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

30,380 篇 会议
4,640 篇 期刊文献
236 册 图书

馆藏范围

35,256 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

21,791 篇 工学
- 15,761 篇 计算机科学与技术...
- 13,251 篇 软件工程
- 5,816 篇 信息与通信工程
- 3,434 篇 控制科学与工程
- 2,683 篇 电子科学与技术（可...
- 2,618 篇 电气工程
- 2,351 篇 生物工程
- 1,891 篇 生物医学工程（可授...
- 1,538 篇 光学工程
- 1,346 篇 机械工程
- 1,217 篇 动力工程及工程热...
- 1,204 篇 仪器科学与技术
- 1,016 篇 化学工程与技术
- 855 篇 安全科学与工程
- 721 篇 交通运输工程
11,170 篇 理学
- 6,041 篇 数学
- 3,059 篇 物理学
- 2,570 篇 生物学
- 1,996 篇 统计学（可授理学、...
- 1,336 篇 系统科学
- 1,088 篇 化学
5,626 篇 管理学
- 3,281 篇 管理科学与工程(可...
- 2,624 篇 图书情报与档案管...
- 1,825 篇 工商管理
1,600 篇 医学
- 1,389 篇 临床医学
- 1,299 篇 基础医学(可授医学...
- 851 篇 药学(可授医学、理...
- 677 篇 公共卫生与预防医...
1,028 篇 法学
- 822 篇 社会学
644 篇 经济学
- 644 篇 应用经济学
490 篇 农学
430 篇 教育学
156 篇 文学
76 篇 军事学
39 篇 艺术学
1 篇 哲学

主题

1,120 篇 accuracy
867 篇 feature extracti...
860 篇 computational mo...
740 篇 deep learning
691 篇 training
679 篇 computer science
538 篇 real-time system...
523 篇 support vector m...
509 篇 machine learning
457 篇 predictive model...
426 篇 internet of thin...
378 篇 convolutional ne...
363 篇 data models
351 篇 computer archite...
334 篇 reliability
316 篇 optimization
284 篇 data mining
281 篇 routing
255 篇 conferences
252 篇 wireless sensor ...

机构

84 篇 institut univers...
82 篇 north-west unive...
80 篇 national centre ...
79 篇 infn sezione di ...
78 篇 tno technical sc...
77 篇 institute of inf...
76 篇 infn sezione di ...
66 篇 università di ca...
65 篇 université de st...
65 篇 dept. of informa...
62 篇 nikhef national ...
60 篇 dept. of informa...
56 篇 dept. of compute...
54 篇 dept. of compute...
53 篇 dept. of compute...
52 篇 school of automa...
50 篇 leiden universit...
48 篇 dept. of compute...
45 篇 dept. of electri...
44 篇 dept. of compute...

作者

85 篇 ferrara g.
85 篇 ardid m.
84 篇 calvo d.
84 篇 gal t.
84 篇 bozza c.
81 篇 chen a.
81 篇 kalekin o.
79 篇 díaz a.f.
77 篇 boumaaza j.
75 篇 coleiro a.
75 篇 gozzini s.r.
71 篇 huang f.
67 篇 dallier r.
60 篇 anguita m.
54 篇 kulikovskiy v.
42 篇 benoit d.m.
42 篇 eddymaoui a.
42 篇 labalme m.
41 篇 gagliardini s.
41 篇 del burgo r.

语言

31,520 篇 英文
3,341 篇 其他
299 篇 中文
54 篇 日文
45 篇 朝鲜文
2 篇 德文
2 篇 斯洛文尼亚文
1 篇 法文
1 篇 葡萄牙文

检索条件"机构=Computer Applications in Science and Engineering dept."

共 35256 条记录，以下是1171-1180 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：

Optimizing Privacy-Accuracy Trade-Off in IoT Intrusion Detection: An Analysis of FedAvg and FedProx with Differential Privacy

Optimizing Privacy-Accuracy Trade-Off in IoT Intrusion Detec...

引用

2024 IEEE International Women in engineering (WIE) Conference on Electrical and computer engineering, WIECON-ECE 2024

作者： Anwar, Sayeda Suaiba Hoque, Mohammed Moshiul Chittagong University of Engineering & Technology Dept. of Computer Science and Engineering Bangladesh East Delta University Chattagram Bangladesh

ISBN: (纸本)9798331535476

Ensuring the privacy and accuracy of interconnected network devices is crucial in the Internet of Things (IoT) landscape, especially when deploying Intrusion Detection Systems (IDS) on devices with constrained resources. This study offers a method to improve intrusion detection in IoT environments by combining Federated Learning with Differential Privacy. The proposed approach builds an efficient intrusion detection model by fusing Bidirectional Long Short-Term Memory (BiLSTM) with Convolutional Neural Networks (CNN). We evaluate this model on the Bot-IoT dataset, meticulously curated by the University of New South Wales (UNSW). This work aims to balance high detection accuracy with robust privacy protection, a crucial yet often neglected aspect of IoT security. We use federated learning to distribute intrusion detection tasks across various IoT devices while protecting data privacy, using differential privacy algorithms to assess and limit information leakage. This study evaluates two aggregation strategies, Federated Averaging (FedAvg) and Federated Proximal (FedProx), and examines how varying epsilon values and noise multipliers affect model accuracy. The findings indicate t hat a noise multiplier o f roughly 0.5 yields a steady accuracy curve, with FedProx achieving higher accuracy than FedAvg. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Monitoring AI-Based Processing for Predicting Poisonous Gas Emissions in Smart Cities Using Novel Temporal Dynamics Prediction Model 2

Monitoring AI-Based Processing for Predicting Poisonous Gas ...

引用

2nd International Conference on Data science and Information System, ICDSIS 2024

作者： Jaisharma, K. Deepa, N. Devi, T. Saveetha Institute Of Medical And Technical Sciences Saveetha School Of Engineering Dept. Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350381665

Smart cities, driven by technological advancements, face challenges related to environmental pollution, including poisonous gas emissions. Existing systems often struggle to efficiently monitor and predict these emissions, leading to limitations in accurately assessing and mitigating air quality issues. This study proposes a groundbreaking solution, the Novel Temporal Dynamics Prediction (NTDP) model, designed to overcome the limitations of current systems. By harnessing the NTDP model's innovative approach, smart cities can enhance their capability to analyze and forecast poisonous gas emissions, thereby improving the effectiveness of environmental management. The NTDP model offers a promising avenue for the future, revolutionizing the way smart cities address and mitigate the impact of toxic pollutants on air quality. The NTDP model achieved an accuracy of 99.1%, sensitivity of 98.9% and RMSE training 1.6 and testing 1.54 ug/m3. The results affirm the robustness and effectiveness of our optimized implementation, positioning it as a standout solution in disease prediction compared to commonly used machine learning techniques. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

IMPLICIT NEURAL REPRESENTATION INFERENCE FOR LOW-DIMENSIONAL BAYESIAN DEEP LEARNING 12

IMPLICIT NEURAL REPRESENTATION INFERENCE FOR LOW-DIMENSIONAL...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Dimitrakopoulos, Panagiotis Sfikas, Giorgos Nikou, Christophoros Dept. of Computer Science & Engineering University of Ioannina Ioannina Greece Dept. of Surveying & Geoinformatics University of West Attica Athens Greece

Bayesian inference is the standard for providing full predictive distributions with well calibrated uncertainty estimates. However, scaling to a modern, overparameterized deep learning setting typically comes at the cost of severe and restrictive approximations, sacrificing model predictive strength. With our approach, we factor model parameters as a function of deterministic and probabilistic components;the model is solved by combining maximum a posteriori estimation of the former, with inference over a low-dimensional, Implicit Neural Representation of the latter. This results in a solution that combines both predictive accuracy and good calibration, as it entails inducing stochasticity over the full set of model weights while being comparatively cheap to compute. Experimentally, our approach compares favorably to the state of the art, including much more expensive methods as well as less expressive posterior approximations over full network parameters. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

A Review of Overfitting Solutions in Smart Depression Detection Models 9

A Review of Overfitting Solutions in Smart Depression Detect...

引用

9th International Conference on Computing for Sustainable Global Development, INDIACom 2022

作者： Gupta, Gaurav Kumar Sharma, Dilip Kumar Gla University Dept. of Computer Engineering and Applications Mathura India

ISBN: (纸本)9789380544441

Overfitting is a common issue in machine learning-based depression detection model. Overfitting occurs when a machine learning model uses garbage data in the training datasets to the amount that deleteriously impacts on the concert of the model on new data. To predict depression level, most of the model uses machine learning and deep learning approaches. In this paper, a survey is conducted on the solution of overfitting in machine learning-based depression detection models. The survey covers the latest research articles and thesis published in the years 2020 and 2021. The findings of the survey reveal that the early stopping methodology, also called Control the Iteration as is better as compared to the penalty methodology, as it can avoid overfitting problems in the machine learning-based depression detection model. We have listed down other methods also to reduce overfitting like regularization methods, applying ensemble learning, training with more data, cross-validation, etc. © 2022 Bharati Vidyapeeth, New Delhi.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Enhanced Cell Nuclei Segmentation in Histopathological Images

Federated Learning for Enhanced Cell Nuclei Segmentation in ...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Usai, Marco Loddo, Andrea Putzu, Lorenzo Ruberto, Cecilia Di University of Cagliari Dept. of Mathematics and Computer Science Cagliari Italy University of Cagliari Dept. of Electrical and Electronic Engineering Cagliari Italy

ISBN: (纸本)9798350362480

This study addresses the critical challenge of cell nuclei segmentation in histopathological image analysis, which is essential for cancer diagnosis and prognosis. Traditional segmentation methods often struggle with complexities such as overlapping nuclei and variations in shape and size. Recent advancements in machine learning and deep learning, particularly convolutional neural networks, have improved segmentation accuracy but face limitations due to the need for large annotated datasets, often constrained by privacy regulations in the medical field. This research explores federated learning as a solution, enabling collaborative model training across institutions without sharing sensitive patient data. By leveraging diverse datasets while maintaining privacy, federated learning enhances model robustness and generalization capabilities. The study evaluates various federated learning techniques on in- and out-of-domain test sets, aiming to improve the reliability of segmentation models in clinical settings. The findings suggest that federated learning techniques can effectively address the challenges of data scarcity and domain shift, paving the way for more accurate and widely applicable segmentation algorithms in computational pathology. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Data-Enhanced Prediction with Decomposition and Amplitude-Aware Permutation Entropy in Distributed Computing Systems

Data-Enhanced Prediction with Decomposition and Amplitude-Aw...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Yuan, Haitao Hu, Qinglong Bi, Jing Zhang, Wei Zhang, Jia Zhou, MengChu School of Automation Science and Electrical Engineering Beihang University Beijing100191 China City University of Hong Kong Dept. of Computer Science 999077 Hong Kong College of Computer Beijing University of Technology Beijing100124 China University of Connecticut Dept. of Computer Science and Engineering StorrsCT06269 United States Southern Methodist University Dept. of Computer Science DallasTX75275 United States New Jersey Institute of Technology Dept. of Electrical and Computer Engineering NewarkNJ07102 United States

ISBN: (纸本)9781665410205

In recent years, distributed computing has wit-nessed widespread applications across numerous organizations. Predicting workload and computing resource data can facilitate proactive service operation management, leading to substantial improvements in quality of service and cost efficiency. However, these data often exhibit non-linearity, high volatility, and inter-dependencies across different categories, presenting challenges for accurate forecasting. Consequently, there is a critical need to develop a method that thoroughly and comprehensively analyzes all available data to forecast future trends effectively. This work proposes a novel integrated data-enhanced prediction model named SVI for achieving high-accuracy workload prediction in distributed computing systems. SVI employs the Savitzky-Golay filter and variational mode decomposition for feature processing, whose features are subsequently utilized by Informer for multivariate joint analysis of the enhanced data, achieving high-precision prediction. Ablation and comparative experiments with advanced prediction models are conducted on the Google cluster trace and other typical datasets. Realistic data-driven results indicate that SVI improves the prediction accuracy by 35.4% compared to the original Informer, with each module contributing to the performance enhancement. Furthermore, compared with Autoformer, SVI enhances the prediction accuracy of workload, CPU, and memory by 62.5%, 65.6%, and 69.1 %, respectively. © 2024 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Semi-Automated Behavior-Driven Testing for the Web Front-Ends 19

Semi-Automated Behavior-Driven Testing for the Web Front-End...

引用

19th IEEE International Conference on e-Business engineering, ICEBE 2023

作者： Ma, Shang-Pin Chen, Yu-An Guo, Yi-Jie Su, Yu-Sheng National Taiwan Ocean University Dept. of Computer Science & Engineering Keelung Taiwan National Chung Cheng University Dept. of Computer Science & Information Engineering Chiayi Taiwan

ISBN: (纸本)9798350325553

The required effort and time increase as web applications grow in size and complexity. Regression testing becomes time-consuming and repetitive, and there is a higher chance of human errors and omissions. Therefore, automating tests by recording test scripts and writing test case code (i.e., code for conducting specific test cases) can reduce effort, time, and human errors. However, technical personnel may not always understand and describe user requirements correctly, leading to issues of misaligned requirements. Therefore, integrating Behavior-Driven Development (BDD) into front-end automated testing can help facilitate communication and discussion with users. By collaboratively establishing user stories and scripts for testing, it should be possible to reduce issues of unclear or misaligned requirements. Currently, some project teams combine automated testing with BDD methods, which has been recognized for its effectiveness. However, the manual creation of test cases and the definition of BDD steps increase the workload. Moreover, there still needs to be a systematic workflow and supporting tools for effectively incorporating script recording tools into BDD testing. To address these issues, we propose a systematic process called 'Recorder-based BDD Testing for Front-end' (RBTF), which combines the script recording capabilities of automated testing tools with BDD practices. We also developed a tool called 'JUnit to Cucumber Converter' (JUCC) that facilitates the conversion between BDD specifications and test case codes. © 2023 IEEE.

关键词： Selenium

来源：评论

学校读者我要写书评

暂无评论

Using the Wavelet Packet Transform to Evaluate Parameters of Harmonics Clustered in Quadruples Using Linear Systems

Using the Wavelet Packet Transform to Evaluate Parameters of...

引用

2024 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2024

作者： Nicolae, Ileana-Diana Nicolae, Petre - Marian Nicolae, Marian-Ştefan University of Craiova Dept. of Computer Science and It Craiova Romania University of Craiova Dept. of Electrical Engineering Energetic and Aeronautics Craiova Romania

ISBN: (纸本)9798350360394

The paper presents an original technique used to evaluate the parameters of quadruples of harmonics clustered in an almost exclusive manner to quadruples of nodes from the bottom level of a Wavelet Packet Tree. The harmonic signal (RHS) generated by harmonics from a quadruple can be deduced with approximation from the analyzed signal by using original computational techniques. Linear systems were conceived based on the harmonics superposition and randomly chosen components of RHC (the approximated version of RHS). Their solving yields sets of possible solutions, that are afterward refined to exclude values with non-zero imaginary parts or deviant values. Averages over refined values are used. The indetermination relative to phase-shifts is solved considering the criterion of "best approximation"of RHC by the signal obtained through the superposition of the computed clustered harmonics. The harmonics from the studied quadruples are: (11, 13, 19, 21), (23,25,39,41) and (27,29,35,37). This paper provides the complementary technique for the odd harmonic identification within the range 3...41 (the odd harmonics not belonging to quadruples are coupled in pairs and were approached in a previous publication). © 2024 IEEE.

关键词： Wavelet analysis

来源：评论

学校读者我要写书评

暂无评论

IoT Attack Detection Method based on Synthetic Minority Over-Sampling with Random Forest Technique 10

IoT Attack Detection Method based on Synthetic Minority Over...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Tripathi, Neha Mishra, Amit Kumar Bagla, Piyush Pandey, Neeraj Kumar Mittal, Saksham Dept. of Computer Science and Engineering Dehradun India National Institute of Technology Dept. of Computer Science and Engineering Jalandhar India School of Computing Dit University Dehradun India

ISBN: (纸本)9789380544472

The primary objective of this study is to create a self-protection system for the Internet of Things (IoT) that relies on machine learning. One such resampling approach is the proposed IoT Attack Detection Method based on Synthetic Minority Over-sampling with Random Forest (IADMSMO-RF). To identify risks in the IoT ecosystem, we employ IADMSMO-RF, which improves network search computation. Assessment is performed on the Network Security Laboratory - Knowledge Discovery in Databases (NSL-KDD) dataset to see how effective the trial is in recognizing attacks on the IoT. For the success of the IoT, it is crucial to have a reliable system for detecting and protecting against cyberattacks. Compared to Synthetic Minority Oversampling Technique - Synthetic Minority Oversampling Technique (PPDT -SMOTE), the suggested technique outperforms it in attack detection and categorization. The proposed system has an accuracy of 97.46%, a false alarm rate of 0.2%, and a curve area of 98.76%. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Early Discovery of Emerging Entities in Persian Twitter with Semantic Similarity 9

Early Discovery of Emerging Entities in Persian Twitter with...

引用

9th International Conference on Web Research, ICWR 2023

作者： Yousefi, Shahin Hooshmand, Mohsen Afsharchi, Mohsen Dept. of Computer Science and Information Technology Zanjan Iran University of Zanjan Dept. of Electrical & Computer Engineering Zanjan Iran

ISBN: (纸本)9798350399691

Discovering emerging entities (EEs) is the problem of finding entities before their establishment. These entities can be critical for individuals, companies, and governments. Many of these entities can be discovered on social media platforms, e.g. Twitter. These identities have been the spot of research in academy and industry in recent years. Similar to any machine learning problem, data availability is one of the major challenges in this problem. This paper proposes EEPT that is an online clustering method able to discover EEs without any need for training on a dataset. Additionally, due to the lack of a proper evaluation metric, this paper uses a new metric to evaluate the results. The results show that EEPT is promising and finds significant entities before their establishment. © 2023 IEEE.

关键词： Semantics

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 << < 114 115 116 117 118 119 120 121 122 123 > >>

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：