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

1,859 篇 会议
6 册 图书
1 篇 期刊文献

馆藏范围

1,866 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,367 篇 工学
- 1,251 篇 计算机科学与技术...
- 999 篇 软件工程
- 317 篇 生物工程
- 314 篇 信息与通信工程
- 189 篇 生物医学工程（可授...
- 164 篇 控制科学与工程
- 125 篇 电气工程
- 118 篇 光学工程
- 83 篇 机械工程
- 74 篇 化学工程与技术
- 66 篇 网络空间安全
- 64 篇 安全科学与工程
- 53 篇 电子科学与技术（可...
- 48 篇 仪器科学与技术
751 篇 理学
- 395 篇 数学
- 325 篇 生物学
- 166 篇 统计学（可授理学、...
- 150 篇 物理学
- 134 篇 系统科学
- 83 篇 化学
442 篇 管理学
- 249 篇 管理科学与工程(可...
- 227 篇 图书情报与档案管...
- 128 篇 工商管理
177 篇 医学
- 165 篇 临床医学
- 158 篇 基础医学(可授医学...
- 117 篇 药学(可授医学、理...
- 65 篇 公共卫生与预防医...
79 篇 教育学
- 79 篇 教育学
74 篇 法学
- 67 篇 社会学
50 篇 农学
- 49 篇 作物学
45 篇 经济学
4 篇 军事学

主题

328 篇 machine learning
128 篇 deep learning
77 篇 support vector m...
66 篇 machine learning...
55 篇 forecasting
47 篇 feature extracti...
37 篇 decision trees
37 篇 accuracy
35 篇 computational mo...
34 篇 computer vision
31 篇 predictive model...
30 篇 training
29 篇 data mining
28 篇 students
28 篇 convolutional ne...
26 篇 neural networks
22 篇 object detection
22 篇 artificial intel...
21 篇 sentiment analys...
20 篇 internet of thin...

机构

12 篇 chitkara univers...
7 篇 shenyang ligong ...
6 篇 uttaranchal inst...
5 篇 department of co...
5 篇 maharishi school...
5 篇 alibaba cloud bi...
4 篇 school of comput...
4 篇 college of compu...
4 篇 key laboratory o...
4 篇 lovely professio...
4 篇 jilin agricultur...
4 篇 uttaranchal univ...
4 篇 key laboratory o...
4 篇 department of co...
4 篇 master of comput...
4 篇 school of inform...
3 篇 school of comput...
3 篇 vivekananda glob...
3 篇 department of el...
3 篇 college of compu...

作者

4 篇 liu gang
4 篇 kumar rakesh
4 篇 waseemullah
4 篇 liu peng
3 篇 zhang tao
3 篇 kumar ajay
3 篇 rakesh kumar
3 篇 babu tina
3 篇 siddhant
3 篇 sharma arun
3 篇 faisal rehman
3 篇 wang xiaofei
3 篇 sharif hanan
3 篇 singh sunil kuma...
3 篇 rehman faisal
3 篇 tina babu
3 篇 yang wei
3 篇 sharma avinash
3 篇 prajwal
3 篇 vinay kukreja

语言

1,802 篇 英文
62 篇 其他
15 篇 中文

检索条件"任意字段=3rd International Conference on Machine Learning and Computer Application, ICMLCA 2022"

共 1866 条记录，以下是1811-1820 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：

An Item-Based Efficient Algorithm of learning from Examples

An Item-Based Efficient Algorithm of Learning from Examples

引用

2010 The 3rd international conference on Computational Intelligence and Industrial application (PACIIA2010)

作者： Yuan Lin and Ruiping Geng Department of Compute Scineceand Technology,College of Information Engineering Minzu University of China Beijing,100081,China

This paper presents a novel algorithm of learning from examples based on items,while the traditional algorithms could be considered as *** deference is that,though both use frequency matrixes as main heuristic information,the traditional algorithm obtain the matrixes through the line-by-line scanning of examples,while the presented algorithm through scanning of items and then carrying out some calculations according to some laws found by the author in examples *** a item may contains a lot of examples and the cost of scanning of a example is as the same as of scanning of a item,the presented algorithm possesses great ability to be able to handle those learning tasks with great number of examples,many variables and assignments,while the traditional algorithms could not treats with those tasks.

关键词： machine learning,learning from example,frequency matrix,item based,new laws in examples space

来源：评论

学校读者我要写书评

暂无评论

Resilient machine learning (rML) Ensemble Against Adversarial machine learning Attacks 3rd

Resilient Machine Learning (rML) Ensemble Against Adversaria...

引用

3rd international conference on Dynamic Data Driven application Systems, DDDAS 2020

作者： Yao, Likai Tunc, Cihan Satam, Pratik Hariri, Salim NSF Center for Cloud and Autonomic Computing University of Arizona Tucson United States Department of Computer Science and Engineering The University of North Texas DentonTX United States

ISBN: (纸本)9783030617240

machine learning (ML) algorithms have been widely used in many critical applications, including Dynamic Data Driven applications Systems (DDDAS) applications, automated financial trading applications, autonomous vehicles, and intrusion detection systems for the decision-making process of users or automated systems. However, malicious adversaries have strong interests in manipulation the operations of machine learning algorithms to achieve their objectives in gaining financially, injecting injury or disasters. Adversaries against ML can be classified based on their capabilities and goals into two types: Adversary who has full knowledge of the ML models and parameters (white-box scenario) and one that does not have any knowledge and use guessing techniques to figure out the ML model and its parameters (black-box scenario). In both scenarios, the adversaries will attempt to maliciously manipulate model either during training or testing. Defending against these attacks can be successful by following three methods: 1) making the ML model robust to adversary, 2) validating and verifying input, or 3) changing ML architecture. In this paper, we present a resilient machine learning (rML) ensemble against adversarial attacks by dynamically changing the ML architecture and the ML models to be used such that the adversaries have no knowledge about the current ML model being used and consequently stop their attempt to manipulate the ML operations at testing phase. We evaluate the effectiveness of our rML ensemble using the benchmarking, zero-query dataset "DAmageNet" that contains both clean and adversarial image samples. We use three main neural networks in our ensemble that includes VGG16, ResNet-50, and ResNet-101. The experimental results show that our rML can tolerate the adversarial samples and achieve high classification accuracy with small execution time degradation. © 2020, Springer Nature Switzerland AG.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Examining Social Media Posts for Identification of Anxiety and Depression Utilizing machine learning Techniques

Examining Social Media Posts for Identification of Anxiety a...

引用

Technological Advancements in Computational Sciences (ICTACS), international conference on

作者： Babasaheb S. Satpute Wasudeo P. Rahane Rajesh Bharati Dept. of Computer Science and Engg. School of Engg. & Technology JAIN (Deemed to be University) Bangalore India Dept. of Information Technology STES's NBN Sinhgad School of Engg. Pune India Dept. of Computer Engg. Dr. D.Y. Patil Institute of Technology Pune India

The prevalence of mental diseases like depression and anxiety among students has become a growing concern in recent years. With the widespread use of social media platforms, individuals often express their emotions, thoughts, and experiences through posts and interactions. This paper investigates the feasibility of classifying students' anxiety and depression based on the content of their social media posts. Recently, some research communities in various domains have shown enthusiasm for investigating the potential of leveraging social media platforms for extracting valuable insights for decision-making and creative knowledge. Social media has been utilized to aid software development activities, analyze cryptocurrency trends, identify network communities, and make recommendations, among others. Apart from other fields within the eHealth domain, the application of social media platforms and the sophisticated analysis of extensive datasets to anticipate mental health disorders like depression, schizophrenia, eating disorders, anxiety, and addictive tendencies has garnered substantial attention and interest. However, one of the challenges lies in either having enough historical data or regular monitoring of a patient's activities to identify a person's mental health condition using traditional methods. To tackle this concern, we introduce an approach aimed at categorizing individuals with past mental health conditions through the utilization of information sourced from a widely-used social media platform such as Facebook.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Modular Information Fusion Model of Landscape Based on machine learning Algorithm 2021

The Modular Information Fusion Model of Landscape Based on M...

引用

2021 3rd international conference on Artificial Intelligence and Advanced Manufacture

作者： Qiong Zeng Jianqiong Xu Jing Chen Guangzhou Huali College China

ISBN: (纸本)9781450385046

With the development of the times, we can obviously find that after a new round of scientific and technological revolution, the quality of life of modern life compared with the previous significant changes, a variety of high-tech is used in real life, housing, education, travel and other aspects of a new round of revolution. In this, our main research is about landscape and other architectural landscape model on the computer model optimization, the purpose of this paper is to use machine learning algorithms to the landscape modular information fusion model research. Based on the systematic hand-drawn models identified by numerous experiences, and the various new technologies that have emerged with the rapid development of modern computer technology, we can more fully determine the structure of the landscape and display it better on the computer. Therefore, after a period of simulation exercises, we found that various algorithms can be used to study the modular information of landscape fusion model. Because machine learning algorithms can naturally learn about information and identify their main points compared to other algorithms, we finally chose this algorithm as an experimental algorithm. Experimental results show that the algorithm can be used to carry out some experimental simulation to better integrate the modular information of landscape, so that the model as a whole is more fluid and natural.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Natural Scene Text Recognition System Based on Deep learning 2021

Design and Implementation of Natural Scene Text Recognition ...

引用

2021 3rd international conference on Artificial Intelligence and Advanced Manufacture

作者： Feilong Liang Tencent Music Entertainment Group China

ISBN: (纸本)9781450385046

With the popularization and rapid development of information technology such as modern multimedia and mobile Internet, people have more and more ways to obtain natural landscape images. How to collect and extract necessary information from rich images becomes more and more important. With the current popularization and development of technologies such as artificial intelligence and deep machine learning, the application requirements for effectively obtaining text resources are also expanding rapidly. This paper aims to study the design and implementation of a natural scene text recognition system based on deep learning. Based on the analysis of system functional requirements, system non-functional requirements and text detection methods, each functional module of the system is designed in detail, and finally in SVT. The performance of the algorithm in this article is analyzed on the public data set, and the test results are compared with the existing algorithms. The test results show that the method and recognition results used in this paper are significantly higher than other methods, and the text recognition results have reached a very high accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of machine Translation Quality Based on Neural Network and Its application on Foreign Language Education 2021

Evaluation of Machine Translation Quality Based on Neural Ne...

引用

2021 3rd international conference on Artificial Intelligence and Advanced Manufacture

作者： Xinyu He Yunnan Technology and Business University China

ISBN: (纸本)9781450385046

The form of communication at home and abroad requires translators to constantly develop new professional skills and language skills to meet the needs of translation, At present, neural network translation has become the mainstream of machine translation technology. Based on this, this paper analyzes the quality of machine translation based on neural network and its impact on foreign language education. Through the combination of questionnaire survey and experimental comparison, this paper studies the use and response of machine translation in students' daily learning through questionnaire survey the differences between traditional machine translation and neural network-based machine translation are analyzed based on the combination of questionnaire and experiment. From the data analysis, we can see that the accuracy and efficiency of neural network machine translation are improved. When the vocabulary is 500, the accuracy is increased by 8%, when the time is increased by 1 s, when the vocabulary is 1000, the accuracy is increased by 11%, when the time is increased by 2.3S, 1500 words The accuracy of convergence time increased by 9%, the time increased by 3.4s, the accuracy of 2000 vocabulary increased by 9%, and the time increased by 4.5s.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Effective Stock Market Prediction using an Advanced machine learning Algorithm and Emotional Analysis

An Effective Stock Market Prediction using an Advanced Machi...

引用

Applied Artificial Intelligence and Computing (ICAAIC), international conference on

作者： Thejaswini Kishore J. Praveenchandar Division of Computer Science and Technology Karunya Institute of Technology and Sciences Karunya Nagar Coimbatore Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Karunya Nagar Coimbatore

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

The structure of the stock exchange is complex, dynamic, and difficult to predict. Emotional analysis and machine learning have increased forecast accuracy. The implementation of sentiment detection and machine learning to stock exchange forecasts will be examined in this study. We’ll also talk about creating a web application which utilizes the most of these technologies to give users access to real-time stock exchange estimates. Sentiment analysis is a technique for analyzing the emotional undertones of texts. Sentiment analysis is a stock exchange prediction tool that uses an examination of social media writes, reports, and other sources of information to ascertain the general sentiment of investors. With the use of emotional analysis algorithms, future stock prices for the following seven days can be predicted, and recommendations for price increases or decreases can be made. Utilizing the anticipated value from the three algorithms–-ARIMA, LSTM, and Linear Regression–-this forecast is made. The AutoRegressive Integrated Moving Average, or AriMA-like, technique is employed in time series prediction and defines the next step as a linear function of the difference between observations and errors. A particular type of recurrent neural network architecture called Long Short-Term Memory, or LSTM, is perfect for categorizing, assessing, and forecasting time series with irregular gaps between important occurrences. One of the best ways for rdNs to learn is through experience. On the contrary, linear regression fits a linear equation to observed data in order to illustrate the relationship amongst one or more independent factors and a dependent variable. It evaluates several variables, including volume, adj close, high, low, date, open, and close

关键词： Sentiment analysis Accuracy Social networking (online) Time series analysis machine learning Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Expression of Concern for: Prediction of Heart attack using Supervised machine learning Technique

Expression of Concern for: Prediction of Heart attack using ...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 international conference on

作者： Rubesh S Rajkumar Rajkumar S. Prayla Shyry J Albert Mayan Y Bevish Jinila Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9781665479714

ISBN: (纸本)9781665479721

Heart is the fundamental organ that siphons blood to the body and for appropriate working of body. Coronary illness is a lethal human infection expanding all around the world in both created and lacking nations and thusly, causes passing. Ordinarily, in this sickness, the heart neglects to supply an adequate measure of blood to different pieces of the body to achieve their ordinary functionalities. Many risk factors for coronary disease and the need for accurate, reliable, and acceptable approaches to manage the condition are connected together in this situation. Medical professionals may better predict coronary heart disease with the use of information mining and artificial intelligence (AI) tools developed by scientists. The suggested approach is to construct an AI model capable of classifying whether or not a certain person has coronary artery disease. Various calculations are pondered and the best model is utilized for anticipating the result.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Medical Recommendation System using machine learning Techniques & Natural Language Processing

Automated Medical Recommendation System using Machine Learni...

引用

Communication, Computing and Industry 4.0 (C2I4), international conference on

作者： Likith V P M. Farida Begam Magadum Neeraj Shashikant Department of Information Science and Engineering CMR Institute of Technology Bengaluru India

ISBN: (数字)9781665474979

ISBN: (纸本)9781665474986

The suggested work in this paper relates to the automation in the medical field in terms of how the diagnosis of irregularities has been going on in the industry and what the future in the said field looks like with the advancing technology. With the advent of application of machine learning approaches, we have observed a significant rise in the performance of detection and prediction with each passing year. With the current norms being that a patient is to perform the necessary tests and wait for a significant period of time to gain a consultation with an esteemed doctor. The methodologies used by other authors from the research papers that we gathered were either using image corpus or using machine learning techniques to detect and identify cancer, while others have used Natural Language Processing techniques to extract information from handwritten or printed texts and have developed models based on it. We have addressed the problem with a unified approach that combines both machine learning and Natural Language Processing techniques in tandem to extract data and correlations which may have been ignored by the other models. The image corpus and handwritten notes would together give better insights and help improve the accuracy of the model. Bearing in mind the objective of relieving novice doctors from feeling perplexed, in addition to answering questions that patients might have, our model aims to allow such medical professionals make better informed decisions in their diagnosis and prognosis procedures. The chatbot, to serve this purpose, will be based on Bidirectional Encoder Representations from Transformers (BERT), which has demonstrated ground-breaking performance in tasks involving natural language understanding, including sentiment analysis, semantic role labelling, sentence classification, and the disambiguation of polysemous words. We aim to not only successfully diagnose and provide prognosis for cancer, but also to detect the chances of remission. Our

关键词： Object oriented modeling Semantics machine learning Medical services Feature extraction Transformers Data mining

来源：评论

学校读者我要写书评

暂无评论

Expression of Concern for: Ensemble machine learning (Grid Search & Random Forest) based Enhanced Medical Expert Recommendation System for Diabetes Mellitus Prediction

Expression of Concern for: Ensemble Machine Learning (Grid S...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 international conference on

作者： Nagaraj P Muneeswaran V Muthamil Sudar K Naga Vardhan Reddy A Deshik G Charan Kumar Reddy C Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Virudhunagar India Department of Electronics and Engineering Kalasalingam Academy of Research and Education Virudhunagar India

"Araetus" was the person who coined the term "Diabetes" and later on the word "mellitus" which means honey-sweet was added to it by Thomas Willis in the year 1675 after noticing the sweet...

ISBN: (数字)9781665479714

ISBN: (纸本)9781665479721

"Araetus" was the person who coined the term "Diabetes" and later on the word "mellitus" which means honey-sweet was added to it by Thomas Willis in the year 1675 after noticing the sweet nature of the blood and urine of the patients. Currently, it is one of the most developing lethal maladies throughout the world to mankind. The number of diabetes people being reported is increasing every day and also annually it costs a lot of money to treat people who are suffering from diabetes mellitus (DM). So initially, the idea of creating a system that is capable of predicting the type of diabetes, and recommending diet, the quantity of insulin to be taken, and the types of physical workouts for the user was only focussed. Later on, this system is designed to propose the benefits for diabetic patients which help them to fight their type of diabetes. This system can make personalized recommendations based on their type and status of diabetes. Here, an ensemble machine learning algorithm is used to predict whether a person is diabetic or not and what type of diabetes the person has. Diabetes mellitus is characterized by pancreatic insufficiency and an increased blood sugar level. As a result, a person with diabetes must be saved by controlling the difficulties of DM. To successfully forecast the presence of DM and to lessen the severity of DM outcomes, a predictive model is necessary. The primary goal of this work is to create and develop a DM prediction model that uses machine learning techniques to operate as a decision-making system to predict and recommend.

关键词：

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187页 << < 178 179 180 181 182 183 184 185 186 187 > >>

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：