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

5,634 篇 会议
90 篇 期刊文献
10 册 图书

馆藏范围

5,734 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,774 篇 工学
- 2,332 篇 计算机科学与技术...
- 1,329 篇 软件工程
- 567 篇 信息与通信工程
- 466 篇 电气工程
- 200 篇 生物工程
- 174 篇 控制科学与工程
- 174 篇 生物医学工程（可授...
- 109 篇 机械工程
- 84 篇 交通运输工程
- 83 篇 化学工程与技术
- 80 篇 电子科学与技术（可...
- 79 篇 光学工程
- 69 篇 仪器科学与技术
- 65 篇 动力工程及工程热...
- 55 篇 土木工程
- 55 篇 安全科学与工程
897 篇 理学
- 478 篇 数学
- 235 篇 生物学
- 231 篇 物理学
- 191 篇 统计学（可授理学、...
- 119 篇 系统科学
- 66 篇 化学
589 篇 管理学
- 327 篇 图书情报与档案管...
- 305 篇 管理科学与工程(可...
- 163 篇 工商管理
289 篇 医学
- 243 篇 临床医学
- 144 篇 基础医学(可授医学...
- 80 篇 药学(可授医学、理...
- 52 篇 公共卫生与预防医...
76 篇 法学
- 71 篇 社会学
54 篇 经济学
45 篇 教育学
39 篇 农学
26 篇 文学
2 篇 军事学
1 篇 历史学
1 篇 艺术学

主题

1,600 篇 data models
535 篇 predictive model...
530 篇 training
498 篇 machine learning
461 篇 data mining
416 篇 big data
405 篇 computational mo...
343 篇 feature extracti...
333 篇 task analysis
327 篇 prediction algor...
268 篇 deep learning
255 篇 machine learning...
245 篇 classification a...
238 篇 analytical model...
191 篇 clustering algor...
190 篇 support vector m...
183 篇 neural networks
158 篇 natural language...
142 篇 training data
141 篇 mathematical mod...

机构

19 篇 sun yat sen univ...
19 篇 daffodil interna...
12 篇 univ chinese aca...
11 篇 tsinghua univers...
11 篇 university of ch...
11 篇 school of data a...
10 篇 carnegie mellon ...
9 篇 renmin univ chin...
9 篇 lviv polytechnic...
8 篇 shenzhen researc...
7 篇 shanghai jiao to...
7 篇 college of compu...
7 篇 university of el...
7 篇 school of comput...
7 篇 national univers...
7 篇 harbin institute...
7 篇 beijing key lab ...
7 篇 natl univ def te...
7 篇 renmin univ chin...
6 篇 university of sc...

作者

7 篇 li li
7 篇 wang wei
7 篇 xiao yanghua
6 篇 wen ji-rong
6 篇 cui bin
6 篇 zhao wayne xin
6 篇 ying liu
6 篇 syed akhter hoss...
5 篇 yang tong
5 篇 liu yang
5 篇 li zhang
5 篇 jia weijia
5 篇 chen liu
5 篇 yang yang
5 篇 xiao hongbo
5 篇 nguyen trong-the
5 篇 yu jie
5 篇 albert bifet
5 篇 wang bin
5 篇 carlos ordonez

语言

5,596 篇 英文
130 篇 其他
14 篇 中文
2 篇 俄文
1 篇 乌克兰文

检索条件"任意字段=2020 International Conference on Data Processing Algorithms and Models, ICDPAM 2020"

共 5734 条记录，以下是711-720 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：

Temporal Fact Reasoning over Hyper-Relational Knowledge Graphs

Temporal Fact Reasoning over Hyper-Relational Knowledge Grap...

引用

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Ding, Zifeng Wu, Jingcheng Wu, Jingpei Xia, Yan Xiong, Bo Tresp, Volker LMU Munich Germany University of Cambridge United Kingdom Germany University of Stuttgart Germany Technical University of Munich Germany

ISBN: (纸本)9798891761681

Stemming from traditional knowledge graphs (KGs), hyper-relational KGs (HKGs) provide additional key-value pairs (i.e., qualifiers) for each KG fact that help to better restrict the fact validity. In recent years, there has been an increasing interest in studying graph reasoning over HKGs. Meanwhile, as discussed in recent works that focus on temporal KGs (TKGs), world knowledge is ever-evolving, making it important to reason over temporal facts in KGs. Previous mainstream benchmark HKGs do not explicitly specify temporal information for each HKG fact. Therefore, almost all existing HKG reasoning approaches do not devise any module specifically for temporal reasoning. To better study temporal fact reasoning over HKGs, we propose a new type of data structure named hyper-relational TKG (HTKG). Every fact in an HTKG is coupled with a timestamp explicitly indicating its time validity. We develop two new benchmark HTKG datasets, i.e., Wiki-hy and YAGO-hy, and propose an HTKG reasoning model that efficiently models hyper-relational temporal facts. To support future research on this topic, we open-source our datasets and model. © 2024 Association for Computational Linguistics.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Leveraging Sequential Pattern Information for Active Learning from Sequential data 25

Leveraging Sequential Pattern Information for Active Learnin...

引用

25th international conference on Pattern Recognition (ICPR)

作者： Fidalgo-Merino, Raul Gabrielli, Lorenzo Checchi, Enrico European Commiss Joint Res Ctr JRC Ispra Italy CNR Ist Sci & Tecnol Informaz I-56124 Pisa Italy

ISBN: (纸本)9781728188089

This paper presents a novel active learning technique aimed at the selection of sequences for manual annotation from a database of unlabelled sequences. Supervised machine learning algorithms can employ these sequences to build better models than those based on using random sequences for training. The main contribution of the proposed method is the use of sequential pattern information contained in the database to select representative and diverse sequences for annotation. These two characteristics ensure the proper coverage of the instance space of sequences and, at the same time, avoids over-fitting the trained model. The approach, called SPIAL (Sequential Pattern Information for Active Learning), uses sequential pattern mining algorithms to extract frequently occurring sub-sequences from the database and evaluates how representative and diverse each sequence is, based on this information. The output is a list of sequences for annotation sorted by representativeness and diversity. The algorithm is modular and, unlike most current techniques, it is independent from the sequential machine learning technique that builds the model as SPIAL does not need to know the set of the features taken into account by the training algorithm. Experiments done on well-known benchmarks involving sequential data show that the models trained using SPIAL increase their convergence speed while reducing manual effort by selecting small sets of very informative sequences for annotation. In addition, the computation cost using SPIAL is much lower than for the state-of-the-art algorithms evaluated.

关键词： database systems

来源：评论

学校读者我要写书评

暂无评论

An Integrated Learning Prediction Study of Diabetes Mellitus Based on Random Forest and Support Vector Machine

An Integrated Learning Prediction Study of Diabetes Mellitus...

引用

Computers, Information processing and Advanced Education (CIPAE), 2020 international conference on

作者： Shengjia Huang Han Xu Changchun University of Science and Technology Changchun China

ISBN: (数字)9798331527662

ISBN: (纸本)9798331527679

In this paper, the prediction of diabetes in the elderly was studied deeply. The model was constructed and verified by integrated learning method combined with random forest and support vector machine model. First of all, we use the random forest model for feature selection to identify the factors that have a significant impact on diabetes prediction, such as hypertension, heart disease and self-rated health, etc., which provides a basis for the subsequent model construction. Secondly, we constructed an integrated learning model based on the Stacking strategy. Random forest and support vector machines are used as base learners and are integrated with meta-learners to improve prediction accuracy and stability. In the process of model construction, we optimized the kernel function of SVM and found that the kernel function of Polynomial performs best in diabetes prediction. Finally, the ensemble learning model is verified by experiments, and the results show that the model achieves high accuracy on training set, cross-validation set and test set, showing good prediction performance. This model not only provides a new and effective tool for the prediction of diabetes in the elderly, but also provides a new idea and method for the prediction of other diseases.

关键词： Support vector machines Accuracy Computational modeling Predictive models data models Polynomials Diabetes Kernel Older adults Random forests

来源：评论

学校读者我要写书评

暂无评论

Analysing Depression in Social Media data Using Machine Learning Techniques

Analysing Depression in Social Media Data Using Machine Lear...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 international conference on

作者： B Jayapradha T. Velmurugan PG and Research Department of Computer Science Dr. Ambedkar Government Arts and Science College Chennai India PG and Research Department of Computer Science Dwaraka Doss Govardhan Doss Vaishnav College Chennai India

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

In the present digital era, a significant volume of text data has started to emerge post-COVID with the increase in the number of people who have started using social media. The text thus generated encapsules a hidden layer of emotion with in it. This emotion hidden in the textual data conveys a lot of understanding of the people who are responsible for the creation of the text and helps to know the person better. However, extracting the emotions from the text data is quiet a challenging task as it involves a series of pre-processing pipelines and also the application of machine learning techniques to the text involved in the research for the purpose of extracting the emotion from it. The primary objective of this research work focusses on extracting depression based emotional text using some of the machine learning techniques. It also gives a comparative analysis between the machine learning techniques in terms of accuracy. This work has utilized machine learning techniques such as Naïve Bayes and Random Forest to find the emotion particularly depressions in the Kaggle data set, particularly, text-based information taken into account for the analysis. Finally, this work concludes that the performance of machine learning algorithms based on its efficiency. This information can then enable appropriate counselling interventions, preventing the person under depression from escalating into suicidal thoughts or to other mental health issues.

关键词： Text mining Accuracy Social networking (online) Pipelines Forestry Mental health Depression Prediction algorithms Naive Bayes methods Random forests

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient MaxBRNN Computation for Streaming Updates 37

Towards Efficient MaxBRNN Computation for Streaming Updates

引用

37th IEEE international conference on data Engineering (IEEE ICDE)

作者： Ning, Wentao Yan, Xiao Tang, Bo Southern Univ Sci & Technol Guangdong Prov Key Lab Brain Inspired Intelligent Dept Comp Sci & Engn Shenzhen Peoples R China Southern Univ Sci & Technol Res Inst Trustworthy Autonomous Syst Shenzhen Peoples R China Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Peng Cheng Lab PCL Res Ctr Networks & Commun Shenzhen Peoples R China

ISBN: (纸本)9781728191843

In this paper, we propose the streaming MaxBRNN query, which finds the optimal region to deploy a new service point when both the service points and client points are under continuous updates. The streaming MaxBRNN query has many applications such as taxi scheduling, shared bike placements, etc. Existing MaxBRNN solutions are insufficient for streaming updates as they need to re-run from scratch even for a small amount of updates, resulting in long query processing lime. To tackle this problem, we devise an efficient slot partitioning-based algorithm (SlotP), which divides the space into equal-sized slots and processes each slot independently. The superiorities of our proposal for streaming MaxBRNN query are: (i) an update affects only a smaller number of slots and works done on the unaffected slots can be reused directly;(ii) the influence value upper bound of each slot can be derived efficiently and accurately, which facilitate pruning many slots from expensive computation. We conducted extensive experiments to validate the performance of the SlotP algorithm. The results show that SlotP is 2-3 orders of magnitude faster than state-of-the-art baselines.

关键词： Upper bound Query processing conferences data engineering Computational efficiency Partitioning algorithms Proposals

来源：评论

学校读者我要写书评

暂无评论

CuWide: Towards Efficient Flow-based Training for Sparse Wide models on GPUs 37

CuWide: Towards Efficient Flow-based Training for Sparse Wid...

引用

37th IEEE international conference on data Engineering (IEEE ICDE)

作者： Miao, Xupeng Ma, Lingxiao Yang, Zhi Shao, Yingxia Cui, Bin Yu, Lele Jiang, Jiawei Peking Univ Dept Comp Sci Qingdao Peoples R China Peking Univ Key Lab High Confidence Software Technol MOE Qingdao Peoples R China Peking Univ Inst Computat Social Sci Qingdao Peoples R China BUPT Sch Comp Sci Beijing Peoples R China Swiss Fed Inst Technol Zurich Switzerland Tencent Inc Shenzhen Peoples R China

ISBN: (纸本)9781728191843

In this paper, we propose an efficient GPU-training framework for the large-scale wide models, named cuWide. To fully benefit from the memory hierarchy of GPU, cuWide applies a new flow-based schema for training, which leverages the spatial and temporal locality of wide models to drastically reduce the amount of communication with GPU global memory. Comprehensive experiments show that cuWide can be up to more than 20x faster than the state-of-the-art GPU solutions and multi-core CPU solutions.

关键词： Training conferences Memory management Graphics processing units data engineering data models

来源：评论

学校读者我要写书评

暂无评论

Predicting Academic Performance of Students Using Machine Learning models

Predicting Academic Performance of Students Using Machine Le...

引用

Artificial Intelligence and Smart Communication (AISC), international conference on

作者： Neeta Sharma Mk Sharma Umang Garg Department of CS Noida International University Greater Noida UP Defence Cyber Agency New Delhi Graphic Era Hill University Dehradun

The NEP- 2020 of India has reemphasized the need of delivering quality education in order to decrease the drop out rate of students by the HEI. In post-cover era, retention of the students specially in Engineering and Management disciplines was more prominent. This paper is an attempt to empower HEI predict students’ performance/ potential drop out using ML algorithms based on six factors namely; Family size, Study time, Time-spent on extra-curricular activities, Absenteeism, Time spent on Internet, and *** ML algorithms namely, KNN, Random Forest and Decision Tree have been implemented and compared on efficiency and accuracy criteria so as to attain at the top algorithm for subject prediction use case. The paper’s findings on academic performance prediction are likely to help educational institutions and the learners by the way of early identification of potential drop out and implementation of corrective measures. A small data set of 390 students on various predictors has been utilized for ML algorithms *** paper seeks to address the problem of quality education delivery system in India and elsewhere. It is pilot research on academic performance monitoring with an aim to reduce dropout rate of students. This research work shall pave way for further scaled up research work implementing various algorithms on larger datasets to make a use case for education industry wide implementation potential.

关键词： Industries Machine learning algorithms Education Forestry Predictive models Prediction algorithms Internet

来源：评论

学校读者我要写书评

暂无评论

The Possible Equivalent Value Set for Incomplete data Set 23rd

The Possible Equivalent Value Set for Incomplete Data Set

引用

23rd international conference on Computational Science and Its Applications, ICCSA 2023

作者： Mamat, Rabiei Mustafa, Asma Nor, Ahmad Shukri Mohd Herawan, Tutut Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Nerus Terengganu Malaysia Sekolah Tinggi Pariwisata Ambarrukmo Yogyakarta Jalan Ringroad Timur No. 52 Bantul Daerah Istimewa Yogyakarta55198 Indonesia AMCS Research Center Jalan Griya Taman Asri Yogyakarta55512 Indonesia Institute for Big Data Analytics and Artificial Intelligence UiTM Shah Alam Selangor Darul Ehsan Shah Alam40450 Malaysia

ISBN: (纸本)9783031371073

Incomplete or missing data is a significant challenge in real-world information systems that can lead to flawed decision-making. The rough set theory has limitations when dealing with incomplete information systems, and researchers have proposed alternative approaches. This paper proposes a new similarity relation that utilises probable equivalent value sets to improve the accuracy of incomplete information systems. The approach enhances the quality of decision-making and provides reliable results. Experiments conducted on various datasets with different levels of missing data show that the approach can improve the accuracy of incomplete information processing by up to 90%. Compared to existing methods, the proposed approach can handle both categorical and continuous attributes, address problems of non-uniqueness and redundancy of probable equivalent value sets, and is not dependent on any specific data distribution. In conclusion, the proposed technique provides an effective solution to the challenges of incomplete information systems. By using probable equivalent value sets, the approach improves the accuracy of incomplete information processing and enhances the quality of decision-making. It has potential for applications in data science and related areas, and further research is needed to explore its limitations and applicability to real-world problems. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Rough set theory

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Method of Sentiment Analysis and Machine Learning Algorithm for the U.S. Presidential Election Forecasting

A Hybrid Method of Sentiment Analysis and Machine Learning A...

引用

IEEE international conference on Big data

作者： Guocheng Feng Kaihao Chen Huaiyu Cai Zhijian Li Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International College Zhuhai China Department of Statistics and Data Science BNU-HKBU United International College Zhuhai China

U.S. Presidential Election forecasting has been a research interest for several decades. Currently, election prediction consists of two main approaches: traditional models that incorporate economic data and poll surveys, and models that leverage X and other social media platforms due to their increasing popularity in the past decade. However, traditional approaches have predominantly focused on national-level predictions, while social media-based approaches often oversimplify the nuanced differences between online discourse and the broader voting population’s political *** this work, we perform a hybrid method of both the machine learning algorithm and the sentiment analysis on the state level with various independent variables including census data, economic indicators, polling averages, and the newly defined average sentiment scores from X. Our prediction for the 2020 U.S. Presidential Election yielded promising results. Most of our models successfully predicted a victory for the Democratic candidate with 96% accuracy using Gradient Boosting Trees and Multi-Layer Perceptron algorithms. This novel prediction framework addresses the limitations of existing U.S. Presidential Election forecasting approaches, particularly in terms of state-level predictions. It provides a valuable foundation for future research in this field and contributes to advancing our understanding of election dynamics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fault Warning of Wind Turbine Based on Optimal Hybrid Neural Network Prediction Model

Fault Warning of Wind Turbine Based on Optimal Hybrid Neural...

引用

Advances in Electrical Engineering and Computer Applications( AEECA), 2020 IEEE international conference on

作者： Ruomeng Lv School of Control and Computer Engineering North China Electric Power University Baoding China

ISBN: (纸本)9798350355260

Aiming at the problems of abnormal points and noise points existing in the original high-dimensional data of wind turbine system, and considering the strict requirements of fault warning on the accuracy of prediction model, a wind turbine fault warning method based on Bayes optimized hybrid neural network prediction model is proposed. In order to ensure the quality of modeling data, Ordering Points To Identify the Clustering Structure (OPTICS) and Isolation forest (iForest) were used to clean the pre-processed data. A "Convolutional Neural Network (CNN)" -"Long Short-Term Memory (LSTM)"-Attention hybrid model based on Bayesian optimization was established, and combined with the spatial feature extraction capability of CNN, the time series processing capability of LSTM and the weight allocation strategy of Attention mechanism, the accurate prediction of wind turbine under normal working conditions was realized through Bayesian optimization. The sliding window method is used to construct an early warning index, and its threshold is calculated by the kernel density estimation method to achieve reliable early warning and reduce the false alarm rate. Experiments with real fault data show that this method has excellent performance in improving prediction accuracy and reducing false positive rate.

关键词： Accuracy Noise Predictive models data models Wind turbines Bayes methods Convolutional neural networks Reliability Optimization Long short term memory

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 << < 68 69 70 71 72 73 74 75 76 77 > >>

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：