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

126 篇 会议
1 册 图书

馆藏范围

127 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

107 篇 工学
- 99 篇 计算机科学与技术...
- 45 篇 软件工程
- 16 篇 信息与通信工程
- 15 篇 生物工程
- 10 篇 控制科学与工程
- 6 篇 电气工程
- 5 篇 电子科学与技术（可...
- 4 篇 交通运输工程
- 4 篇 安全科学与工程
- 3 篇 动力工程及工程热...
- 3 篇 建筑学
- 3 篇 水利工程
- 3 篇 生物医学工程（可授...
- 2 篇 机械工程
- 2 篇 光学工程
- 2 篇 仪器科学与技术
- 2 篇 化学工程与技术
35 篇 理学
- 19 篇 数学
- 17 篇 生物学
- 11 篇 统计学（可授理学、...
- 5 篇 物理学
- 5 篇 系统科学
- 2 篇 大气科学
28 篇 教育学
- 28 篇 教育学
18 篇 管理学
- 14 篇 图书情报与档案管...
- 4 篇 管理科学与工程(可...
3 篇 医学
- 3 篇 基础医学(可授医学...
- 3 篇 临床医学
2 篇 经济学
- 2 篇 应用经济学
2 篇 法学
- 2 篇 社会学
1 篇 军事学

主题

14 篇 machine learning
7 篇 deep learning
6 篇 natural language...
3 篇 support vector m...
3 篇 decision trees
3 篇 accuracy
2 篇 object detection
2 篇 learning systems
2 篇 transformer
2 篇 deep neural netw...
2 篇 gamification
2 篇 data repository
2 篇 data symbion ei
2 篇 data mining
2 篇 multi-task learn...
2 篇 large language m...
2 篇 traffic congesti...
2 篇 image classifica...
2 篇 classification
2 篇 federated learni...

机构

2 篇 harvard grad sch...
2 篇 warsaw univ tech...
2 篇 laboratory of el...
2 篇 university claud...
2 篇 univ fed alagoas...
2 篇 fed rural univ s...
2 篇 department of ra...
2 篇 carnegie mellon ...
2 篇 mars research la...
2 篇 department of el...
2 篇 intelligent tran...
2 篇 yonsei univ dept...
2 篇 indian inst tech...
1 篇 univ poitiers f-...
1 篇 univ wroclaw ins...
1 篇 wiesbaden
1 篇 school of electr...
1 篇 department of co...
1 篇 school of inform...
1 篇 ceprei iptrkl of...

作者

2 篇 rajendran ramkum...
2 篇 hastings peter
2 篇 sotero roberto c...
2 篇 reis marcelo
2 篇 ding naikan
2 篇 sahin halil mert...
2 篇 isotani seiji
2 篇 grieve bruce
2 篇 santos matilde
2 篇 cohn clayton
2 篇 martín de diego ...
2 篇 bittencourt ig i...
2 篇 weitekamp daniel
2 篇 sanchez-bornot j...
2 篇 omri mohamed naz...
2 篇 camacho david
2 篇 omri asma
2 篇 yin hujun
2 篇 santos jario
2 篇 cho sung-bae

语言

127 篇 英文

检索条件"任意字段=24th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2023"

共 127 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：

learning Optimal Q-Function Using Deep Boltzmann Machine for Reliable Trading of Cryptocurrency 19th

Learning Optimal Q-Function Using Deep Boltzmann Machine for...

引用

19th international conference on intelligent data engineering and automated learning (ideal)

作者： Bu, Seok-Jun Cho, Sung-Bae Yonsei Univ Dept Comp Sci Seoul South Korea

ISBN: (纸本)9783030034931;9783030034924

the explosive price volatility from the end of 2017 to January 2018 shows that bitcoin is a high risk asset. the deep reinforcement algorithm is straightforward idea for directly outputs the market management actions to achieve higher profit instead of higher price-prediction accuracy. However, existing deep reinforcement learning algorithms including Q-learning are also limited to problems caused by enormous searching space. We propose a combination of double Q-network and unsupervised pre-training using Deep Boltzmann Machine (DBM) to generate and enhance the optimal Q-function in cryptocurrency trading. We obtained the profit of 2,686% in simulation, whereas the best conventional model had that of 2,087% for the same period of test. In addition, our model records 24% of profit while market price significantly drops by -64%.

关键词： Deep reinforcement learning Q-network Deep Boltzmann Machine Portfolio management

来源：评论

学校读者我要写书评

暂无评论

An Innovative Deep-learning Algorithm for Supporting the Approximate Classification of Workloads in Big data Environments 20th

An Innovative Deep-Learning Algorithm for Supporting the App...

引用

20th international conference on intelligent data engineering and automated learning (ideal)

作者： Cuzzocrea, Alfredo Mumolo, Enzo Leung, Carson K. Grasso, Giorgio Mario Univ Calabria Arcavacata Di Rende Italy Univ Trieste Trieste Italy Univ Manitoba Winnipeg MB Canada Univ Messina Messina Italy

ISBN: (纸本)9783030336172;9783030336165

In this paper, we describe AppxDL, an algorithm for approximate classification of workloads of running processes in big data environments via deep learning (deep neural networks). the Deep Neural Network is trained with some workloads which belong to known categories (e.g., compiler, file compressor, etc...). Its purpose is to extract the type of workload from the executions of reference programs, so that a Neural Model of the workloads can be learned. When the learning phase is completed, the Deep Neural Network is available as Neural Model of the known workloads. We describe the AppxDL algorithm and we report and discuss some significant results we have achieved with it.

关键词： Workload classification Virtualized environment Deep learning

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised learning to Reduce data Needs of Indoor Positioning Models 19th

Semi-supervised Learning to Reduce Data Needs of Indoor Posi...

引用

19th international conference on intelligent data engineering and automated learning (ideal)

作者： Grzenda, Maciej Warsaw Univ Technol Fac Math & Informat Sci Ul Koszykowa 75 PL-00662 Warsaw Poland

ISBN: (纸本)9783030034962;9783030034955

Indoor positioning systems answer the need for ubiquitous localisation systems. Frequently, indoor positioning relies on machine learning models developed based on the training data composed of WiFi received signal strength (RSS) vectors observed in different indoor locations. However, this requires expensive collection of RSS vectors in precisely measured locations. In this study, we propose a semi-supervised method, which can reduce the volume of expensive labelled training data and exploit the availability of unlabelled signal strength measurements. the method relies, inter alia, on the measures of similarity among nearest neighbours of unlabelled vectors. Tests performed with a number of testbed areas confirm that the method improves the accuracy of random forest models used to estimate indoor location of mobile terminals.

关键词： Semi-supervised learning Fingerprinting Indoor positioning

来源：评论

学校读者我要写书评

暂无评论

GPU-Based Acceleration of the Rao Optimization Algorithms: Application to the Solution of Large Systems of Nonlinear Equations 24th

GPU-Based Acceleration of the Rao Optimization Algorithms:...

引用

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

作者： Silva, Bruno Lopes, Luiz Guerreiro Doctoral Program in Informatics Engineering University of Madeira Madeira Is. Funchal Portugal Regional Secretariat for Education Science and Technology Regional Government of Madeira Funchal Portugal Faculty of Exact Sciences and Engineering University of Madeira Madeira Is. Funchal9020-105 Portugal

ISBN: (纸本)9783031482311

In this paper, parallel GPU-based versions of the three Rao metaphor-less optimization algorithms are proposed and used to solve large-scale nonlinear equation systems, which are hard to solve with traditional numerical methods, particularly as the size of the systems get bigger. the parallel implementations of the Rao algorithms were performed in Julia and tested on a high-performance GeForce RTX 3090 GPU with 10 496 CUDA cores and 24 GB of GDDR6X VRAM using a set of challenging scalable systems of nonlinear equations. the computational experiments carried out demonstrated the efficiency of the proposed GPU-accelerated versions of the Rao optimization algorithms, with average speedups ranging from 57.10 × to 315.12 × for the set of test problems considered in this study. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

the Applicability of Federated learning to Official Statistics 24th

The Applicability of Federated Learning to Official Statis...

引用

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

作者： Stock, Joshua Hauke, Oliver Weißmann, Julius Federrath, Hannes Universität Hamburg Hamburg Germany Wiesbaden Germany

ISBN: (纸本)9783031482311

this work investigates the potential of Federated learning (FL) for official statistics and shows how well the performance of FL models can keep up with centralized learning methods. FL is particularly interesting for official statistics because its utilization can safeguard the privacy of data holders, thus facilitating access to a broader range of data. By simulating three different use cases, important insights on the applicability of the technology are gained. the use cases are based on a medical insurance data set, a fine dust pollution data set and a mobile radio coverage data set–all of which are from domains close to official statistics. We provide a detailed analysis of the results, including a comparison of centralized and FL algorithm performances for each simulation. In all three use cases, we were able to train models via FL which reach a performance very close to the centralized model benchmarks. Our key observations and their implications for transferring the simulations into practice are summarized. We arrive at the conclusion that FL has the potential to emerge as a pivotal technology in future use cases of official statistics. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： learning systems

来源：评论

学校读者我要写书评

暂无评论

Globular Cluster Detection in M33 Using Multiple Views Representation learning 24th

Globular Cluster Detection in M33 Using Multiple Views Repr...

引用

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

作者： Singlor, Taned thawatdamrongkit, Phonphrm Techa-Angkoon, Prapaporn Suwannajak, Chutipong Bootkrajang, Jakramate Department of Computer Science Faculty of Science Chiang Mai University Chiang Mai Thailand Chiang Mai Thailand

ISBN: (纸本)9783031482311

Globular clusters (GC) are crucial for understanding galaxy formation and evolution. However, identifying them in large imagery datasets is a time-consuming task. this prompts the development of an automated GC detection algorithm. Although GC detection is fundamentally an object detection problem, the state-of-the-art object detection algorithms are unable to produce accurate results. Motivated by how GCs are identified by astronomers, we propose a deep neural network that fuses multiple views of raw imaging data and learns a better representation of the input image. the proposed network is then combined with YOLO object detection algorithm resulting in YOLO for Globular Cluster detection (YOLO-GC) model. Experimental results based on a real catalog of GCs in the M33 Galaxy showed that the proposed multi-view representation learning technique helps improve detection performance. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Depth and Width Adaption of DNN for data Stream Classification with Concept Drifts 24th

Depth and Width Adaption of DNN for Data Stream Classificati...

引用

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

作者： Zhou, XingZhi Liu, Xiang Wen, YiMin Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9783031482311

To handle data stream classification with concept drifts, recent studies have shown that a continuously evolving network structure can achieve better performance. However, firstly, they only change one hidden node at a time, which is not enough to alleviate underfitting or overfitting of network model, leading to model’s inability to fit data well. Secondly, during the growth process of the network, they did not consider reducing hidden layers, which would affect the learning ability of deep neural network models. To overcome these shortcomings, an adaptive neural network structure (ANSN) is proposed to handle data stream classification with concept drifts. ANSN has a completely open structure, its network structure, depth, and width can evolve automatically in online mode. the experimental results on ten popular data stream datasets show that the proposed ANSN outperforms the comparison methods. the codes of the proposed algorithm is available on https://***/ymw12345/***. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Extensions for Continuous Pattern Mining

Extensions for Continuous Pattern Mining

引用

12th international conference on intelligent data engineering and automated learning (ideal 2011)

作者： Gorawski, Marcin Jureczek, Pawel Silesian Tech Univ Inst Comp Sci PL-44100 Gliwice Poland

ISBN: (纸本)9783642238772

In this paper we present extensions for continuous pattern mining. Our previous continuous pattern mining algorithm mines the set of all frequent sequences satisfying the minSup condition. However, those sequences contain an explosive number of frequent subsequences, which makes the analysis and understanding of patterns very difficult. In order to overcome these difficulties, we propose four new algorithms for mining maximal and closed continuous patterns. these algorithms return a superset of the result patterns and then a post-pruning algorithm is performed to eliminate redundant sequences. For each type of patterns (maximal or closed) two algorithms are presented (with and without some improvements). the key idea is to omit as many redundant sequences as possible during the exploration. the proposed algorithms allow one to reduce the size of the result set when input sequences have low uniqueness.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

A Probabilistic Approach: Querying Web Resources in the Presence of Uncertainty 24th

A Probabilistic Approach: Querying Web Resources in the Pr...

引用

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

作者： Omri, Asma Bensliamne, Djamal Omri, Mohamed Nazih MARS Research Laboratory University of Sousse Sousse Tunisia University Claude Bernard Lyon 1 LIRIS Research Laboratory Villeurbanne France

ISBN: (纸本)9783031482311

Uncertainty in data naturally arises in various applications, such as data integration and Web information extraction. A few examples are the following. When information from different sources is conflicting, inconsistent, or simply presented in incompatible forms the result of integrating these sources necessarily involves uncertainty as to which fact is correct or which is the best mapping to a global schema. data uncertainty is often ignored, or modeled in a specific, per-application manner. this may be an unsatisfying solution in the long run, especially when the uncertainty needs to be retained throughout complex and potentially imprecise processing of the data. In this paper, we study the basic activities of web resources that are affected by uncertainty, more specifically, modeling, programming and evaluation. We propose a probabilistic approach that treats uncertainty in all these activities. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： data integration

来源：评论

学校读者我要写书评

暂无评论

Reduction of Signal Strength data for Fingerprinting-Based Indoor Positioning 16th

Reduction of Signal Strength Data for Fingerprinting-Based I...

引用

16th international conference on intelligent data engineering and automated learning (ideal)

作者： Grzenda, Maciej Warsaw Univ Technol Fac Math & Informat Sci Ul Koszykowa 75 PL-00662 Warsaw Poland

ISBN: (纸本)9783319248349;9783319248332

Indoor Positioning Services (IPS) estimate the location of devices, frequently being mobile terminals, in a building. Many IPS algorithms rely on the Received Signal Strength (RSS) of radio signals observed at a terminal. However, these signals are noisy due to both the impact of the surrounding environment such as presence of other persons, and limited accuracy of strength measurements. Hence, the question arises whether raw RSS data can undergo transformation preserving its information content, but reducing the data and increasing the resilience of the algorithms to inherent noisiness of raw RSS data. this work evaluates the use of binning applied to RSS data and proposes the way the reduction of RSS data can be attained. Results show that the proposed way of using RSS binning causes little or no positioning accuracy degradation. Still, it yields significant RSS data reduction. Interestingly, in some cases data reduction results even in accuracy gains.

关键词： Received signal strength Binning Fingerprinting

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13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：