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

13,740 篇 会议
7,731 篇 期刊文献
256 册 图书

馆藏范围

21,727 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

13,528 篇 工学
- 10,494 篇 计算机科学与技术...
- 8,690 篇 软件工程
- 3,449 篇 信息与通信工程
- 2,242 篇 控制科学与工程
- 1,917 篇 生物工程
- 1,628 篇 电气工程
- 1,414 篇 生物医学工程（可授...
- 1,179 篇 电子科学与技术（可...
- 1,178 篇 光学工程
- 843 篇 网络空间安全
- 803 篇 机械工程
- 679 篇 安全科学与工程
- 638 篇 动力工程及工程热...
- 596 篇 交通运输工程
- 587 篇 仪器科学与技术
- 562 篇 化学工程与技术
6,875 篇 理学
- 3,496 篇 数学
- 2,094 篇 生物学
- 1,786 篇 物理学
- 1,212 篇 统计学（可授理学、...
- 746 篇 系统科学
- 669 篇 化学
4,031 篇 管理学
- 2,442 篇 管理科学与工程(可...
- 1,768 篇 图书情报与档案管...
- 1,070 篇 工商管理
1,569 篇 医学
- 1,228 篇 临床医学
- 1,121 篇 基础医学(可授医学...
- 819 篇 公共卫生与预防医...
- 655 篇 药学(可授医学、理...
850 篇 法学
- 703 篇 社会学
374 篇 经济学
335 篇 农学
229 篇 教育学
185 篇 文学
33 篇 军事学
28 篇 艺术学
5 篇 哲学
3 篇 历史学

主题

918 篇 deep learning
821 篇 accuracy
535 篇 computational mo...
499 篇 machine learning
448 篇 feature extracti...
441 篇 training
378 篇 real-time system...
376 篇 predictive model...
360 篇 internet of thin...
319 篇 convolutional ne...
312 篇 support vector m...
289 篇 computer science
273 篇 data models
267 篇 semantics
258 篇 optimization
230 篇 neural networks
218 篇 computer archite...
209 篇 reliability
209 篇 scalability
203 篇 image segmentati...

机构

261 篇 department of co...
170 篇 school of comput...
137 篇 school of comput...
136 篇 school of comput...
122 篇 department of co...
116 篇 school of comput...
112 篇 school of comput...
104 篇 college of compu...
102 篇 national enginee...
102 篇 department of co...
101 篇 school of comput...
101 篇 department of co...
100 篇 department of co...
100 篇 school of comput...
94 篇 north-west unive...
94 篇 institut univers...
93 篇 department of co...
88 篇 infn sezione di ...
88 篇 national centre ...
83 篇 tno technical sc...

作者

125 篇 niyato dusit
97 篇 ferrara g.
97 篇 ardid m.
96 篇 calvo d.
93 篇 chen a.
88 篇 gal t.
88 篇 bozza c.
88 篇 díaz a.f.
88 篇 boumaaza j.
86 篇 coleiro a.
86 篇 gozzini s.r.
85 篇 zheng wei-shi
82 篇 anjali t.
81 篇 dallier r.
73 篇 kalekin o.
65 篇 anguita m.
65 篇 boettcher m.
61 篇 huang f.
56 篇 kulikovskiy v.
54 篇 benoit d.m.

语言

19,244 篇 英文
2,366 篇 其他
158 篇 中文
2 篇 法文
1 篇 德文
1 篇 日文
1 篇 朝鲜文

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

共 21727 条记录，以下是4781-4790 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：

Turning Images into Words: A Neural Approach to Image Captioning Using VGG16 and LSTM

Turning Images into Words: A Neural Approach to Image Captio...

引用

Electronic Systems and Intelligent computing (ICESIC), International Conference on

作者： K Sai Sarath Chandu A Rakshith V Nivethitha Suthir Sriram Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (数字)9798331522988

ISBN: (纸本)9798331522995

Recently, the task of automatic image captioning has been considered as a challenging and important problem for both computer vision and natural language processing domain. The primary aspect of image captioning is to create textual descriptions that will mirror the content of an image. This task has real significance in several real-world uses including automatic text writing, helping the visually impaired and improving image search technologies. In this paper we present a deep learning-based image captioning model using CNN and LSTM for generating accurate and fluent image description. In particular, we utilize the VGG16 model, one of the popular CNN architectures, for generation of deep features from input images. These feature vectors are subsequently fed into LSTM network as input captions are generated through understanding temporal structure in language.

关键词： Training Visualization Computational modeling Writing Turning Vectors Natural language processing Mirrors Long short term memory Faces

来源：评论

学校读者我要写书评

暂无评论

Innovations in Machine Learning for Flight Delay Prediction: A Targeted Overview

Innovations in Machine Learning for Flight Delay Prediction:...

引用

computers and Artificial Intelligence Technologies (CAIT), International Conference on

作者： Wei Wei Chenchen Yu Zhao Yang Fu Bo School of Computer Science and Engineering and the Shaanxi Key Laboratory for Network Computing and Security Xi'an University Of Technology Xi’an China School of Computer Science and Engineering Xi'an University Of Technology Xi’an China

ISBN: (数字)9798331530891

ISBN: (纸本)9798331530907

Artificial intelligence technology is increasingly being applied to air traffic flow forecasting. Based on the core data of Web of science, this study uses bibliometrics and content review methods to investigate the current situation, methodology evaluation and future research direction of flight delay prediction. Initially, a basic statistical analysis was performed on all the papers. This was followed by topic co-occurrence and keyword co-occurrence analysis, which revealed that most of the research focused on three main categories: machine learning methods, deep learning techniques, and algorithmic optimization strategies. Then reviewing the content in these categories, further content analysis showed that machine learning holds significant potential for handling large and diverse datasets.

关键词： Adaptation models Analytical models Computational modeling Machine learning Predictive models Prediction algorithms Data models Real-time systems Delays Optimization

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Potato Farming: A CNN-Powered Approach for Early Blight and Late Blight Detection to Ensure Global Food Security

Revolutionizing Potato Farming: A CNN-Powered Approach for E...

引用

IEEE Students' Conference on Electrical, Electronics and computer science (SCEECS)

作者： Mahesh Datta Sai Ponnuru Likhitha Amasala School of Computing SRM Institute of Science and Technology Chennai India School of Computer Science and Engineering Vellore Institute of Technology Amaravathi India

Potato, a crucial global food crop, faces persistent threats from diseases like early blight and late blight, jeopardizing both yields and economic stability. In response, we present an innovative approach using CNN for early disease detection in potato crops. Our objective is to empower farmers with rapid and accurate disease identification, facilitating timely treatments to prevent economic losses and reduce agricultural waste. Our CNN model achieved a remarkable validation accuracy of 99.59%, outperforming conventional methods. With 183,747 trainable parameters, our efficient and accurate model is set to revolutionize agricultural practices. Furthermore, we are deploying our model to Google Cloud and developing a React Native mobile app for potato prediction. This integration aims to provide farmers with real-time disease insights, preventing economic losses and ensuring global food security, thereby enhancing economic stability in the potato farming sector.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Graph-Based Approach for Estimating Object Interactions in Surveillance Video Synopsis

A Graph-Based Approach for Estimating Object Interactions in...

引用

Emerging Trends in Information Technology and engineering (ic-ETITE), Conference on

作者： Varnika Sood Santosh Kumar Ray Kiran Kumar Mahato Sidharth A V Kalakunnath Namitha Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

Video synopsis is a technique that condenses surveillance videos into compact equivalent videos. The objective of this paper is to identify and group related moving objects (also referred to as tubes) in a video using a graph-based video synopsis method. To do this, we first develop an interaction matrix to determine the degree of pairwise interaction between the tubes. A tube-set generation graph is then suggested as a way to combine linked tubes into a single tube set. Publicly available video datasets have been utilized by us to demonstrate the effectiveness of our method. Our technique has come up with another way of video synopsis; that is, focusing on the context of the original movie and picking out important details. This makes it a reliable surveillance approach as it greatly improves security efficiency through fast and accurate compression of videos. Moreover, our method grounded in graph preservation eases our understanding of what connects various elements in a film or video.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interactome: A Platform for Comprehensive Drug-Drug Interaction Analysis

Interactome: A Platform for Comprehensive Drug-Drug Interact...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Amrutha Sivakumar Shreya Bhanot M Srinidhi K Aiswariya Milan Department of Computer Science & Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Drug-drug interaction is an important aspect to be taken into consideration when administering multiple drugs to patients with severe diseases. It is important to know if the combination of the drugs causes a positive effect or an ill effect on the person’s body. Thus, Interactome roots to offer a comprehensive solution to assess and find out the interactions between commonly used drugs for the treatment of different ailments such as heart diseases or diabetes and provides an understanding of how the combination of these drugs can cause side effects if not provided with enough details about the drug. Thus, it enables the user to know alternatives to using efficient drugs without any side effects by displaying graphs of the percentage of positive and negative effects and charts depicting the effects. By providing negative and positive feedback on the combination of various drugs used for heart and diabetes patients and displaying the percentage risks with the help of graphs and charts, Interactome ensures the prevention of any unnecessary attacks. Also, it saves the lives of an individual by spreading awareness about drug-drug interactions. We incorporate a Trie data structure that efficiently analyzes the input medications against a database of known interactions. It optimizes the retrieval process by organizing the drugs into a hierarchical structure. Then it ensures rapid and accurate results so that healthcare professionals and individuals receive timely and comprehensive insights into potential drug interactions.

关键词： Drugs Heart Prevention and mitigation Medical services Data structures User experience Diabetes Personnel Diseases Bars

来源：评论

学校读者我要写书评

暂无评论

Enhancing Credit Card Fraud Detection with Deep Learning and Graph Neural Networks

Enhancing Credit Card Fraud Detection with Deep Learning and...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： J G Sherwin Akshay T Vinusha R Sharon Bianca C K Sarath Krishna G Radhika Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Financial fraud poses a major threat to financial service institutions and clients, facilitating anomaly detection capabilities. This paper dives into deep learning models which can be implemented to detect and distinguish fraudulent transactions from normal transactions and flag anomalies. Further, conversion of tabular data to graphs have been implemented for keen understanding and improved pattern analysis of fraudulent transactions, challenges include evolving attack strategies, class imbalance and model interpretability. The proposed methods utilize a synergistic combination of ensemble learning techniques and unsupervised deep neural networks, like Auto-Encoders and Recurrent Neural Networks. In the graphical representation, this study focuses on implementing Louvain Modularity, Girvan-Newman and Label Propagation Algorithm for effectiveness in community detection. The outcomes exhibit consistently reliable results on credit card transaction datasets. A comprehensive comparative analysis follows to compare the proposed approach to traditional fraud detection methods, demonstrating its superiority in accurately identifying fraudulent transactions, adapting to emerging threats, handling high-dimensional data, and mitigating class imbalances with respect to data privacy and security.

关键词： Deep learning Recurrent neural networks Finance Credit cards Graph neural networks Fraud Security Reliability Pattern analysis Financial services

来源：评论

学校读者我要写书评

暂无评论

Feature Enhanced Semi-Supervised Attention U-Net for Cell Segmentation

Feature Enhanced Semi-Supervised Attention U-Net for Cell Se...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Ardra S Raj S. B. Asha G. Gopakumar Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Cell segmentation is crucial for accurately assessing disease severity. Despite advances in deep learning, there is still a gap in understanding how U-Net variants perform in addressing the issue of limited labeled data in cell segmentation. We compare various U-Net models to see how they fare with live cell images. We also examine how different feature extraction methods affect their performance. Using the Laplacian and Standard Deviation features improves performance by more than 3%, giving Attention U-Net mean Intersection over Union (IoU) scores of 0.7956 and mean Dice scores of 0.8844. In addition, we introduce a semi-supervised Mean Teacher Attention U-Net that leverages the same feature extraction techniques. Remarkably, it achieves an IoU score of 0.7908 and a Dice score of 0.8831, outperforming the existing approaches even with only 60% labeled data and utilizing limited computational resources.

关键词： Image segmentation Laplace equations Microprocessors Computational modeling Morphology Focusing computer architecture Feature extraction Data models Standards

来源：评论

学校读者我要写书评

暂无评论

EOG and PPG Fusion for Subject Independent Multimodal Emotion Recognition: A Prototypical Networks Approach

EOG and PPG Fusion for Subject Independent Multimodal Emotio...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： Manju Priya Arthanarisamy Ramaswamy Suja Palaniswamy Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

Multimodal emotion recognition is recognizing the emotion from more than one modality like facial expression, gestures, speech, text and physiological signals. The prototypical networks is a well-known few-shot distance based machine learning algorithm, in which data point is classified based on the proximity to the prototype. In this work, the prototypical network algorithm is modified for multimodal emotion recognition using EOG and PPG, in which Smooth L1 loss is explored for learning the embedding space. This study also explored correlation, Euclidean, squared Euclidean and chord distance as distance metrics to learn the embedding space. The proposed method obtained a prediction accuracy of 60.00% and 61.00% in arousal and valence dimensions respectively which is higher than the accuracy reported in the literature.

关键词： Measurement Emotion recognition Electrooculography Machine learning algorithms Accuracy Text recognition Prototypes Speech recognition Prediction algorithms Physiology

来源：评论

学校读者我要写书评

暂无评论

IoT Sensor Data Stream Compression with Hybrid Compression Algorithms

IoT Sensor Data Stream Compression with Hybrid Compression A...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Karthik Garikipati Tejaswi Muppala A Vinitha Chowdary Apurvanand Sahay Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The recent world advancement in technology especially in the use of IoT devices has posed some serious complications in terms of how effectively we can convey data, this is normally a result of the limited bandwidth and power capacity. In this paper, we look into the need for efficient data compression in IoT devices and come up with a new approach to compress the data stream needed for IoT sensors. In this paper, we propose to integrate Dynamic Huffman Coding with Run Length Encoding smoothly as one novel network coding strategy to decrease the load carried by the communication channels and at the same time ensure the originality of the transmitted data. The proposed method is based on the use of RLE to remove a lot of redundant data and dynamic Huffman coding for further data compression. When compared with other central algorithms like dynamic Huffman, static Huffman, RLE, LZW, ZLIB, LZMA, and BZ2 this hybrid approach provided more efficient compression ratios and consumed less power. Compression can be considered an essential paradigm for IoT devices because it can minimize the restrictions associated with the prevention of limited bandwidths and power sources that are characteristic of such devices, which results in improved data sending and a longer lifespan of devices. As substantiated by the findings from our experiments, this approach holds a high degree of effectiveness and, therefore, is suitable for the IoT domain with a scarcity of resources in particular. The contributions of this research support the promotion of compression strategies while considering the IoT-specific needs thus enhancing standard system outcomes and durability.

关键词： Heuristic algorithms Prevention and mitigation Bandwidth Network coding Encoding Real-time systems Sensors Internet of Things Huffman coding Standards

来源：评论

学校读者我要写书评

暂无评论

Enhanced Gunshot Sound Detection using AlexNet and XGBoost from Fourier Spectrograms

Enhanced Gunshot Sound Detection using AlexNet and XGBoost f...

引用

Intelligent Technologies (CONIT), International Conference on

作者： M.Yagnasri Priya Sanjivani P. Shendre Peeta Basa Pati Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350349900

ISBN: (纸本)9798350349917

Gunshot detection and classification are pivotal for ensuring public safety, law enforcement, defense, and forensic investigations. This paper presents a comparitive study into the effectiveness of deep learning and traditional machine learning models in classifying gunshot sounds through Short-Term Fourier Transform (STFT) spectograms is presented. The study involves integrating Convolutional Neural Networks (CNNs) with standard machine learning techniques to extract and analyze features, particularly focusing on the penultimate layer of CNNs. By leveraging these features, this paper aims to enhance the system’s ability to accurately identify complex sound patterns associated with gunshots. This analysis provides insights into the strengths and weaknesses of deep learning and machine learning approaches in gunshot classification, particularly achieving a perfect accuracy score with AlexNet and XGBoost. These findings pave the way for more effective gunshot detection systems in a variety of operational scenarios, thereby significantly contributing to public safety measures.

关键词： Deep learning Gunshot detection systems Accuracy Signal processing algorithms Feature extraction Public security Real-time systems

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 << < 475 476 477 478 479 480 481 482 483 484 > >>

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：