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

14,209 篇 会议
1,281 篇 期刊文献
3 册 图书

馆藏范围

15,493 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

8,786 篇 工学
- 5,596 篇 计算机科学与技术...
- 3,361 篇 电气工程
- 3,171 篇 软件工程
- 1,021 篇 信息与通信工程
- 751 篇 测绘科学与技术
- 741 篇 控制科学与工程
- 558 篇 仪器科学与技术
- 450 篇 生物医学工程（可授...
- 386 篇 电子科学与技术（可...
- 349 篇 机械工程
- 278 篇 环境科学与工程（可...
- 200 篇 生物工程
- 168 篇 交通运输工程
- 159 篇 土木工程
- 152 篇 光学工程
- 135 篇 建筑学
2,140 篇 理学
- 746 篇 数学
- 597 篇 地球物理学
- 494 篇 物理学
- 318 篇 生物学
- 288 篇 统计学（可授理学、...
- 147 篇 化学
- 132 篇 系统科学
971 篇 管理学
- 625 篇 管理科学与工程(可...
- 421 篇 图书情报与档案管...
- 202 篇 工商管理
755 篇 医学
- 564 篇 临床医学
- 169 篇 特种医学
- 148 篇 基础医学(可授医学...
326 篇 农学
- 204 篇 农业资源与环境
100 篇 法学
53 篇 经济学
47 篇 教育学
34 篇 文学
21 篇 艺术学
10 篇 军事学

主题

2,899 篇 visualization
2,654 篇 data visualizati...
901 篇 data analysis
858 篇 data mining
802 篇 task analysis
658 篇 data models
593 篇 algorithm design...
526 篇 computational mo...
521 篇 feature extracti...
520 篇 training
393 篇 visual analytics
370 篇 big data
326 篇 image color anal...
317 篇 analytical model...
305 篇 three-dimensiona...
302 篇 computer science
288 篇 information anal...
277 篇 computer archite...
260 篇 monitoring
258 篇 remote sensing

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...
35 篇 university of ko...
31 篇 ohio state univ ...
24 篇 university of ch...
24 篇 univ utah salt l...
23 篇 lawrence livermo...
23 篇 tsinghua univers...
23 篇 hong kong univ s...
22 篇 pacific northwes...
21 篇 purdue universit...
20 篇 ohio state univ ...
18 篇 univ utah sci co...
18 篇 univ konstanz co...
18 篇 georgia institut...
18 篇 univ maryland co...
18 篇 lawrence livermo...

作者

52 篇 kwan-liu ma
38 篇 ertl thomas
35 篇 papka michael e.
33 篇 keim daniel a.
25 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

15,334 篇 英文
94 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 15493 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：

Research on Deep Learning-Based Compression Processing Technology for UAV Inspection Images

Research on Deep Learning-Based Compression Processing Techn...

引用

2025 International Conference on Electrical Automation and Artificial Intelligence, ICEAAI 2025

作者： Teng, Aiguo Zha, Junjie Shan, Xinwen Zhu, Jiajia Lu, Jiaxin State Grid Jiangsu Electric Power Co. Ltd. Information & Telecommunication Branch Nanjing Jiangsu210000 China

ISBN: (纸本)9798331506797

With the wide application of channel visualization technology and UAV inspection in the power system, the image intelligent recognition technology has achieved initial success in the power transmission and distribution profession. However, the multiple use of channel visualization devices and UAV inspections has led to the accumulation and storage of super-large-scale datasets, and the unstructured data storage resources are becoming increasingly tight. In this paper, a deep learning-based image compression processing technique for UAV inspection is proposed to address this situation. The research includes feature extraction and analysis of UAV inspection images, compression algorithm design, and image recovery quality assessment. Through experimental verification, the technique can significantly reduce storage requirements while maintaining high image recovery quality, providing a feasible solution for the efficient management of large-scale image data in power systems. This research has important practical significance, which can reduce the storage pressure of unstructured platform and improve the practical level of the system. © 2025 ieee.

关键词： data storage optimization Deep learning drone inspection image compression

来源：评论

学校读者我要写书评

暂无评论

data analysis - Aggregate Function Performance

Data Analysis - Aggregate Function Performance

引用

International symposium on Applied Machine Intelligence and Informatics (SAMI)

作者： Michal Kvet Department of Informatics Žilinská unvierzita v Žiline Fakulta riadenia a informatiky Žilina Slovakia

ISBN: (数字)9798350379365

ISBN: (纸本)9798350379372

Increasingly expanding data analytics brings the need to store a large and structurally diverse amount of data. Related to this is the design of analytical data structures and performance optimization. Individual data are typically aggregated in reports. The goal of this paper is to create a methodology for using aggregation functions in analytical-transactional SQL databases. We focus on the impact of the used parameter format and values, as well as grant total calculation technique with the aim of minimizing processing costs and time.

关键词： Structured Query Language data analysis databases Aggregates data aggregation data structures Informatics Optimization Machine intelligence Meteorology

来源：评论

学校读者我要写书评

暂无评论

Crop Detection Method using Relative Positional Relationships for Small Weeding Robots

Crop Detection Method using Relative Positional Relationship...

引用

ieee/SICE International symposium on System Integration

作者： Yusuke Iuchi Atsuki Koshigoe Soki Nishiwaki Takanori Emaru Graduate School of Engineering Hokkaido University Hokkaido Japan Faculty of Engineering Hokkaido University Hokkaido Japan

ISBN: (数字)9798331531614

ISBN: (纸本)9798331531621

Automation in agriculture is increasingly critical for addressing global food security and sustainability challenges. This paper presents a novel crop detection method using relative positional relationships, specifically designed for small weeding robots. Unlike traditional approaches that rely heavily on visual characteristics and large annotated datasets, our method leverages the spatial arrangement of plants to distinguish crops from weeds, thereby reducing the dependency on extensive data collection and annotation efforts. We implemented a multi-stage detection system that first identifies all plants using an object detection algorithm and then classifies them based on their positional and size information. Experimental results on soybean datasets demonstrate that our approach achieves AP of 71.3% for soy crops and 27.2% for weeds in environments not included in the training dataset, showing comparable effectiveness to traditional visual-based detection methods in scenarios with limited data. This advancement offers potential for enhancing the adaptability and efficiency of agricultural automation technologies.

关键词： Training visualization Automation Crops Object detection System integration Feature extraction Agriculture Sustainable development Robots

来源：评论

学校读者我要写书评

暂无评论

Confounder-Aware Medical data Selection for Fine-Tuning Pretrained Vision Models

Confounder-Aware Medical Data Selection for Fine-Tuning Pret...

引用

ieee International symposium on Biomedical Imaging

作者： Anyang Ji Qingbo Kang Wei Xu Changfan Wang Kang Li Qicheng Lao West China Biomedical Big Data Center West China Hospital Sichuan University Chengdu China College of Computer Science Sichuan University Chengdu China Shanghai Artificial Intelligence Laboratory Shanghai China School of Biomedical Engineering University of Science and Technology of China Hefei China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

The emergence of large-scale pre-trained vision foundation models has greatly advanced the medical imaging field through the pre-training and fine-tuning paradigm. However, selecting appropriate medical data for downstream fine-tuning remains a significant challenge considering its annotation cost, privacy concerns, and the detrimental effects of confounding variables. In this work, we present a confounder-aware medical data selection approach for medical dataset curation aiming to select minimal representative data by strategically mitigating the undesirable impact of confounding variables while preserving the natural distribution of the dataset. Our approach first identifies confounding variables within data and then develops a distance-based data selection strategy for confounder-aware sampling with a constrained budget in the data size. We validate the superiority of our approach through extensive experiments across diverse medical imaging modalities, highlighting its effectiveness in addressing the substantial impact of confounding variables and enhancing the fine-tuning efficiency in the medical imaging domain, compared to other data selection approaches.

关键词： visualization data privacy Costs Foundation models Annotations Clustering algorithms Manuals data models Calibration Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Image analysis for Historical Knowledge Discovery and Preservation

Image Analysis for Historical Knowledge Discovery and Preser...

引用

2025 International Conference on Visual Analytics and data visualization, ICVADV 2025

作者： Sakthivel, K. Ashwin, J. Poongodi, K. Oviya, S. K.S. Rangasamy College of Technology Department of Computer Science and Business Systems Namakkal India

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521394

Digitized archival collections offer rich sources for cultural heritage research. Current systems, though, fail to effectively integrate heterogeneous data forms like images, textual descriptions, and metadata. This study offers a sophisticated framework that blends image recognition, natural language processing (NLP), and knowledge graph methods to facilitate access, enable discovery, and reveal concealed historical patterns. The system comprises several modules such as a data input module, preprocessing pipeline, image recognition, NLP analysis, knowledge graph generation, semantic search engine, and an interactive user interface. Testing the system on a large historical archive dataset proved high accuracy, efficiency, and usability for all modules. Major takeaways are 93.4% accuracy in object detection for images, 94.8% accuracy for named entity recognition, and 95.5% search accuracy in semantic search feature. © 2025 ieee.

关键词： Usability engineering

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Semantic Space Structuring: Cardiac Cycle Position for Cerebral Emboli visualization Using Contrastive Learning

Weakly-Supervised Semantic Space Structuring: Cardiac Cycle ...

引用

ieee International symposium on Biomedical Imaging

作者： Mathilde Dupouy Yamil Vindas Marilys Almar Blaise Kévin Guépié Philippe Delachartre CREATIS UMR 5220 U1294 Univ Lyon INSA-Lyon Université Claude Bernard Lyon 1 CNRS Inserm LYON France Inria INSA Lyon CITI UR3720 Villeurbanne France Atys Medical 17 Parc Arbora Soucieu-en-Jarrest France Laboratoire Informatique et Société Numérique Université de Technologie de Troyes Troyes France

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Transcranial Doppler (TCD) is an important tool for monitoring cerebral emboli, a primary cause of ischemic stroke, by detecting high-intensity transient signals (HITS). The link between HITS and their position in the cardiac cycle is emphasized in the literature, but little exploited for microemboli characterization. We therefore propose to integrate this information directly into the structure of latent spaces derived from unsupervised deep learning models toward a more interpretable data visualization. Specifically, we combine autoencoders (AEs) with a contrastive learning framework, where HITS with the same cardiac cycle position are brought closer together, while those with different positions are pushed apart. This weakly-supervised approach facilitates a guided semantic structuring of the latent space, while preserving the underlying data structure. We evaluate our method on a TCD HITS dataset and demonstrate a 11.85% improvement in the local structuring of latent spaces with respect to cardiac cycle position continuity. This trend is further validated in a more complex scenario where the latent space is structured based on both HITS type and cardiac cycle position, outperforming the AE baseline by 5.92% in terms of category continuity in the latent space. These results validate the use of cardiac cycle positioning of HITS for their characterization and demonstrate its benefits for structuring latent representations. The code is available at https://***/MathildeDupouy/contrastive-cardiac-cycle/.

关键词： Representation learning Semantics data visualization Contrastive learning Information representation Market research Doppler effect Transient analysis Unsupervised learning Monitoring

来源：评论

学校读者我要写书评

暂无评论

Research and Development of Hybrid Intelligent Enhancement analysis and Control System for Stability of large Power Grid

Research and Development of Hybrid Intelligent Enhancement A...

引用

2025 International Conference on Electrical Automation and Artificial Intelligence, ICEAAI 2025

作者： Zhao, Min Li, Yalou Ding, Ping Li, Fang China Electric Power Research Institute Beijing China

ISBN: (纸本)9798331506797

The following achievements have been made: in the research of the operation image model of the large power grid, a real-time operation image model of the large power grid has been proposed. Corresponding solutions or technologies such as serviceability calculation have been proposed for typical difficult problems in dynamic measurement data and analysis calculation. Combined with the production needs of demonstration projects, the overall architecture design of the large power grid image model has been proposed, and the interface with simulation data and measurement data has been established to establish the large power grid image model. We have designed and implemented intelligent analysis and decision-making functions for the static safety and dynamic response characteristics of the power grid, as well as a laboratory validation plan for the effectiveness of response driven stability discrimination and control measures. In the analysis of the evolution of transient safety and stability characteristics in electromagnetically systems, a technical route for power grid image model 'prediction-planning-correction' state deduction has been proposed, providing basic materials for system state analysis under different operating conditions. We have established a provincial-level grid 10000 node point mixed simulation verification platform, which can be used to verify the effectiveness testing of prototypes in operating scenarios, and conducted research on demonstration project implementation plans. © 2025 ieee.

关键词： component image modeling Intelligent enhanced analysis multi-dimensional information visualization multi-level coordinated control style state inference

来源：评论

学校读者我要写书评

暂无评论

Medxchat: A Unified Multimodal large Language Model Framework Towards CXRS Understanding and Generation

Medxchat: A Unified Multimodal Large Language Model Framewor...

引用

ieee International symposium on Biomedical Imaging

作者： Ling Yang Zhanyu Wang Zhenghao Chen Xinyu Liang Luping Zhou School of Electrical and Computer Engineering The University of Sydney Australia School of Information and Physical Sciences The University of Newcastle Australia The First Hospital Attached to Guangzhou University of Chinese Medicine

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Multimodal large Language Models (MLLMs) have shown promise in general image tasks, but their application in medical imaging remains limited. This study explores MLLMs for Chest X-Rays (CXRs) through MedXChat, a unified framework enabling seamless interaction for tasks such as text report generation, visual question-answering (VQA), and Text-to-CXR generation. Our MLLM, which uses natural language as input, breaks task boundaries and simplifies medical professional training to the maximum extent by allowing diverse tasks within a single environment. To understand CXRs, we employ visual encoders (e.g.,ViT) and LLMs (e.g., mPLUG-Owl), which we refine using visual adapters and delta-tuning. For CXR generation, we introduce an innovative synthesis approach that leverages the instruction-following capabilities of the Stable Diffusion (SD) architecture to produce fine-grained medical images without additional parameters. Through comprehensive experiments, our model demonstrates exceptional cross-task adaptability, showcasing proficiency across all three tasks.

关键词： Training visualization Adaptation models large language models Biological system modeling Natural languages data models X-ray imaging Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

EmBARDiment: an Embodied AI Agent for Productivity in XR

EmBARDiment: an Embodied AI Agent for Productivity in XR

引用

ieee Annual International symposium Virtual Reality

作者： Riccardo Bovo Steven Abreu Karan Ahuja Eric J Gonzalez Li-Te Cheng Mar Gonzalez-Franco Google USA Imperial College London UK University of Groningen Netherlands Northwestern University USA

ISBN: (数字)9798331536459

ISBN: (纸本)9798331536466

XR devices running chat-bots powered by large Language Models (LLMs) have the to become always-on agents that enable much better productivity scenarios. Current screen based chat-bots do not take advantage of the the full-suite of natural inputs available in XR, including inward facing sensor data, instead they over-rely on explicit voice or text prompts, sometimes paired with multi-modal data dropped as part of the query. We propose a solution that leverages an attention framework that derives context implicitly from user actions, eye-gaze, and contextual memory within the XR environment. Our work minimizes the need for engineered explicit prompts, fostering grounded and intuitive interactions that glean user insights for the chat-bot.

关键词： Productivity visualization Three-dimensional displays Extended reality large language models Memory management Gaze tracking User interfaces Chatbots Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Automated Optimization of Electrode Placement in Transcutaneous Electrical Nerve Stimulation Using Numerical Simulation

Automated Optimization of Electrode Placement in Transcutane...

引用

ieee International symposium on Biomedical Imaging

作者： Takashi Ota Hideaki Kuzuoka Tomohiro Amemiya Kazuma Aoyama The University of Tokyo Japan Gunma University Japan

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Electrode placement is a crucial parameter in transcutaneous electrical nerve stimulation. However, it is challenging to identify the optimal electrode placement that effectively stimulates a specific tissue because of the complex structure of the human body, which comprises multiple tissues. In this study, we developed a system that automatically identifies the optimal electrode placement from a large number of potential electrode positions. The system uses the finite element method to calculate the current density distribution in the target tissue for all conditions and outputs the optimal placement that stimulates the target tissue most efficiently. To evaluate the effectiveness of this system, we conducted experiments to optimize the electrode placement for electrical stimulation of the lower limbs and head. We confirm that the optimal elec-trode placement determined by the proposed system is reasonable since it was similar to that in a previous study. Fur-thermore, the automation enables verification of several conditions that would be impractical to verify using conventional methods.

关键词： Electrodes Wrist visualization Limbs Force Electrical stimulation Numerical simulation Finite element analysis Optimization Tendons

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 << < 6 7 8 9 10 11 12 13 14 15 > >>

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：