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

2,644 篇 会议
61 篇 期刊文献
38 册 图书
3 篇 学位论文

馆藏范围

2,746 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,237 篇 工学
- 1,991 篇 计算机科学与技术...
- 779 篇 软件工程
- 488 篇 电气工程
- 437 篇 信息与通信工程
- 174 篇 控制科学与工程
- 167 篇 生物工程
- 119 篇 生物医学工程（可授...
- 56 篇 仪器科学与技术
- 55 篇 化学工程与技术
- 50 篇 安全科学与工程
- 46 篇 机械工程
- 42 篇 电子科学与技术（可...
- 38 篇 光学工程
- 26 篇 动力工程及工程热...
537 篇 理学
- 279 篇 数学
- 187 篇 生物学
- 114 篇 物理学
- 108 篇 系统科学
- 108 篇 统计学（可授理学、...
- 54 篇 化学
266 篇 管理学
- 141 篇 图书情报与档案管...
- 136 篇 管理科学与工程(可...
- 64 篇 工商管理
146 篇 医学
- 122 篇 临床医学
- 56 篇 基础医学(可授医学...
- 36 篇 药学(可授医学、理...
- 27 篇 特种医学
- 25 篇 医学技术（可授医学...
41 篇 法学
- 33 篇 社会学
35 篇 教育学
- 28 篇 教育学
22 篇 经济学
22 篇 农学
8 篇 文学
5 篇 艺术学
1 篇 军事学

主题

897 篇 machine learning
218 篇 deep learning
123 篇 feature extracti...
106 篇 training
103 篇 machine learning...
85 篇 classification
72 篇 cloud computing
70 篇 support vector m...
70 篇 neural networks
62 篇 big data
60 篇 data mining
60 篇 computational mo...
53 篇 artificial intel...
49 篇 sentiment analys...
45 篇 predictive model...
43 篇 intrusion detect...
40 篇 reinforcement le...
38 篇 data models
35 篇 neural network
34 篇 internet of thin...

机构

12 篇 univ chinese aca...
11 篇 institute of mac...
7 篇 school of comput...
7 篇 fudan university
7 篇 school of electr...
7 篇 guangxi academy ...
6 篇 università di ca...
6 篇 infn sezione di ...
6 篇 north-west unive...
6 篇 in2p3 lpc campus...
6 篇 institut univers...
6 篇 national centre ...
6 篇 tno technical sc...
6 篇 université de st...
6 篇 nikhef national ...
6 篇 university würzb...
6 篇 université de ha...
6 篇 university of jo...
6 篇 university moham...
6 篇 astrocent nicola...

作者

14 篇 qin xiao
8 篇 yuan chang-an
8 篇 huang de-shuang
7 篇 chen hao
7 篇 yuan changan
7 篇 wu hongjie
7 篇 zhao xingming
6 篇 chen a.
6 篇 benoit d.m.
6 篇 ferrara g.
6 篇 ardid m.
6 篇 calvo d.
6 篇 gagliardini s.
6 篇 eddymaoui a.
6 篇 kulikovskiy v.
6 篇 labalme m.
6 篇 gal t.
6 篇 bozza c.
6 篇 khatun a.
6 篇 kalekin o.

语言

2,639 篇 英文
69 篇 中文
39 篇 其他

检索条件"任意字段=2017 International Conference on Machine Learning and Soft Computing, ICMLSC 2017"

共 2746 条记录，以下是301-310 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：

Image Captioning Using machine/Deep learning 4

Image Captioning Using Machine/Deep Learning

引用

4th international conference on Advances in computing, Communication Control and Networking, ICAC3N 2022

作者： Singh, Vishal Shankar Singh, Ajay Anandhan, K. Galgotias University Computer Science and Engineering Greater Noida India Galgotias University School of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9781665474368

The System that automatically write descriptions or write captions for an image according to the contents of that image is known as Auto Image Captioning. It's literacy problem of the machine that combines computer vision (for understanding image contents) with Natural processing (for textbook product) Auto picture captioning is a fairly new and fleetly adding academic content. Colourful new styles are being launched on a diurnal base in order to attain satisfying outcomes in this discipline. Still, to gain mortal- suchlike results, a lot of attention is still necessary. The thing of this exploration is to discover, in a methodical manner, what different and recent methodologies and models are employed for picture captioning using deep learning. What approach and new ideas are used to make these models better and more accurate. what's further, ideas and strategy are more likely to give suitable result or outcome. To get so, we did a methodical literature analysis of recent exploration published between 2017 and 2019 from well- known datasource (Scopus, Web of Lores, IEEEXplore). We plant an aggregate of over 60+ primary studies that were related to this study. We found out that CNN understands the content in the picture and detect objects in an image, whereas LSTM/RNN is used to induce language. MS COCO, flicker 8k and flicker 30k, which are used in almost every studies, are the most extensively used datasets. The BLEU (1 - 4) standing rating matrix is the most extensively utilised in all projects or studies. The analysis also show that CNN with LSTM is more preferable than CNN with RNN. We found out that the Encoder Decoder and the attention medium are one of the most suitable and best ways for enforcing this model, and combining them can ameliorate outcomes to more accurate and good level. Experimenters or other people that want to work or contribute to auto image captioning will surely find this exploration very useful and can use it as a guidance. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Decentralized Federated learning Loop with Constrained Trust Mechanism 1

引用

22nd international conference on Artificial Intelligence and soft computing, ICAISC 2023

作者： Polap, Dawid Prokop, Katarzyna Srivastava, Gautam Chun-Wei Lin, Jerry Faculty of Applied Mathematics Silesian University of Technology Kaszubska 23 Gliwice44-100 Poland Department of Mathematics and Computer Science Brandon University BrandonR7A 6A9 Canada Western Norway University of Applied Sciences Bergen Norway

ISBN: (数字)9783031425059

ISBN: (纸本)9783031425042

Federated learning has made it possible to introduce parallel training of deep neural networks by multiple users. The use of model aggregation contributes to the generalization of it, although there is a possibility of attacks. An example of this is dataset poisoning. Hence, in this research paper, we propose the introduction of a constrained trust mechanism for individual clients. In addition, a decentralized approach makes it possible to increase the effectiveness of the training process by removing the server and reducing the risk of an attack on the transmitting model. The proposed modification of federated learning was subjected to performance tests and compared with other known solutions. The obtained results indicate an increase in safety and accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep learning Framework for Intrusion Detection: Integrating Dual-Staged Attention and Squirrel Search Optimization for Enhanced Accuracy 2

A Novel Deep Learning Framework for Intrusion Detection: Int...

引用

2nd international conference on machine learning and Autonomous Systems, ICMLAS 2025

作者： Mahaveerakannan, R. Poonguzhali, P.K. Murali Dhar, M.S. Vidhya, R. Natteshan, N.V.S. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Tamil Nadu Chennai India Hindusthan College of Engineering and Technology Department of ECE Coimbatore India Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai600062 India Hindusthan College of Engineering and Technology Department of Computer Science and Engineering Coimbatore641032 India School of computing Kalasalingam academy of research and education TN Krishnan koil India

ISBN: (纸本)9798331505745

The rapid development of computer networks, such as the internet, has caused a sea change in the ways in which people communicate and share information. The advent of widespread computer networks like the internet has caused a sea change in traditional modes of communication and information sharing. On the other hand, this technical progress has also opened the door for malicious actors to take advantage of loopholes and steal sensitive information, disrupt operations, etc. Therefore, intrusion detection systems (IDSs) are essential for screening harmful traffic and warding off frequent attacks. These algorithms used to work by comparing current attacks to those of the past or by following a predetermined set of rules. But now that data and computing power are more accessible than ever before, machine learning seems to be the way to go. In this study, to present DSAM-CGLSTM, a dual-staged attention mechanism based on conversion-gated Long Short Term Memory network, to capture both short-term mutation and long-term dependence info in the study dataset. To enhance the network's capacity to retrieve the short-term mutation information, hyperbolic tangent functions are incorporated into the input-gate and forget-gate of LSTM. Additionally, the network incorporates a dual-staged attention mechanism, which encompasses both input attention and temporal attention. Consequently, a novel algorithm for optimising the parameters of DSAM-CGLSTM, SSA, has been suggested in this research, which is based on metaheuristics. to use a single Jupyter notebook in the Google Colaboratory environment to conduct the entire experiment. to imported and then implemented the necessary software packages, including seaborn, pandas, matplotlib, keras, besides Tensor Flow, and to used the CICIDS 2017 dataset. During the model's training and validation processes, accuracy and loss were taken into account as performance indicators. With a 98.85% accuracy score, the deep learning model performed quit

关键词： Hyperbolic functions

来源：评论

学校读者我要写书评

暂无评论

Leveraging machine learning to Uncover Key Factors Influencing Satisfaction Among Free Tertiary Education Recipients in the Philippines

Leveraging Machine Learning to Uncover Key Factors Influenci...

引用

international conference on Advanced Communication Technology (ICACT)

作者： John Raymund B. Baragas Lea D. Austero Jennifer L. Llovido Lany L. Maceda Mideth B. Abisado Computer Science and Information Technology College of Science Bicol University Albay Philippines College of Computing and Information Technologies National University Manila Philippines

In spite of the broad implementation of the Universal Access to Quality Tertiary Education Act (UAQTE) - a groundbreaking legislation benefitting over 2 million students since its enactment in 2017 - a comprehensive evaluation of its outcomes has been notably absent. To bridge this gap, an extensive survey was undertaken among graduating tertiary students in selected regions of the Philippines. This strategically designed survey aimed to pinpoint overlooked aspects of UAQTE and capture firsthand insights from its recipients. The methodology employed to create this survey included focus-group discussions with various stakeholders (i.e., students, parents, faculty) and a pilot test reflecting the target demographic. To facilitate analysis of the results of 1462 responses, five regression machine learning algorithms were then employed to analyze questionnaire data. The decision tree regressor with a root-mean-squared-error of 0.6881 was found to be the best performing model describing the collected questionnaire data. Shapley explanations of the best performing model highlighted the desire of the recipient to pursue international employment as the top predictor of satisfaction in UAQTE among its recipients. Furthermore, insights from employed topic modeling among the open-ended questions in the deployed survey suggested potential inadequacy of UAQTE subsidies, specifically to recipients whose pursued degrees are in the science, technology, engineering, and mathematics courses. This substantial finding promises valuable insights into the effectiveness of the legislation and may inform future policy adjustments to better address the diverse needs of tertiary education in the Philippines. Overall, this research provides a robust framework for assessing the impact of UAQTE and showcases a methodologically sound approach in integrating machine learning and qualitative analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Differentiation of Gut Microbiome Profiles Between Healthy and IBD Individuals Using 16S rRNA Sequencing and AI-Enhanced Analysis: Insights from Indian Cohorts

Differentiation of Gut Microbiome Profiles Between Healthy a...

引用

Cognitive computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), international conference on

作者： Jyoti Kaurav Sanjay Sharma Ravi Kumar Chaudhary Dept of Computer Science & Engineering USICT Gautam Buddha University Gr. Noida UP Dept. of Research & Development Government Institute of Medical Sciences Gr. Noida UP

ISBN: (数字)9798331518523

ISBN: (纸本)9798331518530

Gut microbiome plays a major role in human health, and its dysbiosis is associated with diseases i.e. inflammatory bowel disease (IBD). This study investigates microbial differences between healthy individuals and IBD patients using 16S rRNA sequencing data from various BioProjects within the Indian Microbiome Database. Data from projects PRJNA397112, PRJNA422434, PRJNA515526, PRJNA559123, and PRJNA637482 were analyzed and taxonomic classification was performed using Qiita (Gonzalez et al. 2018) with the picking method of closed reference Operational Taxonomic Units (OTUs) through SortMeRNA (Kopylova et al. 2012). Additionally, 16S PIP (Miao et al. 2017) was used for pathogenic bacteria identification. To enhance the analysis, Artificial Intelligence (AI)-based methods such as machine learning (ML) clustering and predictive modeling were employed to identify microbial patterns linked to health outcomes. Significant differences were observed in microbial diversity and composition between healthy and IBD samples, with an increase in pathogenic species in IBD patients. These findings, combined with AI analysis, provide insights into microbial markers of gut health and disease, offering potential applications in personalized medicine. This research underscores the potential of AI in identifying microbial markers for personalized treatment strategies.

关键词： Inflammatory bowel disease Sequential analysis Analytical models Databases Precision medicine Computational modeling machine learning Predictive models Cognitive systems Diseases

来源：评论

学校读者我要写书评

暂无评论

The Analysis of Optimizers in Training Artificial Neural Networks Using the Streaming Approach 1

引用

22nd international conference on Artificial Intelligence and soft computing, ICAISC 2023

作者： Duda, Piotr Wojtulewicz, Mateusz Rutkowski, Leszek Department of Computational Intelligence Czestochowa University of Technology Czestochowa Poland Institute of Computer Science AGH University of Science and Technology Cracow Poland System Research Institute of the Polish Academy of Sciences Warsaw Poland

ISBN: (数字)9783031425059

ISBN: (纸本)9783031425042

One of the major challenges in modern artificial neural network training methods is reducing the learning time. To address this issue, a promising approach involves the continuous selection of the most crucial elements from the training set, utilizing data stream analysis. However, transitioning to this new learning paradigm raises several questions. In this study, we explore the significance of employing different optimizers for training neural networks using the streaming method. Experimental results are presented based on a detailed analysis of a convolutional neural network trained on the MNIST dataset. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Custom Classifier to Detect Spambots on CRESCI-2017 Dataset 6th

A Custom Classifier to Detect Spambots on CRESCI-2017 Datase...

引用

6th international conference on Emerging Research in computing, Information, Communication and Applications, ERCICA 2020

作者： Thavasimani, Karthikayini Srinath, N.K. RV College of Engineering Bangalore India

ISBN: (纸本)9789811613371

In recent times, social networks are actively emerging as an encouraging platform for democratic discussions on social, media, and political issues. However, the growing popularity of social networks leads to a surge of concerns on the quality of the shared data. Initially, bots are created with good intentions. Nowadays, bad bots are created and powered by AI to perform malicious activities in social network sites. Statistics say that 94.2% of the entire websites in the world are being affected by the Bots. They are more sophisticated, intelligent enough to mimic like humans and can change their signatures dynamically. It's hard to detect such kind of bots with the existing techniques as the new bots keep evolving. Social networks are growing exponentially. As a result, big data is growing unconditionally. So, we need more computationally efficient algorithms running at a higher detection rate to handle big data. For our study, we used the real-time dataset from the bot repository released by Indiana University. In our work, we propose a new custom bot classifier algorithm to predict the bot accounts. The algorithm detects the bots with an accuracy rate of 96.13%. Furthermore, we made a comparative analysis of our algorithm with existing machine learning algorithms using various classification metrics. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

xIDS-EnsembleGuard: An Explainable Ensemble learning-based Intrusion Detection System 23

xIDS-EnsembleGuard: An Explainable Ensemble Learning-based I...

引用

23rd IEEE international conference on Trust, Security and Privacy in computing and Communications, TrustCom 2024

作者： Adil, Muhammad Jan, Mian Ahmad Bin Hakim, Safayat Song, Houbing Herbert Jin, Zhanpeng University at Buffalo Deptartment of Computer Science Buffalo United States University of Sharjah College of Computing and Informatics Sharjah United Arab Emirates University of Maryland School of Information Systems Baltimore County United States South China University of Technology Guangdong China University at Buffalo School of Future Technology Buffalo United States

In this paper, we focus on addressing the challenges of detecting malicious attacks in networks by designing an advanced Explainable Intrusion Detection System (xIDS). The existing machine learning and deep learning approaches have invisible limitations, such as potential biases in predictions, a lack of interpretability, and the risk of overfitting to training data. These issues can create doubt about their usefulness, and transparency, and decrease the trust of involved stakeholders. To overcome these challenges, we propose an ensemble learning technique called the "EnsembleGuard". This approach uses the predicted outputs of multiple models, including tree-based (LightGBM, GBM, Bagging, XGBoost, CatBoost) and deep learning models such as neural network (LSTM (long short-term memory networks) and GRU (gated recurrent unit), to maintain a balance and achieve trustworthy results. Our work is unique because it combines both tree-based and deep learning models to design an interpretable and explainable meta-model through model distillation. By considering the predictions of all individual models, our neta-model effectively addresses key challenges, and ensures both explainable and reliable results. We evaluate our model using well-known datasets, including UNSW-NB15, NSL-KDD, and CIC-IDS-2017, to assess its reliability against various types of attacks. During analysis, we found that our model outperforms both tree-based models and other comparative approaches when it comes to different kinds of attack scenarios. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Classification of Chest X-Ray Images Using CNN-Based Transfer learning Models

Classification of Chest X-Ray Images Using CNN-Based Transfe...

引用

IEEE international conference on Power, Intelligent computing and Systems (ICPICS)

作者： Danrui Chen Yu Xu School of Computer Science and Technology Southwest University of Science and Technology Mianyang China

ISBN: (数字)9798350374315

ISBN: (纸本)9798350374322

Pneumonia and COVID-19 are infectious and fatal. X-ray is the imaging modality for early detection of pneumonia. However, it is difficult to detect pneumonia due to the small target, low resolution, and insufficient image information content of the pneumonia in X-ray images. This study aims to address these problems by comparing manual identification and other traditional machine learning models with a transfer learning model based on convolutional neural network (CNN) to classify pneumonia from chest X-ray images. A transfer learning model based on a convolutional neural network (CNN) was developed to classify pneumonia from chest X-ray images. This model was pre-trained to accelerate the convergence rate and improve the classification accuracy, thereby enhancing its generalisation ability. To validate the model's effectiveness, experiments were conducted on two datasets. The transfer learning model based on ResNet significantly better than other models on the Chest X-ray 2017, with accuracy, accuracy, recall, kappa and F1 values of 89.99%, 90.70%, 85.94%, 75.66% and 87.77%, respectively. On the COVID-19 radiography database, the transfer learning model based on MobileNetV2 demonstrated significantly superior performance to other models. The accuracy, accuracy, recall, kappa, and F1 values of MobileNetV2 were 85.56%, 81.50%, 89.80%, 77.34%, and 84.65%, respectively. The results demonstrated that the CNN-based transfer learning model was more effective in classifying pneumonia X-ray images, which could reduce misdiagnosis and missed diagnosis and shorten the diagnostic time.

关键词： COVID-19 Pneumonia Accuracy Image resolution Databases Computational modeling Transfer learning Convolutional neural networks X-ray imaging Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Deep learning and Film History: Model Explanation Techniques in the Analysis of Temporality in Finnish Fiction Film Metadata 6

Deep Learning and Film History: Model Explanation Techniques...

引用

6th Digital Humanities in the Nordic and Baltic Countries conference, DHNB 2022

作者： Ginter, Filip Kiiskinen, Harri Kanerva, Jenna Chang, Li-Hsin Salmi, Hannu TurkuNLP Department of Computing University of Turku Finland Department of Cultural History University of Turku Finland

We demonstrate the application of a deep-learning -based regressor, on a case study of predicting movie production year based on its plot summary. We show how the Integrated Gradients (IG) model explanation method can be used to attribute the predictions to individual input features and compare these to human-assigned attributions. Our purpose is to provide an insight into the application of modern NLP methods in the scope of a digital humanities research question, and test the model explanation techniques on a problem that is easy to understand, yet non-trivial for both humans and machine learning algorithms alike. We find that the model clearly outperforms non-expert human annotators, being able to date the movies well within the correct decade on average. We also demonstrate that the model-assigned attributions agree with those assigned by humans, especially for correct predictions. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 international (CC BY 4.0)

关键词： Natural language processing systems

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275页 << < 27 28 29 30 31 32 33 34 35 36 > >>

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：