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

14,304 篇 会议
1,305 篇 期刊文献
4 册 图书

馆藏范围

15,613 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

8,834 篇 工学
- 5,612 篇 计算机科学与技术...
- 3,381 篇 电气工程
- 3,193 篇 软件工程
- 1,031 篇 信息与通信工程
- 754 篇 测绘科学与技术
- 748 篇 控制科学与工程
- 559 篇 仪器科学与技术
- 462 篇 生物医学工程（可授...
- 389 篇 电子科学与技术（可...
- 350 篇 机械工程
- 278 篇 环境科学与工程（可...
- 212 篇 生物工程
- 168 篇 交通运输工程
- 160 篇 土木工程
- 153 篇 光学工程
- 136 篇 建筑学
2,163 篇 理学
- 750 篇 数学
- 600 篇 地球物理学
- 507 篇 物理学
- 321 篇 生物学
- 290 篇 统计学（可授理学、...
- 159 篇 化学
- 133 篇 系统科学
976 篇 管理学
- 629 篇 管理科学与工程(可...
- 423 篇 图书情报与档案管...
- 207 篇 工商管理
770 篇 医学
- 579 篇 临床医学
- 183 篇 特种医学
- 151 篇 基础医学(可授医学...
326 篇 农学
- 204 篇 农业资源与环境
104 篇 法学
57 篇 经济学
49 篇 教育学
36 篇 文学
21 篇 艺术学
10 篇 军事学

主题

2,930 篇 visualization
2,685 篇 data visualizati...
917 篇 data analysis
865 篇 data mining
802 篇 task analysis
672 篇 data models
593 篇 algorithm design...
541 篇 training
531 篇 computational mo...
528 篇 feature extracti...
406 篇 visual analytics
368 篇 big data
334 篇 image color anal...
320 篇 analytical model...
309 篇 three-dimensiona...
302 篇 computer science
288 篇 information anal...
275 篇 computer archite...
262 篇 deep learning
262 篇 monitoring

机构

48 篇 univ calif davis...
44 篇 university of ca...
38 篇 argonne national...
36 篇 univ chinese aca...
35 篇 argonne natl lab...
34 篇 university of ko...
31 篇 ohio state univ ...
26 篇 university of ch...
25 篇 univ utah salt l...
24 篇 tsinghua univers...
23 篇 lawrence livermo...
23 篇 hong kong univ s...
22 篇 purdue universit...
22 篇 pacific northwes...
19 篇 ohio state univ ...
18 篇 univ utah sci co...
18 篇 univ konstanz co...
18 篇 georgia institut...
18 篇 univ maryland co...
17 篇 lawrence berkele...

作者

52 篇 kwan-liu ma
39 篇 ertl thomas
35 篇 papka michael e.
33 篇 keim daniel a.
26 篇 schreck tobias
24 篇 peterka tom
23 篇 klasky scott
22 篇 thomas ertl
22 篇 han-wei shen
20 篇 xiaoru yuan
19 篇 wang chaoli
19 篇 van wijk jarke j...
19 篇 michael e. papka
18 篇 pfister hanspete...
17 篇 vishwanath venka...
16 篇 podhorszki norbe...
16 篇 daniel a. keim
14 篇 insley joseph a.
14 篇 mihai datcu
14 篇 silva claudio t.

语言

15,385 篇 英文
163 篇 其他
55 篇 中文
5 篇 葡萄牙文
5 篇 土耳其文
1 篇 西班牙文

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

共 15613 条记录，以下是941-950 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：

SELF-SUPERVISED LEARNING WITH RADIOLOGY REPORTS, A COMPARATIVE analysis OF STRATEGIES FOR large VESSEL OCCLUSION AND BRAIN CTA IMAGES 20

SELF-SUPERVISED LEARNING WITH RADIOLOGY REPORTS, A COMPARATI...

引用

20th ieee International symposium on Biomedical Imaging (ISBI)

作者： Pachade, S. Datta, S. Dong, Y. Salazar-Marioni, S. Abdelkhaleq, R. Niktabe, A. Roberts, K. Sheth, S. A. Giancardo, L. Univ Texas Hlth Sci Ctr Houston UTHlth Sch Biomed Informat Houston TX 77030 USA UTHlth McGovern Med Sch Houston TX 77030 USA UTHlth Inst Stroke & Cerebrovasc Dis Houston TX 77030 USA

ISBN: (纸本)9781665473583

Scarcity of labels for medical images is a significant barrier for training representation learning approaches based on deep neural networks. This limitation is also present when using imaging data collected during routine clinical care stored in picture archiving communication systems (PACS), as these data rarely have attached the high-quality labels required for medical image computing tasks. However, medical images extracted from PACS are commonly coupled with descriptive radiology reports that contain significant information and could be leveraged to pre-train imaging models, which could serve as starting points for further task-specific fine-tuning. In this work, we perform a head-to-head comparison of three different self-supervised strategies to pre-train the same imaging model on 3D brain computed tomography angiogram (CTA) images, with large vessel occlusion (LVO) detection as the downstream task. These strategies evaluate two natural language processing (NLP) approaches, one to extract 100 explicit radiology concepts (Rad-SpatialNet) and the other to create general-purpose radiology reports embeddings (Distil-BERT). In addition, we experiment with learning radiology concepts directly or by using a recent self-supervised learning approach (CLIP) that learns by ranking the distance between language and image vector embeddings. The LVO detection task was selected because it requires 3D imaging data, is clinically important, and requires the algorithm to learn outputs not explicitly stated in the radiology report. Pre-training was performed on an unlabeled dataset containing 1,542 3D CTA - reports pairs. The downstream task was tested on a labeled dataset of 402 subjects for LVO. We find that the pre-training performed with CLIP-based strategies improve the performance of the imaging model to detect LVO compared to a model trained only on the labeled data. The best performance was achieved by pre-training using the explicit radiology concepts and CLIP strategy

关键词： large vessel occlusion ischemic stroke CLIP BERT

来源：评论

学校读者我要写书评

暂无评论

Ambient Sound analysis for Non-Invasive Indoor Activity Detection in Edge Computing Environments 28

Ambient Sound Analysis for Non-Invasive Indoor Activity Dete...

引用

28th ieee symposium on Computers and Communications, ISCC 2023

作者： Lee, Cheolhwan Kang, Ho-Min Jeon, Yeongjun Kang, Soon Ju School of Electronic and Eletrical Engineering Kyungpook National University Daegu Korea Republic of

ISBN: (纸本)9798350300482

Research on detecting the behavior of residents using sounds generated in living spaces has been conducted by sending the sound data to a server or cloud and utilizing a relatively large artificial intelligence model. However, this method generates excessive data traffic and carries a privacy risk by transmitting sounds unnecessary for behavior detection. In this paper, we explored data processing methods suitable for a non-invasive indoor noisy sound analysis system operating in an edge environment. To achieve this goal, we implemented Mel-spectrogram and Mel-Frequency Cepstral Coefficients (MFCC) based models for classifying environmental sounds, comparing their performance based on different preprocessing parameters and optimizations. Furthermore, we evaluated the computational resource usage and performance of the models in both the Raspberry Pi and microcontroller environments. © 2023 ieee.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Resilience Assessment of large Language Models under Transient Hardware Faults 34

Resilience Assessment of Large Language Models under Transie...

引用

34th ieee International symposium on Software Reliability Engineering (ISSRE)

作者： Agarwal, Udit Kumar Chan, Abraham Pattabiraman, Karthik Univ British Columbia Vancouver BC Canada

ISBN: (纸本)9798350315943

large Language Models (LLMs) are transforming the field of natural language processing and revolutionizing the way machines interact with humans. LLMs like ChatGPT and Google's Bard have already made significant strides in conversational AI, enabling machines to understand natural language and respond in a more human-like manner. In addition to typical applications like sentiment analysis and text generation, LLMs are also used in safety-critical applications such as code generation and speech comprehension in autonomous driving vehicles, where reliability is important. In this work, we investigate the resilience of LLMs under transient hardware faults. Specifically, we used IR-level fault injection (FI) to assess the reliability of five popular LLMs, including Bert, GPT2, and T5, under transient hardware faults. Moreover, we also investigate how the resilience of LLMs varies with different pre-training, fine-tuning objectives, and the number of encoder and decoder blocks. We find that LLMs are quite resilient to transient faults overall. We also find that the behavior of the LLM under transient faults varies significantly with the input, LLM's architecture, and the type of task (e.g., translation vs. fill-in-the-blank). Finally, we find that the Silent data Corruption (SDC) rate varies with different fine-tuning objectives, and for the fill-mask finetuning objective, the SDC rate also increases with the model size. Overall, our findings indicate that the use of LLMs in safety-critical applications needs further investigation.

关键词： Error resilience LLMS Soft Errors

来源：评论

学校读者我要写书评

暂无评论

Finding Needle in a Haystack: An Algorithm for Real-Time Log Anomaly Detection with Real-Time Learning 34

Finding Needle in a Haystack: An Algorithm for Real-Time Log...

引用

34th ieee International symposium on Software Reliability Engineering (ISSRE)

作者： Chitnis, Prachi Asthana, Abhaya Nokia Bell Labs Murray Hill NJ 07974 USA

ISBN: (纸本)9798350319569

Logs represent the language of any modern real-time system and contain the earliest diagnosable symptoms of failures. The system reliability can be significantly improved by implementing real-time log anomaly detection that captures system deviations early, to apply corrective actions. However, challenges like huge volume of logs, system heterogeneity, lack of labeled data for training, dynamic system behavior etc. pose difficulty to implement such real-time anomaly detection engines on a large scale. This paper proposes a novel, computationally efficient, unsupervised, real-time log anomaly detection algorithm that also learns in real-time. Primarily based on frequency spectrum analysis, it also works in offline mode for historical datasets. Besides detecting anomalous logs, it supplies additional information on anomaly type (temporal, lexical, augmented expertise) and an anomaly score. The paper also discusses algorithm's hyperparameter tuning and empirical strategies to improve the serviceability for real-world datasets. Experiments demonstrate the effectiveness of anomaly detection and computational performance on different industrial datasets.

关键词： log anomaly detection real-time analysis system reliability unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Optimization Prediction and Application Based on Statistical analysis and data Mining 3

Intelligent Optimization Prediction and Application Based on...

引用

3rd International symposium on Computer Technology and Information Science, ISCTIS 2023

作者： Cui, Yiming Wenzhou-Kean University Zhejiang Wenzhou China

ISBN: (纸本)9798350325386

In today's era, the leading role of information technology in economic and social development is very obvious. Without informatization, there would be no modernization. With the development of information technology, information data is growing rapidly. Collecting, sorting, summarizing and classifying effective data can help individuals, enterprises and others have a clearer understanding of the future and make reasonable plans in advance. data mining technology can mine valuable information from a large number of data, which makes full use of statistics, databases, knowledge information and so on. The development of artificial intelligence has elevated the development of information technology to a new level, become the focus of international competition, and have a significant impact on economic and social development. Through the research of statistical analysis, data mining technology and artificial intelligence, this paper aims to collect and organize valuable data efficiently from a large number of data. Use intelligent optimization algorithms to make the best use of this data to make predictions. Intelligent optimization prediction can be applied to the personalized plan formulation of network security defense, learning platform, weather forecast, online shopping platform, and short video platform. The experiment shows that intelligent optimal prediction can improve the accuracy of prediction. Applying it to cybersecurity defense can improve detection rates by about 15%, and applying it to weather forecasting can improve prediction success rates by about 30%. © 2023 ieee.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Intelligent Automation of Crime Prediction using data Mining 31

Intelligent Automation of Crime Prediction using Data Mining

引用

ieee 31st International symposium on Industrial Electronics (ISIE)

作者： Al-Ghushami, Abdullah Hussein Syed, Dabeeruddin Sessa, Jadran Zainab, Ameema Community Coll Qatar Dept Informat Technol Doha 7344 Qatar Texas A&M Univ Dept Elect & Comp Engn College Stn TX 77840 USA Univ Milan Dipartimento Informat Milan Italy

ISBN: (纸本)9781665482400

Crime Pattern Theory is a way of elucidating the reasons why specific types of crime happen at certain areas only. According to the theory, the offenders, rather than venturing into unknown territories, frequently commit crimes by taking advantage of the opportunities they encounter in the places of their comfort zones or the places they are most familiar with. Spatial analysis of crimes and areas of higher concentration assist in preventing or at least reducing the amount of future crime from the knowledge discovery of past data. Our approach of crime prediction consists of five modules, namely data extraction, pre-processing, classification, pattern identification, prediction and google map visualization. This paper compares machine learning algorithms namely naive bayes, bayesian networks, weighted k-nearest neighbors, multi-layer perceptron classifier, guassian naive bayes, decision tree, random forest, adaboost, gradient boosting, linear discriminant analysis and quadratic discriminant analysis for crime category identification and crime prediction. The results have been evaluated on a real dataset of crimes in the city of San Francisco. The work successfully uses the temporal and spatial information in the data to locate the crime hotspots, predict the category of a crime in a region and additionally, the emergence of the crimes.

关键词： Crime pattern theory crime prediction data mining machine learning gradient boosting

来源：评论

学校读者我要写书评

暂无评论

A Multi-end Application System for Animal Disease Prevention and Control Based on Spark and Deep Learning 6

A Multi-end Application System for Animal Disease Prevention...

引用

6th ieee International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2023

作者： Guihua, Zhang Hui, Zhang Yuanyuan, Huang Chengdu Jincheng College Department of Computer and Software Sichuan China

ISBN: (纸本)9798350325485

With the increasing production scale and breeding density of poultry and animal husbandry in China, the source of animal diseases has become complicated, and how to effectively carry out epidemic prevention and control has become more and more urgent. In this paper, big data technology and deep learning algorithm are applied to epidemic prevention and management, providing possibilities for the early identification and diagnosis, early warning and trend assessment of current animal diseases. Taking poultry as an example, convolutional neural network algorithm was used to identify chicken manure images, classify the most common poultry diseases, improve the traditional chicken disease detection methods, and improve the accuracy and speed of chicken disease detection. At the same time, in the face of the huge multi-source data information in the monitored area, distributed technology is adopted to manage and store data, build data centers and data warehouses, and connect to the Spark big data computing platform for analysis, calculation and mining, which improves the data computing speed and utilization rate. On the business application platform, we designed a large screen visualization system on the APP and WEB side and a background management system to realize multi-Terminal applications and information interconnection, multi-dimensional, dynamic and real-Time visualization of animal disease distribution and development situation, improve the comprehensive decision-making ability and macro management ability of functional departments, and realize early identification and early warning of poultry diseases. The efficiency of animal disease prevention and control was improved, and the economic loss of farmers was reduced. © 2023 ieee.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

HybridAxes: An Immersive Analytics Tool With Interoperability Between 2D and Immersive Reality Modes 21

HybridAxes: An Immersive Analytics Tool With Interoperabilit...

引用

21st ieee International symposium on Mixed and Augmented Reality (ISMAR)

作者： Seraji, Mohammad Rajabi Stuerzlinger, Wolfgang Simon Fraser Univ SIAT Burnaby BC Canada

ISBN: (数字)9781665453653

ISBN: (纸本)9781665453653

Throughout the visual analytics process, users create visualizations with different dimensionalities. Research shows that in this process users benefit from being able to simultaneously see 2D and 3D modes of their data visualizations. Towards supporting this potential need, we introduce HybridAxes, an immersive visual analytics tool that allows the users to conduct their analysis at either end of the Reality-Virtuality continuum - either in 2D on desktop monitors or 3D in an immersive AR/VR environment - while enabling them to seamlessly switch between the two modes. We believe that by using our system, users will find it easier and faster to understand and analyze multi-dimensional data. An initial pilot test indicates positive trends in terms of users' performance time and usability metrics compared to the standalone desktop or AR/VR counterparts. Our preliminary results also suggest that users experience a lower cognitive load while task-switching between these virtuality modes. This reduction in mental effort causes them to perceive the system to be unobtrusive and pleasant to work with. Going forward, we plan to conduct more rigorous studies to verify our claims and to explore other research questions on this topic.

关键词： Human-centered computing-visualization-visualization application domains-Visual analytics Human-centered computing-Human computer interaction (HCI)-Interaction paradigms-Mixed / augmented reality

来源：评论

学校读者我要写书评

暂无评论

ChatGPT in data visualization Education: A Student Perspective

ChatGPT in Data Visualization Education: A Student Perspecti...

引用

ieee symposium on Visual Languages and Human Centric Computing (VL/HCC)

作者： Nam Wook Kim Hyung-Kwon Ko Grace Myers Benjamin Bach Computer Science Boston College Chestnut Hill United States Computer Science KAIST Daejeon Republic of Korea Bivwac INRIA Bordeaux France

ISBN: (数字)9798350366136

ISBN: (纸本)9798350376920

Unlike traditional educational chatbots that rely on pre-programmed responses, large-language model-driven chatbots, such as ChatGPT, demonstrate remarkable versatility to serve as a dynamic resource for addressing student needs from understanding advanced concepts to solving complex problems. This work explores the impact of such technology on student learning in an interdisciplinary, project-oriented data visualization course. Throughout the semester, students engaged with ChatGPT across four distinct projects, designing and implementing data visualizations using a variety of tools such as Tableau, D3, and Vega-lite. We collected conversation logs and reflection surveys after each assignment and conducted interviews with selected students to gain deeper insights into their experiences with ChatGPT. Our analysis examined the advantages and barriers of using ChatGPT, students’ querying behavior, the types of assistance sought, and its impact on assignment outcomes and engagement. We discuss design considerations for an educational solution tailored for data visualization education, extending beyond ChatGPT’s basic interface.

关键词： Surveys visualization Knowledge based systems Education data visualization Oral communication Chatbots Dynamic scheduling Reflection Interviews

来源：评论

学校读者我要写书评

暂无评论

Streamlining Enterprise data Processing, Reporting and Realtime Alerting using Apache Kafka 11

Streamlining Enterprise Data Processing, Reporting and Realt...

引用

11th International symposium on Digital Forensics and Security, ISDFS 2023

作者： Peddireddy, Kiran Cox Automotive Senior Systems Engineer AtlantaGA United States

ISBN: (纸本)9798350336986

The significance of real-time data processing is increasing in the current business environment as organizations strive to make informed decisions based on the large volumes of data they generate. Apache Kafka, an open-source distributed streaming platform, offers highly scalable and fault-tolerant data processing capabilities to address this need. This paper examines how Apache Kafka can facilitate enterprise data stream processing, alerting, and reporting in a seamless and effortless manner. It delves into the architecture of Kafka and the steps necessary for configuring the platform for real-time data processing and alerting. The paper also explores the application of Kafka Streams in real-time data analysis, filtering, and aggregation to trigger alerts based on specific conditions. Moreover, the paper provides a concise overview of Kafka's use in various industries and refers to relevant literature. Overall, the paper underscores the value of Apache Kafka as a vital tool for organizations seeking to derive insights from their data streams. © 2023 ieee.

关键词： Cost reduction

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 << < 91 92 93 94 95 96 97 98 99 100 > >>

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：