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201-210 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：

FReNG: Federated Optimization by Using Regularized Natural Gradient Descent 22

FReNG: Federated Optimization by Using Regularized Natural G...

引用

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

作者： Sen, Mrinmay Gayatri, C. Indian Institute of Technology Hyderabad Dept. of Artificial Intelligence Hyderabad India Mahindra University Dept. of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350345346

Federated learning (FL) is an important area in machine learning that addresses the challenges of distributed data by collaboratively training a global model. One major issue with FL is the increased communication rounds or FL iterations between the server and the participating data sources or clients, which is caused by the presence of heterogeneous data across all the clients. To address this issue, this paper introduces FReNG, which utilizes regularized natural gradient descent with exponential moving average of the global gradient on the server. The server-based utilization of regularized natural gradient descent and exponential moving average of the global gradient leads to faster convergence of the global model in heterogeneous settings without additional local space and computational complexities, resulting in comparatively fewer communication rounds, while achieving the targeted accuracy from the global model. As FReNG uses regularized natural gradient descent, it can directly compute the update step without calculating and storing the full Fisher information matrix (FIM), which is one of the key advantage of FReNG. Extensive experimental results on image classification tasks using various heterogeneously partitioned datasets show that FReNG outperforms existing state-of-the-art FL algorithms such as FedProx, SCAFFOLD & FedInit and can compete with other state-of-the-art FL algorithms, FedGA, & DONE (with less per FL iteration communication cost & less local time complexity) in terms of reduced communication rounds, while achieving a certain precision of convergence and a targeted test accuracy from the global model. © 2023 IEEE.

关键词： exponential moving average of gradient federated learning increased communication rounds natural gradient descent slow convergence

来源：评论

学校读者我要写书评

暂无评论

Graph Wavenet+TimeGrad Probabilistic Model for High-Dimensional Time Series Prediction 22

Graph Wavenet+TimeGrad Probabilistic Model for High-Dimensio...

引用

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

作者： Sun, Xiuxuan Chen, Jianhua Louisiana State University Division of Computer Science & Engineering Baton RougeLA United States

ISBN: (纸本)9798350345346

Time series prediction has been widely utilized across various domains, including financial markets, weather forecasting, transportation, and Internet of Things (IoT). High-dimensional time-series data poses challenges for traditional time series models in effectively managing its complexity and non-linearity. In this study, we propose a novel approach by combining the truncated GraphWaveNet architecture with the TimeGrad process. This combination allows for probabilistic multi-step prediction of high-dimensional time series data. The primary components of the GraphWaveNet architecture are the gated dilated causal convolutional neural network (GDC-CNN), graph convolutional neural network (GCNN), and residual networks. GDC-CNN and residual networks are employed to extract trend and short-term movement information from the time series data while addressing the gradient degradation/explosion issues. The function of GCNN is to leverage the graph structure and learn effective representations of features. The TimeGrad process generates probabilistic output. Experimental results on five real-world multi-variate time series datasets demonstrate that the truncated GraphWaveNet+TimeGrad model outperforms benchmark models in terms of CRPSsumcriteria. Particularly, GraphWaveNet+TimeGrad probabilistic model exhibits superior performance for traffic prediction. © 2023 IEEE.

关键词： GraphWaveNet high-dimensional time series analysis probabilistic model TimeGrad

来源：评论

学校读者我要写书评

暂无评论

Igniting Precision: Amplifying Wildfire Prediction in Diverse Regions via Teacher-Student Model Fusion 22

Igniting Precision: Amplifying Wildfire Prediction in Divers...

引用

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

作者： Lindemann, Michael Demichele, Kathleen Kapourchali, Masoumeh Heidari Kapourchali, Mohammad Heidari Waigl, Christine Trochim, Erin Zhao, Long University of Alaska Anchorage Department of Computer Science and Engineering AnchorageAK United States University of Alaska Anchorage Department of Electrical Engineering AnchorageAK United States Alaska Center for Energy and Power University of Alaska Fairbanks FairbanksAK United States International Arctic Research Center University of Alaska Fairbanks FairbanksAK United States South Dakota School of Mines and Technology Department of Electrical Engineering and Computer Science United States

ISBN: (纸本)9798350345346

Accurate wildfire prediction in diverse and geographically dispersed areas is crucial for effective wildfire management. However, the limited availability of labeled data in data-challenged regions, along with the unique characteristics of these areas, poses challenges for training robust prediction models. This study investigates the performance of a convolutional neural network (CNN) on datasets comprising Landsat images from Canada and Alaska. Through principal component analysis (PCA), the study uncovers distinct differences in data distribution between the two regions. It is observed that the reduced data size of the Alaskan dataset, along with its distinct data distribution, leads to a decrease in the CNN's accuracy to 75% compared to an impressive 98% achieved on the Canadian dataset. To address this limitation, we propose a teacher-student model approach, transferring knowledge from a CNN trained on the larger Canadian dataset. The results demonstrate a significant accuracy improvement to 88.96% on the Alaskan dataset. Our findings highlight the effectiveness of the teacherstudent model in mitigating data scarcity challenges, enhancing wildfire prediction capabilities in regions with limited training data. This research contributes to improved wildfire monitoring and prevention strategies in challenging geographical locations. © 2023 IEEE.

关键词： knowledge transfer Landsat remote sensing teacher-student wildfire prediction

来源：评论

学校读者我要写书评

暂无评论

Multi-Planar MRI-Based Classification of Alzheimer's Disease Using Tree-Based Machine learning Algorithms 22

Multi-Planar MRI-Based Classification of Alzheimer's Disease...

引用

22nd IEEE/WIC international conference on Web Intelligence and intelligent Agent Technology (WI-IAT)

作者： Shaffi, Noushath Viswan, Vimbi Mahmud, Mufti Hajamohideen, Faizal Subramanian, Karthikeyan UTAS Coll Comp & InfSc Sohar Oman Nottingham Trent Univ Med Technol Innovat Facil Nottingham England

ISBN: (纸本)9798350309188

While most contemporary algorithms typically utilize MRI data from a single plane, this study highlights the importance of incorporating multiplanar MRI features for enhanced performance. Specifically, tree-based machine learning algorithms were employed to compare the accuracy of individual plane analysis versus a multiplanar approach using the popular ADNI dataset. The results unequivocally demonstrate that the multiplanar approach consistently outperforms any single plane analysis in terms of classification accuracy for any given algorithm. These findings provide evidence-based results supporting the integration of multiplanar MRI features to achieve improved performance in MRI-based classification tasks. A significant improvement in accuracy of 8-10% is achieved by the utilization of multiplanar MRI features as against the single plane.

关键词： Alzheimer's Disease Machine learning Multiplanar MRI Ensemble XGBoost AdaBoost Random Forest Decision Tree

来源：评论

学校读者我要写书评

暂无评论

automated Detection of Refilling Stations in Industry Using Unsupervised learning 32nd

Automated Detection of Refilling Stations in Industry Using ...

引用

32nd international conference on Flexible Automation and intelligent Manufacturing

作者： Ribeiro, Jose Pinheiro, Rui Soares, Salviano Valente, Antonio Amorim, Vasco Filipe, Vitor Univ Tras Os Montes & Alto Douro UTAD Sch Sci & Technol P-5000801 Vila Real Portugal IEETA Inst Elect & Informat Engn Aveiro P-3810193 Aveiro Portugal INESC TEC INESC Tecnol & Ciencia P-4200465 Porto Portugal Univ Tras Os Montes & Alto Douro UTAD Incubadora Empresas Neocept Edificio P2Gabinete 16 P-5000081 Vila Real Portugal

ISBN: (纸本)9783031381645;9783031381652

The manual monitoring of refilling stations in industrial environments can lead to inefficiencies and errors, which can impact the overall performance of the production line. In this paper, we present an unsupervised detection pipeline for identifying refilling stations in industrial environments. The proposed pipeline uses a combination of image processing, pattern recognition, and deep learning techniques to detect refilling stations in visual data. We evaluate our method on a set of industrial images, and the findings demonstrate that the pipeline is reliable at detecting refilling stations. Furthermore, the proposed pipeline can automate the monitoring of refilling stations, eliminating the need for manual monitoring and thus improving industrial operations' efficiency and responsiveness. This method is a versatile solution that can be applied to different industrial contexts without the need for labeled data or prior knowledge about the location of refilling stations.

关键词： Industry 4.0 Refilling Stations Assembly Lines Computer Vision Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

Automatic Classification and Recognition of Seismic Waveforms Based on Convolutional Neural Networks 2

Automatic Classification and Recognition of Seismic Waveform...

引用

2nd IEEE international conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Shan, Juhao Huang, Hanming Ministry of Education Guangxi Normal University Key Lab of Education Blockchain and Intelligent Technology China Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining and Security China Guangxi Normal University School of Computer Science and Engineering Guilin China

ISBN: (纸本)9798350372892

The development of efficient, high-precision, and universally applicable automatic waveform picking algorithms is becoming increasingly important in the era of seismic big data. The main challenge of waveform automatic picking algorithm lies in how to adapt to the classification and screening of different types of seismic events in different regions. Traditional seismic phase identification relies on the theoretical knowledge and experience of relevant researchers, which has problems such as large workload, long interpretation time, strong subjectivity, and low efficiency. Deep learning technology can learn the hidden features in data. This article studies how to use deep convolutional neural networks to learn the nonlinear mapping relationship between seismic data and seismic phases, providing technical support for achieving automated seismic phase recognition. This article mainly focuses on the automatic classification and recognition of seismic waveforms using convolutional neural networks. Firstly, relevant research is summarized, relevant application methods are proposed, and the results are discussed to provide assistance for the development of related fields. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Long-Term Photovoltaic Power Forecasting with Transformer NN 22nd

Long-Term Photovoltaic Power Forecasting with Transformer NN

引用

22nd National conference on Sensors and Microsystems

作者： Piantadosi, G. Ferlito, Sergio Dutto, Sofia Di Francia, Girolamo ENEA CR Portici Piazzale Enrico Fermi 1 I-80055 Naples Italy Univ Naples Federico II Via Claudio 21 I-80125 Naples Italy

ISBN: (纸本)9783031820786;9783031820762;9783031820755

The international Energy Agency's World Energy Outlook 2023 highlights the essential role of photovoltaic (PV) energy in the global energy transition. Despite advancements, solar energy utilization lags behind PV production capacity. Addressing this requires active involvement from energy stakeholders and consumers, often within energy communities, to develop tools for economic and sustainable PV energy production. Accurate PV production forecasts are crucial for market positioning, grid integration, and energy exchange coordination. Current models, which rely on irradiance data, fall short in capturing complex atmospheric phenomena, limiting predictions to short-term forecasts. This proposal aims to provide PV production forecasts by integrating validated meteorological data with advanced models, targeting reliable two-week ahead forecasts. A nowcasting model, trained on historical weather and PV production data, will predict production based on weather forecasts. The approach generalizes predictions beyond the training dataset, applicable to diverse PV installations. The methodology combines global numerical models with machine learning techniques, including Long Short-Term Memory (LSTM) and Transformer Neural Networks (NN), evaluated against classical methods. Training with real data from five PV sites will optimize model performance through a weighted combination of losses. This hybrid approach aims to enhance PV production accuracy and integration, promoting effective solar energy utilization.

关键词： Photovoltaic Energy Forecasting Energy Communities Deep learning Transformers

来源：评论

学校读者我要写书评

暂无评论

HCT: Hybrid Convnet-Transformer for Parkinson's Disease Detection and Severity Prediction from Gait 22

HCT: Hybrid Convnet-Transformer for Parkinson's Disease Dete...

引用

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

作者： Naimi, Safwen Bouachir, Wassim Bilodeau, Guillaume-Alexandre Data Science Laboratory Montréal Canada Polytechnique Montréal Litiv Lab. Montréal Canada

ISBN: (纸本)9798350345346

In this paper, we propose a novel deep learning method based on a new Hybrid ConvNet-Transformer archi-tecture to detect and stage Parkinson's disease (PD) from gait data. We adopt a two-step approach by dividing the problem into two sub-problems. Our Hybrid ConvNet-Transformer model first distinguishes healthy versus parkinsonian patients. If the patient is parkinsonian, a multi-class Hybrid ConvNet-Transformer model determines the Hoehn and Yahr (H&Y) score to assess the PD severity stage. Our hybrid architecture exploits the strengths of both Convolutional Neural Networks (ConvNets) and Transformers to accurately detect PD and determine the severity stage. In particular, we take advantage of ConvNets to capture local patterns and correlations in the data, while we exploit Transformers for handling long-term dependencies in the input signal. We show that our hybrid method achieves superior performance when compared to other state-of-the-art methods, with a PD detection accuracy of 97% and a severity staging accuracy of 87%. Our source code is available at https://***/SafwenNaimi. © 2023 IEEE.

关键词： Convolutional Neural Networks H&Y scale Parkinson's disease detection Transformers VGRF Signals

来源：评论

学校读者我要写书评

暂无评论

Optimal Asynchronous Federated learning for the Internet of Battlefield Things (IoBT) 22

Optimal Asynchronous Federated Learning for the Internet of ...

引用

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

作者： Hagos, Desta Haileselassie Tankard, Earl Bhurtel, Manish Rawat, Danda B. Howard University Department of Electrical Engineering and Computer Science WashingtonDC United States

ISBN: (纸本)9798350345346

Federated learning (FL) is a distributed machine learning technique that enables multiple devices or systems to collaboratively train a distributed model without sharing raw data. This is particularly useful for the Internet of Battlefield Things (IoBT) as it enhances the performance and capabilities of military devices through distributed training of models without compromising data privacy or security for involved parties. In this paper, we delve into the potential of FL to enhance military devices within the IoBT. Distinguishing our work from other works in this line of research, we introduce a tailored battlefield dataset tailored specifically for battlefield scenarios. Our approach combines both synchronous and asynchronous FL techniques, demonstrating their practicality in the context of the IoBT using this custom dataset. Our study not only explores the benefits and challenges of employing FL in battlefield scenarios but also highlights the capability of asynchronous FL to achieve comparable accuracy to synchronous FL while significantly reducing resource consumption. By addressing these critical aspects, our research advances the use of FL in military applications and contributes to the ongoing development of secure and efficient systems for the IoBT. © 2023 IEEE.

关键词： Asynchronous Federate learning Internet of Battlefield Things IoT Privacy-Preserving Machine learning

来源：评论

学校读者我要写书评

暂无评论

Stress Beats: a continuum of learning methods for personalized stress detection 22

Stress Beats: a continuum of learning methods for personaliz...

引用

22nd IEEE/WIC international conference on Web Intelligence and intelligent Agent Technology (WI-IAT)

作者： Parousidou, Vasiliki Yfantidou, Sofia Karagianni, Christina Vakali, Athena Aristotle Univ Thessaloniki Sch Informat Thessaloniki Greece

ISBN: (纸本)9798350309188

The pervasive use of wearable technology widens opportunities for personalized Machine learning (ML) for mental health and well-being, providing non-intrusive means of tracking physiological stress indicators (e.g., heart rate, skin conductance) in real-time. Stress detection is a critical task for mitigating its adverse effects on physical and mental health. However, prior work primarily focused on "one-size-fits-all" ML approaches, neglecting individual differences and often suffering from "cold-start" problems and overfitting due to limited data availability. To overcome these challenges, this work aims to accurately identify an individual's stress levels using data from wearables. To achieve this, we employ a "continuum" of ML techniques tailored to capture the unique patterns of each person's stress response. For leveraging these personalized "stress beats", we emphasize multi-task learning and personalization on a user, group, and population level, capturing the interplay between inter- and intra-personal stress indicators. Our models are validated using real-world datasets, which are benchmarked under a spectrum of learning paradigms. The experimental results demonstrate the superiority of personalized models over "one-size-fits-all" approaches, underscoring the importance of personalization. Notably, group-based personalized models achieved up to 99% F1-score in lab settings and up to 66% F1-score in-the-wild, outperforming "one-size-fits-all" approaches by 15% and illustrating the potential of personalized ML techniques in healthcare applications beyond stress detection.

关键词： Personalized Machine learning Stress Detection Multi-task learning Benchmarking User Clustering

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 << < 17 18 19 20 21 22 23 24 25 26 > >>

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：