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

13,794 篇 会议
7,643 篇 期刊文献
257 册 图书

馆藏范围

21,694 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

13,432 篇 工学
- 10,387 篇 计算机科学与技术...
- 8,664 篇 软件工程
- 3,407 篇 信息与通信工程
- 2,159 篇 控制科学与工程
- 1,904 篇 生物工程
- 1,591 篇 电气工程
- 1,407 篇 生物医学工程（可授...
- 1,170 篇 光学工程
- 1,168 篇 电子科学与技术（可...
- 830 篇 网络空间安全
- 791 篇 机械工程
- 677 篇 安全科学与工程
- 633 篇 动力工程及工程热...
- 592 篇 交通运输工程
- 584 篇 仪器科学与技术
- 556 篇 化学工程与技术
6,835 篇 理学
- 3,488 篇 数学
- 2,089 篇 生物学
- 1,771 篇 物理学
- 1,218 篇 统计学（可授理学、...
- 742 篇 系统科学
- 654 篇 化学
4,012 篇 管理学
- 2,426 篇 管理科学与工程(可...
- 1,767 篇 图书情报与档案管...
- 1,067 篇 工商管理
1,562 篇 医学
- 1,221 篇 临床医学
- 1,119 篇 基础医学(可授医学...
- 820 篇 公共卫生与预防医...
- 655 篇 药学(可授医学、理...
848 篇 法学
- 701 篇 社会学
373 篇 经济学
334 篇 农学
236 篇 教育学
183 篇 文学
32 篇 军事学
28 篇 艺术学
5 篇 哲学
3 篇 历史学

主题

921 篇 deep learning
849 篇 accuracy
534 篇 computational mo...
484 篇 machine learning
464 篇 feature extracti...
447 篇 training
393 篇 real-time system...
387 篇 predictive model...
370 篇 internet of thin...
317 篇 support vector m...
316 篇 convolutional ne...
285 篇 computer science
280 篇 semantics
271 篇 data models
256 篇 optimization
230 篇 neural networks
221 篇 computer archite...
214 篇 reliability
214 篇 scalability
204 篇 image segmentati...

机构

253 篇 department of co...
153 篇 school of comput...
140 篇 school of comput...
136 篇 school of comput...
127 篇 school of comput...
121 篇 department of co...
112 篇 school of comput...
111 篇 school of comput...
106 篇 department of co...
101 篇 college of compu...
101 篇 national enginee...
101 篇 department of co...
97 篇 school of comput...
95 篇 department of co...
95 篇 department of co...
93 篇 north-west unive...
93 篇 institut univers...
88 篇 national centre ...
87 篇 infn sezione di ...
83 篇 tno technical sc...

作者

123 篇 niyato dusit
96 篇 ferrara g.
96 篇 ardid m.
95 篇 calvo d.
92 篇 chen a.
89 篇 gal t.
89 篇 bozza c.
88 篇 anjali t.
88 篇 díaz a.f.
87 篇 boumaaza j.
85 篇 zheng wei-shi
85 篇 coleiro a.
84 篇 gozzini s.r.
82 篇 dallier r.
73 篇 kalekin o.
66 篇 anguita m.
64 篇 boettcher m.
63 篇 huang f.
61 篇 kulikovskiy v.
55 篇 enzenhöfer a.

语言

17,418 篇 英文
4,166 篇 其他
167 篇 中文
2 篇 法文
1 篇 德文
1 篇 日文
1 篇 朝鲜文
1 篇 斯洛文尼亚文

检索条件"机构=MTech Computer Science and Engineering School of Computing Science and Engineering"

共 21694 条记录，以下是4431-4440 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：

Harnessing Diversity in Face Recognition: A Voting and Bagging Ensemble Approach

Harnessing Diversity in Face Recognition: A Voting and Baggi...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Aniket Gupta Suthir Sriram V Nivethitha Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

Facial recognition plays a crucial role in various applications, as it tackles challenges such as changes in lighting, position, and facial expressions. This study aims to explore the effectiveness of ensemble learning methods, specifically the voting classifier and bagging classifier, in enhancing the accuracy of face recognition. We extensively examine our ensemble technique, leveraging the diversity that emerges from combining multiple classifiers. The voting classifier showcases superior accuracy (0.91), underscoring the effectiveness of blending numerous models. The bagging classifier, even though it has achieved a respectable accuracy of 0.72, demonstrates a noteworthy improvement compared to individual classifiers. These findings emphasize the effectiveness of ensemble learning in alleviating the challenges encountered in face recognition tasks. Improving facial recognition systems in real-life situations is one useful piece of advice that this research offers, as it advances our knowledge of ensemble learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cervical Cancer Diagnosis: Deep Learning and Explainable AI in Multiclass Image Classification

Enhancing Cervical Cancer Diagnosis: Deep Learning and Expla...

引用

Women in computing (InCoWoCo), International Conference for

作者： Kuthati Shreya Lasya Priya Divakarla Kanderi Johith Kumar Tripty Singh Afnaan K Dept of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798331518943

ISBN: (纸本)9798331518950

Cervical Cancer is a major health concern amongst many women around the world. Cervical Cancer is usually caused by the Human Papilloma Virus (HPV). This causes unusual growth in the cervix region. All though this is such a serious health concern, proper treatment and diagnosis are not that prominent and available to the patients. Regular checkups and tests are quite necessary which can help in early detection and diagnosis. It has been observed if these cancerous growths are detected at an early stage then the patient has a high recovery rate. If not detected early then there are chances that these cancer cells spread to the other organs which can be a fatal condition for the patient. A technique has been introduced involving the use of deep learning models to categorize cancer cells into four distinct classes, aiding in accurate identification and effective diagnosis. Explainable AI techniques like Local Interpretable Model Agnostic Explanations (LIME) have been used with these models in order to identify the regions in the medical images that contribute towards the image classification of the cancer cells which can further provide a better understanding for performing diagnosis.

关键词： Deep learning Accuracy Explainable AI Computational modeling Predictive models Prediction algorithms Classification algorithms Cervical cancer Biological cells Image classification

来源：评论

学校读者我要写书评

暂无评论

Designing Multimodal Video Search by Examples (MVSE) user interfaces: UX requirements elicitation and insights from semi-structured interviews 23

Designing Multimodal Video Search by Examples (MVSE) user in...

引用

2023 European Conference on Cognitive Ergonomics, ECCE 2023

作者： Boyd, Kyle Mcallister, Patrick Mulvenna, Maurice Bond, Raymond Wang, Hui Spence, Ivor Wu, Guanfeng Haider, Abbas School of Computing Ulster University Belfast United Kingdom School of Electronics Electrical Engineering and Computer Science Queens University United Kingdom BBC Research and Development AI Research London United Kingdom

ISBN: (纸本)9798400708756

In order to search for content from large video archives, it is typically undertaken via keyword queries using predefined metadata such as title and other tags. However, it is difficult to use keywords to search for specific moments in a video. Video search by examples is a desirable approach for this scenario as it allows users to search for content using one or more examples without having to specify a keyword. However, video search by examples is notoriously challenging, and performance is poor. To improve search performance, multiple modalities may be considered - image, sound, voice and text, multiple search cues could be used to identify more relevant content. This is multimodal video search by examples (MVSE), where users can search for content using multiple modalities. In this paper, typical end users - BBC archivists, programme support staff - are interviewed to identify how their search needs can be addressed with the technical capabilities of a MVSE tool. Such a search tool will be useful for organisations such as the BBC who maintain large collections of video archives and want to provide a search tool for their own staff as well as for the public. It will also be useful for companies such as Youtube who host videos from the public and want to enable video search by examples. The study's objectives explored in this paper were to inform the design and development of the UX workflows to gain a broader understanding of what opportunities and issues may arise from the proposed prototype tool. Results from the thematic analysis was highlighted 4 main themes: Opportunities, Time constraints, Activities, and Pain points. Further analysis highlighted key areas that should be considered for an MVSE-based system, such as scene recognition, face recognition, speed issues, and integration.. © 2023 Owner/Author.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

An Investigation of Federated Learning Strategies for Disease Diagnosis

An Investigation of Federated Learning Strategies for Diseas...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Abhay Das Aishwarya Krishnadas Vaishakh S Krishnan Avani Farida Greeshma Sarath Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Traditional healthcare systems utilize centralized approaches for building machine-learning models for disease diagnosis. It requires sharing raw data to the centralized server, which is practically difficult due to patient’s privacy. This leads to significant vulnerabilities and challenges. As a result, switching to approaches for scalable and distributed AI at the network edge for privacy-preserving smart healthcare applications is essential. Deep learning models need to train on data, on any nodes, in a privacy-preserving manner, but not give up the distinction of patients. This paper aims to investigate the application of FL in providing health diagnosis while enhancing the patient’s data privacy, by adopting the Flower platform. It employs the following four algorithms for federated learning that can facilitate collaborative model training with shared patient data: FedAvg, FedProx, FedAdagrad, and FedAdam. To evaluate FL’s effectiveness, deep learning models trained on decentralized COVID-19 and Pneumonia datasets are used from different sources. FL methods were compared to a Centralized Convolutional Neural Network (CNN) to check the performance. The analysis shared in this paper shows that implementing FL contributes to establishing the subject’s accurate diagnostics concerning the patient’s data protection in the healthcare industry.

关键词： Deep learning Training Accuracy Federated learning Buildings Switches Flowering plants Data models Convolutional neural networks Medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

Ambient Intelligent System for Appointment Management

Ambient Intelligent System for Appointment Management

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Akash R Prabhu K Vaisakhkrishnan S Sree Pranavi Sk Shriyah V Anantha Narayanan Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

In today’s fast-paced world, efficient management of appointments is crucial for both service providers and consumers. Efficient appointment management is essential in the modern service industry to enhance both operational efficacy and client satisfaction. This project report presents the development of an Ambient Intelligent System (AIS) for Appointment Management designed to optimize the handling of appointments in dynamic environments. Utilizing Bluetooth technology, the AIS efficiently manages both scheduled and ad-hoc appointments by detecting user presence via ESP32 micro-controllers. This system dynamically adapts to changing conditions, prioritizing appointments based on real-time data to minimize wait times and enhance user experience. The comprehensive architecture includes mobile applications for users and administrative staff, backend services, and a robust database system to ensure real-time synchronization and responsiveness. This study evaluates the AIS’s performance in streamlining appointment processes, demonstrating significant improvements over traditional methods in both efficiency and user satisfaction.

关键词： Industries Privacy computer architecture Real-time systems User experience Database systems Mobile applications Delays Synchronization Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Image Dehazing Using Pix2Pix GAN and Inception

Image Dehazing Using Pix2Pix GAN and Inception

引用

Conference on Information and Communication Technology (CICT)

作者： C Mithul Puvvadi Harsha Vardhan Sai Varun Harsha Vardhan SS Prabhakar T.V. Nidhin Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798331531539

ISBN: (纸本)9798331531546

Remote sensing imagery is commonly used in variety of visual data applications, including military surveillance, earthquake damage assessment, autonomous vehicles, and satellite monitoring. However, atmospheric haze is known to reduce visibility in these scenes, which negatively impacts the analysis and compromises the accuracy of advanced applications. The suggested method makes use of both generative adversarial networks (GANs) and Inception Blocks to enhance the expression power of the Generator by adding features from multiple convolutional paths, enabling it to generate more detailed images, than a generator that creates dehazed images from hazy input and a discriminator that separates produced images from real photos make up the components of this GAN based dehazing model. The dehazed pictures are further refined using a CNN-based enhancement network, which further corrects colour distortions, captures minute details, and improves overall output. This approaches success is demonstrated by experimenting with remote sensing datasets, which outperform conventional dehazing approaches and highlight the potential of GANs and CNNs to reduce haze and enhance image quality. The technique shows the potential to clear foggy satellite images.

关键词： Image quality Visualization Satellites Surveillance Generative adversarial networks Generators Satellite images Information and communication technology Military satellites Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Identifying Influential Communicators based on Correlation and Minimum Distance in Social Media Data Streams 9

Identifying Influential Communicators based on Correlation a...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Zhu, Jie Shi, Lei-Lei Liu, Lu Han, Zi-Xuan Jiang, Liang Panneerselvam, John Jiangsu University School of Computer Science and Telecommunication Engineering China Jiangsu University Jiangsu Key Laboratory of Security Technology for Industrial Cyberspace China University of Leicester School of Computing and Mathematical Sciences United Kingdom Jiangsu University of Science and Technology School of Ocean China

ISBN: (纸本)9798350319804

Twitter has become a crucial social networking platform for users to receive and exchange information about current events. Identifying the most influential users in social networks is pivotal for the efficient propagation of information. However, traditional influencer identification models often fall short of assessing users' influence comprehensively and neglect overlapping influence, which greatly restrains their efficiency and accuracy in identifying key users. To address such issues, we propose a method for identifying key users based on correlation and minimum distance (CM-UDM). This method can evaluate users' influence based on their individual, global, local, and propagation path characteristics in social networks. Additionally, we propose a key user decision graph in order to address the problem of overlapping users' influence. We have conducted experiments using one classical dataset and three real Twitter datasets, where the performance of our proposed method in identifying highly influential users is demonstrated. © 2023 IEEE.

关键词： Influence maximization Influence overlap Twitter

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multi-Class Fetal Plane Detection with Limb Localization in Ultrasound Images

Enhanced Multi-Class Fetal Plane Detection with Limb Localiz...

引用

Contemporary computing and Communications (InC4), IEEE International Conference on

作者： Kolla Gnapika Sindhu R Annamalai Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (数字)9798350383652

ISBN: (纸本)9798350383669

In this novel study, we address the critical need for automated interpretation and analysis of ultrasound images in the context of fetal development assessment. The current large-scale retrospective analyses suffer from the laborious and specialized process of manually identifying standard fetal ultrasound planes, requiring sonographer expertise. Our innovative approach leverages state-of-the-art deep-learning techniques, specifically vision transformers, to automate the detection of standard fetal ultrasound planes. Our methodology involves the integration of two datasets, with a particular emphasis on musculoskeletal planes, notably fetal limbs. The resulting comprehensive classification model comprises eight distinct classes: fetal limbs, fetal abdomen, fetal thorax, fetal femur, maternal cervix, and fetal arms. Notably, the application of vision transformers, specifically ViT -L16 (Vision Transformer), to mid-pregnancy prenatal screening achieved a remarkable test accuracy of 97.2%. The primary goal of incorporating vision transformers into prenatal screening is to enhance the efficiency and accuracy of identifying critical anatomical structures. This advancement facilitates the prompt evaluation of fetal growth metrics and enables early identification of irregularities. Serving as a valuable tool for ultrasound technicians, our study signifies a significant leap in transforming the assessment of fetal well-being through ultrasound techniques. Moreover, it sets new benchmarks for detecting abnormal fetal development within ultrasound visuals, contributing to the ongoing evolution of fetal health assessment methodologies.

关键词： computer vision Visualization Ultrasonic imaging Accuracy Attention mechanisms Computational modeling Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Gesture Recognition Technology in Smart Gloves Enhanced by Machine Learning

Gesture Recognition Technology in Smart Gloves Enhanced by M...

引用

Ubiquitous computing and Intelligent Information Systems (ICUIS), International Conference on

作者： Thangam S Nithin Kandi Dorai Sai Charan Vijay Gosu J. Jesy Janet Kumari Virupaxappa G Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidhyapeetham Bengaluru India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

Gesture recognition systems are changing how people interact with devices, promising natural and intuitive hands-free control in various applications. Based on the ESP32 microcontroller and machine learning techniques, the proposed work is developing a compact, power-efficient system for recognizing hand gestures from data gathered by flex sensors and accelerometers. The entire system fits within memory constraints, as lightweight machine learning models are first trained on a computer using Python and then ideally deployed in optimized versions onto the ESP32. In this respect, the stream of pre-processed sensor data happens to be fed to the ML model for inference, sending back results to the ESP32, which hence triggers specific actions or commands. This fundamentally new approach shows the feasibility of machine learning on resource-constrained platforms, opening the road for wearable technologies that will be more clever and reactive.

关键词： Hands Flexible printed circuits Heuristic algorithms Machine learning Gesture recognition Sensor fusion Real-time systems Sensor systems Reliability Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

A Collaborative Elevator System Optimization: A Finite Automata Approach

A Collaborative Elevator System Optimization: A Finite Autom...

引用

Global Conference for Advancement in Technology (GCAT)

作者： Amrutha Sivakumar G Bhavya Reddy Yalakanti Tanvi Samreen Sidhu Radha D Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

Modern high-rises and metropolitan areas rely largely on efficient elevator systems to control the vertical movement of people. However, traditional elevator control systems frequently fail to fulfill the needs of a growing population and changing usage patterns. The proposed paper seeks to evaluate how automata theory can be used to establish an elevator system that works efficiently. Each elevator is represented as an individual finite automaton. A composite automaton to coordinate the actions, the system’s behaviour and interactions is modelled. The Deterministic Finite Automaton (DFA) model specifies the states and transitions of the two cooperating lifts to optimise passenger service. The model considers numerous situations that include passenger requests through the floor, emergencies, maintenance, and the adaptation for power failures. This DFA-based design is targeted to increase elevator efficiency many times over, reduce waiting time, save energy, and provide a better passenger service experience before the implementation.

关键词： Adaptation models Urban areas Automata Collaboration Control systems Elevators Maintenance Optimization Floors

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 << < 440 441 442 443 444 445 446 447 448 449 > >>

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：