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

509 篇 会议
29 篇 期刊文献
2 册 图书

馆藏范围

540 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

352 篇 工学
- 283 篇 计算机科学与技术...
- 141 篇 软件工程
- 40 篇 电气工程
- 27 篇 信息与通信工程
- 14 篇 力学（可授工学、理...
- 14 篇 建筑学
- 13 篇 仪器科学与技术
- 13 篇 土木工程
- 12 篇 电子科学与技术（可...
- 12 篇 控制科学与工程
- 11 篇 化学工程与技术
- 9 篇 生物医学工程（可授...
- 9 篇 生物工程
- 8 篇 机械工程
- 7 篇 光学工程
- 7 篇 动力工程及工程热...
- 6 篇 环境科学与工程（可...
90 篇 理学
- 49 篇 数学
- 21 篇 物理学
- 18 篇 统计学（可授理学、...
- 16 篇 生物学
- 6 篇 化学
- 6 篇 海洋科学
- 6 篇 系统科学
54 篇 管理学
- 35 篇 图书情报与档案管...
- 26 篇 管理科学与工程(可...
- 17 篇 工商管理
27 篇 医学
- 19 篇 临床医学
- 12 篇 基础医学(可授医学...
12 篇 教育学
- 9 篇 教育学
5 篇 法学
4 篇 文学
2 篇 农学
1 篇 经济学

主题

83 篇 visualization
71 篇 data visualizati...
39 篇 data mining
24 篇 data analysis
23 篇 big data
15 篇 visual analytics
15 篇 algorithm design...
15 篇 image color anal...
15 篇 training
12 篇 three-dimensiona...
11 篇 performance anal...
11 篇 feature extracti...
11 篇 software
11 篇 data models
10 篇 tools
10 篇 human-centered c...
10 篇 computational mo...
9 篇 computer archite...
9 篇 dimensionality r...
9 篇 analytical model...

机构

4 篇 northern illinoi...
4 篇 argonne natl lab...
4 篇 northern illinoi...
4 篇 argonne national...
3 篇 deutsches klimar...
3 篇 lawrence berkele...
3 篇 nvidia
3 篇 univ illinois il...
3 篇 ohio state univ ...
3 篇 leipzig universi...
2 篇 academy of scien...
2 篇 uva
2 篇 penn state univ ...
2 篇 univ konstanz co...
2 篇 utah state univ ...
2 篇 twitter 1355 mar...
2 篇 beijing forestry...
2 篇 aalto univ sch s...
2 篇 university of ca...
2 篇 univ waikato cyb...

作者

5 篇 papka michael e.
5 篇 insley joseph a.
4 篇 michael e. papka
4 篇 silvio rizzi
4 篇 mateevitsi victo...
4 篇 agrawal gagan
4 篇 victor a. mateev...
4 篇 rizzi silvio
3 篇 joseph a. insley
3 篇 jefferson amstut...
3 篇 yang juncheng
3 篇 rashmi k. v
3 篇 yue yao
3 篇 amstutz jefferso...
3 篇 burch michael
2 篇 andres sewell
2 篇 castro miguel ra...
2 篇 park cheol woo
2 篇 lessley brenton
2 篇 li jin

语言

528 篇 英文
6 篇 其他
4 篇 葡萄牙文
2 篇 中文
1 篇 意大利文

检索条件"任意字段=14th Symposium on Large Data Analysis and Visualization"

共 540 条记录，以下是41-50 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：

Counterfactual-Enhanced Information Bottleneck for Aspect-Based Sentiment analysis 38

Counterfactual-Enhanced Information Bottleneck for Aspect-Ba...

引用

38th AAAI Conference on Artificial Intelligence (AAAI) / 36th Conference on Innovative Applications of Artificial Intelligence / 14th symposium on Educational Advances in Artificial Intelligence

作者： Chang, Mingshan Yang, Min Jiang, Qingshan Xu, Ruifeng Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Key Lab High Performance Data Min Shenzhen Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Harbin Inst Technol Shenzhen Shenzhen Peoples R China

ISBN: (纸本)1577358872

Despite having achieved notable success for aspect-based sentiment analysis (ABSA), deep neural networks are susceptible to spurious correlations between input features and output labels, leading to poor robustness. In this paper, we propose a novel Counterfactual-Enhanced Information Bottleneck framework (called CEIB) to reduce spurious correlations for ABSA. CEIB extends the information bottleneck (IB) principle to a factual-counterfactual balancing setting by integrating augmented counterfactual data, with the goal of learning a robust ABSA model. Concretely, we first devise a multi-pattern prompting method, which utilizes the large language model (LLM) to generate high-quality counterfactual samples from the original samples. then, we employ the information bottleneck principle and separate the mutual information into factual and counterfactual parts. In this way, we can learn effective and robust representations for the ABSA task by balancing the predictive information of these two parts. Extensive experiments on five benchmark ABSA datasets show that our CEIB approach achieves superior prediction performance and robustness over the state-of-the-art baselines. Code and data to reproduce the results in this paper is available at: https://***/shesshan/CEIB.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Domain Adaptation Method Based on Deep Coral for Rolling Bearing Fault Diagnosis 14

A Domain Adaptation Method Based on Deep Coral for Rolling B...

引用

14th IEEE International symposium on Diagnostics for Electrical Machines, Power Electronics and Drives, SDEMPED 2023

作者： Wang, Zexiao Ming, Xinguo Shanghai Jiao Tong University School of Mechanical Engineering Department of Industrial Engineering & Management Shanghai City China

ISBN: (纸本)9798350320770

As a key component of motor, the operating status of rolling bearings directly affects the overall function and performance of each mechanism system of mechanical equipment the traditional rolling bearing intelligent fault diagnosis method has problems such as requiring a large amount of in-service data for fault analysis, poor generalization capability, etc. In addition, it is extremely costly to obtain labeled rolling bearing high quality condition data. Transfer learning is one of the methods that can effectively solve the above problems. In this paper, we propose a transfer learning model based on Coral transfer loss function as a rolling bearing fault diagnosis method. the model uses ResNet50 as the feature extractor, Coral loss function as the transfer loss function, and CrossEntropyLoss as the classification loss function. Finally, we validated the feasibility of the proposed method by using the Case Western Reserve University bearing dataset under variable operating conditions, the model was validated with correct transfer rates of over 90% for all twelve transfer types;which greatly surpasses other typical transfer learning fault diagnosis methods, which proved the rationality of the proposed method. © 2023 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

MFABA: A More Faithful and Accelerated Boundary-Based Attribution Method for Deep Neural Networks 38

MFABA: A More Faithful and Accelerated Boundary-Based Attrib...

引用

38th AAAI Conference on Artificial Intelligence (AAAI) / 36th Conference on Innovative Applications of Artificial Intelligence / 14th symposium on Educational Advances in Artificial Intelligence

作者： Zhu, Zhiyu Chen, Huaming Zhang, Jiayu Wang, Xinyi Jin, Zhibo Xue, Minhui Zhu, Dongxiao Choo, Kim-Kwang Raymond Univ Sydney Sydney NSW Australia Univ Malaya Kuala Lumpur Malaysia CSIRO Data61 Eveleigh Australia Wayne State Univ Detroit MI 48202 USA Univ Texas San Antonio San Antonio TX USA

ISBN: (纸本)1577358872

To better understand the output of deep neural networks (DNN), attribution based methods have been an important approach for model interpretability, which assign a score for each input dimension to indicate its importance towards the model outcome. Notably, the attribution methods use the axioms of sensitivity and implementation invariance to ensure the validity and reliability of attribution results. Yet, the existing attribution methods present challenges for effective interpretation and efficient computation. In this work, we introduce MFABA, an attribution algorithm that adheres to axioms, as a novel method for interpreting DNN. Additionally, we provide the theoretical proof and in-depth analysis for MFABA algorithm, and conduct a large scale experiment. the results demonstrate its superiority by achieving over 101.5142 times faster speed than the state-of-the-art attribution algorithms. the effectiveness of MFABA is thoroughly evaluated through the statistical analysis in comparison to other methods, and the full implementation package is open-source at: https://***/LMBTough/MFABA.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Variational Hybrid-Attention Framework for Multi-Label Few-Shot Aspect Category Detection 38

Variational Hybrid-Attention Framework for Multi-Label Few-S...

引用

38th AAAI Conference on Artificial Intelligence (AAAI) / 36th Conference on Innovative Applications of Artificial Intelligence / 14th symposium on Educational Advances in Artificial Intelligence

作者： Peng, Cheng Chen, Ke Shou, Lidan Chen, Gang Zhejiang Univ State Key Lab Blockchain & Data Secur Hangzhou 310000 Peoples R China

ISBN: (纸本)1577358872

Multi-label few-shot aspect category detection (FS-ACD) is a challenging sentiment analysis task, which aims to learn a multi-label learning paradigm with limited training data. the difficulty of this task is how to use limited data to generalize effective discriminative representations for different categories. Nowadays, all advanced FS-ACD works utilize the prototypical network to learn label prototypes to represent different aspects. However, such point-based estimation methods are inherently noise-susceptible and bias-vulnerable. To this end, this paper proposes a novel Variational Hybrid-Attention Framework (VHAF) for the FS-ACD task. Specifically, to alleviate the data noise, we adopt a hybrid-attention mechanism to generate more discriminative aspect-specific embeddings. then, based on these embeddings, we introduce the variational distribution inference to obtain the aspect-specific distribution as a more robust aspect representation, which can eliminate the scarce data bias for better inference. Moreover, we further leverage an adaptive threshold estimation to help VHAF better identify multiple relevant aspects. Extensive experiments on three datasets demonstrate the effectiveness of our VHAF over other state-of-the-art methods. Code is available at https://***/chengzju/VHAF.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Speed and Torque Estimation in Induction Motor through the analysis of Stray Flux Signals 14

Speed and Torque Estimation in Induction Motor through the A...

引用

14th IEEE International symposium on Diagnostics for Electrical Machines, Power Electronics and Drives, SDEMPED 2023

作者： Diaz-Saldana, Geovanni Zamudio-Ramirez, Israel Ugalde, Oscar Ugalde Osornio-Rios, Roque A. Antonino-Daviu, Jose A. Universidad Autónoma de Querétaro Facultad de Ingeniería Querétaro76807 Mexico Instituto Tecnológico de la Energía Valencia46022 Spain

ISBN: (纸本)9798350320770

Induction motors are elements of great importance within the industry due to the large number of applications they have;because of this, their monitoring is essential to ensure the correct performance of the tasks. Several methods have been created for the estimation of speed and torque in these machines, many of these methods use sensors that are invasive to the motor or require taking it off-line to perform a series of tests to obtain the necessary parameters for its estimation. the present research proposes a methodology for the estimation of speed and torque in induction motors through the analysis of stray flux signals obtained in a non-invasive manner and the information provided by the manufacturer on the data plate of the machine. Preliminary results show a speed estimation with an error of less than 0.2% and a methodological proposal for torque estimation, as well as clear prospectives to improve the methodology to obtain better results in torque estimation and to generalize the method by testing the algorithm with different machines. © 2023 IEEE.

关键词： Induction motors

来源：评论

学校读者我要写书评

暂无评论

large-Scale Non-convex Stochastic Constrained Distributionally Robust Optimization 38

Large-Scale Non-convex Stochastic Constrained Distributional...

引用

38th AAAI Conference on Artificial Intelligence (AAAI) / 36th Conference on Innovative Applications of Artificial Intelligence / 14th symposium on Educational Advances in Artificial Intelligence

作者： Zhang, Qi Zhou, Yi Prater-Bennette, Ashley Shen, Lixin Zou, Shaofeng Univ Buffalo Buffalo NY 14260 USA Univ Utah Salt Lake City UT USA Air Force Res Lab Wright Patterson AFB OH USA Syracuse Univ Syracuse NY USA

ISBN: (纸本)1577358872

Distributionally robust optimization (DRO) is a powerful framework for training robust models against data distribution shifts. this paper focuses on constrained DRO, which has an explicit characterization of the robustness level. Existing studies on constrained DRO mostly focus on convex loss function, and exclude the practical and challenging case with non-convex loss function, e.g., neural network. this paper develops a stochastic algorithm and its performance analysis for non-convex constrained DRO. the computational complexity of our stochastic algorithm at each iteration is independent of the overall dataset size, and thus is suitable for large-scale applications. We focus on the general Cressie-Read family divergence defined uncertainty set which includes chi(2)-divergences as a special case. We prove that our algorithm finds an epsilon-stationary point with an improved computational complexity than existing methods. Our method also applies to the smoothed conditional value at risk (CVaR) DRO.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

KeywordMap: Attention-based Visual Exploration for Keyword analysis 14

KeywordMap: Attention-based Visual Exploration for Keyword A...

引用

14th IEEE Pacific visualization symposium (IEEE PacificVis)

作者： Tu, Yamei Xu, Jiayi Shen, Han-Wei Ohio State Univ Columbus OH 43210 USA

ISBN: (纸本)9781665439312

With the high growth rate of text data, extracting meaningful information from a large corpus becomes increasingly difficult. Keyword extraction and analysis is a common approach to tackle the problem, but it is non-trivial to identify important words in the text and represent the multifaceted properties of those words effectively. Traditional topic modeling based keyword analysis algorithms require hyper-parameters which are often difficult to tune without enough prior knowledge. In addition, the relationships among the keywords are often difficult to obtain. In this paper, we utilize the attention scores extracted from Transformer-based language models to capture word relationships. We propose a domain-driven attention tuning method, guiding the attention to learn domain-specific word relationships. From the attention, we build a keyword network and propose a novel algorithm, Attention-based Word Influence (AWI), to compute how influential each word is in the network. An interactive visual analytics system, KeywordMap, is developed to support multi-level analysis of keywords and keyword relationships through coordinated views. We measure the quality of keywords captured by our AWI algorithm quantitatively. We also evaluate the usefulness and effectiveness of KeywordMap through case studies.

关键词： Text/Document data Machine Learning Task and Requirements analysis

来源：评论

学校读者我要写书评

暂无评论

Out-of-Core Dimensionality Reduction for large data via Out-of-Sample Extensions

Out-of-Core Dimensionality Reduction for Large Data via Out-...

引用

IEEE symposium on large data analysis and visualization (LDAV)

作者： Luca Reichmann David Hägele Daniel Weiskopf University of Stuttgart

ISBN: (数字)9798331516925

ISBN: (纸本)9798331516932

Dimensionality reduction (DR) is a well-established approach for the visualization of high-dimensional data sets. While DR methods are often applied to typical DR benchmark data sets in the literature, they might suffer from high runtime complexity and memory requirements, making them unsuitable for large data visualization especially in environments outside of high-performance computing. To perform DR on large data sets, we propose the use of out-of-sample extensions. Such extensions allow inserting new data into existing projections, which we leverage to iteratively project data into a reference projection that consists only of a small manageable subset. this process makes it possible to perform DR out-of-core on large data, which would otherwise not be possible due to memory and runtime limitations. For metric multidimensional scaling (MDS), we contribute an implementation with out-of-sample projection capability since typical software libraries do not support it. We provide an evaluation of the projection quality of five common DR algorithms (MDS, PCA, t-SNE, UMAP, and autoencoders) using quality metrics from the literature and analyze the trade-off between the size of the reference set and projection quality. the run-time behavior of the algorithms is also quantified with respect to reference set size, out-of-sample batch size, and dimensionality of the data sets. Furthermore, we compare the out-of-sample approach to other recently introduced DR methods, such as PaCMAP and TriMAP, which claim to handle larger data sets than traditional approaches. To showcase the usefulness of DR on this large scale, we contribute a use case where we analyze ensembles of streamlines amounting to one billion projected instances.

关键词： Measurement Dimensionality reduction Runtime Software libraries data analysis High performance computing Software algorithms Memory management data visualization Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

SimWrapper, an open source web-based platform for interactive visualization of microsimulation outputs and transport data 14

SimWrapper, an open source web-based platform for interactiv...

引用

14th International Conference on Ambient Systems, Networks and Technologies Networks, ANT 2023 and the 6th International Conference on Emerging data and Industry 4.0, EDI40 2023

作者： Charlton, William Sana, Bhargava Technische Universitat Berlin Chair of Transport Systems Planning and Transport Telematics Straße des 17. Juni 135 Berlin10623 Germany San Diego Association of Governments 401 B Street Unit 800 San DiegoCA92101 United States

A new open-source, web-based, configurable data visualization platform is presented that is specifically designed to support large-scale transportation simulations including MATSim and ActivitySim. It produces a wide array of interactive charts, maps, animations and analysis dashboards that are generally useful in the transportation domain. Interactive visualizations can be created and viewed locally on an analyst's laptop, or public web-based dashboards can be published for viewing on the open Internet. the details of software design are provided along with several examples of implementation at public agencies. User feedback shows the platform is found to be very flexible, while the straightforward configuration approach enables efficient development and deployment of web-based interactive visualizations. While it is not intended to replace geographic information systems or commercial software packages, the smaller curated set of capabilities is found by users to warrant its current adoption at several public agencies. Further work is needed to add more useful features, improve the platform's quality and user experience, and extend documentation. © 2023 Elsevier B.V.. All rights reserved.

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-Resolution Encoding for Interactive large-Scale Volume visualization through Functional Approximation

Adaptive Multi-Resolution Encoding for Interactive Large-Sca...

引用

IEEE symposium on large data analysis and visualization (LDAV)

作者： Jianxin Sun David Lenz Hongfeng Yu Tom Peterka University of Nebraska-Lincoln Argonne National Laboratory

ISBN: (数字)9798331516925

ISBN: (纸本)9798331516932

Functional approximation as a high-order continuous representation provides a more accurate value and gradient query compared to the traditional discrete volume representation. Volume visualization directly rendered from functional approximation generates high-quality rendering results without high-order artifacts caused by trilinear interpolations. However, querying an encoded functional approximation is computationally expensive, especially when the input dataset is large, making functional approximation impractical for interactive visualization. In this paper, we proposed a novel functional approximation multi-resolution representation, Adaptive-FAM, which is lightweight and fast to query. We also design a GPU-accelerated out-of-core multi-resolution volume visualization framework that directly utilizes the Adaptive-FAM representation to generate high-quality rendering with interactive responsiveness. Our method can not only dramatically decrease the caching time, one of the main contributors to input latency, but also effectively improve the cache hit rate through prefetching. Our approach significantly outperforms the traditional function approximation method in terms of input latency while maintaining comparable rendering quality.

关键词： visualization Adaptation models Interpolation three-dimensional displays Prefetching Rendering (computer graphics) Sampling methods Encoding Function approximation Testing

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54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：