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

2,220 篇 会议
13 册 图书
5 篇 期刊文献

馆藏范围

2,238 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,595 篇 工学
- 1,376 篇 计算机科学与技术...
- 960 篇 软件工程
- 321 篇 控制科学与工程
- 241 篇 信息与通信工程
- 217 篇 电气工程
- 174 篇 生物工程
- 126 篇 生物医学工程（可授...
- 90 篇 机械工程
- 76 篇 交通运输工程
- 56 篇 光学工程
- 49 篇 电子科学与技术（可...
- 43 篇 化学工程与技术
- 41 篇 安全科学与工程
- 35 篇 仪器科学与技术
- 32 篇 土木工程
459 篇 理学
- 237 篇 数学
- 182 篇 生物学
- 101 篇 统计学（可授理学、...
- 75 篇 物理学
- 47 篇 系统科学
- 38 篇 化学
430 篇 管理学
- 285 篇 管理科学与工程(可...
- 159 篇 图书情报与档案管...
- 78 篇 工商管理
166 篇 医学
- 159 篇 临床医学
- 80 篇 基础医学(可授医学...
- 54 篇 药学(可授医学、理...
- 33 篇 公共卫生与预防医...
76 篇 教育学
- 74 篇 教育学
47 篇 法学
- 43 篇 社会学
30 篇 经济学
18 篇 农学
2 篇 军事学

主题

172 篇 machine learning
159 篇 deep learning
132 篇 training
98 篇 data models
78 篇 feature extracti...
74 篇 accuracy
68 篇 data mining
67 篇 neural networks
65 篇 predictive model...
60 篇 reinforcement le...
57 篇 computational mo...
52 篇 support vector m...
46 篇 real-time system...
42 篇 machine learning...
39 篇 artificial intel...
37 篇 training data
35 篇 learning systems
35 篇 visualization
34 篇 adaptation model...
31 篇 big data

机构

18 篇 kazan natl res t...
12 篇 king mongkuts un...
10 篇 institute of inf...
9 篇 school of cyber ...
7 篇 chitkara univers...
7 篇 college of compu...
6 篇 king mongkuts un...
6 篇 department of co...
6 篇 the key laborato...
5 篇 chinese acad sci...
5 篇 department of co...
5 篇 department of co...
4 篇 peng cheng lab
4 篇 univ chinese aca...
4 篇 department of ci...
4 篇 school of electr...
4 篇 department of el...
4 篇 school of inform...
4 篇 univ chinese aca...
4 篇 school of comput...

作者

7 篇 yang qiang
7 篇 piriyasurawong p...
6 篇 ouya samuel
6 篇 akatimagool soms...
5 篇 mendy gervais
5 篇 cortez paulo
5 篇 kraysman natalia...
4 篇 peng shaoliang
4 篇 liu sheng
4 篇 you linlin
4 篇 li han
4 篇 barabanova svetl...
4 篇 wang wei
4 篇 huang kaiqi
4 篇 lei baiying
4 篇 wang jinyan
4 篇 khatsrinova olga...
4 篇 shen dinggang
4 篇 li wei
4 篇 li qianmu

语言

2,182 篇 英文
50 篇 其他
26 篇 中文
1 篇 葡萄牙文

检索条件"任意字段=22nd International Conference on Intelligent Data Engineering and Automated Learning"

共 2238 条记录，以下是261-270 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：

FedGAC: Graph Federated learning with Gradients Aggregation Calibration for Non-IID and Long-Tailed data 22

FedGAC: Graph Federated Learning with Gradients Aggregation ...

引用

22nd IEEE international Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Li, Jie Wang, Jinyan Deng, Rongbin Yan, Dongqi Li, Qiyu Guangxi Normal University Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guilin541004 China Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining and Security Guilin541004 China Guangxi Normal University School of Computer Science and Engineering Guilin541004 China

ISBN: (纸本)9798331509712

Federated graph learning (FGL) combines the advantages of graph neural networks and federated learning, extracting valuable information from decentralized graph data while preserving data privacy. Existing FGL methods typically consider mitigating the effect of non-IID under the class balanced assumption. However, in many real-world scenarios, the data class distribution often exhibits a long-tailed distribution, which can lead to the model being severely biased towards the head classes, thus affecting the overall performance of the global model. To address the challenges posed by non-IID and long-tailed distribution data in FGL, this paper proposes a method called FedGAC to train a globally balanced model. In the local stage, FedGAC employs feature-structure decoupled graph attention network to train client models, introduces class-importance balanced strategy to mitigate class imbalance issues, and leverages knowledge relearning strategy to enhance model generalization. In the global stage, FedGAC employs an adaptive gradients aggregation strategy that dynamically adjusts balancing factors based on the degree of class imbalance in each client's data, thereby optimizing the aggregation process. Additionally, it utilizes global class gradients to calibrate learnable features. Experimental results demonstrate that, compared to the state-of-the-art federated learning methods, FedGAC achieves superior performance on highly non-IID and long-tailed distribution datasets. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

MetaCo-Distillation: A Robust Collaborative Distillation Framework for Multivariate Knowledge 22

MetaCo-Distillation: A Robust Collaborative Distillation Fra...

引用

22nd IEEE international conference on Smart City, SmartCity 2024

作者： Wang, Jianing Liu, Jiqiang Zhang, Tao Wang, Jian Tang, Xiangyun Sun, Geng Yang, Zhaohui Han, Zhu Niyato, Dusit School of Cyberspace Science and Technology Beijing Jiaotong University Beijing China School of Information Engineering Minzu University of China Beijing China College of Computer Science and Technology Jilin University Changchun China College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Department of Electrical and Computer Engineering University of Houston HoustonTX United States School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798331540487

Federated learning (FL), as a rapidly evolving privacy-preserving collaborative machine learning paradigm, has shown great potential in the emerging Metaverse areas. Although numerous studies have theoretically demonstrated the feasibility of FL, practical applications in the Metaverse face challenges such as learning forgetting due to non-independent and identically distributed (non-i.i.d.) data, high communication overhead from model parameter transmission, and the inability to accommodate heterogeneous models. To address these challenges, this paper proposes a collaborative distillation framework called Co-distillation. In this distributed environment, each device independently trains its local model using private data, communicates predictions on an unlabeled public dataset, and generates surrogate labels for the public dataset based on received predictions. These surrogate labels, along with the received predictions, serve as teacher logits for local model distillation. This approach is more adaptable to heterogeneous streaming data continuously generated by industrial devices, offers higher communication efficiency than traditional methods, allow for heterogeneous models. Experiments have been conducted, demonstrating the superior performance of the proposed framework. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Generalized XGBoost-Based Approach for Camera-Driven Beam Selection 22

A Generalized XGBoost-Based Approach for Camera-Driven Beam ...

引用

22nd IEEE Consumer Communications and Networking conference, CCNC 2025

作者： Zarei, Zahra Kang, Chung G. School of Electrical Engineering Korea University Seoul Korea Republic of

ISBN: (纸本)9798331508050

Incorporating non-RF data in beam selection can speed up decision-making in situations that require a thorough search of all candidate options. Therefore, using camera sensory data at base stations to enhance millimeter-wave (mmWave) beam selection is becoming increasingly popular. This paper introduces a machine learning framework using a robust model along with XGBoost in beam prediction scenarios. Our approach enhances beam selection in both single and multi-candidate real-world vehicle-to-infrastructure (V2I) settings. © 2025 IEEE.

关键词： Beam prediction Machine learning V2I XGBoost

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Single Object Tracking Algorithms for intelligent Driving: A Review 22

Vision-Based Single Object Tracking Algorithms for Intellige...

引用

22nd COTA international conference of Transportation Professionals (CICTP) - Intelligence, Connectivity, and Mobility

作者： Zhang, Hanning Lin, Haiying Cui, Hanzhang Liu, Zhiwen Beihang Univ Sch Transportat Sci & Engn Beijing Peoples R China

ISBN: (数字)9780784484265

ISBN: (纸本)9780784484265

With the rapid development of intelligent driving, object tracking has been widely used in many fields, such as intelligent transportation, video tracking, and human-computer interaction. As an important part of environment perception in intelligent driving, object tracking provides important information for vehicle control decisions. At the same time, as an important field of computer vision, the research of video object tracking is of great significance. With the rise of correlation filtering theory and deep learning method, single object tracking (SOT) algorithm has developed from traditional algorithms to algorithms based on correlation filters and algorithms based on deep learning. In this paper, we review the development of SOT and introduce the SOT algorithms in detail. Then we use the LaSOT data set to compare and analyze these SOT algorithms. Finally, we have made a summary and outlook on the SOT algorithm.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Cardio Vascular Disease Prediction based on ANN Algorithm 2

Cardio Vascular Disease Prediction based on ANN Algorithm

引用

2nd international conference on Electronics and Renewable Systems, ICEARS 2023

作者： Anitha, K. Arunprasath, M. Dinesh Kumar, K. Gokul, P. Gowtham, N. M Kumarasamy College of Engineering Department of Information Technology Karur India

ISBN: (纸本)9798350346640

Cardiovascular disease is a leading cause of mortality and disability in the United States. However, there aren't many efficient methods available to find hidden trends and linkages in e-health data. Medical diagnosis is a difficult process that has to be carried out precisely and effectively if people are to be saved. To lower the cost of performing clinical tests, an appropriate and accurate computer-based automated decision support system is required. The use of ML in health analytics has been proposed to anticipate precise patient data analysis. The data generated by the healthcare sector is not mined. datasets containing patient risk factors can be utilised to create intelligent models in the medical industry by utilising data mining techniques. The growth of methods and tools for using data has surprised knowledge discovery in database. This study sheds light on machine learning and deep learning approaches used in disease detection. There are several data mining classifiers that have been developed recently for accurate and efficient illness diagnosis. The heart attack prediction system proposed in this research uses deep learning techniques, more especially Multi-Layer Perceptron (MLP), to forecast the patient's likelihood of developing heart-related disorders. The Deep learning technique in Artificial Neural Networks is used by MLP, a particularly potent classification system. To provide reliable results with a minimal amount of error, the suggested model combines deep learning with data mining. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement learning for Bus Scheduling Considering Complex Passenger Flow 22

Deep Reinforcement Learning for Bus Scheduling Considering C...

引用

22nd COTA international conference of Transportation Professionals (CICTP) - Intelligence, Connectivity, and Mobility

作者： Fu, Hui Chen, Niu Yao, Yipeng Han, Shuang Wang, Yefei Guangdong Univ Technol Dept Ind Engn Guangzhou Peoples R China Guangdong Yonghua Technol Co Ltd Foshan Peoples R China

ISBN: (数字)9780784484265

ISBN: (纸本)9780784484265

Public transportation scheduling problem is a complex problem considering various influencing factors (such as passenger flow, etc.). However, the effect is not ideal when using the traditional machine learning method. Therefore,this paper aims to propose a Deep Reinforcement learning Proximal Policy Optimization (DRL-PPO) algorithm for public transport scheduling according to different actual passenger flow. At the end of the paper, we make bus arrival time records and passenger OD data of Guangzhou route 560, for three months from July 1, 2019, to September 30, 2019 for training. Compared with GA algorithm, PPO algorithm is better than GA in convergence speed and final effect, which verifies the effectiveness of PPO in bus scheduling with complex passenger flow characteristics.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Wavelet Transform and Deep Stacking Ensemble Model for Network Traffic Prediction 22

Hybrid Wavelet Transform and Deep Stacking Ensemble Model fo...

引用

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

作者： Joojili, Nader Amezaga-Hechavarria, Alexis Shafiq, Omair Bin Sediq, Akram Chang, Peiliang Abou-Zeid, Hatem School of Information Technology Carleton University OttawaON Canada Ericsson-Canada OttawaON Canada Ericsson Stockholm Sweden University of Calgary Department of Electrical and Software Engineering CalgaryAB Canada

ISBN: (纸本)9798350345346

Predicting packet volume accurately plays a vital role in network management and optimization. This study proposes a novel approach combining a hybrid wavelet transform and a deep stacking ensemble model to forecast packet volume. The proposed model leverages the wavelet transform's strengths and deep stacking ensemble techniques to enhance the predictive performance. The univariate prediction is conducted for different horizons, including 1, 3, 7, and 10 steps ahead. The wavelet transform is employed to capture the time-frequency characteristics of the packet volume data, enabling a more comprehensive analysis. The model can extract local and global features by decomposing the time series into different scales using wavelet analysis, improving prediction accuracy. The deep stacking ensemble model is utilized to leverage the collective intelligence of multiple base models. Through a series of stacking layers, the model learns to combine the predictions of individual models, allowing for a more robust and accurate forecast. The proposed hybrid wavelet transform and deep stacking ensemble model was subjected to experimental evaluations using real-world packet volume datasets. The outcomes of these evaluations exhibit the effectiveness of the model. The model achieves superior predictive performance compared to traditional methods, showcasing its potential for practical network management and optimization applications. © 2023 IEEE.

关键词： Deep learning Forecasting Stacking Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Bearing Fault Diagnosis Using One-Dimensional Convolutional Neural Network 22

Bearing Fault Diagnosis Using One-Dimensional Convolutional ...

引用

22nd international conference on Control, Automation and Systems (ICCAS)

作者： Gao, Zhanyuan Wei, Zhennan Chen, Yuan Ying, Tianqi Gao, Haojie Hohai Univ Coll IOT Engn Nanjing 210098 Peoples R China WeiMing Intelligent Technol Co Ltd Wuxi 214000 Jiangsu Peoples R China South China Agr Univ Coll Engn Guangzhou 510642 Peoples R China

ISBN: (纸本)9788993215243

In this paper, a fault diagnosis strategy using one-dimensional convolutional neural network (CNN) is developed for rolling bearing. Firstly, each basic unit in the CNN model to be proposed is introduced in detail, and the optimization algorithm required for the CNN is described to show the working principle, which provides a theoretical basis for the one-dimensional CNN model. Next, a series of preprocessing such as overlap sampling and unique thermal coding are performed on the rolling bearing dataset from Case Western Reserve University, and a batch normalization algorithm is proposed to improve the training efficiency and performance of the CNN model. Finally, the designed one-dimensional CNN model is trained, the adaptive ability of the model with variable load is tested, and good results are obtained.

关键词： big data deep learning convolutional neural network rolling bearing fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Proceedings of the 22nd international conference on Business Informatics Research, BIR 2023

Proceedings of the 22nd International Conference on Business...

引用

Proceedings of the 22nd international conference on Business Informatics Research, BIR 2023

ISBN: (纸本)9783031431258

The proceedings contain 24 papers. The special focus in this conference is on Business Informatics Research. The topics include: An Approach for Knowledge Graphs-Based User Stories in Agile Methodologies;A Flexible, Extendable and Adaptable Model to Support AI Coaching;Improving IT Governance, Security and Privacy Using Fractal Enterprise Modeling: A Case of a Highly Regulated Company;model-Based Digital Business Ecosystems: A Method Design;managing Variability of Large Public Administration Event Log Collections: Dealing with Concept Drift;digital Store Window: A Promising Approach for Stationary Retailer in Germany?;enriching Enterprise Architecture Stakeholder Analysis with Relationships;developing Digital Competencies in Small and Medium-Sized Enterprises Through Microlearning Applications: A Research Agenda;exploring Smart Meters: What We Know and What We Need to Know;value Creation from data Science Applications - A Literature Review;open Government data in Educational Programs Curriculum: Current State and Prospects;Towards a Framework for intelligent Cyber-Physical System (iCPS) Design;a Model-Based Approach to Decision Support for Designing Inclusive Services;predicting Patterns of Firms’ Vulnerability to Economic Crises Using Open data, Synthetic Minority Oversampling Technique and Machine learning;user Interaction Mining: Discovering the Gap Between the Conceptual Model of a Geospatial Search Engine and Its Corresponding User Mental Model;extending Conceptual Model with Object Life Cycles;towards Healthcare Digital Twin Architecture;Morphological Box for AI Solutions: Evaluation and Refinement with a Taxonomy Development Method;preface;towards Agile Requirements engineering in Maritime Freight Transportation;knowledge Visualization Towards Digital Literacy Development: Critical Success Factors;Exploring Techno-Invasion and Work-Life Balance on Digital Platforms: A Preliminary Study with Amazon MTurk’s Gig Workers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Conditioned Cycles in Sparse data Domains: Applications to Electromagnetics 22

Conditioned Cycles in Sparse Data Domains: Applications to E...

引用

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

作者： Barger, Maria Paffenroth, Randy Pathak, Harsh Worcester Polytechnic Institute Data Science WorcesterMA United States Worcester Polytechnic Institute Mathematics Computer Science and Data Science WorcesterMA United States

ISBN: (纸本)9798350345346

Training neural networks is difficult with small datasets, yet small training data sets are commonly found with machine learning problems in the physical sciences. Prediction accuracy within such sparse data domains can be improved by the utilization of conditioning, inspired by classical statistics, and cycles, similar to those of CycleGANs. In this paper, we propose the addition of 'oracle' conditioning, where the true condition value is provided during training (but not during testing), to improve final prediction accuracy in sparse data domains. For example, in over-water electromagnetic (EM) source localization, the range of the emitter can be thought of as a 'condition' on the generation of a received EM signal. Oracle conditioning utilizes an encoder-decoder framework where the conditioning of the decoder is not contingent on the output of an encoder's prediction (e.g, predicting the range from a received EM signal). While our primary application involves source localization for EM signals, this paper is intended to inspire a general approach toward neural network training for problems in the physical sciences with similar characteristics. Our multi-component loss function is intended to serve as a general method for small data problems which can benefit from the addition of cycles and oracle conditioning. © 2023 IEEE.

关键词： conditional generation cycles electromagnetics loss function oracle conditioning

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224页 << < 23 24 25 26 27 28 29 30 31 32 > >>

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：