 篇 internet of thin...
35 篇 machine learning
33 篇 support vector m...
31 篇 optimization
31 篇 data models
30 篇 monitoring
30 篇 convolutional ne...
28 篇 computer archite...
28 篇 analytical model...
27 篇 semantics
27 篇 security
27 篇 testing

机构

21 篇 dept. of compute...
21 篇 computer enginee...
15 篇 dept. of compute...
13 篇 computer enginee...
12 篇 politeknik elekt...
10 篇 national institu...
10 篇 dept. of informa...
9 篇 department of ph...
9 篇 faculty of scien...
9 篇 bahcesehir unive...
9 篇 kirchhoff-instit...
9 篇 department physi...
9 篇 institute of phy...
9 篇 department of ph...
9 篇 department of ph...
9 篇 rf and microwave...
8 篇 dept. of applied...
8 篇 school of comput...
8 篇 institute of phy...
8 篇 dept. of compute...

作者

28 篇 bouras christos
20 篇 kostas berberidi...
19 篇 christos bouras
15 篇 mesaritakis char...
14 篇 dewantara bima s...
14 篇 bogris adonis
13 篇 berberidis kosta...
12 篇 vasileios kokkin...
11 篇 catalyurek umit
10 篇 sarigiannidis pa...
10 篇 ankur gupta
10 篇 choo hyunseung
10 篇 megalooikonomou ...
10 篇 kokkinos vasilei...
10 篇 veeraiah vivek
10 篇 vivek veeraiah
9 篇 bellos p.
9 篇 bona m.
9 篇 bachacou h.
9 篇 bressler s.

语言

2,655 篇 英文
98 篇 其他
20 篇 中文
3 篇 日文
2 篇 朝鲜文
1 篇 阿拉伯文
1 篇 土耳其文

检索条件"机构=Dept. of Informatics and Computer Engineering Education"

共 2779 条记录，以下是41-50 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：

Transformer-Based Embeddings for Greek Language Categorization 24

Transformer-Based Embeddings for Greek Language Categorizati...

引用

24th IEEE/ACIS International Conference on computer and Information Science, ICIS 2024

作者： Liapis, Charalampos M. Kyritsis, Konstantinos Perikos, Isidoros Paraskevas, Michael University of Patras Computer Technology Institute & Press 'Diophantus' Mathematics Dept. Patras26504 Greece University of Peloponnese Electrical and Computer Engineering Dept. Patras Greece University of Patras Computer Engineering and Informatics Department Patras Greece University of Peloponnese Computer Technology Institute and Press 'Diophantus' Electrical and Computer Engineering Dept. Patras Greece

ISBN: (纸本)9798350376647

The Greek School Network (GSN) provides support to students, teachers, and school units in secondary education across Greece. Handling numerous user queries manually can be challenging, necessitating the development of an automated system for accurate categorization of these queries. This paper presents a comparative study of various transformer-based models for multi-class text categorization of Greek language queries submitted to the GSN helpdesk. We introduce a new experimental balanced dataset and extract vector representations from eleven transformer-based models. These representations are evaluated using ten classic machine learning classifiers. Our findings highlight the superior performance of the Multilingual E5 Text Embeddings model, particularly when paired with the extreme gradient-boosting classifier. This combination demonstrates a clear advantage in accurately categorizing user queries, paving the way for more efficient automated helpdesk systems. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

HGP-NLP at BioLaySumm: Leveraging LoRA for Lay Summarization of Biomedical Research Articles using Seq2Seq Transformers 23

HGP-NLP at BioLaySumm: Leveraging LoRA for Lay Summarization...

引用

23rd Meeting of the ACL Special Interest Group on Biomedical Natural Language Processing, BioNLP 2024

作者： Malik, Hemang Pradeep, Gaurav Seth, Pratinav Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Dept. of Data Science & Computer Applications India Dept. of Computer Science & Engineering India

ISBN: (纸本)9798891761308

Lay summarization aims to generate summaries of technical articles for non-experts, enabling easy comprehension for a general audience. The technical language used in research often hinders effective communication of scientific knowledge, making it difficult for non-experts to understand. Automatic lay summarization can enhance access to scientific literature, promoting interdisciplinary knowledge sharing and public understanding. This has become especially important for biomedical articles, given the current global need for clear medical information. Large Language Models (LLMs) (Yao et al., 2024), with their remarkable language understanding capabilities, are ideal for abstractive summarization, helping to make complex information accessible to the public. This paper details our submissions to the BioLaySumm 2024 Shared Task: Lay Summarization of Biomedical Research Articles (Goldsack et al., 2024). We fine-tune and evaluate sequence-to-sequence models like T5 across various training dataset settings and optimization methods such as LoRA (Hu et al., 2021b) for lay summarization. Our submission achieved the 53rd position overall.. ©2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Transformer Models in Zero-Shot Text Classification 15

A Comparative Analysis of Transformer Models in Zero-Shot Te...

引用

15th International Conference on Information, Intelligence, Systems and Applications, IISA 2024

作者： Kyritsis, Konstantinos Liapis, Charalampos M. Spatiotis, Nikolaos Perikos, Isidoros Paraskevas, Michael University of Peloponnese Electrical & Computer Engineering Dept. Patras26334 Greece University of Patras Mathematics Dept. Patras26504 Greece Computer Technology Institute & Press 'Diophantus' Patras26504 Greece University of Patras Computer Engineering & Informatics Dept. Patras26504 Greece

ISBN: (纸本)9798350368833

Ahstract-Zero-shot text classification leverages pre-trained transformer models to categorize texts without the need for task-specific training. This paper analyzes a variety of transformer-based pre-trained methods on the task of zero-shot text classi-fication. Specifically, we present a deep comparative analysis of various transformer models, such as BART, DeBerta, DistiIBART, RoBERTa, and their variants, and evaluate their performance in various zero-shot text classification schemes. Furthermore, we examine the models' generalization capabilities. The findings highlight key strengths and weaknesses of each model, providing insights into their suitability for different text categorization tasks. Our research contributes to the broader understanding of transformer-based approaches and offers guidance for selecting models for zero-shot text classification. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

A Highly Interpretable Deep Equilibrium Network for Hyperspectral Image Deconvolution 48

A Highly Interpretable Deep Equilibrium Network for Hyperspe...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Gkillas, Alexandros Ampeliotis, Dimitris Berberidis, Kostas University of Patras Dept. of Computer Engineering & Informatics Greece Ionian University Dept. of Digital Media and Communication Greece

ISBN: (纸本)9781728163277

In this paper, a novel technique for the hyperspectral image deconvolution problem is developed. First, considering the highly ill-posed nature of the examined problem, it is imperative to incorporate proper priors (regularizers) to capture the strong spectral and spatial dependencies of the hyperspectral images. Then, in light of this, a novel optimization problem is proposed by employing a convolutional neural network to act as a regularizer, which is learnt to reflect the properties of the signals of interest. To solve the proposed optimization problem, we use the half quadratic splitting methodology, thus designing an efficient iterative solver (iteration map). Based on the Deep Equilibrium (DEQ) modeling, which aims to express the proposed iterative solver as an equilibrium (fixed-point) computation, a highly interpretable deep learning-based network is derived, which can be trained endto-end. Extensive numerical results using two publicly available datasets illustrate that the proposed method markedly outperforms other state-of-the-art approaches. © 2023 IEEE.

关键词： deconvolution deep equilibrium models deep unrolling Hyperspectral images learnable regularizers

来源：评论

学校读者我要写书评

暂无评论

Deep Equilibrium Models Meet Federated Learning 31

Deep Equilibrium Models Meet Federated Learning

引用

31st European Signal Processing Conference, EUSIPCO 2023

作者： Gkillas, Alexandros Ampeliotis, Dimitris Berberidis, Kostas Dept. of Computer Engineering and Informatics University of Patras Greece Dept. of Digital Media and Communication Ionian University Greece

ISBN: (纸本)9789464593600

In this study the problem of Federated Learning (FL) is explored under a new perspective by utilizing the Deep Equilibrium (DEQ) models instead of conventional deep learning networks. We claim that incorporating DEQ models into the federated learning framework naturally addresses several open problems in FL, such as the communication overhead due to the sharing large models and the ability to incorporate heterogeneous edge devices with significantly different computation capabilities. Additionally, a weighted average fusion rule is proposed at the server-side of the FL framework to account for the different qualities of models from heterogeneous edge devices. To the best of our knowledge, this study is the first to establish a connection between DEQ models and federated learning, contributing to the development of an efficient and effective FL framework. Finally, promising initial experimental results are presented, demonstrating the potential of this approach in addressing challenges of FL. © 2023 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Selection of Outsource Security Guard using Multi-Objective Optimization Ratio Analysis Method 7

Selection of Outsource Security Guard using Multi-Objective ...

引用

7th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2023

作者： Aditya Firmansyah, Mochamad Rafly Ismail, Iklima Ermis Hidayati, Anita Politeknik Negeri Jakarta Dept. of Computer and Informatics Engineering Jawa Barat Depok Indonesia

ISBN: (纸本)9798350342154

The security guard profession is no longer a profession that only relies on the physical but also other aspects, such as attitude, leadership, language, and others. There are several problems faced by companies providing security guards, namely the demand for security personnel is quite high, the number of applicants is also large, but the selection process has to go through an administrative and interview process. With a limited number of interviewers, it takes a longer time to get the selection results. Interview results also tend to be more subjective, making it difficult to determine which candidates are under the company's criteria and specifications. This study aims to develop a decision support system for selecting the acceptance of new outsourced security guards using the MOORA method for a security guard service provider company, namely PT. Purba Alter Service. There are 19 criteria used in the selection of security guards. This research developed the system on a web-based using the MOORA method for calculating the selection of alternative security guards. By comparing the results of the selection system processing using the MOORA method with the results of the previous three years without a system, of the 14 alternative names tested, 12 names appeared in both results, and obtained 85.7% accuracy. The result shows that the MOORA method is successfully implemented in selecting security personnel. © 2023 IEEE.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cabbage Plant Protection: CNN Algorithm for Insect Identification

Enhancing Cabbage Plant Protection: CNN Algorithm for Insect...

引用

2024 International Conference on Information Technology Research and Innovation, ICITRI 2024

作者： Senjaya, Remi Musa, Purnawarman Sularsih, Puji Novrina, Novrina Aryunani, Witari Suhartini, Suhartini Gunadarma University dept. of Informatics Engineering Depok Indonesia Gunadarma University dept. of Electrical Engineering Depok Indonesia Gunadarma University dept. of Information Technology Depok Indonesia Gunadarma University dept. of Computer Science Depok Indonesia

ISBN: (纸本)9798350376210

People frequently find it straightforward to identify insects that feed on cabbage plants based on the insects' characteristics. However, challenges arise when employing a computer for precise bug categorization and identification. The implementation of Deep Learning (DL) utilizes the Convolutional Neural Network (CNN) technique, renowned for its effectiveness in categorizing and recognizing objects in digital photo data. The CNN algorithm delivers notable results in photo identification, simulating the human visual brain's image recognition through artificial neural networks in the Python programming language. To enrich the user experience, frameworks like Keras and TensorFlow are employed in neural network development. Our research will use the CNN algorithm to determine insect species in cabbage images. Achieving high accuracy involves coupling the CNN algorithm with the VGGNet architectural model. Notably, utilizing an epoch value of 150 resulted in a 97.75% accuracy rate during the training model technique;however, the validation accuracy was slightly lower at 94.25%. The corresponding loss and validation rates were 0.0613% and 0.2945%, respectively. Moreover, based on the model (150 epochs), the testing outcomes in the study, involving 48 images beyond the dataset and incorporating additional information, resulted in an accuracy rate of 91.66%. © 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

Emotion Recognition from Video Frame Sequence using Face Mesh and Pre-Trained Models of Convolutional Neural Network 24

Emotion Recognition from Video Frame Sequence using Face Mes...

引用

24th International Seminar on Intelligent Technology and Its Applications, ISITIA 2023

作者： Adi, Derry Pramono Yuniarno, Eko Mulyanto Wulandari, Diah Puspito Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Dept. of Electrical Engineering Surabaya Indonesia Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Dept. of Electrical Engineering Dept. of Computer Engineering Surabaya Indonesia Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Dept. of Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350313956

Emotions are a collection of subjective cognitive experiences and psychological and physiological characteristics that express a wide range of feelings, thoughts, and behaviors in human interaction. Emotions can be represented through several means, such as facial expressions, tone of voice, and behavior. Deep Learning (DL) research has focused on incorporating facial expressions. Images with facial expressions are commonly used as data input for the DL model. Unfortunately, most DL models in Facial Emotion Recognition (FER) use static images. This method does not take into consideration all conceivable facial expressions. The static image of facial expressions is insufficient for recognizing emotions, but a sequential image from a video is required. In this study, we extract MediaPipe's face mesh feature, the state-of-the-art multidimensional expression key points embedded in the video image sequence. Furthermore, we feed sequence image data into the pre-trained Convolutional Neural Network (CNN) model. The data we used is from The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) with the emotion classes of 'Anger,' 'Fearful,' 'Happy,' and 'Sad.' For this specific FER task, we found that the best pre-trained CNN model achieved 92.8% accuracy (using the VGG-19 model), with the fastest runtime of ∼2.3 seconds (achieved using the SqueezeNet model). © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Detection of Cybercriminal Activities in Smartphones via NLP-Based Communication Pattern Analysis 3

Detection of Cybercriminal Activities in Smartphones via NLP...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Swetha, K. Sivaraman, K. Bharath Institute of Higher Education and Research Dept. of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331518592

Smartphones have become a very important part as they handle sensitive personal and financial information in our everyday life. Given their prominence, they are susceptible to various cyber threats, including identity theft, fraud, and phishing. At times, traditional cybersecurity solutions may struggle to tackle the complex threats that arise from communication. The paper presents a new method to enhance the identification of smartphone threats by combining Long Short-Term Memory networks with NLP. This study demonstrates the ability of LSTMs to detect nuanced signs of cybercrime and analyze complex communication patterns using a large dataset of anonymous communications from various sources. The proposed model demonstrates an exceptional accuracy rate of 98.93%, surpassing traditional methods and other machine learning models. This approach highlights the advantages of utilizing BBAD and natural language processing (NLP) to detect and understand malicious activities. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Performance estimation of direct and indirect transmission in V2X communications

Performance estimation of direct and indirect transmission i...

引用

2024 Panhellenic Conference on Electronics and Telecommunications, PACET 2024

作者： Keramidi, Irene Uzunidis, Dimitris Moscholios, Ioannis Yiannopoulos, Konstantinos Sagias, Nikos Sarigiannidis, Panagiotis University of Peloponnese Dept. Informatics and Telecommunications Tripolis Greece University of West Attica Dept. Electrical and Electronic Engineering Athens Greece University of W. Macedonia Dept. Electrical and Computer Engineering Kozani Greece

ISBN: (纸本)9798350318845

In this paper, we evaluate the performance of a vehicular ad hoc network that enables Vehicle-to-Everything (V2X) communication considering direct and indirect packet transmission. As a performance indicator, we use the blocking probability due to the unavailability of resources. For the blocking probability calculation, we utilize two loss models from the teletraffic theory. The results demonstrate that both the capacity of the V2X links and the number of hops in the multi-hop transmission significantly affect the blocking probability of a request for service and consequently the QoS. © 2024 IEEE.

关键词： Blocking probability

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278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：