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

100 篇 会议
22 篇 期刊文献

馆藏范围

122 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

52 篇 工学
- 36 篇 计算机科学与技术...
- 28 篇 软件工程
- 10 篇 信息与通信工程
- 10 篇 生物工程
- 9 篇 控制科学与工程
- 7 篇 电气工程
- 6 篇 安全科学与工程
- 4 篇 机械工程
- 4 篇 土木工程
- 4 篇 船舶与海洋工程
- 4 篇 环境科学与工程（可...
- 4 篇 生物医学工程（可授...
- 3 篇 光学工程
- 3 篇 动力工程及工程热...
- 3 篇 石油与天然气工程
30 篇 理学
- 11 篇 生物学
- 9 篇 数学
- 6 篇 统计学（可授理学、...
- 5 篇 物理学
- 4 篇 大气科学
- 4 篇 海洋科学
22 篇 管理学
- 13 篇 管理科学与工程(可...
- 7 篇 工商管理
- 7 篇 图书情报与档案管...
- 4 篇 公共管理
8 篇 医学
- 7 篇 基础医学(可授医学...
- 6 篇 公共卫生与预防医...
- 5 篇 临床医学
7 篇 法学
- 7 篇 社会学
5 篇 经济学
- 5 篇 应用经济学
3 篇 农学
2 篇 文学
1 篇 教育学

主题

9 篇 predictive model...
9 篇 accuracy
7 篇 real-time system...
7 篇 convolutional ne...
5 篇 deep learning
5 篇 data models
4 篇 computational mo...
4 篇 uncertainty
4 篇 technological in...
4 篇 measurement
4 篇 renewable energy...
3 篇 urban areas
3 篇 generative adver...
3 篇 transformers
3 篇 temperature dist...
3 篇 neural networks
3 篇 long short term ...
3 篇 reviews
3 篇 security
3 篇 standards

机构

5 篇 computer science...
4 篇 masters in compu...
3 篇 masters in infor...
3 篇 department of da...
3 篇 graduate doctora...
3 篇 computer science...
3 篇 masters in compu...
2 篇 department of ar...
2 篇 centre for cyber...
2 篇 masters program ...
2 篇 school of comput...
2 篇 the university o...
2 篇 department of el...
2 篇 department of co...
2 篇 masters in compu...
2 篇 senior software ...
2 篇 masters in compu...
2 篇 bachelors in ece...
2 篇 masters of compu...
2 篇 herbert wertheim...

作者

4 篇 shashishekhar ra...
4 篇 rony mohammad ab...
4 篇 saha pritom
4 篇 islam mohammad s...
4 篇 niharika karne
4 篇 ahammad mejbah
3 篇 aruna sri rongal...
3 篇 hole shreyas raj...
3 篇 kolluru vinothku...
3 篇 shreyas rajendra...
3 篇 chinna babu mupp...
3 篇 vinothkumar koll...
3 篇 sudeep mungara
3 篇 mounika nalluri
3 篇 mungara sudeep
2 篇 ramagundam shash...
2 篇 md saifur rahman
2 篇 a. bhuvanesh
2 篇 yagnesh challagu...
2 篇 neetu rani

语言

106 篇 英文
16 篇 其他

检索条件"机构=Masters of Science in Computer Science"

共 122 条记录，以下是61-70 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：

African Vultures Based Feature Selection with Multi-modal Deep Learning for Automatic Seizure Prediction

African Vultures Based Feature Selection with Multi-modal De...

引用

Distributed Computing and Optimization Techniques (ICDCOT), International Conference on

作者： Mounika Nallur Sandhya M Zabiha Khan Mohan B R C P Nayana S A Rajashekhar Software Engineer Masters in Computer Information Systems Murray State University USA Department of Computer Science and Engineering East West Institute of Technology Bengaluru India Department of Artificial Intelligence & Machine Learning Nitte Meenakshi Institute of Technology Bengaluru India

The superiority of life for people with epilepsy can be greatly improved with the assistance of accurate seizure prediction and early warning. An automatic prediction model is required to procedure the EEG signals and account for the leads optimization problematic, as opposed to the majority of hand-designed prediction approaches. In this research, we put forth a fully automated model for seizure prediction using Channel and Spatial attention (CASA). The first step in the feature extraction practice is to pre-process the raw EEG signals. Large amounts of computation can be saved by adding more features to the system, but finding the right ones can be tricky. The African vulture optimization algorithm's (AVOA) strong capacity to break out of local optima is what makes this procedure possible. CASA saved the raw EEG data's temporal and geographical details. Automatic optimization of EEG full-lead data was completed with channel attention (CA), leading to an increase in the accuracy of predictions. The aforementioned adaptive learning of feature parameters was accomplished via spatial attention (SA). When all else fails, a fully associated layer is used to make the seizure forecast. The suggested algorithm is tested on the Freiburg EEG database, and the results reveal that the AVOA-based system performs admirably when it comes to predicting seizures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Expression of Concern for: Analyzing the Impact of Deep Learning Approaches on Real-Time Data Analysis in Machine Learning

Expression of Concern for: Analyzing the Impact of Deep Lear...

引用

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Deepti Mounika Nalluri Chinna babu Mupparaju Aruna Sri Rongali Sohong Dhar P. Ajitha Sloan School of Management Sloan Fellow Candidate 2023 MIT Masters in Computer Information Systems Murray State University USA Masters in Computer Science university of central Missouri warrensburg USA Graduate Doctoral Information Technology/Graduate (Information Technology Emphasis/Information Technology Ph.D.) University of The Cumberlands US Azure Microsoft library & information science Jadavpur University India School of Computing Sathyabama Institute of science and technology Chennai

ISBN: (数字)9798350357769

ISBN: (纸本)9798350357776

Deep learning is a powerful subset of synthetic intelligence, and it has the potential to significantly enhance the skills of machine getting to know. it's miles primarily based on the idea of artificial neural networks, which might be laptop fashions that are capable of gaining knowledge of from records and making decisions, just like the manner a human mind works. Deep mastering isn't the same as traditional system mastering algorithms in that it can technique complex inputs with multiple layers of abstraction, main to greater accurate evaluation. Deep studying algorithms are capable of unexpectedly examine raw facts and generate styles, making them perfect for actual-time statistics analysis. Deep studying is capable of as it should be predicting behaviors and trends, which may be used to optimize procedures and enhance operational efficiencies. Deep studying models can also be used for automated fault detection and predictive renovation, permitting businesses to count on and prevent capacity troubles. Additionally, deep mastering models frequently offer quicker consequences than other device studying or conventional techniques, as well as permitting an extra diploma of control over the resolution of the data being analyzed. This has widespread implications for real-time programs, such as medical diagnostics, independent automobiles, and manufacturing monitoring.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Deep Learning Approaches on Real-Time Data Analysis in Machine Learning

Analyzing the Impact of Deep Learning Approaches on Real-Tim...

引用

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

关键词：

来源：评论

学校读者我要写书评

暂无评论

DeepDerm: Elevating Precision in Dermatological Diagnosis with Enhanced CNN

DeepDerm: Elevating Precision in Dermatological Diagnosis wi...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Monica R Mundada S Seema Sowmya B J Sonia Fathima Student Department of Masters of Compiuter Application Ramaiah Institute of Technology Banglore India Department of Computer Science and Engineering Ramaiah Institute of Technology Banglore India Department of Artificial Intelligence and Machine Learning Ramaiah Institute of Technology Banglore India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Since human skin illnesses are among the most common dermatological conditions worldwide, visual observations are usually the first step in the diagnosis process. Accurate classification of skin biopsies and scrapings requires dermoscopic analysis and clinical screening due to medical criteria. It gets more difficult to classify skin diseases using medical photographs because of the complex forms, wide range of colors, and data security issues. In this study, we offer a dependable approach for the classification of 20 distinct types of skin illnesses, based on an improved Convolutional Neural Network (CNN) model. Our enhanced CNN design exceeds the standard CNN, which only achieves an accuracy of 31.38%, with an astounding accuracy of 98.21%. The accuracy of two benchmark algorithms, AlexNet and VGG19, is also not particularly high (32.14% and 52.30%, respectively). In contrast to traditional CNN models the enhanced CNN performs better, demonstrating its efficacy and dependability in accurately identifying a wide range of skin disorders. including well-known architectures like AlexNet and VGG19. Positive implications of this discovery include the development of more precise diagnostic tools for dermatology.

关键词： Training Visualization Accuracy computer architecture Skin Classification algorithms Convolutional neural networks Medical diagnostic imaging Standards Diseases

来源：评论

学校读者我要写书评

暂无评论

An Investigation Method Incorporates with Contextual Information and Transformer Residual BiLSTM to Improve the Accuracy of Detecting Sensitive Content in Various Contexts

An Investigation Method Incorporates with Contextual Informa...

引用

International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)

作者： Niharika Karne Chandra Shekar Ramagundam Ranga Rao Patnala Shashishekhar Ramagundam Sai Nitisha Tadiboina Department of Electrical Engineering Masters in Electrical Engineering Sr. Principal Systems Engineer in C&RS Platform Services DT Amtrak University of South Alabama USA Senior Software Engineer in Cloud Platform Services City Of Philadelphia Pennsylvania USA Vice President US AL. Department of Computer Science Masters In Computer Science Software Development & Engineering in Content Discovery & AI Comcast Troy University Montgomery Campus USA Department of Information Technology GEICO - Chevy Chase MD United States

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376432

In the modern era, the internet is an emerging technology with a rapidly growing user. Sensitive content uploaders consider this platform as a way to transmit disturbing visual content, such as animated cartoon videos to circulate unsuitable content among youngsters. Previous researches show that the interaction of online sensitive information has substantial offline effects on historically impoverished communities. As a result, it is strongly recommended that social media platforms have an automatic real-time sensitive content filtering method for detecting contextual information. In this proposed model, a novel deep-learning framework is developed for detecting sensitive content from contextual information. For this, the suggested architecture performs under three stages (i) text collection, (ii) preprocessing, and (iii) detection. Initially, the required texts from the contextual information are gathered from the standard available data resource. The collected text is subjected to text preprocessing, where the text is cleaned and prepared for further analysis. Finally, in the detection phase, the developed Transformer Residual Bidirectional Long Short-Term Memory (TR-BiLSTM) is employed to learn the effective representation from the preprocessed text and perform the sensitive content detection. Furthermore, performance comparisons are carried out between the proposed frameworks with other standard approaches. The developed architecture achieved better results in detecting the sensitive content from the text.

关键词： Visualization Accuracy Recurrent neural networks Noise Transformers Real-time systems Long short term memory Standards Context modeling Videos

来源：评论

学校读者我要写书评

暂无评论

Investigating Neural Network-Based Deep Learning Strategies for Real-Time Data Analysis in Machine Learning

Investigating Neural Network-Based Deep Learning Strategies ...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Walke, Suchita Nalluri, Mounika Lavanya, R. Rongali, Aruna Sri Vanjari, Hrishikesh Bhanudas Ritu Pillai Collage of Engg and Technology Mumbai University Computer Engineering India Murray State University Masters in Computer Information Systems United States Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Ece India Graduate Doctoral Information Technology Information Technology Emphasis/Information Technology University of the Cumberlands United States BVCOE Lavale Sppu Pune E &tc Engineering Dept Maharashtra India Ambala Haryana Mullana India

ISBN: (纸本)9798350357769

there are numerous distinct strategies and techniques that fall under the huge class of neural network-primarily based deep gaining knowledge of in device getting to know. those strategies revolve around developing and schooling synthetic neural networks, that are computational models that mimic the capabilities and structure of the human brain, to analyze huge datasets and make predictions or decisions based totally on the *** of the key challenges in actual-time information analysis is being capable of method incoming information fast and efficiently, as well as adapt to converting data styles or sudden occasions. traditional device learning algorithms are frequently restricted in their ability to deal with these demanding situations, that is in which deep gaining knowledge of techniques are available *** getting to know techniques contain education neural networks with a couple of layers, every of which strategies one-of-a-kind aspects of the data. This lets in for greater complex and accurate evaluation of the facts, in addition to the potential to handle larger and more numerous datasets. One famous method in deep studying is known as convolutional neural networks (CNNs). Those networks are specifically properly-suitable for studying visual information, including snap shots, by means of breaking down the data into smaller parts and studying them at one of a kind ranges of abstraction. This permits for the identification of patterns and features in the data which could then be used for category or prediction responsibilities. © 2023 IEEE.

关键词： actual-time convolutional neural networks numerous prediction synthetic neural networks

来源：评论

学校读者我要写书评

暂无评论

Kullback–Leibler Divergence-Based Feature Selection Method for Image Texture Classification 5th

Kullback–Leibler Divergence-Based Feature Selection Method ...

引用

5th International Conference on computer and Communication Technologies, IC3T 2023

作者： Rao, M. Subba Devi, Guntoju Kalpana Mubeen, Suraya Prashanth, Badam Fatima, Tazzeen Madhavi, K. Reddy Kumar, Voruganti Naresh Chintalacheri, Charan Yadav Andhra Pradesh Rajampet516126 India Department of CSE CMR Technical Campus Telangana Hyderabad India Department of ECE CMR Technical Campus Telangana Hyderabad India CMR Technical Campus Telangana Hyderabad India Department of ECE Shadan Women’s College of Engineering and Technology Telangana Hyderabad India AI&ML School of Computing Mohan Babu University Tirupati India Masters in Computer Science University of Kansas Lawrence United States

ISBN: (纸本)9789819997039

Nowadays, with the Big Data phenomenon, the need of the usage of feature selection (FS) methods is critical. FS can assist to address photograph analysis, and in reality it has been gaining importance within a rapid few years ago, however also to relieve the computational burden required for extracting records from the snapshots. An exhaustive assessment and evaluation of the latest contributions of FS to the field of image analysis is necessary. By eliminating unimportant features from the original set, selection of features significantly enhances the efficiency of texture classification, which is a key factor in machine learning performance. By selecting a characteristic, one can achieve accuracy in database type while also accelerating the class rate. The primary goal of the endeavor is to choose the most substantial skills in the function set to carry out a particular undertaking. Kullback–Leibler (KL) divergence approach showed that accuracy in classification is proven with the use of the present methods when feature selection is applied to Feature extraction. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Forecasting of Photovoltaic Power with ARO based AI approach

Forecasting of Photovoltaic Power with ARO based AI approach

引用

Distributed Computing and Optimization Techniques (ICDCOT), International Conference on

作者： Mounika Nallur B M Nalini Zabiha Khan S Nayana Prasad N Achyutha G Manjula Masters in Computer Information Systems Murray State University USA Department of Computer Science and Engineering East West Institute of Technology Bengaluru India Department of Artificial Intelligence and Machine Learning Nitte Meenakshi Institute of Technology Bengaluru India Department of CSE BGS College of Engineering and Technology Bangalore India

Renewable power from sunlight can power the future smart grid with massive amounts of electricity. Systems struggle with solar energy's unpredictability and intermittent nature. Unpredictability of solar electricity hinders smart grid optimization and planning. Photovoltaic (PV) power generation must be accurately estimated to reduce power interruptions. PV power must be accurately predicted to avoid grid disturbances from PV facilities. Thus, we describe a transfer learning and AlexNet-based CNN architecture for short-term power forecasting. Past power, solar radiation, wind speed, and temperature readings determine the input. AlexNet's hyper-parameters are optimized using the artificial rabbit method. By adding selective opposition to ARO, local solution tracking efficiency is improved. CNN input features are created from all input parameters as 2D feature maps. After analyzing real PV data from Limberg, Belgium, the math shows that PV systems work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Virtual Mouse Using Face Gesture and NLP

Virtual Mouse Using Face Gesture and NLP

引用

North Karnataka Subsection Flagship International Conference (NKCon), IEEE

作者： Ajay Zad Jagannatha S Manish Kumar S Ajitha Prakash B R Department of Masters of Computer Applications M S Ramaiah Institute of Technology Bangalore India Department of Computer Applications East Point College of Engineering Bangalore India Department of Master of Computer Applications M S Ramaiah Institute of Technology Bangalore India Department of Computer Science Government First Grade College Tumkur Karnataka India

The mouse plays a very important role in interacting with laptop’s and computer system, to perform necessary operations. In this paper, we are proposing a method to carry out mouse operations on the computer system without a physical mouse by utilizing voice commands and face-motion gestures. The system employs an internal webcam to detect facial gestures and an internal microphone to receive voice commands from the user. By employing a virtual mouse based on face gestures and natural language processing (NLP), we can accomplish all the fundamental functionalities of a mouse by issuing voice commands to the computer system. The system accepts these commands and executes corresponding mouse events such as "click," "right-click," "double-click," "scroll-up," "scroll-down," "minimize," and "close." The mobility of the mouse cursor on the monitor is achieved through face motion gestures, enabling the cursor to move up, down, left, and right, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study of Methods for Forecasting Wind Power Generation Based on the Processing of Meteorological Data

Study of Methods for Forecasting Wind Power Generation Based...

引用

Dynamics of Systems, Mechanisms and Machines (Dynamics)

作者： A. Gorshenin D. Vasina Department of information technology and computer science Omsk State Technical University Omsk Russia Department of Elite Education and Masters Omsk State Technical University Omsk Russia

ISBN: (纸本)9781665465281

A study of the characteristics of wind farms was carried out in order to determine methods suitable for forecasting. The methods of polynomial regression and the method based on an artificial neural network are considered. The value of the data volume for the forecast with the required accuracy is obtained. Graphs were obtained that showed the dependencies, according to which a hypothesis was put forward about the possibility of forecasting the generation of electricity from a wind farm according to weather conditions. The expediency of the method of polynomial regression for building simulation models is revealed. Mathematical models of polynomial regression are constructed. The method based on an artificial neural network is more suitable for developing forecasting algorithms.

关键词： Renewable energy sources Temperature distribution Heuristic algorithms Wind speed Artificial neural networks Wind farms Wind power generation

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13页 << < 3 4 5 6 7 8 9 10 11 12 > >>

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：