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

2,338 篇 会议
9 册 图书
1 篇 期刊文献

馆藏范围

2,348 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,521 篇 工学
- 1,377 篇 计算机科学与技术...
- 1,168 篇 软件工程
- 345 篇 生物工程
- 324 篇 信息与通信工程
- 197 篇 生物医学工程（可授...
- 133 篇 控制科学与工程
- 118 篇 电气工程
- 110 篇 光学工程
- 80 篇 机械工程
- 76 篇 安全科学与工程
- 74 篇 化学工程与技术
- 69 篇 电子科学与技术（可...
- 57 篇 农业工程
790 篇 理学
- 408 篇 数学
- 362 篇 生物学
- 201 篇 统计学（可授理学、...
- 156 篇 物理学
- 131 篇 系统科学
- 69 篇 化学
411 篇 管理学
- 221 篇 管理科学与工程(可...
- 217 篇 图书情报与档案管...
- 135 篇 工商管理
195 篇 医学
- 185 篇 临床医学
- 184 篇 基础医学(可授医学...
- 129 篇 药学(可授医学、理...
- 76 篇 公共卫生与预防医...
90 篇 农学
- 90 篇 作物学
88 篇 法学
- 77 篇 社会学
65 篇 教育学
- 65 篇 教育学
54 篇 经济学
- 54 篇 应用经济学
3 篇 文学
1 篇 军事学

主题

323 篇 machine learning
147 篇 deep learning
94 篇 support vector m...
93 篇 accuracy
91 篇 machine learning...
71 篇 predictive model...
61 篇 adversarial mach...
59 篇 feature extracti...
50 篇 forecasting
49 篇 training
48 篇 convolutional ne...
45 篇 computational mo...
39 篇 data models
32 篇 decision trees
31 篇 real-time system...
30 篇 analytical model...
30 篇 computer vision
29 篇 prediction algor...
28 篇 data mining
28 篇 sentiment analys...

机构

25 篇 chitkara univers...
9 篇 college of manag...
8 篇 computer science...
8 篇 graphic era hill...
7 篇 school of comput...
6 篇 computer science...
6 篇 greater bay area...
6 篇 school of nursin...
6 篇 department of co...
5 篇 kkr and ksr inst...
5 篇 institute of art...
5 篇 school of comput...
5 篇 department of in...
4 篇 school of comput...
4 篇 the state key la...
4 篇 guangdong univer...
4 篇 henan engineerin...
4 篇 chitkara centre ...
4 篇 school of comput...
4 篇 school of comput...

作者

9 篇 kukreja vinay
8 篇 mehta shiva
7 篇 mahamudul hasan
7 篇 shiva mehta
7 篇 william p.
7 篇 hasan mahamudul
5 篇 p. william
5 篇 wang yu
4 篇 ali md sawkat
4 篇 zhang tao
4 篇 zhou tianwei
4 篇 maheen islam
4 篇 faisal rehman
4 篇 patnaik sanghami...
4 篇 maranan ramya
4 篇 md sawkat ali
4 篇 wang wei
4 篇 mohanty arpeeta
4 篇 taskeed jabid
4 篇 pattnayak partha...

语言

2,264 篇 英文
84 篇 其他
18 篇 中文

检索条件"任意字段=4th International Conference on Machine Learning and Computer Application, ICMLCA 2023"

共 2348 条记录，以下是21-30 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：

A distributed machine learning dynamic remote proof scheme that resists collusion attacks 4

A distributed machine learning dynamic remote proof scheme t...

引用

4th international conference on Network Communication and Information Security, ICNCIS 2024

作者： Wang, Ke Wu, Qiuxin Qin, Yu School of Applied Science Beijing Information Science and Technology University Beijing100192 China Trusted Computing and Information Assurance Laboratory Institute of Software Chinese Academy of Science Beijing100190 China

ISBN: (数字)9781510688261

ISBN: (纸本)9781510688254

Based on the security of distributed machine learning data and model based on remote proof, a cross-domain dynamic remote proof scheme based on ring signature improves the efficiency of computer cluster proof, the application of dynamic signature, realizes the real-time measurement of the confidence of computer cluster, and strengthens the real-time protection of data and model. computers with different security domain may adopt different remote proof mechanism, and convert the proof information of different proof methods into unified proof information, thus realizes the cross-domain dynamic remote proof between computer clusters. Noise is added when the cloud server distributes data to a distributed computer cluster. Due to the particularity of distributed architecture and the unsolution of indefinite equations, the enemy cannot conspire with one or more computers to steal data or the model parameters trained by endpoints. Finally, the safety of this method is verified through safety analysis and experimental analysis, and the computational overhead required in the proof process is reduced compared with other methods. © 2025 SPIE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Enhancing Mobile application Security through Android threat Classification 4

Enhancing Mobile Application Security Through Android Threat...

引用

4th international conference on Evolutionary Computing and Mobile Sustainable Networks, ICECMSN 2024

作者： Josephine, Helen V.L. Rajagopal, Manikandan Gayatri, S. Lakshmi, K. Business Analytics School of Business and Management Chrisut University Bangalore560074 India School of Business and Management Chrisut University Bangalore560029 India School of Business and Management Christ Univeristy Bangalore560074 India School of Computer Science and Application Reva University Bangalore India

the Android application market has grown significantly, offering customers an ever-growing range of features to suit a variety of purposes. Users are exchanging more and more sensitive data thanks to the widespread usage of mobile applications, therefore safeguarding personal information is crucial. But this boom has also opened the door for a corresponding rise in cybersecurity risks, especially for malware and adware that target mobile devices. It is imperative to categorise mobile applications into distinct groups such as malware, adware, and benign in order to fortify the mobile ecosystem. this project's primary objective is to create and apply cutting-edge machine learning algorithms that can precisely categorise mobile apps into groups including adware, malware, and benign apps. this will necessitate investigating various machine learning strategies and ensemble methods to improve classification accuracy and robustness. Multiple machine learning models were developed based on feature importance, utilizing various machine learning techniques. the evaluation metrics showcase the effectiveness of the final model, especially the Tuned XGBoost model. While achieving a high overall accuracy of 92.51%, the findings highlight the importance of considering diverse features beyond traditional flow-based ones, providing a more robust and complete perspective on mobile network security. © 2025 the Authors. Published by Elsevier B.V.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Aggregation Methods in Federated learning on MNIST 4th

A Comparative Analysis of Aggregation Methods in Federated L...

引用

4th international conference on Artificial Intelligence and Knowledge Processing

作者： Agarwal, Vedik Chandnani, Chirag Jitendra Kulkarni, Shlok Chetan Aren, Aditya Srinivasan, Kathiravan VIT Vellore Sch Comp Sci SCOPE Vellore 632014 Tamil Nadu India

ISBN: (纸本)9783031734762;9783031734779

machine learning methods that protect privacy are now highly sought after in the big data and ubiquitous connection era. Federated learning (FL) is a unique and revolutionary method that solves this problem by allowing machine learning models to be trained on several dispersed clients or devices without requiring the transfer of raw data between the devices and servers. Since then, it has emerged as a prospective paradigm for training various machine learning models while preserving data privacy. this paper offers a thorough analysis of different Federated learning aggregation procedures and how they affect the accuracy and loss of the model. Within the Federated learning framework, this paper explores and contrasts four different aggregating methods: Federated Averaging (FedAvg), Federated Proximal (FedProx), Federated Median (FedMedian) and q-FedAvg. We assess these strategies using the Modified National Institute of Standards and Technology (MNIST) dataset, a benchmark dataset for handwritten digit classification, using a Convolutional Neural Network (CNN) based model. Our test results show notable differences in model performance between various aggregation techniques. the paper unveils distinct convergence behaviors and stability characteristics of each algorithm under various data distribution scenarios. Notably, FedProx emerges as a promising choice, demonstrating consistent performance across diverse data distributions. the paper's findings underscore the importance of careful algorithm selection based on specific application requirements and data characteristics.

关键词： Federated learning Aggregation Techniques Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

A Grading Model for Jasmine Flowers Using Deep learning and Quantum machine learning 4

A Grading Model for Jasmine Flowers Using Deep Learning and ...

引用

4th international conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Pratiksha Cauvery, K.P. thrisha, R. Harshitha, T. Panigrahi, Suman thangavel, Senthil Kumar Somasundaram, K. Boopathy, C.P. Amrita School of Physical Sciences Department of Mathematics Tamil Nadu Coimbatore India Amrita School of Computing Department of Computer Science and Engineering Tamil Nadu Coimbatore India Amrita School of Engineering Department of Elelctical and Electronics Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798331523923

the flowers of Jasmine hold immense economic importance in the agricultural sector and the perfume industry, as the value and satisfaction of the market, are heavily influenced by the quality of these flowers. the already very labor-intensive, subjective, and inefficient manual method of grading plants based on their physical and aromatic characteristics is unsuitable on a large scale. this paper handles these limitations by introducing automation in the grading process using Deep learning and Quantum machine learning. the conceptual methodology mandates automatic flower placement and high-resolution imagery with a conveyor belt. the deep learning model, exactly a type of Convolutional Neural Network (CNN), would explain freshness in terms of visual features like color, texture, structural strength, and vice versa. Additionally, quantum-inspired algorithms have been employed to enhance the computation and performance of the model. From the analysis, a decision-making module classifies entrant flowers into fresh and otherwise, thereby sending them to their respective places, where all packing or disposal could be achieved. this DL-QML hybrid approach points out the exemplary high accuracy, scalability, and efficiency in jasmine grading and hence minimizes manual intervention in quality control assembly lines. the findings provide the card of the feasibility of joining QML in addressing computational challenges of agro-product quality assessment, opening avenues in application far broader than floriculture. © 2025 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A QoS and Load Balancing Predictive Model Based on LSTM and Random Forest Regression in SDN: A Rest API Approach 4th

A QoS and Load Balancing Predictive Model Based on LSTM and ...

引用

4th international conference on Data and Information in Online Environments

作者： Ansari, Muhammad Salman Zhang, JianXun Shaban Tianjin Univ Technol & Educ Tianjin Peoples R China Univ Elect Sci & Technol Chengdu Peoples R China

ISBN: (纸本)9783031807121;9783031807138

Fog Computing, Software Define Networking, RESTful API and machine learning are new technologies in the area of ICT as well as in Networking. Fog computing brought high performance computing at the edge of network and Software Defined networking. As we intended to head towards QoS and Load balancing in SDN. In this work we cover an initial segment which is machine leaning model implementation on a network traffic information to predict future outcomes for traffic flow. Meanwhile, in comprehensive research we intended to reduce network congestion, jitter, QoS and load balancing by learning past traffic flow information. As well as, we aim to improve maximum utilization of link-bandwidth. through RESTful API of SDN, we can embed machine learning based prediction model to the network server which can modify the network policies by learning from past experiences. In this paper, we proposed a QoS and load balancing framework. A Server and SDN based application for network monitoring, management and controlling the policies over network gateway for better performance in regard of traffic flow. Experiment result shows that implementation of machine learning over network traffic flow information immensely important for new emerging technologies. the evaluation results of machine learning model we implemented in this work depicts that model performs well. Meanwhile the model improves by increasing with the number of epochs.

关键词： machine learning in Networking SDN RESTful API QoS and Load balancing

来源：评论

学校读者我要写书评

暂无评论

application of machine learning in port throughput prediction 4

Application of machine learning in port throughput predictio...

引用

4th international conference on computer Vision, application, and Algorithm, CVAA 2024

作者： Liu, Shulin Huang, Lei School of Economics and Management Beijing Jiaotong University Beijing China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

the rapid growth of global trade has made ports indispensable core nodes in the global logistics network. the study of port throughput has become a hot topic for modern researchers. this study focuses on Guangzhou Port Group, extracting its throughput data from 2014 to 2023 for preliminary time series analysis. By observing the autocorrelation and partial autocorrelation graphs based on monthly throughput data, we explored how port throughput is influenced by changes in industrial structure, the economic conditions of the hinterland, transportation capacity, and unexpected factors. Furthermore, through regression analysis, we identified key factors significantly impacting port throughput, including total import and export trade volume (in billions of RMB), total retail sales of consumer goods (in ten thousand RMB), waterway freight volume (in million tons), fixed asset investment growth rate (%), and overseas pandemic death tolls. Additionally, this study developed a combined RF-SVM-XGB port throughput prediction model, improving the average error by 3 percentage points. In terms of predictive performance and model error, the combined prediction model demonstrated better fitting accuracy. Finally, to enhance the model’s stability and generalization ability, cross-validation was used for result validation. Feasibility suggestions for port development were also provided. © 2025 SPIE.

关键词： Autocorrelation

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Federated learning, Deep learning, and Traditional machine learning Techniques for IoT Malware Detection 4

Comparative Analysis of Federated Learning, Deep Learning, a...

引用

4th IEEE international conference on Artificial Intelligence in Cybersecurity, ICAIC 2025

作者： Darwish, Rami Roy, Kaushik North Carolina A&T State University Department of Computer Science GreensboroNC United States

ISBN: (纸本)9798331518882

this paper addresses the challenge of classifying Internet of things (IoT) binary files as either malware or benign using graph-theoretical features derived from Control Flow Graphs (CFGs). We use a dataset of 248,276 IoT binary files, each represented by 23 features. Our analysis presents traditional machine learning (ML) classifiers, including Logistic Regression (LR), K-Nearest Neighbors (KNN), and Random Forest (RF), with deep learning (DL) techniques-a Deep Neural Network (DNN) and a Convolutional Neural Network (CNN). Further developing these techniques, we propose the first application of Federated learning (FL) for IoT binary file classification based on CFG features, which provides a decentralized and privacy-preserving solution to malware detection. FL is simulated with two models, FL-DNN and FL-CNN, under IID (Independent and Identically Distributed) and Non-IID scenarios. IID divides the data equally among clients, while Non-IID causes an imbalance to reflect real-world scenarios where data distribution is significantly varied among the clients. In order to handle the challenges in imbalanced data scenarios, threshold tuning and class weighting have been applied to improve FL performance. Our results showed that, among the machine learning techniques, RF achieved the highest accuracy of 96.06%, followed by KNN at 92.78%, and LR at 74.25%. For DL models, DNN and CNN are competitive, achieving accuracies of 93.55% and 93.24%, respectively. Within the FL framework, FL-CNN achieved an accuracy of 95.27% under the IID scenario, while FL-CNN and FL-DNN achieved 95.09% and 94.76% under the Non-IID scenario. Our findings illustrate the feasibility of applying FL for IoT malware detection based on the analysis of IoT binary files with regard to CFG-based features, which can be extended to broader IoT domains such as health care, industrial IoT, and autonomous vehicles. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Streamlining Financial Predictions: A Web application for Stock, Cryptocurrency, and Market Sentiment Analysis 4

Streamlining Financial Predictions: A Web Application for St...

引用

4th international conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Vivekanand, Chettiyar Vani Kumar, P. Amizhthini, A. Rajalakshmi Engineering College Computer Science and Engineering Chennai India

ISBN: (纸本)9798331523923

Among the high-degree lines of study in this area, one of the most interesting ones is stock price prediction, particularly in the context of machine learning and time series forecasting models. the traditional past ones include ARIMA, and SARIMAX, while deep learning models have been recently applied for predicting the stock prices based upon historical data. However, these models do hold much promise and also come with volatility and non-linearity in financial markets. Causes for such inaccuracies in predictions include sudden market shifts, external economic events, and investor sentiment. All these factors are difficult to model well. this study will propose a web application that uses advanced time series models to try and overcome such challenges. the system is implemented with Streamlit and Flask, so it gives users a smooth interface. It has five critical modules: Nifty 50, which deals with the analysis and forecasting of stocks using ARIMA and SARIMAX models;Global Market Data, which fetches real-time data from the Yahoo Finance API for granular analysis;Cryptocurrency, which relies heavily on Ethereum data with historical analysis and price forecasting;Twitter Sentiment Analysis, which focusses on real-time analysis of market sentiment through tweets;and the prediction module, which evaluates the accuracy of the models using Root Mean Square Error to measure prediction quality. this solution will provide a straightforward yet potent platform for analyzing stocks, cryptocurrency, and sentiment in real-time. the goal is to raise precision, reliability, and overall user experience concerning financial prediction, while more valuable insights become available to the investor and the researcher, having multiple sources integrated into the model. © 2025 IEEE.

关键词： Ethereum

来源：评论

学校读者我要写书评

暂无评论

An Optimal Real-Time Routing and Clustering Protocol for UAV Networks Based on Security 4

An Optimal Real-Time Routing and Clustering Protocol for UAV...

引用

4th international conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Sophia, S. Leelipushpam Paulraj, Getzi Jeba Yuvarajan, D. Karunya Institute of Technology and Sciences Division of Artificial Intelligence and Machine Learning Coimbatore India Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798331523923

Unmanned Aerial Vehicle (UAV) networks play an important role in different application areas such as military surveillance, emergency services, and infrastructure. However, these networks face significant challenges such as data leakage, unauthorized access, limited processing capacity, and energy constraints. Available techniques such as Elliptic Curve Cryptography (ECC), hash-based techniques, and dynamic clustering algorithms have been proposed to enhance security and operational performance;however, they often encounter challenges concerning scalability, adaptability to real-time changes within the network, and resource-related constraints. this research presents a streamlined authentication framework with the intent to facilitate secure and effective functionalities in turbulent and fluctuating settings. the proposed protocol uses Dijkstra's algorithm for optimal real-time routing, Adaptive Optimization Clustering (AOC) for dynamic resource distribution, and K-means clustering for noise classification. the proposed methodology achieves substantial improvements in power efficiency, latency, and Packet Delivery Rate (PDR) due to reduced computational overhead as well as risks such as data interception and replay attacks. Simulation results conclude that the system suggested here would be secure, scalable, and energy-efficient to be used for applications in demanding scenarios, such as mission-critical scenarios. © 2025 IEEE.

关键词： Emergency services

来源：评论

学校读者我要写书评

暂无评论

Diffusion-Augmented learning for Long-tail recognition 4

Diffusion-Augmented learning for Long-tail recognition

引用

4th international conference on computer Vision, application, and Algorithm, CVAA 2024

作者： Wang, Xiaochun Nanjing University of Science and Technology Nanjing China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

In general, natural data are long-tail distributed over semantic classes. Existing recognition methods tackle the imbalanced classification problem by designing architectures that focus more on the tail classes without altering the imbalance in the original dataset. In this paper, we propose an augmentation learning strategy, which not only alleviates the bias of the classifier towards head classes but also generates a balanced augmented dataset. Our method is called Diffusion-Augmented learning (DA), which can be easily applied to any long-tail recognition model. Its core idea is to leverage the generative capabilities of diffusion models to generate a balanced augmented dataset with high confidence and rich feature information. Subsequently, through a specific sampling strategy, we mix the original dataset with the augmented dataset to tackle long-tail recognition. the purpose of our method is twofold: 1) to utilize the generative capability of diffusion models to add sufficient and reliable augmented data for training, which improves the robustness of the model, and 2). to introduce more augmented data for tail classes through both probabilistically replacing strategy and an improved diffusion model, which alleviates the model's bias towards head classes. We carried out a series of contrast experiments on the CIFAR10-LT, CIFAR100-LT, and ImageNet-LT datasets, and the experimental results demonstrate the superiority of our proposed method and that the augmented dataset is versatile. © 2025 SPIE.

关键词： Adversarial machine learning

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235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：