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

7,070 篇 会议
48 篇 期刊文献
39 册 图书

馆藏范围

7,157 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,912 篇 工学
- 4,098 篇 计算机科学与技术...
- 2,521 篇 软件工程
- 1,046 篇 信息与通信工程
- 789 篇 控制科学与工程
- 663 篇 生物工程
- 640 篇 电气工程
- 424 篇 生物医学工程（可授...
- 285 篇 交通运输工程
- 281 篇 机械工程
- 226 篇 仪器科学与技术
- 226 篇 安全科学与工程
- 206 篇 建筑学
- 197 篇 动力工程及工程热...
- 185 篇 光学工程
- 166 篇 化学工程与技术
- 154 篇 土木工程
1,900 篇 理学
- 1,065 篇 数学
- 718 篇 生物学
- 442 篇 统计学（可授理学、...
- 285 篇 物理学
- 252 篇 系统科学
- 140 篇 化学
1,152 篇 管理学
- 656 篇 管理科学与工程(可...
- 582 篇 图书情报与档案管...
- 316 篇 工商管理
408 篇 医学
- 354 篇 临床医学
- 298 篇 基础医学(可授医学...
- 188 篇 药学(可授医学、理...
244 篇 教育学
- 243 篇 教育学
211 篇 法学
- 197 篇 社会学
119 篇 农学
111 篇 经济学
50 篇 文学
7 篇 艺术学
5 篇 军事学

主题

556 篇 machine learning
456 篇 deep learning
264 篇 training
253 篇 data mining
235 篇 data models
220 篇 feature extracti...
215 篇 accuracy
184 篇 support vector m...
178 篇 predictive model...
138 篇 neural networks
137 篇 machine learning...
130 篇 computational mo...
121 篇 reinforcement le...
107 篇 convolutional ne...
103 篇 real-time system...
93 篇 forecasting
90 篇 artificial intel...
89 篇 learning systems
87 篇 transfer learnin...
86 篇 big data

机构

69 篇 chitkara univers...
17 篇 school of electr...
15 篇 computer science...
14 篇 harbin engineeri...
13 篇 graphic era hill...
12 篇 building civil a...
12 篇 uttaranchal inst...
12 篇 computer science...
11 篇 university of ch...
10 篇 school of electr...
10 篇 school of comput...
10 篇 graphic era deem...
10 篇 school of electr...
10 篇 yonsei univ dept...
9 篇 wuhan university...
9 篇 univ chinese aca...
9 篇 school of inform...
8 篇 school of remote...
7 篇 university of sa...
7 篇 microsoft resear...

作者

17 篇 kukreja vinay
15 篇 vinay kukreja
13 篇 yin hujun
12 篇 liu yang
12 篇 corchado emilio
11 篇 mehta shiva
10 篇 shiva mehta
10 篇 hujun yin
10 篇 cho sung-bae
9 篇 notsu akira
9 篇 silva catarina
9 篇 alhajj reda
7 篇 ksieniewicz pawe...
7 篇 hammer barbara
7 篇 zhang byoung-tak
7 篇 wozniak michal
7 篇 hussain abir
7 篇 soubra hassan
7 篇 huang de-shuang
7 篇 camacho david

语言

6,794 篇 英文
352 篇 其他
28 篇 中文
1 篇 西班牙文
1 篇 俄文

检索条件"任意字段=11th International Conference on Intelligent Data Engineering and Automated Learning"

共 7157 条记录，以下是891-900 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：

Cognitive Deep learning System for Real-Time Traffic Sign Detection and Driver Alerts 4

Cognitive Deep Learning System for Real-Time Traffic Sign De...

引用

4th international conference on Emerging Systems and intelligent Computing, ESIC 2024

作者： Ganesh Kumar, P.S. Tejaswini, Pokala Anuhya, Yarlagadda Revanth, Sama Taraka Madhava Srinivasaraju, Sagiraju Sr Gudlavalleru Engineering College Dept of Cse Andhra Pradesh Gudlavalleru521356 India

ISBN: (纸本)9798350349856

As the number of vehicles on the road rises, making sure that road safety has become a main concern. Traffic signs plays as one of the crucial roles in to guide and control the traffic, but human error and distractions can lead to making a mistake, resulting in cause of accidents and traffic violations. the constructed system uses convolutional neural networks (CNNs) for accurate traffic sign recognition. the model's architecture is designed to capture features of different traffic signs enabling robust recognition even under varying conditions. Once a traffic sign is detected and recognized, the system employs natural language generation techniques to create contextually relevant alert messages. this alert message is produced in the form of voice alert which informs driver about the detected sign. this ensures that drivers receive clear and concise information about the sign, promoting quick and appropriate responses. In this process, we trained various German traffic sign data images and verify the implementation which can be used in further processing. the proposed approach is expected to accurately recognizing a wide range of traffic signs and generating informative alert messages using python libraries. Here, we are implementing YOLOv5 by using this algorithm overall, this research contributes to enhancing road safety by imposing deep learning techniques for automated traffic sign recognition and real-time generation of alert messages, ultimately reducing the risk of accidents and traffic violations. © 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

Generating Adversarial Examples Using LAD 24th

Generating Adversarial Examples Using LAD

引用

24th international conference on intelligent data engineering and automated learning, IDEAL 2023

作者： Chauhan, Sneha Mahmoud, Loreen Sheth, Tanay Gangopadhyay, Sugata Gangopadhyay, Aditi Kar Department of Computer Science and Engineering IIT Roorkee Roorkee India Department of Computer Science and Engineering NIT Uttarakhand Srinagar India BITS Pilani Goa Campus Sancoale India Department of Mathematics IIT Roorkee Roorkee India

ISBN: (纸本)9783031482311

Nowadays, Machine learning models are widely used in many fields and employed to solve problems from different sectors. However, we often face issues when running these models in case the training data is insufficient. these issues happen when the dataset available is small or only part of it is available because of its sensitive content or even because the dataset is imbalanced. thus, synthetic data generation is needed to provide data similar to actual data. We have proposed the use of the Logical Analysis of data methodology to generate adversarial data from any given dataset. For our study, we have used an intrusion detection dataset, and the results demonstrate the potential of Logical Analysis of data by evaluating adversarial datasets using various machine learning classifiers. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

FROM t-SNE TO UMAP WIth CONTRASTIVE learning 11

FROM t-SNE TO UMAP WITH CONTRASTIVE LEARNING

引用

11th international conference on learning Representations, ICLR 2023

作者： Damrich, Sebastian Böhm, Jan Niklas Hamprecht, Fred A. Kobak, Dmitry IWR Heidelberg University Germany University of Tübingen Germany

Neighbor embedding methods t-SNE and UMAP are the de facto standard for visualizing high-dimensional datasets. Motivated from entirely different viewpoints, their loss functions appear to be unrelated. In practice, they yield strongly differing embeddings and can suggest conflicting interpretations of the same data. the fundamental reasons for this and, more generally, the exact relationship between t-SNE and UMAP have remained unclear. In this work, we uncover their conceptual connection via a new insight into contrastive learning methods. Noise-contrastive estimation can be used to optimize t-SNE, while UMAP relies on negative sampling, another contrastive method. We find the precise relationship between these two contrastive methods and provide a mathematical characterization of the distortion introduced by negative sampling. Visually, this distortion results in UMAP generating more compact embeddings with tighter clusters compared to t-SNE. We exploit this new conceptual connection to propose and implement a generalization of negative sampling, allowing us to interpolate between (and even extrapolate beyond) t-SNE and UMAP and their respective embeddings. Moving along this spectrum of embeddings leads to a trade-off between discrete/local and continuous/global structures, mitigating the risk of over-interpreting ostensible features of any single embedding. We provide a PyTorch implementation. © 2023 11th international conference on learning Representations, ICLR 2023. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Deep learning based indirect monitoring to identify bridge natural frequencies using sensors on a passing train 11th

Deep learning based indirect monitoring to identify bridge n...

引用

11th international conference on Bridge Maintenance, Safety and Management, IABMAS 2022

作者： Lorenzen, S.R. Berthold, H. Rupp, M. Schmeiser, L. Apostolidi, E. Schneider, J. Brotzmann, J. thiele, C.-D. Ruppel, U. Darmstadt Germany Darmstadt Germany

ISBN: (纸本)9781032345314

In this paper a supervised deep learning based approach to extract bridge natural frequencies from acceleration sensors on a passing train is presented. To overcome the problem of obtaining a sufficient amount of acceleration signals with a known corresponding bridge frequency, it is proposed to use transfer learning. data acquired from simulations is used to learn the features and their weighing is trained on real measurement data. To validate the proposed method synchronous acceleration measurements at an ICE 4 train and a double track steel box girder bridge from a field measurement campaign were used. the model presented in this paper is able to extract the natural frequencies from a single sensor and a single passage even while high speeds. With the experimental data it is possible to extract bridge natural frequencies from acceleration measurements on a passing train under regular operational conditions. © 2022 the Author(s).

关键词： Natural frequencies

来源：评论

学校读者我要写书评

暂无评论

Novel Test Bench for End-to-End Validation of Monocular Depth Estimation Under the Influence of Glaring Situations 27

Novel Test Bench for End-to-End Validation of Monocular Dept...

引用

27th IEEE international conference on intelligent Transportation Systems, ITSC 2024

作者： Ulreich, Fabian Kaup, Andre Ebert, Martin Friedrich-Alexander-Universität Erlangen-Nürnberg Chair of Multimedia Communications and Signal Processing Erlangen91058 Germany Technische Hochschule Ingolstadt Ingolstadt85049 Germany Technische Hochschule Ingolstadt Faculty of Electrical Engineering and Information Technology Ingolstadt85049 Germany

ISBN: (纸本)9798331505929

the black-box nature of deep learning models employed in automated driving functions requires suitable evaluation tools. Efforts are being made to increase the validity of testing environments for real-world operations. Understanding the impact of the sensor characteristics and degradation on the downstream task of perception is another field of research. We propose a test environment for vision-based autonomous driving functions in which a real camera and a deep learning model can be evaluated jointly. Our approach enables the validation under real-world brightness conditions through projector technology. To demonstrate its applicability, we employed a Vision Transformer to perform monocular depth estimation. Our experimental setup included a challenging scenario involving glare to assess the differences in performance between the testing environments: camera test bench and simulation. We quantified the gap by contrasting image quality metrics of partly-synthetic and pure synthetic data with real-world data contained in the KITTI depth dataset. With our approach, we were able to produce images that are 37 % closer to real-world than synthetic image data. Also, the gap in data variability is 18 % less than with synthetic data. In addition, we found that clipping in glare situations does not necessarily lead to large errors in depth prediction. © 2024 IEEE.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

Instance Selection Techniques for Large Volumes of data 24th

Instance Selection Techniques for Large Volumes of Data

引用

24th international conference on intelligent data engineering and automated learning, IDEAL 2023

作者： Cubillos, Marco Antonio Peña Ballesteros, Antonio Javier Tallón Department of Electronic Computer Systems and Automation Engineering International University of Andalusia Huelva Spain

ISBN: (纸本)9783031482311

Instance selection (IS) serves as a vital preprocessing step, particularly in addressing the complexities associated with high-dimensional problems. Its primary goal is the reduction of data instances, a process that involves eliminating irrelevant and superfluous data while maintaining a high level of classification accuracy. IS, as a strategic filtering mechanism, addresses these challenges by retaining essential instances and discarding hindering elements. this refinement process optimizes classification algorithms, enabling them to excel in handling extensive datasets. In this research, IS offers a promising avenue to strengthen the effectiveness of classification in various real-world applications. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of Serverless Computing on Peer To Peer Training Machine learning 11

Exploring the Impact of Serverless Computing on Peer To Peer...

引用

11th IEEE international conference on Cloud engineering (IC2E)

作者： Barrak, Amine Trabelsi, Ranim Jaafar, Fehmi Petrillo, Fabio Univ Quebec Chicoutimi UQAC Dept Comp Sci & Math Chicoutimi PQ Canada ETS Ecole Technol Super Dept Genie Log Montreal PQ Canada

ISBN: (纸本)9798350343946

the increasing demand for computational power in big data and machine learning has driven the development of distributed training methodologies. Among these, peer-to-peer (P2P) networks provide advantages such as enhanced scalability and fault tolerance. However, they also encounter challenges related to resource consumption, costs, and communication overhead as the number of participating peers grows. In this paper, we introduce a novel architecture that combines serverless computing with P2P networks for distributed training and present a method for efficient parallel gradient computation under resource constraints. Our findings show a significant enhancement in gradient computation time, with up to a 97.34% improvement compared to conventional P2P distributed training methods. As for costs, our examination confirmed that the serverless architecture could incur higher expenses, reaching up to 5.4 times more than instance-based architectures. It is essential to consider that these higher costs are associated with marked improvements in computation time, particularly under resource-constrained scenarios. Despite the cost-time trade-off, the serverless approach still holds promise due to its pay-as-you-go model. Utilizing dynamic resource allocation, it enables faster training times and optimized resource utilization, making it a promising candidate for a wide range of machine learning applications.

关键词： Serverless FaaS Function as a Service P2P peer-to-peer architecture Distributed Training Machine learning

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Energy Recommendations Using Federated learning and Local LLMs on the Edge 11

Privacy-Preserving Energy Recommendations Using Federated Le...

引用

11th IEEE/ACM international conference on Big data Computing, Applications and Technologies, BDCAT 2024

作者： Chronis, Christos Varlamis, Iraklis Dimitrakopoulos, George Bensaali, Faycal Papadopoulos, Georgios th. Harokopio University of Athens Dept. of Informatics and Telematics Athens Greece Qatar University Dept. of Electrical Engineering Doha Qatar

ISBN: (纸本)9798350367300

Effective energy management in households is critical to achieving overall energy efficiency and sustainability goals. this study introduces a novel approach to predicting short-term energy consumption for households using federated learning (FL) models. the approach achieves short-term energy consumption predictions (i.e. for the next 10 minutes) by analyzing local data, such as the current watt consumption and activated devices. the key innovation in this approach is the use of privacy-preserving machine learning techniques, ensuring that personal data is never shared during the training process. the models are used to predict potential spikes in energy demand, allowing for proactive management. In addition, a local Large Language Model (LLM) is integrated to generate personalized recommendations for users, aimed at avoiding predicted consumption spikes and promoting energy-efficient behavior. this approach not only preserves user privacy but also enhances user engagement by providing actionable insights based on local consumption patterns. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Proceedings of the 11th international conference on Communities and Technologies - Humanization of Digital Technologies 2023, C and T 2023

Proceedings of the 11th International Conference on Communit...

引用

11th international conference on Communities and Technologies: Humanization of Digital Technologies, C and T 2023

ISBN: (纸本)9798400707582

the proceedings contain 31 papers. the topics discussed include: turning robotic process automation onto intelligent automation with machine learning;a case study of cross-organizational co-design with public bodies: opportunities for a collaborative platform;user experience for non-expert audiences in data exploration;updating natureculture practices in Abruzzo: towards the prototyping of new ecological relationships between shepherds, farmers, animals and plants;beyond human sensors: more-than-human citizen sensing in biodiversity urban living labs;connecting through objects: sharing memories through participatory stop-motion animation with personal objects of the Armenian diaspora;two-sided cultural niches: topic overlap, geospatial correlation, and local group activities on event-based social networks;supporting innovation in a context of uncertainty: the role of design and technology;and accessibility of Kahoot! and Quizizz: utilizing educational games with elderly students.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Adaptive Neural Network Asymptotic Control for Non-Triangular Stochastic Nonlinear Systems 11

Event-Triggered Adaptive Neural Network Asymptotic Control f...

引用

11th IEEE data Driven Control and learning Systems conference, DDCLS 2022

作者： Liu, Yongchao Zeng, Bowen Institute of Complexity Science School of Automation Qingdao University Qingdao China College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

this paper designs an event-triggered adaptive neural network asymptotic control (ANNAC) method for non-triangular stochastic nonlinear systems (SNS). In contrast to published neural network schemes where the tracking errors converge bounded regions, a bound estimation scheme is given for every subsystem based on backstepping technique. the presented event-triggered ANNAC method can make the considering closed-loop systems to be asymptotically stable. © 2022 IEEE.

关键词： Backstepping

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 << < 86 87 88 89 90 91 92 93 94 95 > >>

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：