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

106,776 篇 会议
685 篇 期刊文献
560 册 图书
4 篇 学位论文

馆藏范围

108,024 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

60,928 篇 工学
- 49,906 篇 计算机科学与技术...
- 39,834 篇 软件工程
- 13,431 篇 信息与通信工程
- 11,483 篇 生物工程
- 8,515 篇 控制科学与工程
- 6,743 篇 电气工程
- 6,346 篇 生物医学工程（可授...
- 3,872 篇 光学工程
- 3,330 篇 机械工程
- 2,987 篇 电子科学与技术（可...
- 2,763 篇 网络空间安全
- 2,723 篇 安全科学与工程
- 2,516 篇 动力工程及工程热...
- 2,322 篇 化学工程与技术
- 2,189 篇 仪器科学与技术
26,005 篇 理学
- 12,117 篇 生物学
- 12,067 篇 数学
- 5,173 篇 物理学
- 4,920 篇 统计学（可授理学、...
- 3,517 篇 系统科学
- 2,333 篇 化学
17,449 篇 管理学
- 11,015 篇 管理科学与工程(可...
- 7,615 篇 图书情报与档案管...
- 5,172 篇 工商管理
13,607 篇 教育学
- 13,406 篇 教育学
6,413 篇 医学
- 5,474 篇 临床医学
- 5,225 篇 基础医学(可授医学...
- 3,407 篇 药学(可授医学、理...
- 2,891 篇 公共卫生与预防医...
3,375 篇 法学
- 2,921 篇 社会学
1,965 篇 文学
1,768 篇 农学
1,663 篇 经济学
267 篇 艺术学
106 篇 军事学
11 篇 历史学
10 篇 哲学

主题

7,165 篇 machine learning
6,965 篇 deep learning
5,342 篇 accuracy
5,031 篇 training
4,826 篇 computational mo...
4,192 篇 education
3,835 篇 students
3,548 篇 feature extracti...
3,029 篇 support vector m...
3,026 篇 predictive model...
3,024 篇 machine learning...
2,975 篇 convolutional ne...
2,482 篇 real-time system...
2,333 篇 data models
2,231 篇 neural networks
1,982 篇 cloud computing
1,830 篇 teaching
1,486 篇 reinforcement le...
1,445 篇 artificial intel...
1,385 篇 internet of thin...

机构

826 篇 chitkara univers...
145 篇 lovely professio...
106 篇 computer science...
98 篇 karnataka bangal...
94 篇 college of compu...
89 篇 school of comput...
79 篇 chitkara univers...
76 篇 school of comput...
72 篇 department of co...
64 篇 department of co...
64 篇 department of co...
60 篇 department of co...
58 篇 school of comput...
50 篇 department of in...
49 篇 chitkara univers...
49 篇 department of co...
43 篇 department of me...
42 篇 school of automa...
41 篇 vellore institut...
41 篇 chennai

作者

70 篇 shiva mehta
70 篇 anjali t.
53 篇 li yang
42 篇 sharma vikrant
40 篇 wang lei
40 篇 kukreja vinay
39 篇 rakesh kumar
37 篇 gill kanwarparta...
35 篇 sharma neha
34 篇 wang jing
32 篇 vinay kukreja
31 篇 lei wang
31 篇 zhang lei
30 篇 huang yueh-min
29 篇 liu bo
29 篇 yu wang
27 篇 li xin
26 篇 amandeep nagpal
25 篇 vinay gautam
25 篇 shang wang

语言

100,203 篇 英文
7,459 篇 其他
786 篇 中文
27 篇 西班牙文
17 篇 葡萄牙文
5 篇 阿拉伯文
3 篇 法文
3 篇 土耳其文
2 篇 俄文

检索条件"任意字段=International Conference on Teaching and Learning in Computing and Engineering"

共 108025 条记录，以下是4521-4530 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：

Relavation Schemes of Malicious Data For Distributed Machine learning 2

Relavation Schemes of Malicious Data For Distributed Machine...

引用

2nd international conference on Advancements in Smart, Secure and Intelligent computing, ASSIC 2024

作者： Vidhya, Veda Kiran, Ajmeera Rao, Yedavalli Venkata Raghava Kalyani, A. Naga Vamsinath, J. Purushotham, P. Mlr Institute of Technology Department of Computer Science and Engineering Hyderabad India Cse Aiml Avniet Jntuh Aiml Dept India Hyderabad India Vnr Vignana Jyothi Institute of Enginnering and Technology Department of Cse Hyderabad India

ISBN: (纸本)9798350370188

Distributed machine learning (DML) may train on large datasets even if nodes cannot give accurate results quickly. This exposes more attacker targets than non-distributed. Semi and Basic comprise DML. Central cyberspace sends research activities to distributed computers, which integrate learning. Semi-DML learning records receive centre server resources with Basic DML. For fundamental DML, I included data poisoning detection (4304). It uses cross-learning to find tainted data. To estimate the right number of loops, we must mathematically verify that the co-learning mechanism produces training loops. We upgrade a semi-DML data poisoning detection method to safeguard central resource learning. Resource allocation is optimised to maximise system resources. Simulations suggest that 60% strategic reversion and 20% supporting vector machines can improve the final replica's precision in basic DML. Basic-DML resource waste can be reduced by 20-100% with better resource allocation and data poisoning detection. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Towards Safe Online Machine learning Model Training and Inference on Edge Networks 22

Towards Safe Online Machine Learning Model Training and Infe...

引用

22nd IEEE international conference on Machine learning and Applications, ICMLA 2023

作者： Maruf, Md Al Azim, Akramul Auluck, Nitin Sahi, Mansi Ontario Tech University Department of Electrical Computer and Software Engineering Oshawa Canada Indian Institute of Technology Departmcnt of Computer Science and Engineering Ropar India

ISBN: (纸本)9798350345346

With the increasing demand for edge computing in cyber-physical system (CPS) applications, ensuring the safety and reliability of machine learning models running on edge devices during online model training and inference is essential. Although data and model parallelism offer significant advantages for large machine learning model training, adopting parallel computing architecture in edge networks is challenging. It introduces safety concerns while splitting and integrating machine learning models over different computing nodes, which can pose risks to the integrity and reliability of the system. Therefore, online model training and inference in edge networks require a safe parallel computing architecture to achieve improved performance with optimal resource utilization. To address this challenge, we propose an efficient machine learning model partitioning algorithm that considers the safety constraint and requirements of edge networks and includes the triple-modular redundancy (TMR) technique for trusted computation. Our proposed approach achieves a significant speedup of approximately 56.3% in net training time compared to the non-partitioning approach, making it more efficient and suitable for real-time applications in edge networks. © 2023 IEEE.

关键词： Edge Networks Machine learning Model Partitioning Triple Modular Redundancy (TMR)

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement learning for Optimal Planning of Fast Electric Vehicle Charging Stations at a Large Scale

Deep Reinforcement Learning for Optimal Planning of Fast Ele...

引用

ASCE international conference on computing in Civil engineering (I3CE)

作者： Heo, Jae Chang, Soowon Purdue Univ Sch Construct Management Technol Smart & Sustainable Human Urban Bldg Interact Lab W Lafayette IN 47907 USA

ISBN: (数字)9780784485248

ISBN: (纸本)9780784485248

Electric vehicles (EVs) have been widely adopted with the expectation of reducing CO2 emissions. However, the lack of public fast charging stations has hindered the growth of EVs. Despite extensive research on optimal installation of EV charging stations (EVCS), a decision model for a large scale and diverse spatial conditions has been still lacking. This research intends to explore a deep reinforcement learning model using deep Q-network (DQN) algorithms and test the model for optimal planning of fast EVCS at a large scale. The DQN model considers geographic (e.g., building footprints, street network), economic (e.g., capacity of charging station), and environmental (e.g., solar energy) perspectives. The learning model identifies the energy balance between electricity generation and consumption and investigates spatial patterns nearby potential charging stations. This study can aid in decision-making for suitable EVCS sites with advancing the microgrid approach-based infrastructure systems, ultimately enhancing urban sustainability considering vehicle-to-building integration.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Agricultural Practices: Deep learning for Vegetable Classification 1

Agricultural Practices: Deep Learning for Vegetable Classifi...

引用

1st international conference on Innovations in Communications, Electrical and Computer engineering, ICICEC 2024

作者： Jillelamudi, Ruchitha Tarimella, Sai Suchitra Kotha, Indhu Peruri, Niharika Kamepalli, Sujatha Chekuri, Anjana Vfstr Deemed to be University School of Computing Guntur India

ISBN: (纸本)9798350376517

The agricultural industry is undergoing significant advancements, yet traditional methods for classifying vegetables by attributes such as size, color, texture, and freshness remain a challenge for farmers and vendors. This paper explores the application of deep learning models to automate the classification and recognition of vegetables, aiming to enhance efficiency and innovation in agricultural practices. Deep learning-powered automated systems can handle large volumes of produce, optimizing processes like sorting, grading, and quality inspection, thereby accelerating these tasks. Additionally, such systems can improve self-checkout mechanisms in retail by accurately identifying and pricing vegetables, enhancing customer convenience and minimizing errors. Utilizing a specialized dataset of vegetable images, this study employs various deep learning models, incorporating preprocessing techniques like data augmentation and normalization. The effectiveness of these models, particularly a Convolutional Neural Network (CNN) and VGG16, is rigorously tested. The results demonstrate that the CNN model achieves superior accuracy at 92.69 percentage, compared to 87.37 percentage for VGG16, highlighting the potential of deep learning models in revolutionizing vegetable recognition and classification. © 2024 IEEE.

关键词： Vegetables

来源：评论

学校读者我要写书评

暂无评论

Adaptive MP3 Steganography Based on Adversarial Gradient 4

Adaptive MP3 Steganography Based on Adversarial Gradient

引用

4th international conference on Electronic Information engineering and Computer Science, EIECS 2024

作者： Yang, Hanlin Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Sichuan Province Chengdu China

ISBN: (纸本)9798331531409

In this research, we present a new adaptive MP3 steganography technique that utilizes adversarial gradients. With the development of deep learning technology and the improvement of GPU computing performance, MP3 steganalysis methods that employ neural networks display significant detection precision under certain scenarios. To counteract these deep learning-based MP3 steganalysis methods within the realm of QMDCT (Quantization Modified Discrete Cosine Transform), we propose a new steganography method that leverages adversarial gradient. Firstly, we train a state-of-the-art deep learning steganalyzer as the adversarial model. Then, adversarial gradients are computed based on this adversarial model. Finally, these gradients are used as distortion costs that guide the embedding of data, leading the adversarial model to incorrectly classify the secret file as a benign carrier file. Our experiments demonstrate that this method is highly effective in evading detection by existing deep learning-based MP3 steganalysis methods and shows promising generalization capabilities. © 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

Fed-Avis: A Lightweight Federated learning Assisted Anti-Vehicle Infiltration System 24

Fed-Avis: A Lightweight Federated Learning Assisted Anti-Veh...

引用

25th international conference on Distributed computing and Networking, ICDCN 2024

作者： Agrawal, Dewesh Singh, Gurpreet Singh, Harinderjit Singh, Kulvir Jha, Prianshu Patel, Yashwant Singh Computer Science & Engineering Thapar Institute of Engineering & Technology Punjab Patiala India

ISBN: (纸本)9798400716737

Vehicle anti-infiltration systems play a crucial role in modern security infrastructure, particularly in military security scenarios where unauthorized access poses a significant threat. However, current vehicle infiltration systems encounter with mobility, operational efficiency, and privacy-related challenges. Most of the conventional solutions often necessitate substantial processing power and complex hardware requirements. Thus, the integration of federated learning into anti-vehicle intrusion systems reduces the need for extensive computing resources while reducing operational costs and enhancing data accuracy and privacy. Hence, in this work, we introduce Fed-AVIS (Federated learning-based Anti-Vehicle Infiltration System), which leverages motion sensors and camera traps in conjunction with lightweight deep learning models to reduce and simplify processing requirements. We apply the federated learning approach to a dataset comprising a total of 6,772 images, encompassing six distinct categories of military and civilian vehicles. To maintain system simplicity, we employ lightweight deep-learning models like TinyYOLOv4 and MobileNetV2. Additionally, to minimize latency, we utilize the Azure service bus queue for alert messages and location passing. The average message delay in Fed-AVIS is 6.5 seconds, with the longest delay observed at 11 seconds and the shortest at 4 seconds. Edge devices employed in the surveillance system, such as Raspberry Pi, exhibited power consumption ranging from approximately 2.84 to 4 watts when operating at maximum capacity. Overall the Fed-AVIS improves the performance in terms of computational cost, classification accuracy, energy saving, privacy, and communication latency comparing with the current approaches. © 2024 ACM.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Optimization of Financial Market Forecasting Model Based on Machine learning Algorithm

Optimization of Financial Market Forecasting Model Based on ...

引用

2023 international conference on Networking, Informatics and computing, ICNETIC 2023

作者： Tang, Denglin Guizhou University of Commerce Guiyang550004 China

ISBN: (纸本)9798350313314

With the rapid growth of economic and social fields from digitalization to intelligence, the traditional risk management system is not suitable for the new model of financial innovation and development. Based on the advantages of machine learning, it is of great significance to use artificial neural network (ANN) to analyze the characteristics of financial markets. In this paper, the deep neural network model in machine learning algorithm is used for financial risk forecast, and a forecast model based on ANN is constructed. The model collects the relevant data of financial market, designs the deep learning network structure according to the training samples, trains the sample set by using the ANN-based forecast model, outputs the optimal solution, and completes the financial risk forecast. Simulation results show that, after many iterations, the accuracy of this method is obviously better than that of traditional Support Vector Machines (SVM) algorithm, with the accuracy as high as 96.84%, 20.55% higher than that of SVM algorithm, and the error reduced by 32.84%. Therefore, the financial market forecasting model based on ANN is a reasonable and feasible evaluation model. © 2023 IEEE.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Machine learning Approach for Human Brain Counselling 15

Machine Learning Approach for Human Brain Counselling

引用

15th international conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Palkar, Jayashri D. Jain, Chetana Hasmukh Kashinath, Kendre Priyanka Vaidya, Anusha Omkar Borate, Vishal Kisan Mali, Yogesh Kisan Trinity Academy of Engineering Wagholi Pune India Dr D Y Patil College of Engineering & Innovation Talegaon Pune India G.H Raisoni College of Engineering and Management Wagholi Pune India

ISBN: (纸本)9798350370249

An innovative step in treating the mental health issues common to college students is the PEACE web tool. With the use of cutting-edge machine learning (ML) algorithms, this platform tailors counselling advice to each student's unique needs. By means of its creative methodology, PEACE not only pinpoints the unique needs of students, but also pairs them with counsellors who have specialized knowledge, which increases the counselling process' effectiveness. PEACE seeks to remove obstacles standing in the way of students seeking mental health assistance by offering a private and convenient online platform for counselling services. By streamlining the matching process, the application's machine learning algorithm guarantees that kids are matched with counsellors who are qualified to manage their challenges. This strategy not only helps to lessen the stigma associated with mental health issues, but it also makes support services more easily accessible, which eventually creates an atmosphere that is better for students' mental health in general. Furthermore, the PEACE application is a noteworthy development in the field of mental health support in addition to providing a prompt resolution to the urgent problems encountered by college students. PEACE advances the field of mental health care by incorporating state-of-the-art technologies into the counselling process, opening the door for more effective and individualized therapies. As such, the application is a ray of hope, providing a revolutionary method for resolving mental health issues among college students. ©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

Credit Card Fraud Detection: A Hybrid of PSO and K-Means Clustering Unsupervised Approach 13

Credit Card Fraud Detection: A Hybrid of PSO and K-Means Clu...

引用

13th international conference on Cloud computing, Data Science and engineering, Confluence 2023

作者： Sharma, Nityanand Ranjan, Vivek Maulana Azad National Institute of Technology Computer Science and Engineering Bhopal India

ISBN: (纸本)9781665462631

With the rise of the internet and online shopping, the use of credit cards for online purchases skyrocketed and so did the incidents of online financial frauds. In the year 2018 alone, 24.26 Billion USD was lost worldwide due to credit card frauds. As a result of these frauds, many innocent people have lost a lot of their earnings which discouraged them from ever taking part in online payment activities. The most common victims of such frauds are people in old age as they are less tech-savvy. Traditionally machine learning and deep learning approaches to credit card fraud detection have been around supervised learning methods but supervised learning methods always have to rely on labelled datasets which means that they need to get prior ideas about what type of transaction is considered fraud before giving predictions on other transactions. Some recent work has been done on fraud detection using unsupervised learning. In this work, we analyze the performance of unsupervised learning techniques such as k-means clustering on a credit card fraud detection dataset. We also try to further the research in this area by proposing a Particle swarm optimization and k-means clustering hybrid model for the same. The model based on our proposed approach has improved the performance of k-means clustering approach. Our Hybrid approach has shown better accuracy, precision, and recall than the k-means clustering approach. © 2023 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Improving Time-Series Forecasting Performance Using Imputation Techniques in Deep learning

Improving Time-Series Forecasting Performance Using Imputati...

引用

2024 international conference on Smart computing, IoT and Machine learning, SIML 2024

作者： Utama, Agung Bella Putra Wibawa, Aji Prasetya Handayani, Anik Nur Irianto, Wahyu Sakti Gunawan Aripriharta Nyoto, Amat Universitas Negeri Malang Department of Electrical Engineering and Informatics Malang Indonesia Universitas Negeri Malang Department of Mechanical Engineering and Industry Malang Indonesia

ISBN: (纸本)9798350364101

This study investigates the effectiveness of various missing data imputation techniques on the performance of deep learning models for time-series forecasting using the Beijing PM2.5 dataset. Imputation methods including Mean, Mode, Median, Multiple Imputation by Chained Equations (MICE), Last Observation Carried Forward (LOCF), and K-Nearest Neighbors (KNN) are compared across different deep learning architectures: Recurrent Neural Networks (RNN), Long Short-Term Memory Networks (LSTM), Bidirectional LSTM Networks (Bi-LSTM), and Gated Recurrent Units (GRU). Performance is evaluated using metrics such as Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R2). Results indicate that the KNN imputation method consistently outperforms other techniques across all models, achieving lower MAPE (0.186) and RMSE (18.495) values. Furthermore, KNN-imputed models exhibit higher R2 values, indicating better model fit than other imputation methods. These findings underscore the importance of preprocessing in time-series forecasting and highlight the potential of KNN imputation to enhance predictive accuracy in real-world applications. Robust imputation strategies like KNN promise to improve forecasting accuracy and reliability, particularly in domains where accurate predictions are crucial for decision-making. Future research may focus on refining and integrating imputation techniques with advanced deep-learning methodologies to enhance forecasting capabilities in diverse application scenarios. © 2024 IEEE.

关键词： Forecasting

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 << < 449 450 451 452 453 454 455 456 457 458 > >>

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：