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

41,147 篇 会议
6,893 篇 期刊文献
316 册 图书

馆藏范围

48,356 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

29,956 篇 工学
- 17,997 篇 计算机科学与技术...
- 14,920 篇 软件工程
- 8,171 篇 信息与通信工程
- 5,794 篇 电子科学与技术（可...
- 5,552 篇 电气工程
- 5,070 篇 控制科学与工程
- 2,623 篇 生物工程
- 2,335 篇 光学工程
- 2,231 篇 生物医学工程（可授...
- 2,041 篇 机械工程
- 2,027 篇 动力工程及工程热...
- 1,931 篇 仪器科学与技术
- 1,504 篇 化学工程与技术
- 1,166 篇 材料科学与工程（可...
- 916 篇 安全科学与工程
- 885 篇 交通运输工程
- 784 篇 建筑学
15,741 篇 理学
- 8,320 篇 数学
- 5,237 篇 物理学
- 2,855 篇 生物学
- 2,685 篇 统计学（可授理学、...
- 1,928 篇 系统科学
- 1,572 篇 化学
6,136 篇 管理学
- 3,761 篇 管理科学与工程(可...
- 2,605 篇 图书情报与档案管...
- 2,117 篇 工商管理
1,712 篇 医学
- 1,495 篇 临床医学
- 1,390 篇 基础医学(可授医学...
- 927 篇 药学(可授医学、理...
1,096 篇 法学
- 899 篇 社会学
773 篇 经济学
527 篇 教育学
474 篇 农学
193 篇 文学
126 篇 军事学
47 篇 艺术学
3 篇 哲学
1 篇 历史学

主题

1,032 篇 computational mo...
993 篇 accuracy
791 篇 feature extracti...
741 篇 training
726 篇 computer science
529 篇 deep learning
502 篇 optimization
485 篇 machine learning
461 篇 predictive model...
453 篇 real-time system...
422 篇 support vector m...
408 篇 internet of thin...
397 篇 computer archite...
364 篇 neural networks
363 篇 data models
359 篇 bandwidth
340 篇 reliability
330 篇 mathematical mod...
316 篇 robustness
303 篇 wireless sensor ...

机构

170 篇 dept. of electri...
83 篇 institut univers...
82 篇 north-west unive...
80 篇 national centre ...
79 篇 infn sezione di ...
76 篇 infn sezione di ...
69 篇 institute of inf...
66 篇 università di ca...
62 篇 dept. of electr....
58 篇 dept. of electri...
57 篇 dept. of informa...
56 篇 dept. of compute...
53 篇 leiden universit...
52 篇 dept. of electri...
52 篇 school of automa...
51 篇 tno technical sc...
45 篇 université de st...
44 篇 dept. of compute...
43 篇 dept. of electri...
42 篇 infn lnf via enr...

作者

85 篇 ferrara g.
85 篇 ardid m.
85 篇 gal t.
84 篇 calvo d.
84 篇 bozza c.
81 篇 chen a.
78 篇 kalekin o.
74 篇 díaz a.f.
66 篇 huang f.
65 篇 boumaaza j.
55 篇 coleiro a.
52 篇 kulikovskiy v.
50 篇 gozzini s.r.
41 篇 benoit d.m.
41 篇 eddymaoui a.
40 篇 gagliardini s.
40 篇 labalme m.
37 篇 androulakis g.
35 篇 khatun a.
35 篇 del burgo r.

语言

46,003 篇 英文
1,550 篇 其他
570 篇 中文
207 篇 朝鲜文
37 篇 日文
4 篇 德文
1 篇 阿拉伯文
1 篇 法文
1 篇 斯洛文尼亚文
1 篇 土耳其文

检索条件"机构=Dept. of Electrical and Computer Engineering and Computer Science University of Cincinnati"

共 48356 条记录，以下是4811-4820 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：

Robustly Optimized Multimedia Local and Global Context Analysis at Multi-modal Balance 25

Robustly Optimized Multimedia Local and Global Context Analy...

引用

40th Annual ACM Symposium on Applied Computing, SAC 2025

作者： Yoon, Junho Lim, Kiho Choi, Chang Dept. of Computer Engineering Gachon University Seongnam Korea Republic of Dept. of Computer Science William Paterson University of New Jersey NJ United States

ISBN: (纸本)9798400706295

Recent media have increasingly shifted towards multimedia formats that simultaneously utilize visual and linguistic information. Research on multimodal AI is actively conducted to analyze large-scale multimodal data effectively. Multimodal AI fuses the probability and feature values extracted from single modalities by a backbone model, enabling the simultaneous analysis of multimodal information. This allows for discovering new insights that may not be detectable through single-modality analysis. Depending on the data collection environment, multimedia can be classified into one-to-one and one-to-many modality balances. Previous multimodal AI approaches analyze these one-to-many relationships by downsampling or duplicating data to fit a one-to-one relationship. In this paper, we optimize multimedia analysis in one-to-one and one-to-many modality balances based on the local and global context analysis capabilities of multimodal AI and the multimodal analysis characteristics of backbone models. The multimedia analysis system employs late score and feature fusion to independently analyze the local context as the baseline for multimodal AI. In contrast, early and hierarchical feature fusion is utilized for comprehensive global context analysis. The backbone models used include ViT and RoBERTa to analyze the overall structure of multimodal data and BEiT and DeBERTa to analyze structural features. Experimental results show that, in the duplication method, late score and feature fusion, which independently analyze the local context of multimodal data, are 0.56% more accurate and achieve an f1 score that is 0.025 higher. Additionally, BEiT and DeBERTa, which analyze structural features, demonstrate a 0.2% increase in accuracy and a 0.0167 improvement in f1 score. In the downsampling method, early and hierarchical feature fusion, which comprehensively analyzes the global context, outperforms by 1.17% in accuracy and 0.0164 in f1 score. Furthermore, ViT and RoBERTa, which foc

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Hybrid Software Reliability Prediction Model Using Feature Selection and Support Vector Classifier 4

Hybrid Software Reliability Prediction Model Using Feature S...

引用

4th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2022

作者： Rath, Suneel Kumar Sahu, Madhusmita Das, Shom Prasad Mohapatra, Srikanta Kumar C. V. Raman Global University Dept. of Computer Science Engineering Odisha Bhubaneswar India Birla Global University Dept. of Computer Science Engineering Odisha Bhubaneswar India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9781665400732

The primary purpose of the software industry is to provide high-quality software. Software system failure is caused by faulty software components. The goal of reliable software is to reduce the amount of software programme failures. Software defect prediction is a crucial aspect of developing high-quality software. One can predict software failures by implement essential prediction metrics and previous fault information. A good software fault prediction model makes testing easier while also improving the quality and consistency of software. For defect prediction systems based on diverse parameters, several methodologies have been proposed. However, none of the models meet the criteria for software reliability defect prediction. So in this article we proposed a hybrid software reliability model using feature selection and support vector classifier. In terms of software reliability defect prediction, the provided methodology is acceptable for different software metrics with experimental approvals utilizing a standard dataset. In the methodology, the NASA Metrics Data Program datasets are used for real-time verification and validation. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Stereo dept. Estimation Based on Adaptive Stacks from Event Cameras 49

Stereo Depth Estimation Based on Adaptive Stacks from Event ...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Jianguo, Zhu Pengfei, Wang Sunan, Huang Cheng, Xiang Huat Rodney, Teo Swee National University of Singapore Dept. of Electrical and Computer Engineering Singapore Nanyang Technological University Saab-NTU Joint Lab Singapore National University of Singapore Temasek Lab. Singapore

ISBN: (纸本)9798350331820

In recent years, the combination of event cameras and computer vision has shown increasingly excellent performance. Due to high sensitivity, event cameras are capable of addressing the issue of motion blur in conventional cameras, and are well-suited for analyzing fast-moving objects, making them highly suitable for dept. estimation in UAV applications This paper focuses on methods for dept. estimation using events generated by event cameras. Due to the asynchronicity of events, it is difficult to directly transmit events to the dept. estimation network. So the method to preprocess events is important. Unlike existing processing methods, this paper creatively proposes the idea of adaptive stacks, which can change the size of weighted stacks in real time according to the events generation rate. In this way, we can solve the problems caused by traditional processing methods, and better utilize the effective information of events. Then, a dept. estimation network corresponding to the adaptive stacks is designed to form a complete end-to-end events dept. estimation model: Adaptive Stacks dept. Estimation Network (ASNet). Compared with other models, ASNet has demonstrated excellent dept. estimation accuracy and has great application prospects. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Unified Face Matching and Physical-Digital Spoofing Attack Detection

Unified Face Matching and Physical-Digital Spoofing Attack D...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision Workshops, WACVW 2025

作者： Kunwar, Arun Rattani, Ajita University of North Texas Dept. of Computer Science and Engineering Denton United States

ISBN: (纸本)9798331536626

Face recognition technology has dramatically trans-formed the landscape of security, surveillance, and authentication systems, offering a user-friendly and non-invasive biometric solution. However, despite its significant advantages, face recognition systems face increasing threats from physical and digital spoofing attacks. Current research typically treats face recognition and attack detection as distinct classification challenges. This approach necessitates the implementation of separate models for each task, leading to considerable computational complexity, particularly on devices with limited resources. Such inefficiencies can stifle scalability and hinder performance. In response to these challenges, this paper introduces an innovative unified model designed for face recognition and detection of physical and digital attacks. By leveraging the advanced Swin Transformer backbone and incorporating Hil:o attention in a convolutional neural network framework, we address unified face recognition and spoof attack detection more effectively. Moreover, we introduce augmentation techniques that replicate the traits of physical and digital spoofing cues, significantly enhancing our model ro-bustness. Through comprehensive experimental evaluation across various datasets, we showcase the effectiveness of our model in unified face recognition and spoof detection. Additionally, we confirm its resilience against unseen physical and digital spoofing attacks, underscoring its potential for real-world applications. © 2025 IEEE.

关键词： digital attacks face matching physical attacks unified models

来源：评论

学校读者我要写书评

暂无评论

Image to Audio Using LLM for Blind People

Image to Audio Using LLM for Blind People

引用

Data, Computation and Communication (ICDCC), International Conference on

作者： Kumaresan T Geetha A Rajeshkumar G Benita Gracia Thangam J Malathi Eswaran Thivya Rajkumar Dept. of Computer Science and Engineering Bannari Amman Institute of Technology Sathyamangalam India Dept. of Computer Science and Engineering Presidency University Bangalore India Dept. of Artificial Intelligence and Data science Velalar college of Engineering and Technology Erode India Dept. of Computer Technology Kongu engineering College Perundurai India

ISBN: (数字)9798331532956

ISBN: (纸本)9798331532963

Blind people face many difficulties while engaging with their surroundings. This project is all about creating innovative solutions for the blind people by providing the information in the format of audio. Image-to-Audio transformation system specifically designed for natural language understanding using Large Language Model (LLM).The system will capture a picture or video of the situation present in front of the blind person and then provide descriptions about the images. The objective is to provide guidelines for blind people by understanding their surroundings through an LLM model and provide audio response. The CLIP model analyzes the objects, scenes, text etc.. and provides relevant information. The extracted visual data is then passed through GTTs (Google-Text-To-Speech) to create rich audio descriptions. It provides accurate and detailed representation of the visual content, allowing blind people to understand their surroundings. The project involves integrating convolutional neural networks and Large Language Model (e.g GPT-4) technologies to create a real-time image-to-text system for blind individuals. The CNN model is used to calculate the distance of the object from the user. We are integrating the Google Assistants to open the app automatically by the blind people with help of their voice.

关键词： Visualization Navigation Large language models Blindness Real-time systems Natural language processing Internet Convolutional neural networks Multimedia communication Monitoring

来源：评论

学校读者我要写书评

暂无评论

Integrating Social Platforms with IoT: Security Challenges, Applications, and Trust Issues 5

Integrating Social Platforms with IoT: Security Challenges, ...

引用

5th IEEE India Council International Subsections Conference, INDISCON 2024

作者： Mohanta, Bhabendu Kumar Dehury, Mohan Kumar Tulasi, Desetti Das, Sunayana United Arab Emirates University College of Information Technology Al AinP.O. Box 15551 United Arab Emirates Amity Institute of Information Technology Amity University Jharkhand Ranchi India Koneru Lakshmaiah Education Foundation Dept. of Computer Science and Engineering Vaddeswaram Guntur India Driems University Tangi Dept. of Computer Scinece and Engineering Odisha Cuttack754 022 India

ISBN: (纸本)9798350376753

The term Social Internet of Things (Social IoT) refers to an expansion of the term Internet of Things (IoT) that integrates social networking capabilities and concepts into IoT applications. The number of connected devices has already crossed the total world population. With the development of other technologies like Blockchain, Artificial Intelligence, Machine Learning, and Data science, IoT become more usable in many applications. With the rapid use of digital devices, social media like Facebook and others are part of the human lifestyle. The integration of IoT with a social platform for different services become an emerging research field in recent times. In this paper, the authors investigated the impact of social services in IoT and its corresponding decentralized architecture. The paper also identified the security challenges associated with the Social IoT and trust issues. Finally, the paper addresses some of the emerging technologies which are capable of addressing the security challenges in Social IoT. © 2024 IEEE.

关键词： Decentralization IoT Privacy Secure Communication Security Social IoT Trust Management

来源：评论

学校读者我要写书评

暂无评论

Autism Spectrum Disorder Detection Based on Optimal Feature Selection Technique

Autism Spectrum Disorder Detection Based on Optimal Feature ...

引用

Smart Technologies, Communication and Robotics (STCR)

作者： Lakshaya Kaushik Ranjit Singh Manjit Singh Dept. of Computer Science & Engineering Chandigarh University Gharuan Mohali Punjab India

ISBN: (数字)9798350357530

ISBN: (纸本)9798350357547

A neurodevelopmental disorder autism spectrum disorder (ASD) still remains a challenge among research fields, and the current diagnostic procedures still need to be improvised for more precise detections. Although several investigations by involving the usage of different machine learning (ML) algorithms toward the identification of ASD among individuals, there is still a large gap in optimizing feature selection methods toward better accuracy and efficiency. Systematic comparisons among various feature selection methods are rather neglected in prior studies, so there is less potential for discovering the best diagnostic markers. In this light, our work brings forth a comprehensive framework that investigates three different kinds of feature selection methods-mutual information, wrapper-based selection by Random Forest, and LASSO regularization by XGBoost. Our methodology implements structured evaluations toward the assessment of the impact of each tool for the identification of detecting accuracy and computation. Also, comparative evaluation results that though wrapper-based selection increased the first model’s accuracy up to 90%, the use of XGBoost with LASSO regularization outperformed it with an accuracy of 99.8%. Results establish the importance of our approach in streamlining clinical assessment processes and identifying features about ASD that are crucial towards advancing data-driven detection methodologies.

关键词： Autism Accuracy Systematics Machine learning algorithms Computational modeling Pipelines Feature extraction Robots Random forests Mutual information

来源：评论

学校读者我要写书评

暂无评论

Improved Sampling Methods for Evaluation of Classification Performance

Improved Sampling Methods for Evaluation of Classification P...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Yue-Shi Lee Show-Jane Yen Yi-Jie Tang Dept. of Computer Science & Information Engineering Ming Chuan University Taoyuan Taiwan

ISBN: (数字)9798331507022

ISBN: (纸本)9798331507039

To evaluate the classification accuracy of a classification algorithm on a certain dataset, it is necessary to sample training and test data from the original dataset. After building the classification model from the training data, the test data can be used to evaluate the classification accuracy. However, in order to evaluate the classification accuracy of a classification algorithm on an original dataset, it is usually necessary to sample the training/test data many times, build the classification model many times, and then average the accuracies of all the evaluation, which will consume a lot of time and resources. To address this, we propose a sampling method so that the sampled training/test data can replace the results of building multiple models and averaging multiple classification accuracy, that is close to the evaluation results of the original data. Our approach introduces different methods for calculating the similarity of data distributions and incorporates feature weights in the similarity calculation process to select training/test sets that are close to the distribution of the original dataset.

关键词： Training Earth Accuracy Buildings Training data Sampling methods Data models Classification algorithms Artificial intelligence Testing

来源：评论

学校读者我要写书评

暂无评论

Improving Real-Time Aerial 3D Reconstruction: Towards Fusion of a Hand-Crafted SfM Algorithm with a Data-Driven Deep Neural Network

Improving Real-Time Aerial 3D Reconstruction: Towards Fusion...

引用

2023 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2023

作者： Akers, Jack Buck, Andrew Anderson, Derek Keller, James Camaioni, Raub Deardorff, Matthew Luke, Robert University of Missouri Dept. of Electrical Engineering and Computer Science ColumbiaMO United States U.S. Army DEVCOM C5ISR Center Fort BelvoirVA United States

ISBN: (纸本)9798350359527

dept. estimation from imagery is a crucial component of numerous real-Time systems, such as unmanned aerial vehicles. Traditional approaches, like structure from motion (SfM), rely on stereo cameras or sequential images from a single moving camera to infer dept.. However, these methods often yield sparse or incomplete dept. maps. Moreover, their accuracy is contingent on factors like baseline and platform motion. Recent advancements leveraging deep neural networks have exhibited remarkable outcomes in predicting dense dept. from a single image. Nonetheless, the reliability of these black box models is a concern, and the dept. approximations they provide often require refinement. In this study, we delve into the merits and drawbacks of each approach, exploring the potential synergies that could arise from their combination. The initial approach, serving as our baseline, relies solely on sparse SfM dept. estimates. In contrast, the second method employs spatial interpolation to fill in missing SfM dept.s. These methodologies are then contrasted with the performance of two deep nets-one trained on simulated data and the other on real data. The validation of all four approaches is conducted against a gold standard generated using the Unreal Engine. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Synergistic Approach to Detect Malicious Behaviour through Correlation-Based Feature Selection with Deep Learning

A Synergistic Approach to Detect Malicious Behaviour through...

引用

International Conference on electrical, computer and Communication engineering (ECCE)

作者： Fahad Hossain Mohammad Nafizul Islam Md. Ariful Islam Mohammed Mushfiq Ali Fahim Muntasir Md. Mahiuddin Dept. of Computer Science & Engineering International Islamic University Chittagong Chattogram Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Malware presents a persistent cybersecurity threat by infiltrating systems to steal sensitive data. Detecting malware traffic is challenging due to its consistent asymmetry, distinguishing it from benign traffic. This paper proposes an advanced malware detection system using deep learning and feature selection techniques. A Bidirectional-GRU approach is introduced, which improves model performance by effectively selecting and removing specific features, outperforming traditional dense-layer methods. The effectiveness of feature selection is demonstrated by enhancing the performance of traditional models such as Naive Bayes and XGBoost, surpassing Gradient Boosting. Our results indicate that at a 0.6 threshold with the selection of 21 features, Bidirectional-GRU achieved a performance of 99.98%, slightly outperforming other models. Additionally, XGBoost, GRU, and Random Forest also demonstrated strong performance in malware detection. The study highlights threshold-specific performance, showing that Bi-GRU excels at lower thresholds, while GRU performs optimally at higher thresholds, showcasing adaptability to varying configurations. Key features used in the model include stime, mm users, gtime, among others, which contributed significantly to the improved detection accuracy.

关键词： Deep learning Adaptation models Accuracy Computational modeling Feature extraction Boosting Malware Bayes methods computer security Random forests

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 << < 478 479 480 481 482 483 484 485 486 487 > >>

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：