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

85,859 篇 会议
397 篇 期刊文献
68 册 图书
1 篇 学位论文

馆藏范围

86,325 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

53,946 篇 工学
- 43,083 篇 计算机科学与技术...
- 31,581 篇 软件工程
- 13,370 篇 信息与通信工程
- 9,673 篇 控制科学与工程
- 8,710 篇 电气工程
- 4,910 篇 生物工程
- 4,109 篇 生物医学工程（可授...
- 3,830 篇 电子科学与技术（可...
- 3,463 篇 机械工程
- 3,264 篇 仪器科学与技术
- 2,954 篇 动力工程及工程热...
- 2,870 篇 交通运输工程
- 2,742 篇 安全科学与工程
- 2,377 篇 网络空间安全
- 2,135 篇 光学工程
20,152 篇 理学
- 10,696 篇 数学
- 5,372 篇 生物学
- 4,193 篇 统计学（可授理学、...
- 3,564 篇 物理学
- 3,174 篇 系统科学
- 2,082 篇 化学
15,760 篇 管理学
- 10,187 篇 管理科学与工程(可...
- 7,507 篇 图书情报与档案管...
- 4,854 篇 工商管理
4,289 篇 医学
- 3,501 篇 临床医学
- 3,351 篇 基础医学(可授医学...
- 2,101 篇 公共卫生与预防医...
- 1,794 篇 药学(可授医学、理...
2,401 篇 法学
- 1,960 篇 社会学
1,776 篇 经济学
- 1,764 篇 应用经济学
1,212 篇 农学
736 篇 教育学
294 篇 文学
187 篇 军事学
66 篇 艺术学
3 篇 哲学
3 篇 历史学

主题

4,178 篇 data mining
3,606 篇 data models
3,409 篇 computer science
2,417 篇 real-time system...
2,378 篇 training
2,280 篇 computational mo...
2,203 篇 feature extracti...
2,066 篇 accuracy
1,984 篇 big data
1,791 篇 machine learning
1,766 篇 predictive model...
1,484 篇 deep learning
1,414 篇 cloud computing
1,243 篇 monitoring
1,242 篇 internet of thin...
1,147 篇 neural networks
1,112 篇 conferences
1,096 篇 computer archite...
995 篇 databases
984 篇 learning systems

机构

154 篇 university of sc...
98 篇 school of comput...
91 篇 school of automa...
83 篇 chitkara univers...
77 篇 institute of inf...
77 篇 college of compu...
73 篇 school of comput...
72 篇 huazhong univers...
69 篇 school of comput...
55 篇 department of co...
54 篇 school of comput...
53 篇 shandong provinc...
52 篇 academy of mathe...
52 篇 tsinghua univers...
50 篇 school of inform...
49 篇 college of compu...
49 篇 sathyabama insti...
43 篇 lovely professio...
42 篇 shanghai jiao to...
40 篇 graphic era hill...

作者

55 篇 wang lei
51 篇 zhang lei
50 篇 li yang
44 篇 li peng
41 篇 li xin
38 篇 wang jing
37 篇 gill kanwarparta...
37 篇 jun wang
36 篇 zhang tao
33 篇 lei wang
32 篇 rui wang
32 篇 yang bo
30 篇 yu wang
27 篇 xiao liu
23 篇 zhang lin
22 篇 zheng wei
22 篇 hui wang
21 篇 anjali t.
21 篇 pareek piyush ku...
21 篇 wang hui

语言

83,188 篇 英文
2,847 篇 其他
294 篇 中文
8 篇 俄文
7 篇 西班牙文
4 篇 土耳其文
2 篇 法文
2 篇 葡萄牙文

检索条件"任意字段=IEEE International Conference on Data Science and Data Intensive Systems"

共 86325 条记录，以下是271-280 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：

Cycle Consistency Loss with Long Short Connection in Convolutional Neural Network-Generative Adversarial Network for Image Steganography 1

Cycle Consistency Loss with Long Short Connection in Convolu...

引用

1st international conference on Intelligent systems and Computational Networks, ICISCN 2025

作者： Fatima, Syeda Imrana Garapati, Yugandhar Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798331529246

Image steganography is the practice of concealing secret information within a digital image in such a way that the alteration is undetectable to the human eye. It ensures secure communication by embedding data into the pixel values of a carrier image. However, the extraction of a secret message from highly compressed or noisy images poses some challenges, which diminishes the reliability and robustness of steganographic methods. This research proposes Cycle consistency loss, combined with Long Short Connection Convolutional Neural Network-Generative Adversarial Network (CLSCCNN-GAN) to enhance the security of hidden data and prevent the adversarial recovery of the secret message. In the discriminator, the CLSCCNN is incorporated to enhance the model's ability to distinguish among real and steganographic images by leveraging LSC and Cycle Consistency Loss (CCL). The LSC preserves significant image information that enhance robustness of the discriminator, while CCL ensures that the stego image looks similar to the cover image which makes it harder for adversaries to identify hidden information. The proposed CLSCCNN-GAN obtains a high Peak-to-Signal-Noise-Ratio (PSNR) with a PSNR of 42.09 and 49.46 respectively on the MNIST and CIFAR10 datasets, outperforming existing methods namely, Hiding data and Adversarial attacking with GAN (HAG-Net). © 2025 ieee.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning Models for Proactive Disaster Forecasting 1

Leveraging Machine Learning Models for Proactive Disaster Fo...

引用

1st international conference on AIML-Applications for Engineering and Technology, ICAET 2025

作者： Affan, Daimi Syed Ahmed, Askari Arslaan Maaz, Ahmed Syed Asma, Iqbal Computer Science and Engineering Muffakham Jah College of Engineering and Technology Hyderabad India Electronics and Communication Engineering Deccan College of Engineering and Technology Hyderabad India

ISBN: (纸本)9798350355611

The increasing frequency and intensity of natural disasters, such as earthquakes, tsunamis, floods, and forest fires, necessitate the development of advanced early warning systems. Current disaster prediction systems are hampered by limitations in sensor technology, which is often expensive and primarily effective for large-scale disasters. This project aims to enhance disaster prediction accuracy and timeliness by utilizing real-time data and advanced machine learning algorithms, including XGBoost, Voting classifier, and Random Forest classifier. Additionally, recognizing the long-term health impacts of poor air quality, the project extends its scope to predict the Air Quality Index (AQI). The project seeks to enable proactive risk management and effective disaster response by integrating real-time environmental data and machine learning models. We aim to improve proactive risk management and disaster response by employing real-time data. The outcomes of this project promise significant advancements in disaster preparedness, ultimately safeguarding human lives and infrastructure. © 2025 ieee.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

A Route Recommendation Algorithm Based on Multi-Dimensional data Fusion and Analysis of its Social Utility 3

A Route Recommendation Algorithm Based on Multi-Dimensional ...

引用

3rd international conference on Integrated Circuits and Communication systems, ICICACS 2025

作者： Dai, Yazhe Li, You College of Electrical and Information Engineering JiLin Agricultural Science and Technology University Jilin China

ISBN: (纸本)9798331508456

The current route recommendation algorithm has problems such as single data. This paper designs a route recommendation algorithm based on multidimensional data fusion, uses convolutional neural network (CNN) to extract the features of user behavior data, geographic location information and environmental factor data, and then uses the attention mechanism to realize the fusion processing of multidimensional data. Based on the fused multidimensional data features, collaborative filtering and content-based recommendation algorithms are used to generate personalized route recommendations in combination with user preferences and real-time traffic conditions. Experiments have shown that the recommendation accuracy of this algorithm can reach up to 100%under controlled test conditions. Compared with the Bellman-Ford algorithm, this algorithm takes an average of 5.46 minutes less time, and the adoption rate of the recommendation results of this algorithm is as high as 99.9%, which proves the effectiveness of the algorithm in the cultural and tourism route recommendation scenario. © 2025 ieee.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Comparison of Convergence Rates in Federated Learning and Federated Multi-Task Learning Using the CIFAR-10 dataset

Comparison of Convergence Rates in Federated Learning and Fe...

引用

2025 ieee international conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Upadhye, Truptee Nanjundan, Preethi CHRIST University Department of Data Science Bangalore India

ISBN: (纸本)9798331512965

Many smart or cell phones have built-in distance, signal, and air pollution sensors. While collecting information, an acceleration registering device is a three-dimensional one and it can be applied in the gait analysis to address issues such as falls and health status determination. Indeed, the data is abundance in terms of quantity and some of the data may be of great concern in terms of privacy. In the time of Industry 4.0 the data has emerged as a key resource. Personal information/identity must not be maintained and hence cannot be stored at one place or all collected in a single place. AI models are moving to decentralized where a machine learning setting called Federated learning (FL) is being applied. FL has adversities such as statistical and systems heterogeneity. Actually, to better use shared information and build local models, Federated Multi-task learning (FMTL) has been devised. We also compare the number of iterations required to converge using CIFAR dataset of FL and FMTL. Several graphs illustrated in this paper show that convergence rates depend on the algorithm, number of communication rounds and number of clients or devices. Thus, it is clear that in some cases FL outperforms with FMTL in terms of convergence or conversely. However, it cannot be deduced that the type of FMTL always converges better than FL. The reliance on this graph is evident in this paper in order to as explain as prove the fact that, as the number of clients in FL rises, the rate of convergence declines. If ten communication rounds are employed with the use of the MOCHA algorithm, the model does not converge appropriately. The RMSE score declined from 1.14 to 1.02 throughout 20 epochs. © 2025 ieee.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Dual-Plate Verification System for Vehicle Identifcation using IoT and Embedded systems 3

Dual-Plate Verification System for Vehicle Identifcation usi...

引用

3rd international conference on Intelligent data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Sampath, A.V.S.S. Malagati, Nischal S. Kanapathi, V. Belwal, Meena Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

This research uses a dual-plate verification system for improving vehicle security by using IoT and embedded systems. The system compares front and rear license plates to detect any anomaly, which signals unauthorized modifications. Using real-time image processing and IoT-based data communication, this solution gives us an accurate plate matching system, making sure of reliable vehicle identity verification. Its possible applications include traffic monitoring, parking management, and detecting any unlawful activity. This project is unique because it integrates the dual plate verification system with an Arduino IoT setup. For hassle-free text recognition, this system uses deep learning frameworks combined with a wireless mobile setup that serves as a camera. The system’s accuracy is shown through experiments, displaying its value in improving transportation security with automation. The number plates were detected, and the respective penalties for the vehicles were imposed accordingly. © 2025 ieee.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Comb-H-Sine Activation Function Based Long Short-Term Memory for Quality Optimization in English Machine Translation 3

Comb-H-Sine Activation Function Based Long Short-Term Memory...

引用

3rd international conference on Integrated Circuits and Communication systems, ICICACS 2025

作者： Sun, Cuiqin Shandong Vocational College of Science and Technology Weifang China

ISBN: (纸本)9798331508456

Quality optimization in English machine translation involves a mix of advanced neural networks, linguistic preprocessing and evaluation metrics to enhance translation fluency, accuracy, and contextual understanding. Machine translation systems often struggle with accuracy and fluency, leading to errors in word alignment, contextual meaning, and natural sentence construction. To overcome this research, Comb-H-Sine-Long Short-Term Memory (CHS-LSTM) is a proposed for quality optimization in English machine translation that helps to enhance the translation accuracy and fluency. The parallel translation corpus dataset is an input to the proposed methodology. The data pre-processing such as data cleaning, tokenization and stemming are performed for enhance the quality of text data. The feature extraction such as word embeddings utilized to extract the data from pre-processed data. To improve accuracy and fluency in English machine translation, ongoing research focuses on improving contextual understanding, reducing word alignment errors, and enhancing language modeling techniques. The proposed CHS-LSTM attains accuracy of 95.87 while compared to existing method like bag of words respectively. © 2025 ieee.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Optimized Path Selection and Packet Transfer based on Block Chain using Wireless Sensor Network 1

Optimized Path Selection and Packet Transfer based on Block ...

引用

1st international conference on Intelligent systems and Computational Networks, ICISCN 2025

作者： Nithya, R. Venkatasalam, K. Mahendra Engineering College Department of Computer Science and Engineering Namakkal India

ISBN: (纸本)9798331529246

When designing wireless sensor networks, security and energy efficiency are regarded as crucial considerations. Since nodes in wireless networks run on power sources, it is crucial to create an energy-efficient technique to reduce energy usage and increase the lifespan of the network. This research introduces BC-RSA, an energy-effective and reliable clustering-based data packet transmission technique that combines blockchain-enabled safe data transfer with a clustering technique based on the reptile search algorithm (RSA) in wireless sensor networks. The clustering process is carried out by the suggested BC-RSA technique employing the RSA technology after node initialization. Cluster head identification and cluster building are done via the clustering approach. Blockchain-driven protected data transmission between cluster members and heads occurs using the proposed approach. The BC-RSA technique's experimental validation is evaluated from a number of viewpoints, and the outcomes are contrasted with those of other existing approaches. The results acquired confirmed that the BC-RSA technique has demonstrated higher performance in terms of latency, productivity, efficacy, network lifespan, and distribution ratio. © 2025 ieee.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Models for Predicting Species Distribution in Fishing data 3

Comparative Analysis of Machine Learning Models for Predicti...

引用

3rd international conference on Electronics and Renewable systems, ICEARS 2025

作者： Amora, Epifelward Niño O. Bohol Island State University College of Sciences Computer Science Department Candijay Campus Candijay Bohol Cogtong Philippines

ISBN: (纸本)9798331509675

This study investigates the predictive performance of several machine learning models using a large and detailed fishing effort dataset to predict species distribution. The models being tested are Random Forest, Gradient Boosting, XGBoost, Logistic Regression, SVM, Naive Bayes, and K-Nearest Neighbors. The best model in terms of prediction accuracy was Random Forest at 97.79%, followed closely by Gradient Boosting and XGBoost. Naive Bayes also exhibited a good performance. These results clearly demonstrate that ensemble methods are extremely effective for the prediction of species distribution from ecological datasets. © 2025 ieee.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Reference-Less CDR Using SAR-Based Frequency-Acquisition Technique Achieving 55ns Constant Band-Searching Time and up to 63.64Gb/s/μs Acquisition Speed 72

A Reference-Less CDR Using SAR-Based Frequency-Acquisition T...

引用

72nd ieee international Solid-State Circuits conference, ISSCC 2025

作者： Zhao, Xiaoteng Zhang, Yuhao Chang, Hao Dong, Yilong Han, Chenxi Yang, Zekai Dong, Zhicheng Zhou, Rong Liu, Shubin Zhu, Zhangming Xidian University Xi'an China

ISBN: (纸本)9798331541019

Reference-less clock and data recovery (CDR) circuits are prevalently employed in applications that demand a continuous data rate due to their simplicity and cost-effectiveness, as they eliminate the need for an external reference [1]-[6]. The frequency acquisition (FA) speed of such CDRs is critical for link setup, particularly in systems with dynamic data traffic management that necessitate frequent transitions from sleep to wake up [7], [8]. According to [9], part of the links can be turned off without congesting the network, even in high-load scenarios like data centers. However, the interface wake-up delay has been identified as the most significant bottleneck in the overall network. To address this issue, this paper proposes a fast FA reference-less CDR using a successive approximation register (SAR)-based frequency band switching technique, achieving a constant band switching time of 55ns. With the help of the proposed charge pump (CP) with positive net current, the total FA time of less than 150ns is achieved, which is at least 4× shorter than comparable work. © 2025 ieee.

关键词： Clock and data recovery circuits (CDR circuits)

来源：评论

学校读者我要写书评

暂无评论

Construction of an Innovation Information Mining Platform Integrating Knowledge Graph 3

Construction of an Innovation Information Mining Platform In...

引用

3rd international conference on Electronics and Renewable systems, ICEARS 2025

作者： Wan, Dawei Huang, Peisen Sichuan University of Arts and Science Sichuan Dazhou635000 China

ISBN: (纸本)9798331509675

With the continuous expansion of data mining scenarios, an accurate data analysis algorithm framework is urgently needed. In this study, the construction of an innovation information mining platform integrating knowledge graph is discussed. The designed platform combines multiple layers of knowledge fusion, matching and problem solving. This architecture can greatly improve the intelligent extraction and mining of innovative information. The designed platform mainly consists of four key parts: 1. At the data acquisition level, network logs are analyzed through Web data mining. At the same time, GoAccess tool is used to extract access logs and conduct preliminary analysis. 2. At the data mining level, this study uses a probabilistic graph model based on a word pair model to perform cluster analysis on large-scale text data. At the same time, the innovative information points are classified through calorific value calculation and information entropy theory to obtain the mining effect. 3. At the system improvement level, we integrate knowledge graphs and data mining algorithms, and use the Jena inference engine to reason and complete data relationships. 4. At the platform optimization level, the cloud platform architecture of this study further optimizes the allocation of computing resources and application deployment, while using Kubernetes and Docker container technologies to ensure the high performance of the system. Through data mining accuracy test, K-mean and FCM algorithms were used to verify the algorithm effect of this study. © 2025 ieee.

关键词： Knowledge graph

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 << < 24 25 26 27 28 29 30 31 32 33 > >>

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：