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

1,092 篇 会议
15 篇 期刊文献
14 册 图书

馆藏范围

1,121 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

819 篇 工学
- 731 篇 计算机科学与技术...
- 613 篇 软件工程
- 197 篇 信息与通信工程
- 163 篇 生物工程
- 95 篇 生物医学工程（可授...
- 86 篇 控制科学与工程
- 63 篇 电气工程
- 62 篇 安全科学与工程
- 58 篇 动力工程及工程热...
- 51 篇 光学工程
- 46 篇 机械工程
- 40 篇 交通运输工程
- 38 篇 化学工程与技术
- 31 篇 仪器科学与技术
- 31 篇 电子科学与技术（可...
409 篇 理学
- 196 篇 数学
- 177 篇 生物学
- 83 篇 统计学（可授理学、...
- 71 篇 物理学
- 58 篇 系统科学
- 43 篇 化学
253 篇 管理学
- 151 篇 图书情报与档案管...
- 128 篇 管理科学与工程(可...
- 81 篇 工商管理
99 篇 医学
- 93 篇 临床医学
- 91 篇 基础医学(可授医学...
- 62 篇 药学(可授医学、理...
- 43 篇 公共卫生与预防医...
70 篇 法学
- 50 篇 社会学
33 篇 经济学
- 33 篇 应用经济学
30 篇 农学
23 篇 教育学
5 篇 军事学

主题

53 篇 computational mo...
45 篇 big data
44 篇 machine learning
38 篇 deep learning
38 篇 cloud computing
35 篇 predictive model...
31 篇 feature extracti...
28 篇 machine learning...
26 篇 internet of thin...
25 篇 neural networks
24 篇 data mining
23 篇 blockchain
23 篇 data models
22 篇 support vector m...
21 篇 forecasting
21 篇 training
20 篇 covid-19
20 篇 sentiment analys...
17 篇 technological in...
15 篇 object detection

机构

13 篇 teerthanker maha...
11 篇 jain university ...
9 篇 school of comput...
6 篇 galgotias univer...
4 篇 galgotias univer...
4 篇 department of in...
4 篇 kite group of in...
4 篇 department of co...
4 篇 chandigarh unive...
4 篇 department of ne...
4 篇 school of cyber ...
4 篇 department of co...
4 篇 department of co...
4 篇 college of compu...
3 篇 college of compu...
3 篇 university of en...
3 篇 department of co...
3 篇 china academy of...
3 篇 christ universit...
3 篇 institute of art...

作者

6 篇 jacob lija
6 篇 n. suresh kumar
6 篇 joshi kapil
6 篇 lija jacob
5 篇 vishal bharti
5 篇 aruna bhat
5 篇 bhat aruna
5 篇 naohiro ishii
4 篇 li yang
4 篇 annamalai suresh
4 篇 sharma vishnu
4 篇 ippei torii
4 篇 s. vijayalakshmi
4 篇 vishnu sharma
4 篇 wang tao
4 篇 bharti vishal
4 篇 malik aruna
4 篇 gupta gaurav
4 篇 vijayalakshmi s.
4 篇 li wei

语言

1,111 篇 英文
10 篇 其他
1 篇 中文

检索条件"任意字段=4th International Conference on Computing and Data Science, CONF-CDS 2022"

共 1121 条记录，以下是901-910 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：

Automatic Detection of Rice Diseases using Deep Convolutional Neural Networks with SGD and ADAM

Automatic Detection of Rice Diseases using Deep Convolutiona...

引用

Advances in computing, Communication Control and Networking (ICAC3N), international conference on

作者： Pardeep Seelwal Alok Sharma Department of Computer Science and Applications Baba Mastnath University Rohtak India

Rice diseases are the major problem in all over the world of agriculture sector. the early detection of this disease will prevent the huge economic loss for the farmer. this paper proposes a deep learning algorithm to classify the disease in the rice plant. Images of healthy and blast disease affected leaves are taken for the proposed system. the features are extracted for the healthy and brown spot, leaf blast, hispa disease of the rice leaf. the total data set is divided for training and testing purposes. these images are processed with the proposed multi-classification method and the leaf is categorized into brown spot, leaf blast, hispa disease and healthy. In this work CNN model is employed using two different optimizers i.e. SGD and ADAM. It is found that SGD performed well as compared to ADAM for our application as the training accuracy is obtained from proposed model with ADAM optimizer is 92.04 % while with SGD produced the training accuracy 96.32 %.the proposed model capable of getting promising accuracy for healthy and brown spot, leaf blast, hispa disease of the rice using multi-classification model.

关键词： Training Deep learning Economics Computational modeling Feature extraction data models Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Home Automation & Application with Bolt IoT

Home Automation & Application with Bolt IoT

引用

Advances in computing, Communication Control and Networking (ICAC3N), international conference on

作者： Ashish Sudhir Kakne P. M. Chouragade Computer Science & Engineering Government College of Engineering Amravati Maharashtra India

As communications technology has developed, home automation and applications have gained a lot of interest. Due to the importance of the internet in today’s digital world, techniques for protecting data from third parties who can only interact wirelessly must be developed. this system provides guidance for doing operational activities, in particular for monitoring locations and their structures, as well as for controlling assets online using a web application and an IoT approach. Home automation is a crucial component that has to adhere to strict criteria for graphical interface and stability. the Bolt IoT platform, a home automation system that permits remote wireless access to and administration of home devices, is really the foundation around which the whole process is constructed. this system may control a number of gadgets, such as LEDs, fans, and DC motors, as well as the temperature of the surrounding area. the Bolt IoT module also provides connectivity to the cloud for the whole system and sends sensor data there. A temperature sensor might be used to gauge the room’s temperature. this all-encompassing strategy permits the adoption of an effective, long-lasting IoT-based approach system that has a user-friendly interface that can be utilized on both PCs and smartphones.

关键词： Temperature sensors Wireless communication Wireless sensor networks Home automation Stability criteria Fasteners Temperature control

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Smart Home System Based on STM32

Design and Implementation of Smart Home System Based on STM3...

引用

science and Technology Innovation (IAECST), international Academic Exchange conference on

作者： Mi - Liu Yubo-Zhang Zhentao-Shi Zhengzhou Business University Zhengzhou China Suzhou Babayi Intelligent Technology Co. Ltd Jiangsu China Nanjing Hengtian Lingrui Automobile Co. Ltd Jiangsu China

With the rapid development of Internet communication and Electronic science and technology, people’s life style has also undergone earth shaking changes. With the development of science and technology, the products of the new era play an important role in people’s life. Smart home related industries have also developed rapidly, providing people with a more comfortable daily life. the smart home system of this design adopts STM32 Series MCU. With the help of smoke gas sensor, light intensity sensor, temperature and humidity sensor, etc., the data detected by the sensor is sent to STM32 microprocessor for analysis, and the received data is sent to Alibaba Intelligent Cloud Internet of things service through EPS 8266 WiFi chip. the control part sends the data to EPS8266 through Alibaba cloud through the web interface, then send instructions to the STM32 microprocessor to control the curtains, lights, plugins, etc. through the detection of various parameters in the indoor environment and the control of equipment in the home, not only security and remote control are realized, but also intelligent control can be carried out according to the conditions of the indoor environment.

关键词： Temperature sensors Cloud computing Temperature distribution Technological innovation Microprocessors Smart homes Indoor environment

来源：评论

学校读者我要写书评

暂无评论

Investigation of Routing Techniques to Develop a Model for Software-Defined Networks using Border Gateway Protocol

Investigation of Routing Techniques to Develop a Model for S...

引用

Advancements in computing (ICAC), international conference on

作者： Banuka Dayapala Vigneshwaran Palanisamy Satkunarajah Suthaharan Department of ICT University of Vavuniya Sri Lanka Department of Computing and Information Systems Sabaragamuwa University of Sri Lanka. Sri Lanka Department of Physical Science University of Vavuniya Sri Lanka

ISBN: (纸本)9798350398106

Software-Defined Network (SDN) is a networking opportunity that brings together all control functions in one place and changes traditional network architecture by making centralized decisions. In SDN architecture, controllers perform control decision-making functions when directing packets. Unlike traditional routing protocols, efficient r outing protocols are required for efficient data center infrastructure services. the separation of the network data plane from the network control plane is advocated by SDN in a networking design concept. Traditional networks mix data and control planes on the same device and forcing each device to make its own routing decisions based on distributed routing protocols. In this paper, we develop Microsoft Azure Software Defined-Wide Area Networks (SD-WAN) with the concept of HUB-SPOKE to show how the controller’s centralized decision-making capability changes network architecture with network flexibility and programming capability by taking the SPOKE network. this research also focuses on the key status of controllers used in the network industry. Further, we analyze the performance of SD-WAN routing against conventional routing with respect to routing convergence time and address how much efficient SDN routing rather than the conventional routing in various network topology using real-time SD-WAN on corporate environment of Microsoft Azure Cloud Tenant.

关键词： data centers Decision making Network architecture Routing Routing protocols Software Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Hybrid model for detection of frauds in credit cards*

Hybrid model for detection of frauds in credit cards*

引用

Advances in computing, Communication Control and Networking (ICAC3N), international conference on

作者： Divya Sharma Sandeep Singh Kang Department of Computer Science & Engg Chandigarh University Mohali India

the goal of this study is to decide on the correct model that can predict a credit card holder’s likelihood of missing their next payment based on their demographic characteristics and payment history. Our goal is to reduce the number of defaulters that are labelled as non-defaulters. that’s because our company can afford to have non-defaulters who do default but not non-defaulters who do not default, as it is implied that the bank has a stringent no-NPA policy (more or less). When putting machine learning algorithms into practice, supervised learning must be used since we have known upstream and downstream values and anticipate a prediction model at the conclusion. the correlation amid attributes and target sets is established in the first stage. Classification stage classifies input data into certain categories. In order to examine the performance of recommended approach, the comparison of recommended approach and other available approaches has been conducted in this work along with this achieving the 85% accuracy *** accurately categorizing credit card delinquencies and non-defaulters, the mortgage lenders will be able to utilize the accuracy of the model to lower the high delinquent rate.

关键词： Loans and mortgages Machine learning algorithms Computational modeling Supervised learning Predictive models Credit cards Fraud

来源：评论

学校读者我要写书评

暂无评论

Handwritten Digit Recognition using Ensemble learning techniques: A Comparative performance Analysis

Handwritten Digit Recognition using Ensemble learning techni...

引用

Advances in computing, Communication Control and Networking (ICAC3N), international conference on

作者： Saima Afreen Pradeep Kumar Department of Computer Science and Information Technology Maulana Azad National Urdu University Hyderabad India

the detection of some digits written by humans may seem very easy; however, in reality, it is a very challenging and tedious task to extract text from real images because of the wide variety of font sizes, shapes, textures and backgrounds, etc. this study aimed to recognize handwritten digit images by extracting the features from datasets. then theses learned characteristics are subsequently submitted to the classifier to improve the overall performance. the Bagging and boosting techniques of ensemble learning were performed by integrating different base models. Each single base model corrected the errors of the previous model. Six bagging and boosting ensemble learning algorithms were used to recognize the handwritten digit images. therefore, with 98% of accuracy, the extreme gradient boosting machine outperformed the other methods in terms of overall performance. A detailed analysis of the allocation of data among the base learners and their overall performance, including the model correctness, computation time, and error rate, was evaluated and projected.

关键词： Handwriting recognition Image recognition Error analysis Text recognition Shape Boosting Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Novel Double-threshold Neural Classifier for Non-Linearly Separable Applications

A Novel Double-Threshold Neural Classifier for Non-Linearly ...

引用

Advances in computing, Communication Control and Networking (ICAC3N), international conference on

作者： Mohd. Kashif Syed Atiqur Rahman Mohammad Samar Ansari Department of Electronics Engineering Aligarh Muslim University India Faculty of Science and Engineering University of Chester United Kingdom

Classification of data finds applications in various engineering and scientific problems. When real-time operation is desired, hardware solutions tend to be more amenable as compared to algorithmic/heuristic solutions. this paper presents a novel current-mode dual-threshold neuron designed and implemented at 32nm CMOS technology node. Subsequently, a current-mode double-threshold classifier is presented which is capable of classifying input patterns of non-linearly separable problems. thereafter, application of the current-mode dual-threshold neuron in the realization of the XOR function using only a single neural unit is discussed. the proposed neuron as well as both the applications discussed are capable of operating from sub-1V power supplies. Computer simulations using HSPICE yield promising results with the values of delay and power consumption estimated to be lower than existing circuits.

关键词： Power demand Computer simulation Neurons CMOS technology Real-time systems Hardware Delays

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of SVM kernel for YOUTUBE Comment Filtering

Effectiveness of SVM kernel for YOUTUBE Comment Filtering

引用

Advances in computing, Communication Control and Networking (ICAC3N), international conference on

作者： Shailender Kumar Shweta Gupta Department of Computer Science & Engineering Delhi Technological University Delhi India

the impact of Social networking platform is evident in each generation and almost all fields. It made many tasks more convenient that was not possible earlier. YouTube is one such platform. It can be utilized as a source of entertainment, discussion portal, information sharing, knowledge gathering. Various newborn and popularly known organizations display their advertisements over the platform as short video or links in comment section that help content creators of the video through some financial gains. these advertisements can be greatly helpful to visitors and firm. Also the comment section may contain some cogitative discussions. With all such activities found on the platform some spiteful ones are also lurking over it. Spammers used to suffuse malicious links and data over the platform. In this study, we directed towards the comment section of the platform and executed a comparative analysis of different SVM kernels for the classification of Spam or ham comments over the YouTube application. We also studied the impact of feature extraction incorporating two feature extraction techniques Tf-Idf and BOW.

关键词： Support vector machines Video on demand Filtering Social networking (online) Computational modeling Unsolicited e-mail Standards organizations

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Compound TCP with Various End-to-End Congestion Control Mechanisms

Comparative Analysis of Compound TCP with Various End-to-End...

引用

Advances in computing, Communication Control and Networking (ICAC3N), international conference on

作者： Subhra Priyadarshini Biswal Sheshank Gupta Arun Kumar Sanjeev Patel Department of Computer Science and Engineering National Institute of Technology Rourkela Odisha India

Congestion control is a fundamental mechanism offered by the Transmission Control Protocol (TCP) to make sure stable data flow and efficient bandwidth allocations in the network. It mainly focuses on the adjustment of the incoming sending rate with respect to the receiving rate. the reliable TCP helps to manage the transmission rate by avoiding the state of network congestion. In recent years, different variants of TCP congestion control protocols have been proposed to enhance TCP reliability and performance under different network scenarios. Moreover, it is associated with several types of network states such as latency, throughput, and packet loss. In this paper, we have performed a comparative study on the performance analysis of various TCP congestion control protocols on NS2 simulator. the results show that CUBIC gives the highest average throughput, Vegas gives the lowest packet loss ratio, and Veno gives the lowest average end-to-end delay among other TCP congestion control techniques that are considered in this paper.

关键词： Wireless communication Protocols Packet loss Channel allocation throughput Delays Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Accuracy of Supervised Learning Classifier for breast cancer classification

Comparative Analysis of Accuracy of Supervised Learning Clas...

引用

Advances in computing, Communication Control and Networking (ICAC3N), international conference on

作者： Vrinda Sachdeva Vasudha Arora Department of Computer Science Engineering ITS Engineering College Greater Noida Uttar Pradesh India

Breast Cancer is widely spreading disease among women all over the world. this cancer is considered as one of the deadly disease among women. data mining algorithms play a vital role to predict the early stage cancer .the research problem is that there are lots of classifier with different level of accuracy. An approach for improving the performance and accuracy of three different classifiers, Decision Tree, Logistic Regression, and SVM, is proposed in this study. We also compare the classifier on Wisconsin breast cancer dataset. Accuracy of classifier depends on the shape of data. Imbalanced data is a big problem for the classification phase. Each classifier's efficiency is accessed in terms of confusion matrix accuracy, AUC, and *** are five sections to this study. First, we'll load the dataset and applied correlation to remove some features. For scaling and to filter data, preprocessing algorithm is applied then dataset is splited into training and testing data set and then applied CART algorithms for classification purpose. then generate some graph to visualize the data. Based on the WBC dataset using Jupyter notebook software, the goal of this paper is to discover the most accurate classifier. the results have been compared with the results of previous papers and reveal that they are extremely precise. the SVM classifier model was discovered to be the best classifier of all the types. It also removes the over fitting of data.

关键词： Support vector machines Training Shape Software algorithms Supervised learning Prediction algorithms Breast cancer

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113页 << < 87 88 89 90 91 92 93 94 95 96 > >>

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：