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

4,526 篇 会议
572 篇 期刊文献
10 篇 学位论文
5 册 图书
1 篇 科技报告

馆藏范围

5,114 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,628 篇 工学
- 2,190 篇 计算机科学与技术...
- 1,429 篇 软件工程
- 574 篇 电气工程
- 353 篇 控制科学与工程
- 331 篇 信息与通信工程
- 258 篇 机械工程
- 248 篇 石油与天然气工程
- 214 篇 化学工程与技术
- 204 篇 生物医学工程（可授...
- 192 篇 生物工程
- 186 篇 仪器科学与技术
- 172 篇 土木工程
- 160 篇 光学工程
- 155 篇 建筑学
- 149 篇 动力工程及工程热...
- 132 篇 材料科学与工程（可...
- 121 篇 电子科学与技术（可...
- 120 篇 航空宇航科学与技...
1,573 篇 理学
- 599 篇 物理学
- 415 篇 数学
- 312 篇 地球物理学
- 269 篇 地质学
- 217 篇 生物学
- 200 篇 统计学（可授理学、...
- 188 篇 化学
- 120 篇 系统科学
650 篇 管理学
- 416 篇 管理科学与工程(可...
- 262 篇 图书情报与档案管...
- 171 篇 工商管理
398 篇 医学
- 306 篇 临床医学
92 篇 法学
85 篇 农学
66 篇 教育学
58 篇 经济学
30 篇 文学
12 篇 艺术学
4 篇 军事学
1 篇 历史学

主题

659 篇 visualization
378 篇 data visualizati...
241 篇 visual analytics
169 篇 data mining
148 篇 data analysis
135 篇 feature extracti...
99 篇 data models
91 篇 image color anal...
90 篇 task analysis
89 篇 deep learning
88 篇 training
79 篇 computational mo...
79 篇 accuracy
72 篇 analytical model...
70 篇 big data
64 篇 machine learning
61 篇 cameras
57 篇 predictive model...
57 篇 semantics
55 篇 information visu...

机构

17 篇 center for space...
17 篇 nagoya universit...
17 篇 department of el...
16 篇 infn sezione di ...
16 篇 department of ph...
16 篇 quantum ict adva...
16 篇 department of ph...
16 篇 department of ph...
15 篇 vrvis res ctr au...
15 篇 institute of spa...
15 篇 faculty of scien...
15 篇 infn sezione di ...
15 篇 institute of par...
15 篇 national institu...
15 篇 via madonna del ...
15 篇 department of as...
15 篇 faculty of engin...
14 篇 univ konstanz co...
14 篇 waseda research ...
14 篇 jem utilization ...

作者

22 篇 asano k.
18 篇 schreck tobias
18 篇 cherry m.l.
18 篇 krizmanic j.f.
17 篇 tamura t.
17 篇 bruno a.
17 篇 kawakubo y.
17 篇 katayose y.
17 篇 binns w.r.
17 篇 castellini g.
17 篇 israel m.h.
17 篇 uchihori y.
17 篇 ebisawa k.
17 篇 yoshida a.
17 篇 bongi m.
17 篇 bigongiari g.
17 篇 shiomi a.
17 篇 collazuol g.
17 篇 nakahira s.
17 篇 ozawa s.

语言

4,759 篇 英文
161 篇 俄文
146 篇 其他
48 篇 中文
3 篇 乌克兰文
2 篇 德文
1 篇 法文
1 篇 葡萄牙文

检索条件"任意字段=Conference on Visual Data Exploration and Analysis V"

共 5114 条记录，以下是101-110 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：

Augmented Fusion Method for the Diagnosis of ILD and the Promotion of Better Clinical Results

Augmented Fusion Method for the Diagnosis of ILD and the Pro...

引用

visual Analytics and data visualization (ICvADv), International conference on

作者： vijaya Kishore v. Kalpana v. Chekuri Nalini K. Gopi Dept of ECE K.S.R.M College of Engineering Kadapa India Dept of ECE KLM College of Engineering for Women Kadapa India Department of ECE School of Engineering Mohan Babu University Tirupati India Vijayam institute of Technology Chittoor India

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521400

The Interstitial Lung Diseases (ILDs) are characterized by lung fibrosis (scarring). Nodule, Idiopathic Pulmonary Fibrosis (IPF) and Honeycomb are the main categories of ILDs. The goal of medical image fusion is to create a unified representation of clinical information from multiple sources that can be used for more accurate diagnosis. Using image enhancing approaches along with fusion techniques that are based on wavelet transform and IHS transform-based techniques may help with early detection of these ILDs. A mathematical technique called wavelet transformations can record changes in edges and textures at various sizes in images. A frequent sharpening approach is the IHS method, which includes transforming a color picture from the RGB space to the IHS space using a variety of operations. More precise abnormality extraction can be achieved by using image fusion and enhancement techniques and assessing those using metrics like Structural Similarity Index Method (SSIM), Mean Square Error (MSE), and Global Consistency Error (GCE) across various pulmonary image modalities. The SvM classifier uses characteristics that were retrieved from upgraded pictures to categorize the illness, improving prognosis, preventing severe diseases and diagnosing ILDs at the earliest.

关键词： Wavelet transforms Measurement Support vector machines Lungs Mean square error methods Wavelet analysis Feature extraction Indexes Image fusion Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Automating Aeronautical Information Management: A Geospatial Big data Approach in India

Automating Aeronautical Information Management: A Geospatial...

引用

Integrated Communications, Navigation and Surveillance conference, ICNS

作者： Arvind v. Lal S. v. Satish Yogendra Rohilla Sandeep Mittal Bhuvanamitra S SatSure Analytics India Private Limited Bangalore India Airports Authority of India New Delhi India

ISBN: (数字)9798331534738

ISBN: (纸本)9798331534745

The Indian National Electronic Terrain Repository for Aviation, or iNetra, is a comprehensive geospatial big data platform designed to revolutionize aeronautical data management for the Airports Authority of India (AAI), which is the airport developer and sole Air Navigation Service Provider in India. SatSure developed this multi-module system, which helps transition from traditional paper-based processes to an automated, digital workflow aligned with International Civil Aviation Organization (ICAO) standards and recommended practices. The platform integrates advanced technologies, including high-resolution satellite imagery, PostgreSQL database management, and Geographic Information System (GIS) functionalities, for efficient data acquisition, processing, storage, and visualization. Some of the key modules include Electronic Terrain and Obstacle data (eTOD), Aerodrome Mapping database (AMDB), and Electronic Charting (eCharting), deployed across five international airports in India. iNetra addresses critical challenges in aeronautical data management by providing dynamic, time-stamped, and validated data ingestion capabilities. The global standards which the system upholds are supported by strong data security protocols, such as a 32-bit Cyclic Redundancy Check. Seamless data exchange, removal of redundant operations, and the support for transforming an Aeronautical Information Service into an Aeronautical Information Management and thus make iNetra mark a technological frontier in the evolution of aviation information management in India.

关键词： Technological innovation Automation Digital transformation Pipelines Manuals Big data Airports Geospatial analysis visual databases Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Personalized Content-based Movie Recommendation System: A Comparative analysis

Personalized Content-based Movie Recommendation System: A Co...

引用

2025 International conference on visual Analytics and data visualization, ICvADv 2025

作者： Nithya, B. Asha, v. Sreeja, S.P. Sinha, Abhay Aditya Akash, P. Akshay Bharadwaj, S. New Horizon College of Engineering Department of Master of Computer Applications Bengaluru India

ISBN: (纸本)9798331521394

A recommendation system is an analytical tool designed to provide personalized suggestions to users for specific resources such as literature, films, or music, derived from a comprehensive dataset. Movie recommendation systems aim to predict movies a user might enjoy based on attributes of previously liked movies. These systems are particularly advantageous for organizations that manage data from extensive customer bases and seek to deliver optimal suggestions. Factors such as genre, cast, and filmmakers significantly influence recommendations, which may be based on a single attribute or a combination of features. This paper focuses on a genre-based recommendation system employing content-based filtering to cater to user preferences. Using Python, the design tools algorithms like Cosine Similarity, Jaccard Similarity, and Pearson Correlation on a large dataset to identify patterns and preferences eIectively. Through a detailed evaluation of these approaches, the system provides robust and applicable movie suggestions. By smoothing user-friendly navigation and aligning recommendations with user interests, the system enhances user engagement and satisfaction. Also, this study examines the strengths and limitations of the applied algorithms, emphasizing the implicit for combining multiple similarity measures to enhance accuracy. The findings emphasize the significance of substantiated content delivery in optimizing user experience. © 2025 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

The Impact of Machine Learning Algorithms on Credit Card Fraud Detection: A Comparative Study

The Impact of Machine Learning Algorithms on Credit Card Fra...

引用

2025 International conference on visual Analytics and data visualization, ICvADv 2025

作者： Mohamed Rusaam, S. Nijanthan, v. Muthukumaran, N. Pratheeshba, B. Riyas Ahamed, M. Centre for Computational Imaging and Machine Vision India Sri Eshwar College of Engineering Department of Ece Tamil Nadu Coimbatore India

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521394

Credit card fraud detection is a critical challenge for financial institutions, with billions of dollars lost annually due to fraudulent activities. Traditional rule-based systems struggle to keep up with evolving fraud patterns, often producing high false positive rates. This study presents a comparative analysis of machine learning algorithms for credit card fraud detection, focusing on their accuracy, efficiency, and real-time detection capabilities. Using a highly imbalanced dataset containing 284,807 transactions, we evaluated the performance of Logistic Regression, Decision Trees, Random Forest, Support vector Machines (SvMs), Artificial Neural Networks (ANNs), and Gradient Boosting Machines (GBMs). The results demonstrate that ensemble methods, particularly GBMs such as XGBoost, outperform simpler models in terms of accuracy and recall, effectively handling the imbalanced data. ANNs also showed promising results but require significant computational resources. The study highlights the need for a balance between accuracy, processing speed, adaptability, and scalability in real-world fraud detection systems. Future research should explore advanced deep learning models, continuous learning, transfer learning, and explainable AI approaches to enhance the transparency and trust in automated fraud detection systems. © 2025 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

data Brain: Streamlining data Science with AI-Assisted Conversations 1st

Data Brain: Streamlining Data Science with AI-Assisted Conve...

引用

1st International Research conference on Computing Technologies for Sustainable Development, IRCCTSD 2024

作者： Krithik, Santhakumar S. Aditya, v. Reddy, Kurapati Praneeth Sai Gayathri, R. SRM Institute of Science and Technology Vadapalani Chennai India

ISBN: (纸本)9783031823855

The "data Brain" initiative introduces an innovative AI data Assistant, revolutionising the data science landscape by streamlining the analysis process and making it more accessible. By integrating a user-friendly web interface via stream-lit, alongside robust data manipulation through pandas and visual insights via matplotlib, "data Brain" caters to both novice and experienced data enthusiasts. OpenAI's advanced AI models and custom-built algorithms are employed to offer a conversational interface that guides users through exploratory data analysis, problem-solving, and algorithm selection, based on the analysis of uploaded CSv datasets. Furthermore, "data Brain" enhances query understanding and response accuracy through Sentence Transformers and Pinecone's vector search technology, ensuring user queries are addressed with precision. This seamless integration of AI and machine learning technologies not only democratises data science by simplifying complex analysis tasks but also fosters an environment where users can effortlessly extract actionable insights from their data. "data Brain" stands as a testament to the potential of AI in enhancing data accessibility, promoting an intuitive and interactive experience that empowers users to unlock the full value of their data. Through "data Brain," the field of data science is made approachable, allowing users to navigate and analyse data with an unprecedented level of support and efficiency. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： data accuracy

来源：评论

学校读者我要写书评

暂无评论

A Low-Power IoT-Based Smart Desk Integrated with a Facial Recognition Attendance System

A Low-Power IoT-Based Smart Desk Integrated with a Facial Re...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Khapper, Krupa v. Darwish, Hiba Alhmoud, Issa W. Gokaraju, Balakrishna Islam, A.K.M. Kamrul Graves, Corey A. North Carolina A&T State University GreensboroNC United States North Carolina A&T State University GreensboroNC United States

ISBN: (纸本)9798331504847

Internet of Things (IoT) technology in classrooms improves efficiency, security, and interactivity by automating tasks and tracking attendance in real-time. This paper explores the application of low-power IoT technology in classrooms, focusing on designing and implementing a system that integrates a facial recognition attendance system into a smart desk infrastructure. This study develops a secure and automated attendance system that enables real-time image capture, secure transmission, and detection of known and unknown faces to streamline attendance tracking. The system integrates components such as the ESP32-WROvER with a camera and Wi-Fi at each student's desk, facilitating wireless communication. The instructor's setup is designed to ensure effective control and monitoring, contributing to the efficient management of the smart classroom system. The system includes a user-friendly graphical user interface for real-time attendance monitoring of each smart desk, allowing instructors to manage and review attendance efficiently. The system employs robust encryption methods and secure transmission protocols to ensure data security, protecting student information against unauthorized access. The system generates CSv files that log all attendance data, which can be easily exported for record keeping and analysis. Additionally, when a face is detected, an LED at the student's desk is activated, providing immediate visual confirmation. This feature enhances the smart classroom system's usability and effectiveness. The combination of real-time monitoring, secure data handling, and automated processes supports a more efficient and responsive educational environment. © 2025 IEEE.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Identification of Abnormal Activities in Surveillance Scenes using Deep Auto Encoder and Sequential Extreme Learning Machine

Identification of Abnormal Activities in Surveillance Scenes...

引用

2025 International conference on visual Analytics and data visualization, ICvADv 2025

作者： Rahul Chiranjeevi, v. Malathi, D. Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Chennai603203 India

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521394

video anomaly detection is an essential task in computer vision, focused on spotting unexpected or unusual events in surveillance footage. This study presents a hybrid framework that combines a Deep Autoencoder (AE) with a Sequential Extreme Learning Machine (ELM) to enhance anomaly detection. The AE plays a crucial role in capturing local features, executing nonlinear transformations, and compressing time-series data, which significantly minimizes the need for manual feature design and labeling. Furthermore, the Sequential ELM offers quick training and adaptability, allowing for dynamic analysis of real-time data. The framework employs convolutional neural network (CNN)-based autoencoders to analyze video data, where convolutional and pooling layers enhance feature extraction, ensuring effective anomaly classification. By utilizing a bottleneck architecture, the AE generates compact representations that are subsequently used to train the Sequential ELM. Experiments conducted on benchmark datasets, such as UCSD Peds2, Avenue, and ShanghaiTech, highlight the effectiveness of the proposed method compared to state of art models. The findings reveal extensive performance in detecting both spatial and temporal abnormal events while handling challenges presented by dynamic environments and diverse data. various evaluation metrics, including Area Under the Curve (AUC) and Peak Signal-to-Noise Ratio (PSNR), indicate that the model achieved more results compared to existing methods in terms of accuracy and resource efficiency. The proposed system demonstrates high precision in identifying anomalous activities, offering a scalable solution for real-time automated surveillance. Future work will focus on integrating more advanced deep learning architectures and broadening evaluations across various datasets. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Predicting Box Office Success: A Transformer-Based Multi-Modal Approach

Predicting Box Office Success: A Transformer-Based Multi-Mod...

引用

Sentiment analysis and Deep Learning (ICSADL), International conference on

作者： R. Arul Jose R. Santhana Krishnan K. Penyameen J. Relin Francis Raj v. vinoth Kumar M. Priya Department of Electrical and Electronics Engineering Rajarajeswari College of Engineering Bengaluru India Department of Electronics and Communication Engineering SCAD College of Engineering and Technology Cheranmahadevi India Department of Information Technology Velammal College of Engineering and Technology Madurai India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Information Technology PSNA college of Engineering and Technology Dindigul India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

This research presents a Transformer-based multi-modal architecture for predicting box office revenue by integrating diverse data sources: text, visuals, and numerical features. The proposed framework leverages RoBERTa for textual data such as movie descriptions, reviews, and scripts, vision Transformers (viT) for visual data including posters and trailers, and MLPs for numerical data like budget, genre, and actor popularity. A cross-attention mechanism is employed to fuse multi-modal embeddings, enabling comprehensive analysis and accurate predictions. The model is trained using PyTorch, optimized with AdamW, and enhanced by data augmentation and TPUs for efficiency. Performance is evaluated using metrics like MAE, RMSE, and R 2 . Deployment on AWS via FastAPI ensures scalable access, with SHAP explainability providing insights into model decisions. This system offers a robust and interpretable solution for predicting box office performance, catering to the evolving needs of the entertainment industry.

关键词： Deep learning Analytical models Adaptation models visualization Computer vision Predictive models Transformers data augmentation data models Numerical models

来源：评论

学校读者我要写书评

暂无评论

An Improved Inception v3 Deep learning model for Cardiovascular Disease Prediction

An Improved Inception V3 Deep learning model for Cardiovascu...

引用

Emerging Systems and Intelligent Computing (ESIC), International conference on

作者： Lingineni Lakshmi Sowjanya Kodali Kowshya Manduri Sai Roshini Bogireddy Krishna venkatrama Phani Kumar S venkata Krishna Kishore Kolli Department of CSE VFSTR Deemed to be University Guntur India

ISBN: (数字)9798331522100

ISBN: (纸本)9798331522117

Accurate prediction of cardiovascular disease risk is essential for improving healthcare outcomes and resource management. This study uses a cardiovascular disease dataset and applies deep learning models to forecast disease risk in specific patient populations. In our approach, data preprocessing encompassed normalization and partitioning of the dataset into training and test subsets. We utilized the Inception v3 model, conducting training over ten epochs for data analysis. We also assessed alternative models to broaden our evaluation—specifically, vGG 16, vGG 19, ResNet 34, and ResNet 50. These models were analyzed based on essential performance metrics, such as accuracy, precision, recall, and F1 score. Inception v3 achieved the highest accuracy at 98%, followed by vGG 16 at 86%, vGG 19 at 80%, ResNet 34 at 78%, and ResNet 50 at 68%. We further enhanced our analysis with visual tools such as histograms and heat maps to identify key trends and correlations in the data. These insights provided a clearer understanding of significant risk factors and potential prevention strategies. Our findings demonstrate that deep learning models, particularly Inception v3, are highly effective for cardiovascular disease prediction, contributing to improved healthcare strategies and decision-making.

关键词： Deep learning Training Analytical models visualization Accuracy Computational modeling Medical services Predictive models Cardiovascular diseases Resource management

来源：评论

学校读者我要写书评

暂无评论

Electrical Performance analysis of Old Photovoltaic Modules under Outdoor Condition in Dhaka: Thermal Image-Based Investigation

Electrical Performance Analysis of Old Photovoltaic Modules ...

引用

International conference on Electrical, Computer and Communication Engineering (ECCE)

作者： Md. Sabbir Alam Ahmed Al Mansur Shahariar Ahmed Himo Md. Ashraful Islam Md. Mohi Uddin Mohin M M Naushad Ali Department of Electrical and Electronic Engineering Green University of Bangladesh Dhaka Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

This study looks at the performance deterioration of six 10-watt photovoltaic (Pv) modules after five years in Bangladesh's humid environment. The research utilized a comprehensive approach, doing visual, thermal image, and electrical examinations to provide an integrated comprehension of the Pv module in outdoor conditions. A visual analysis of the top and rear views revealed various deterioration causes, including discoloration, delamination, back sheet damage, corrosion, and dust and hotspots. In the thermal image analysis of the Pv modules, the maximum temperature of the module was 60.70C, whereas the minimum was 28.30C. Simultaneously, electrical performance was assessed outside using an I-v tracer, and the experimental findings showed that the modules degraded over time. The highest output power for the old Pv panel was 9.584 watts, and the minimum was 5.766 watts. The highest yearly deterioration rate among the six panels was 8.468%, while the lowest was 0.832%. Over five years, the largest percentage deterioration rate was 42.34%, while the least was 4.16%. We measured the extent of performance reduction by comparing the collected data to the manufacturer's standards. This paper stresses the association between visual abnormalities and electrical degeneration, shining light on the interaction of these elements.

关键词： Degradation visualization Corrosion Thermal engineering Thermal conductivity Thermal analysis Solar panels Stress Meteorology Thermal degradation

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 << < 7 8 9 10 11 12 13 14 15 16 > >>

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：