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

115 篇 会议
3 册 图书

馆藏范围

118 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

96 篇 工学
- 87 篇 计算机科学与技术...
- 29 篇 软件工程
- 13 篇 信息与通信工程
- 11 篇 控制科学与工程
- 9 篇 生物工程
- 7 篇 生物医学工程（可授...
- 4 篇 机械工程
- 4 篇 网络空间安全
- 3 篇 光学工程
- 3 篇 电气工程
- 2 篇 仪器科学与技术
- 2 篇 电子科学与技术（可...
- 2 篇 建筑学
- 2 篇 交通运输工程
21 篇 理学
- 11 篇 数学
- 9 篇 生物学
- 5 篇 统计学（可授理学、...
- 4 篇 物理学
- 1 篇 大气科学
15 篇 管理学
- 9 篇 管理科学与工程(可...
- 7 篇 图书情报与档案管...
- 3 篇 工商管理
- 3 篇 公共管理
11 篇 医学
- 8 篇 基础医学(可授医学...
- 7 篇 临床医学
- 6 篇 药学(可授医学、理...
- 5 篇 公共卫生与预防医...
3 篇 法学
- 3 篇 社会学
3 篇 文学
- 3 篇 新闻传播学
1 篇 经济学
- 1 篇 应用经济学

主题

11 篇 machine learning
9 篇 data mining
7 篇 training
5 篇 deep learning
5 篇 training data
5 篇 classification
5 篇 accuracy
3 篇 neural networks
3 篇 educational inst...
3 篇 pattern recognit...
3 篇 visualization
3 篇 clustering algor...
3 篇 artificial intel...
3 篇 convolutional ne...
2 篇 learning systems
2 篇 support vector m...
2 篇 education data m...
2 篇 diabetic retinop...
2 篇 automation
2 篇 extreme learning...

机构

4 篇 univ birmingham ...
2 篇 nanjing normal u...
2 篇 warsaw univ tech...
2 篇 department of ph...
2 篇 electrical engin...
2 篇 chitkara univers...
2 篇 department of ph...
2 篇 school of civil ...
2 篇 department of in...
2 篇 univ politecn va...
2 篇 school of busine...
2 篇 univ sfax natl e...
2 篇 china constructi...
1 篇 wroclaw univ eco...
1 篇 national institu...
1 篇 univ east saraje...
1 篇 graduate school ...
1 篇 department of co...
1 篇 icmc/university ...
1 篇 univ jaen dep co...

作者

4 篇 naranjo valery
3 篇 ben amar chokri
3 篇 jaedong lee
3 篇 zaied mourad
3 篇 jee-hyong lee
3 篇 yin hujun
2 篇 penhaker marek
2 篇 hujun yin
2 篇 colomer adrian
2 篇 jemai olfa
2 篇 kasik vladimir
2 篇 herrera francisc...
2 篇 snášel václav
2 篇 grzenda maciej
2 篇 yang ming
1 篇 huang tao
1 篇 aruna sri rongal...
1 篇 yang bin
1 篇 espin santiago
1 篇 sheth tanay

语言

116 篇 英文
1 篇 其他
1 篇 中文

检索条件"任意字段=15th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2014"

共 118 条记录，以下是91-100 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：

A pervasive intelligent system for scoring MEWS and TISS-28 in intensive care 15

引用

15th international conference on Biomedical engineering, ICBME 2013

作者： Portela, Filipe Santos, Manuel Filipe Silva, Álvaro Machado, José Abelha, António Rua, Fernando Algoritmi Centre University of Minho Portugal CCTC University of Minho Portugal Serviço de Cuidados Intensivos Centro Hospitalar do Porto Hospital Santo António Portugal

ISBN: (纸本)9783319029122

usually intensive care medicine practice is highly supported on scores as SOFA, SAPS and Glasgow. More recently, two new scores have been considered: MEWS and *** paper presents how the Scoring System (SS) of the Intensive Care Unit (ICU) of Centro Hospitalar do Porto, evolved in order to accommodate the new scores. SS can automatically, in real-time and using online learning, provide a set of scores with a minimum human effort. SS is integrated in the Electronic Nursing Record (ENR) used for better comprehension of the patient condition through a set of information available: vital signs graphs, therapeutic plans, interventions, laboratory results and others. those systems are supported by a pervasive platform for monitoring patient data anywhere and anytime. SS calculates the TISS-28 Score per day and nursing turn and the MEWS per minute, hour and day. these two new scores improve the understanding of the real condition of the patients. SS allows for obtaining automatically and in real-time the following scores: SAPS II, SAPS III, SOFA, GLASGOW, TISS28 and Mews anywhere and anytime. the development of SS only was possible due to a continuous and real-time execution of the data acquisition and data processing. the introduction of MEWS and TISS-28 brought some benefits at level of the decision process and workload and, consequently, to the ICU management process. © Springer international Publishing Switzerland 2014.

关键词： intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Stabilization control of an inverted pendulum by complex-valued neuro-fuzzy learning algorithm

Stabilization control of an inverted pendulum by complex-val...

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： Jin Arai Ryusuke Hata Kazuyuki Murase Graduate School of Engineering University of Fukui Fukui Japan

As an automatic generation method of the fuzzy rules, the complex-valued neuro-fuzzy (CVNF) learning algorithm has been suggested. that is a method expanded the conventional neuro-fuzzy (NF) learning algorithm into the complex domain. the purpose of this study is to verify the effectiveness of the CVNF by performing the stabilization control of an inverted pendulum using CVNF, and comparing it with NF. As a result, the control of the inverted pendulum was possible in CVNF with higher precision than in NF.

关键词： Noise measurement Training data Training Educational institutions Fuzzy logic Approximation algorithms Gravity

来源：评论

学校读者我要写书评

暂无评论

Process-controlled forming using an intelligent tool on a servo press 15

Process-controlled forming using an intelligent tool on a se...

引用

15th international conference on Metal Forming 2014

作者： Engel, Bernd Kersten, Sebastian Kopfer, Peter Forming Technology University of Siegen Paul-Bonatz-Straße 9-11 Siegen57076 Germany Automotive Center Südwestfalen Kölner Straße 125 Attendorn57439 Germany

ISBN: (纸本)9783038351931

With regard to the climate change as well as the shortage and increase in price of natural resources, efficient resource management becomes more and more important, also for production processes. More than half of the sheet metal used in the automotive industry is wasted. Considering the amount of energy and the added value associated to the discards, enormous savings are possible. the approach of this research work is to avoid waste during a forming process by means of a continuous process monitoring and a self-learning intelligent tool interacting with the servo press. the flexibility of the servo press, which is so far used to optimize the single press stroke, only, shall be exerted to respond on altering material properties of blank sheets and the thereby changing forming behaviour. the sample process includes a two-tiered bending process, in which a conventional punch performs the pre-bending in the first step and an independent servo axis the compensation-bending in the second step. If an inadmissible bending angle is measured after the second step, the servo press stops automatically and the additional servo axis performs a teachingstroke to adjust the compensation angle. After that, the continuous process starts again. this paper presents the springback compensation strategy which uses flexible correction algorithms based on data of the on-line process monitoring as well as data of the previous bending steps. Finite Element Analyses are carried out to validate the strategy. © (2014) Trans Tech Publications, Switzerland.

关键词： Process control

来源：评论

学校读者我要写书评

暂无评论

Incremental learning with self-organizing neural grove

Incremental learning with self-organizing neural grove

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： Tomohiro Miyakoda Hirotaka Inoue Advanced Course National Institute of Technology Kure Hiroshima Japan Dept. of Electrical Engineering & Information Science National Institute of Technology Kure Hiroshima Japan

Multiple classifier systems (MCS) have become popular during the last decade. Self-generating neural tree (SGNT) is one of the suitable base-classifiers for MCS because of the simple setting and fast learning. In an earlier paper, we proposed a pruning method for the structure of the SGNT in the MCS to reduce the computational cost and we called this model as self-organizing neural grove (SONG). In this paper, we investigate a performance of incremental learning using SONG for two classification problems. the result shows that the SONG can reinsure rapid and efficient incremental learning.

关键词： Iris recognition Neurons Pattern recognition Neural networks Accuracy Training Training data

来源：评论

学校读者我要写书评

暂无评论

A Machine learning Approach to Predict Cyclists’ Functional threshold Power 24th

A Machine Learning Approach to Predict Cyclists’ Functional...

引用

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

作者： Stockwell, Ronald Andrew Corradini, Andrea Oakville ON Canada MCI Universitätsstraße 15 Innsbruck6020 Austria

ISBN: (纸本)9783031482311

the estimated Functional threshold Power (eFTP) obtained from a cyclists best 20-min effort, expressed in watts, and multiplied by 95% is sometimes overstated, especially for non-elite level cyclists or cyclists just starting out. Since Functional threshold Power (FTP) is used for training prescription, in terms of creating power zones to train in, it is of utmost importance that the correct FTP is used. If FTP is overstated, a cyclist will overtrain at a level that is unrealistic to achieve. this research project aims at validating eFTP using a large, big data dataset, as well as to build out a supervised machine learning model, in the form of a weighted logistic regression, that can be used to predict FTP (pFTP), to create predictor of FTP that’s better than the currently accepted eFTP formula. Based on the data provided, our approach predicts FTP with far greater accuracy than eFTP, which turned out to overestimate cyclists’ FTP. the model outcome for each athlete, pFTP, was evaluated versus eFTP, by comparing each of these outcomes to the actual FTP (aFTP) observed in the data. To do this, Mean Squared Error and Mean Absolute Error were computed with pFTP producing values of 314.87 and 10.38 respectively when compared to aFTP, and eFTP producing 6417.32 and 61.16. With more accurate FTP estimations, cyclists are more likely to train in the correct power zones. It also validates that a laboratory environment is not always required when trying to validate eFTP and that a large, big data dataset can act as a valid substitute. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

On-Device Training of Deep learning Models on Edge Microcontrollers 15

On-Device Training of Deep Learning Models on Edge Microcont...

引用

2022 IEEE Congress on Cybermatics: 15th IEEE international conferences on Internet of things, ithings 2022, 18th IEEE international conferences on Green Computing and Communications, GreenCom 2022, 2022 IEEE international conference on Cyber, Physical and Social Computing, CPSCom 2022 and 8th IEEE international conference on Smart data, Smartdata 2022

作者： De Vita, Fabrizio Nocera, Giorgio Bruneo, Dario Tomaselli, Valeria Falchetto, Mirko University of Messina Department of Engineering Italy STMicroelectronics Italy

ISBN: (数字)9781665454179

ISBN: (纸本)9781665454179

Recent advancements in Artificial Intelligence (AI) together with the increase of device computational power catalyzed the widespread diffusion of intelligent Cyber Physical Systems (ICPSs) as a novel solution to run smart applications where the inference is performed on the Micro Controller Unit (MCU). Unfortunately, the hardware constraints of these devices limit the tasks that can be accomplished, for this reason, most of the times hybrid Cloud/Edge approaches have been proposed to enable the offloading of those operations (e.g., the training of deep learning models) that would not fit the computation, memory, and energy requirements. However, when security, latency, and connection stability aspects are relevant, it is clear that the use of such an approach is no longer suitable. this becomes even more evident in those contexts where it is asked the detection of new data patterns that can emerge over time. Focusing our attention on the analysis of time series data, in this paper we propose a novel Echo State Network (ESN) model that enables the on-device training directly on the MCUs of the STM32 family. Starting from a custom layer implementation on Keras, we extended the functionalities of the X-CUBE-AI tool provided by STMicroelectronics to recognize this type of network and enable the automatic deployment on the smart boards. To test the proposed solution, we realized a testbed and conducted a set of experiments that demonstrate the feasibility of our MCU on-device training approach which reached a good level of precision, recall, and F1-score. © 2022 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Rough Set Classifier Based on Discretization and Attribute Selection 15th

A Rough Set Classifier Based on Discretization and Attribute...

引用

15th international conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2019, co-located with the 5th international conference on Harmony Search, Soft Computing and Applications, ICHSA 2019

作者： Sun, Yingjuan Pu, Dongbing Gu, Dongbing Gan, John Q. Yang, Kun College of Computer Science and Technology Changchun Normal University Changchun China School of Computer Science and Electronic Engineering University of Essex Colchester United Kingdom School of Information Science and Technology Northeast Normal University Changchun China

ISBN: (纸本)9783030325909

Rough set is useful for classification in learning model. the main advantage of rough set is to find out the relativity among attributes directly from attributes of data without any preliminary or additional information. A rough set classifier based on discretization and attribute selection is proposed in this paper. Our rough set classifying algorithm give a full consider about condition attribute significance during the process of rule forming. We verified our algorithm on five well-known UCI machine learning data sets. the experiment results are expressed by mean of accuracies. At last, we compare our experiment results with the classical algorithms of other two references [8] and [9]. Results prove proposed algorithm is better than them. It can get higher classification accuracy, lower breakpoints and rules in all data sets of our experiments. © 2020, Springer Nature Switzerland AG.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A multi-agent architecture for labeling data and generating prediction models in the field of social services 15th

A multi-agent architecture for labeling data and generating ...

引用

15th international conference on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2017

作者： Serrano, Emilio Del Pozo-Jiménez, Pedro Suárez-Figueroa, Mari Carmen González-Pachón, Jacinto Bajo, Javier Gómez-Pérez, Asunción Ontology Engineering Group Universidad Politécnica de Madrid Madrid Spain

ISBN: (纸本)9783319602844

Prediction models are widely used in insurance companies and health services. Even when 120 million people are at risk of suffering poverty or social exclusion in the EU, this kind of models are surprisingly unusual in the field of social services. A fundamental reason for this gap is the difficulty in labeling and annotating social services data. Conditions such as social exclusion require a case-by-case debate. this paper presents a multi-agent architecture that combines semantic web technologies, exploratory data analysis techniques, and supervised machine learning methods. the architecture offers a holistic view of the main challenges involved in labeling data and generating prediction models for social services. Moreover, the proposal discusses to what extent these tasks may be automated by intelligent agents. © Springer international Publishing AG 2017.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

K-means clustering based SVM ensemble methods for imbalanced data problem

K-means clustering based SVM ensemble methods for imbalanced...

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： Jaedong Lee Jee-Hyong Lee Dept. of Electrical and Computer Engineering Sungkyunkwan University Suwon Republic of Korea

ISBN: (纸本)9781479959563

When the number of data in one class is significantly larger or less than the data in other class, under machine learning algorithm for classification, a problem of learning generalization occurs to the specific class and this is called imbalanced data problem. In this paper, we propose a novel method to solve the imbalanced data problem. We first divide data into clusters using K-means clustering algorithm and create classifier using the Support Vector Machine (SVM) method on each cluster. Before making classifier for each cluster, we are balancing the data for each cluster using data sampling techniques. After all classifiers are made for each cluster, we validate each classifier's performance using validation data. Final classification result would be calculated using the test data by aggregating all the cluster's classification results. We are using not only the results from the classifiers in each clusters, but also the credit of each classifier and data membership to each cluster. We have verified that the proposed classification method shows better performance than the existing machine learning algorithms for imbalanced data classification problem.

关键词： Support vector machines Machine learning algorithms Clustering algorithms Rain Pattern recognition Training data

来源：评论

学校读者我要写书评

暂无评论

Automatic view composition for improving co-training

Automatic view composition for improving co-training

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： HyeWoo Lee Kyoungmin Kim Jaedong Lee Jee-Hyong Lee Department of Electrical and Computer Engineering Sungkyunkwan Univ Suwon Republic of Korea

ISBN: (纸本)9781479959563

In this paper, we propose a view composition method for co-training. In order to compose views properly, two assumptions should be satisfied. One is that two views are class-conditionally independent on each other; the other is that the classification information between labels and view is high. We apply Class-Conditional Independent Component Analysis (CC-ICA) to obtain new features which are mutually independent, and compose views hold a high classification information. We show that our method is promising and effective through the experiment.

关键词： Mutual information Transforms Training data Training Semisupervised learning Independent component analysis Electroencephalography

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12页 << < 3 4 5 6 7 8 9 10 11 12 > >>

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：