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

2,236 篇 会议
13 册 图书
5 篇 期刊文献

馆藏范围

2,254 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,606 篇 工学
- 1,382 篇 计算机科学与技术...
- 966 篇 软件工程
- 321 篇 控制科学与工程
- 241 篇 信息与通信工程
- 218 篇 电气工程
- 177 篇 生物工程
- 129 篇 生物医学工程（可授...
- 91 篇 机械工程
- 76 篇 交通运输工程
- 57 篇 光学工程
- 50 篇 电子科学与技术（可...
- 43 篇 化学工程与技术
- 42 篇 安全科学与工程
- 35 篇 仪器科学与技术
- 32 篇 土木工程
466 篇 理学
- 237 篇 数学
- 182 篇 生物学
- 101 篇 统计学（可授理学、...
- 81 篇 物理学
- 47 篇 系统科学
- 41 篇 化学
434 篇 管理学
- 287 篇 管理科学与工程(可...
- 162 篇 图书情报与档案管...
- 79 篇 工商管理
170 篇 医学
- 163 篇 临床医学
- 81 篇 基础医学(可授医学...
- 54 篇 药学(可授医学、理...
- 34 篇 公共卫生与预防医...
76 篇 教育学
- 74 篇 教育学
49 篇 法学
- 44 篇 社会学
30 篇 经济学
18 篇 农学
2 篇 军事学

主题

173 篇 machine learning
160 篇 deep learning
135 篇 training
100 篇 data models
78 篇 feature extracti...
76 篇 accuracy
70 篇 data mining
67 篇 neural networks
66 篇 predictive model...
61 篇 reinforcement le...
57 篇 computational mo...
52 篇 support vector m...
46 篇 real-time system...
42 篇 machine learning...
39 篇 training data
39 篇 artificial intel...
36 篇 visualization
35 篇 learning systems
35 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

2,155 篇 英文
93 篇 其他
27 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 2254 条记录，以下是471-480 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：

Drift Detection in Text data with Document Embeddings 22nd

Drift Detection in Text Data with Document Embeddings

引用

22nd international conference on intelligent data engineering and automated learning

作者： Feldhans, Robert Wilke, Adrian Heindorf, Stefan Shaker, Mohammad Hossein Hammer, Barbara Ngomo, Axel-Cyrille Ngonga Huellermeier, Eyke Bielefeld Univ Bielefeld Germany Paderborn Univ Dept Comp Sci DICE Grp Paderborn Germany Univ Munich LMU Munich Germany

ISBN: (纸本)9783030916077;9783030916084

Collections of text documents such as product reviews and microblogs often evolve over time. In practice, however, classifiers trained on them are updated infrequently, leading to performance degradation over time. While approaches for automatic drift detection have been proposed, they were often designed for low-dimensional sensor data, and it is unclear how well they perform for state-of-the-art text classifiers based on high-dimensional document embeddings. In this paper, we empirically compare drift detectors on document embeddings on two benchmarking datasets with varying amounts of drift. Our results show that multivariate drift detectors based on the Kernel Two-Sample Test and Least-Squares Density Difference outperform univariate drift detectors based on the Kolmogorov-Smirnov Test. Moreover, our experiments show that current drift detectors perform better on smaller embedding dimensions.

关键词： Drift detection Document embeddings BERT Word2Vec

来源：评论

学校读者我要写书评

暂无评论

Cannabis Use Estimators Within Canadian Population Using Social Media Based on Deep learning Tools 22nd

Cannabis Use Estimators Within Canadian Population Using Soc...

引用

22nd international conference on Artificial Intelligence and Soft Computing (ICAISC)

作者： Ibrahim, Doaa Inkpen, Diana Al Osman, Hussein Ottawa Univ Ottawa ON K1N 6N5 Canada

ISBN: (纸本)9783031425073;9783031425080

Cannabis has become the most used drug worldwide with the highest risks and associated criminal problems in many countries. Therefore, identifying users at risk of cannabis use is an important and essential task. This will help doctors and people with authority to react fast and on time. We used two datasets (8,725 users in total) to build a strong model for predicting users at-risk in a sample of Twitter users that is representative of the Canadian population. Using a Bidirectional GRU classifier, we achieved high accuracy and F1-score (84.74% and 87.56%, respectively). This model was applied on the population dataset to predict the patterns of cannabis users all over Canada. The geographic patterns of cannabis users highly match the cannabis users statistics reported by Statistics Canada (with a small overall difference of 1.4%). To the best of our knowledge, this is the first study to demonstrate that the number of cannabis users in a country can be accurately estimated by analyzing a representative sample of Twitter users from various regions of the country.

关键词： CNN LSTM BERT BioBERT attention cannabis marijuana weed substance use classification risk behavior natural language processing social media transfer learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Monitoring and Control of Motor Drive Parameters Using Internet of Things Protocol for Industrial Automation 1

引用

2nd international conference on Computational Intelligence in Machine learning, ICCIML 2022

作者： MadhusudhanaRao, G. Dasam, Srinivas Pala Prasad Reddy, M. Rajagopal Reddy, B. Department of Electrical Engineering OP Jindal University Raigarh India Department of Electrical and Computer Engineering Mattu University Metu Oromia Ethiopia Department of EEE Institute of Aeronautical Engineering Hyderabad India Department of EEE Vardhaman College of Engineering Hyderabad India

ISBN: (数字)9789819979547

ISBN: (纸本)9789819979530

Nowadays, the vast majority of systems are automated. To automate, electromechanical equipment must be replaced by supervisory control and data acquisition (SCADA) systems and programmable logic controllers (PLCs) (SCADA). "PLC & SCADA-based distribution monitoring and control" refers to the use of an automobile system in an electrical distribution system for monitoring the voltage, current, power factor, etc., if any malfunction arises in the electrical system, with the use of a personal computer." The goal of this project is to use IoT to improve DRIVE monitoring. DC motors are frequently employed in industrial settings. The speed management of DC motors has become simpler because of advancements in semiconductor technology with the programming language. The SCADA system gathers data by corresponding with the PLC, while the PLC directly monitors and regulates the input sent to the drive. Only an IoT connection can be used to send the message from SCADA with the message communication protocol (MCP). As a result, there is a push to make users more reachable, which lowers labor expenses by cutting back on-site visits for data collection, inspection, and correction. To make distribution automation more intelligent, efficient, and economical, research and development efforts worldwide are concentrated on the communication technologies revolution and the use of IEC 61850 protocols in distribution automation. Employing the parameters may easily control any load in our strategy to enhance system performance, dependability, etc. Alternatively, protection control and electrical parameter monitoring can be integrated using SCADA and PLC communication systems for optimal benefit. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： DC motors

来源：评论

学校读者我要写书评

暂无评论

Machine learning approach to predict the position of a new online position measurement system's target 22

Machine Learning approach to predict the position of a new o...

引用

22nd international conference of the European Society for Precision engineering and Nanotechnology, EUSPEN 2022

作者： Garcia, Luis Bielke, Uwe Hageney, Theo Banzhaf, Klaus Wiedenmann, Ernst Borret, Rainer Aalen University Aalen Germany Glasgow Caledonian University Glasgow United Kingdom eµmetron GmbH Aalen Germany Serious Enterprises Aalen Germany

ISBN: (纸本)9781998999118

This article discusses a Machine learning approach for position determination of a target, that is used in a new measurement device called Multi-Aperture-Positioning-System (MAPS). The MAPS consists of two components, the measurement unit itself and the LED-Target, which is mounted to a machine under test - for example, an industrial robot or a coordinate measurement machine (CMM). The measurement system is based on a photogrammetric approach using an aperture array and a single camera. To achieve high accuracy in position calculation, multiple complex algorithms with high computing effort are used. Actual the MAPS offers an accuracy equal to or better compared to existing photogrammetric devices. Using Machine learning, a Convolutional Neural Network (CNN) is trained by artificial data and tested on real data. In order to generate these data sets, proprietary simulation software is used to generate artificial images. The CMM is used to move the LED-Target to different positions while MAPS takes images at these. The simulated images are used as input for training, while the real images are used to measure the performance of the CNN. Previously MAPS used several algorithms to calculate the position of the target from the taken image. The key idea behind the Machine learning approach is, that a Neural Network, trained on thousands of labelled data, should be as accurate as the originally used algorithms in determining the position of the target while being much faster. In addition, systematic errors, model errors, and uncertainties in the system parameters can be eliminated. While the Neural Network learns directly from the captured data, algorithms use formulas to calculate the position from the images. These formulas have a lot of influencing factors, that cannot always be precisely determined, change over time, or are not even known. When using a Neural Network instead, the model learns the relation between input and output data including all influences that exist

关键词： Computer software

来源：评论

学校读者我要写书评

暂无评论

Paddy Pest Classification Using Deep learning Based Features 2

Paddy Pest Classification Using Deep Learning Based Features

引用

2nd international conference on Next Generation intelligent Systems, ICNGIS 2022

作者： Ananyasreya, P.P. Subhija, E.N. Government Engineering College Department of Electronics and Communication Ramavarmapuram Kerala Thrissur680009 India

ISBN: (纸本)9781665467926

The agricultural sector has immense potential in day to day world to improve the requirements and supplies of healthy and nutritious food. Insect pest attacks are the major threats faced by farmers during cultivation and so pest identification is of utter importance in terms of productivity and quality. Pest identification is a difficult task for farmers and it creates severe damage to the yield of crops as well as degradation in the quality of the products. The insect pest attack should also be recognized in the initial state of invasion to avoid spreading. Conventional methods such as naked-eye detection are nonefficient and time-consuming and are difficult in large crop cultivation. This project aims in developing an automated pest classification system using deep learning strategies. Input data is augmented and preprocessed using histogram equalization. Deep learning is used for feature extraction and features are provided to conventional classifiers such as Support Vector Machine(SVM), Naive Bayes(NB), Random Forest(RF), and Logistic Regression(LR). SVM has achieved a better classification accuracy of 97% compared to other algorithms. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Fog-Assisted Smart Healthcare Prediction System for Diabetics Patients 1

引用

Emergent Converging Technologies and Biomedical Systems Select Proceedings of the 2nd international conference, ETBS 2022

作者： Sekhar Tripathy, Subhranshu Bhusan Panda, Shashi Pati, Abhilash Rath, Mamata Tripathy, Niva Sahu, Premananda Odisha Bhubaneswar India Department of Electronics and Telecommunication Engineering Raajdhani Engineering College Odisha Bhubaneswar India Department of Computer Science and Engineering Siksha ‘O’ Anusandhan University Odisha Bhubaneswar India Department of Computer Science and Engineering DRIEMS Autonomous College Odisha Cuttack India Department of Computer Science and Engineering SRMIST Delhi-NCR Campus UP Ghaziabad India

ISBN: (数字)9789819922710

ISBN: (纸本)9789819922703

Accurately, forecasting human diseases continues to be a challenging issue in the search for better and more crucial studies. Diabetic multifunctional sickness is a potentially dangerous condition that afflicts people all around the entire globe. Among the important parts of the human body it affects are the heart, neuropathy, retinopathy, and nephropathy. A healthcare monitoring recommendation system accurately detects and also suggests diabetes complications using adaptive machine learning methods and data fusion techniques on medical management datasets. Recently, various machine learning approaches and algorithms for predicting diabetic illness have been created. Even so, a lot of systems are unable to handle the massive volume of multi-feature raw data on the diabetes mellitus condition. An intelligent diabetic health management strategy is created using deep machine learning and data fusion technologies. By combining the data, we can reduce the unnecessary burden on organization computing power and increase the effectiveness of the suggested method, allowing us to predict and advise this life-threatening condition more accurately. Finally, the adaptive prediction system is assessed, and a machine learning model for diabetes diagnosis that is effective and up-to-date is trained. The suggested approach attained the maximum level of accuracy against standard advanced classification algorithms. The strategy we provide is therefore more effective in predicting and advising multimodal diabetic illness. Our proposed system’s improved disease diagnosis performance warrants its inclusion in automated diabetes patient diagnostic and recommendation systems. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Application of Machine learning to Automatic Gear Shift Schedule Design of Alternative Drive Systems 22

Application of Machine Learning to Automatic Gear Shift Sche...

引用

22nd international Symposium on Electrical Apparatus and Technologies, SIELA 2022

作者： Dineva, Adrienn Zsuga, Adam Szurke, Szabolcs Kocsis Vehicle Industry Research Center Széchenyi István University Győr Hungary Óbuda University Kálmán Kandó Faculty of Electrical Engineering Budapest Hungary

ISBN: (纸本)9781665411394

intelligent automatic transmission shift schedule design has been well established in the last decade. However, due to the paradigm change is currently taking place in mobility sector, which resulted in a rapid progress of Electric Vehicles and Autonomous Vehicles, intelligent automatic gear shift strategies are still in the focus of much research. In addition, the proper transmission shift schedule generation is especially important from the viewpoint of energy efficiency optimizing algorithms, which is affected by the driving style, power losses, etc. Fundamentally, conventional shift schedule design relies on lookup tables obtained from test-bench measurements and real-world driving measurements. During real time test data collection, the measurement of some variables may be impractical and/or patterns of important driving conditions may be unavailable during short-distance routes neglecting the comprehensive effects of the transient operation. Machine learning methods in combination with model-based data generation is a promising alternative, which allows a significant reduction in development time and a more precise calibration by using rich historical data rich. Such models can be easily fitted to alternative drive systems also, which may raise more specific requirements regarding gear shift scheduling issues coupled with efficiency. In this paper the performances of Machine learning models are investigated in automatic gear shift schedule generation based on simulated driving cycle test data. Results of simulation investigations validate the applicability and efficiency of the proposed approach. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

GCN-Enhanced Multi-Agent MAC Protocol for Vehicular Communications 22

GCN-Enhanced Multi-Agent MAC Protocol for Vehicular Communic...

引用

22nd IEEE international conference on Industrial Informatics, IndIN 2024

作者： Li, Mengfei Wang, Wei Feng, Shijie Fu, Tiange Wang, Yan Zhang, Hui State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China Sichuan Jiuzhou Electronic Group Co. Ltd. Mianyang621000 China Department of Civil and Environmental Engineering The Hong Kong Polytechnic University Hong Kong School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9798331527471

In the vehicular ad-hoc network (VANET) environment, the constant changes in traffic systems due to the real-time mobility of vehicles pose a challenge in developing communication strategies that can swiftly adapt to dynamic topological variations. Traditional protocols such as CSMA/CD offer dynamic access to shared media, but their efficiency is compromised by CSMA/CA’s collision avoidance strategy, which reduces channel use due to its backoff algorithm. This paper introduces a novel Graph Convolutional Network-based Multi-Agent Reinforcement learning MAC protocol (GMMAC) for vehicular networks. Unlike the Neuro-DCF protocol, GMMAC incorporates local vehicular data directly, enabling more context-aware learning. Compared to other GNN-based MARL approaches like GraphComm, GMMAC better handles real-time changes and interactions among vehicles. Experimental results show that GMMAC significantly improves successful transmission numbers and reduces collisions, outperforming traditional CSMA/CA methods and other MARL approaches without GCN integration. © 2024 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

An Architecture-Based Approach to Mitigate Confidentiality Violations Using Machine learning 22

An Architecture-Based Approach to Mitigate Confidentiality V...

引用

22nd IEEE international conference on Software Architecture, ICSA 2025

作者： Niehues, Nils Hahner, Sebastian Heinrich, Robert Karlsruhe Institute of Technology Karlsruhe Germany

ISBN: (纸本)9798331520908

Today's software systems have become increasingly connected and complex, requiring comprehensive analysis to ensure quality properties like confidentiality. Architecture-based confidentiality analysis enables the early identification of confidentiality violations to counter data breaches effectively. However, uncertainty within the software system and its environment hinders the precise and comprehensive analysis of software architectures. Furthermore, the complexity of both architectural models and uncertainties and their outcomes impede automated model repair due to combinatorial explosion. Ultimately, software architects must manually address all confidentiality violations, which is both bothersome and error-prone. Although existing approaches can identify confidentiality violations due to uncertainty, they fall short of mitigating their effects. In this paper, we address this by utilizing machine learning in the confidentiality analysis both to evaluate the criticality of identified violations and to automatically repair them. This bridges the gap between analysis and mitigation, thereby effectively supporting software architects. Evaluation results show that logistic regression provides the best ranking of the importance of uncertainty sources. Combined with incremental testing, our approach outperforms the state of the art and achieves up to a 60-fold reduction in runtime. © 2025 IEEE.

关键词： data flow analysis

来源：评论

学校读者我要写书评

暂无评论

Inspection of Part Placement Within Containers Using Point Cloud Overlap Analysis for an Automotive Production Line 32nd

Inspection of Part Placement Within Containers Using Point C...

引用

32nd international conference on Flexible Automation and intelligent Manufacturing

作者： Costa, Carlos M. Dias, Joana Nascimento, Rui Rocha, Claudia Veiga, Germano Sousa, Armando Thomas, Ulrike Rocha, Luis INESC TEC Inst Syst & Comp Engn Ctr Robot Ind & Intelligent Syst Porto Portugal Univ Porto Fac Engn Porto Portugal Tech Univ Chemnitz Robot & Human Machine Interact Lab Chemnitz Germany

ISBN: (纸本)9783031382406;9783031382413

Reliable operation of production lines without unscheduled disruptions is of paramount importance for ensuring the proper operation of automated working cells involving robotic systems. This article addresses the issue of preventing disruptions to an automotive production line that can arise from incorrect placement of aluminum car parts by a human operator in a feeding container with 4 indexing pins for each part. The detection of the misplaced parts is critical for avoiding collisions between the containers and a high pressure washing machine and also to avoid collisions between the parts and a robotic arm that is feeding parts to a air leakage inspection machine. The proposed inspection system relies on a 3D sensor for scanning the parts inside a container and then estimates the 6 DoF pose of the container followed by an analysis of the overlap percentage between each part reference point cloud and the 3D sensor data. When the overlap percentage is below a given threshold, the part is considered as misplaced and the operator is alerted to fix the part placement in the container. The deployment of the inspection system on an automotive production line for 22 weeks has shown promising results by avoiding 18 hours of disruptions, since it detected 407 containers having misplaced parts in 4524 inspections, from which 12 were false negatives, while no false positives were reported, which allowed the elimination of disruptions to the production line at the cost of manual reinspection of 0.27% of false negative containers by the operator.

关键词： Part placement inspection 3D perception Point cloud registration Point cloud overlap analysis Automotive industry

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226页 << < 44 45 46 47 48 49 50 51 52 53 > >>

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：