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

4,137 篇 会议
38 册 图书
6 篇 期刊文献

馆藏范围

4,181 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,738 篇 工学
- 2,465 篇 计算机科学与技术...
- 2,042 篇 软件工程
- 616 篇 生物工程
- 587 篇 信息与通信工程
- 362 篇 生物医学工程（可授...
- 266 篇 控制科学与工程
- 216 篇 电气工程
- 211 篇 光学工程
- 148 篇 安全科学与工程
- 136 篇 机械工程
- 124 篇 电子科学与技术（可...
- 118 篇 化学工程与技术
- 107 篇 交通运输工程
- 91 篇 动力工程及工程热...
1,369 篇 理学
- 675 篇 数学
- 646 篇 生物学
- 332 篇 统计学（可授理学、...
- 307 篇 物理学
- 197 篇 系统科学
- 127 篇 化学
720 篇 管理学
- 393 篇 管理科学与工程(可...
- 388 篇 图书情报与档案管...
- 237 篇 工商管理
340 篇 医学
- 315 篇 临床医学
- 308 篇 基础医学(可授医学...
- 221 篇 药学(可授医学、理...
- 125 篇 公共卫生与预防医...
159 篇 法学
- 138 篇 社会学
157 篇 教育学
- 155 篇 教育学
141 篇 农学
- 140 篇 作物学
89 篇 经济学
9 篇 军事学
5 篇 文学

主题

526 篇 machine learning
243 篇 deep learning
117 篇 support vector m...
99 篇 adversarial mach...
92 篇 accuracy
92 篇 machine learning...
83 篇 forecasting
75 篇 convolutional ne...
70 篇 predictive model...
69 篇 feature extracti...
58 篇 artificial intel...
53 篇 students
51 篇 learning systems
48 篇 decision trees
48 篇 training
47 篇 reinforcement le...
47 篇 computational mo...
47 篇 computer vision
46 篇 internet of thin...
41 篇 neural networks

机构

46 篇 chitkara univers...
15 篇 graphic era hill...
10 篇 college of manag...
9 篇 graphic era deem...
8 篇 computer science...
8 篇 beijing universi...
7 篇 school of comput...
7 篇 school of comput...
7 篇 school of comput...
7 篇 department of in...
6 篇 università di ca...
6 篇 infn sezione di ...
6 篇 north-west unive...
6 篇 computer science...
6 篇 lovely professio...
6 篇 in2p3 lpc campus...
6 篇 kkr and ksr inst...
6 篇 institut univers...
6 篇 national centre ...
6 篇 greater bay area...

作者

18 篇 kukreja vinay
15 篇 mehta shiva
10 篇 william p.
8 篇 sharma vikrant
7 篇 mahamudul hasan
7 篇 shiva mehta
6 篇 chen a.
6 篇 benoit d.m.
6 篇 ferrara g.
6 篇 ardid m.
6 篇 calvo d.
6 篇 gagliardini s.
6 篇 eddymaoui a.
6 篇 kulikovskiy v.
6 篇 labalme m.
6 篇 gal t.
6 篇 bozza c.
6 篇 khatun a.
6 篇 kalekin o.
6 篇 huang f.

语言

3,930 篇 英文
250 篇 其他
34 篇 中文

检索条件"任意字段=Proceedings of the 2023 4th International Conference on Machine Learning and Computer Application"

共 4181 条记录，以下是3471-3480 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：

A deep learning framework: Prediction of the number of participants in Wordle and the distribution of game outcomes 23

A deep learning framework: Prediction of the number of parti...

引用

proceedings of the 2023 4th international conference on computer Science and Management Technology

作者： Shijie Wu Zhongzheng Wang Xinyi Liu Xue Bai School of Energy Science and Engineering Harbin Institute of Technology China Faculty of Computing Harbin Institute of Technology China School of Mathematics Harbin Institute of Technology China School of Economics and Management Harbin Institute of Technology China

ISBN: (纸本)9798400709517

Wordle is a new word guessing game that has become popular around the world. It compares the result entered by the player with the correct answer and gives hints through different letter colors. the player is considered successful if he or she matches the result to the hint and determines the correct answer within six attempts. the game has two modes: normal mode and hard mode. the data generated by New York Times allows us to know the total number of players who report the results every day and the total number of players in the difficult mode and the number of guesses by most people. Our purpose is to explore the future trend of the number of players for this game and to get the results of the prediction report for different words. In this paper, we make use of ARIMA time series model and CIWOA_BP neural network, which solve our needs well. We can provide innovative ideas and inspiration for game company managers and technicians, so that make users can have a better game experience.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on the application of Children's Reading Analysis Based on Artificial Intelligence - - Take Small "raccoon Reading" and "jiao Jiao Reading" as examples 4

Research on the Application of Children's Reading Analysis B...

引用

2021 4th international conference on Advanced Algorithms and Control Engineering, ICAACE 2021

作者： Nini, Huang Kong, Dehua Faculty of Literature and Law Wuhan Donghu University Hubei Province Wuhan430212 China School of Computer Science Wuhan Donghu University Hubei Province Wuhan430212 China

Artificial intelligence technology is widely used in the field of education, and the development of children's Chinese reading field is increasingly mature. Using the boundary awareness of AI algorithm for reference, the Chinese reading class should also awaken the boundary awareness of Chinese subject. In the AI algorithm, only the annotated data are valid data. the reading text can become effective learning materials through natural language processing only when it is "annotated"out of ability points. through machine learning, AI constantly generates self-learning data sets based on trial-and-error feedback. the feedback mechanism, trial-and-error opportunity and Chinese teaching design are transformed into each other to build student portrait and specifically improve students' independent Chinese learning ability. this article analyzes the application of artificial intelligence technology in the development of children's Chinese reading services by taking the examples of [[CHECK_DOUBLEQUOT_ENT]] Small raccoon Reading"and "Jiao Jiao Reading. © Published under licence by IOP Publishing Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Research on Rotation Detection of Aircraft Glass Canopy Defects Based on Deep learning 22

Research on Rotation Detection of Aircraft Glass Canopy Defe...

引用

proceedings of the 2022 5th international conference on machine learning and machine Intelligence

作者： Jing Wang Kexin Wang Jianhong Li School of Computer Science and Technology Xidian University China

ISBN: (纸本)9781450397551

Aircraft Glass Canopy (AGC) is an important part of human-aircraft interface, and efficient and real-time AGC surface defect detection has become a prerequisite for pilots to perceive the external field of vision normally. While existing deep learning models are sufficient for routine defect detection, AGC surface defects are characterized by tiny and high aspect ratios, which make accurate defect detection challenging. therefore, this paper proposes an improved YOLOv4 rotating target detection model. Specifically, we firstly employs the decoupled head to improve the model performance and convergence efficiency on the basis of the original YOLOv4 model. Secondly, we construct a multi-dimensional coordinate structure for high aspect ratio defects, and achieve rotation detection by optimizing the loss function. Finally, we utilize Fuzzy C-means (FCM) to cluster AGC surface defects to obtain the most suitable initial anchor box size. Experimental results show that the mAP value is improved by 6.16% compared to the original YOLOv4 model, which proves the effectiveness of our proposed model.

关键词： Aircraft Glass Canopy FCM YOLOv4 defect detection rotation detection

来源：评论

学校读者我要写书评

暂无评论

Surface Defect Detection of Transparent Parts Based on Improved YOLOv4 Model 22

Surface Defect Detection of Transparent Parts Based on Impro...

引用

proceedings of the 2022 5th international conference on machine learning and machine Intelligence

作者： Jing Wang Jianhong Li Siwen Wei School of Computer Science and Technology Xidian University China

ISBN: (纸本)9781450397551

With the development of science and technology, transparent parts are almost used in various industries and play an indispensable role. It is meaningful to measure the surface quality of transparent parts. To improve the detection accuracy of surface defects on transparent parts, an improved YOLOv4 target detection model is proposed in this paper. Firstly, to expand the amount of dataset, we adopt Mosaic strategy combined with Copy-Pasting strategy for data augmentation. Secondly, the Canopy + K-means clustering algorithm is employed to select the initial anchor box size. Finally, to improve the feature representation ability of the model, Squeeze-and-Excitation Networks (SENet) with an attention mechanism is embedded to the model. Experiments show that the mAP value of the improved YOLOv4 model on the test set reaches 91.07%, which is 6.4% higher than that of Faster R-CNN and 4.15% higher than that of the original YOLOv4 model, which proves the effectiveness of our model.

关键词： SENet YOLOv4 defect detection transparent parts

来源：评论

学校读者我要写书评

暂无评论

An application Programming Interface to Recognize Emotion using Speech Features

An Application Programming Interface to Recognize Emotion us...

引用

Sustainable Technologies for Industry 4.0 (STI), international conference on

作者： Shimul Chandra Das Md. Benajir Alam Most. Sumiya Akter Moon Md. Solaiman Mia Department of Computer Science and Engineering Green University of Bangladesh Bangladesh

With the recent increasing interest in the study of the emotional component of speech signals, a number of methods have been put forth to ascertain the emotional content of uttered words. Often, we can tell how someone is feeling by looking at their faces. Another method is to detect someone’s emotions by auditory cues or speech. With a more straightforward architecture and fewer learnable parameters, the aim of this paper is to identify someone’s emotion from an audio input. three aspects have been suggested in the proposed methodology named MFCC (Mel-frequency Cepstral Coefficients), Mel-spectrogram and Chromagram, and MLP (Multilayer Perceptron). these features have been employed in this paper, because they perform better. MLP is a supervised machine learning, which is frequently used in various research to categorize human voice recognition. In addition, MLPs are appropriate for classification prediction issues where inputs are given as a class or label. they are also appropriate for regression prediction issues in which a real-valued quantity is forecasted from a collection of inputs. With the help of our proposed methods, we are able to achieve an accuracy of 80% on the RAVDESS Dataset.

关键词： Human computer interaction Emotion recognition Speech recognition machine learning Multilayer perceptrons Nonhomogeneous media Fourth Industrial Revolution

来源：评论

学校读者我要写书评

暂无评论

machine learning-Based Android Malware Detection

Machine Learning-Based Android Malware Detection

引用

international conference on Data Science and Advanced Analytics (DSAA)

作者： David Ojo Nusayer Masud Siddique Carson K. Leung Connor C.J. Hryhoruk Department of Computer Science University of Manitoba Winnipeg MB Canada

the use of mobile phones, particularly smartphones, has been growing exponentially in recent times. From 2016 to 2021, smartphone users increased by more than 70%. With the increase in the popularity of smartphones, smartphones have become the prime target for criminal hackers. As a result, Android malware samples are coming to the market at an alarming rate. A study shows that there are more than 4 million malicious Android apps in the market, and each day around 11,000 new malwares add to this number. To combat this mass number of malware, we need a malware detection system that is efficient in detecting malicious Android apps. there are numerous existing malware detection systems, but most of them require countless features from both dynamic and static analysis. thus, they are not scalable, lightweight, and efficient in detecting malware. Additionally, most studies that used limited features like only permission data, had done their research on much older dataset. Hence, there is a need for new research on this topic. In this paper, we build a permission-based malware detector for Android application with a new dataset and significantly less permissions. Initially, we used support vector machine (SVM) and all the extracted permission data as features to build our classification model. the model accuracy, precision, recall and F1 score were 97.41 percent, which is higher than the other state of the art similar approaches done on an older dataset. Next, we replicated this similar study with a few different machine learning algorithms: random forest, decision tree and logistic regression, and observed they all give similar results. However, tree-based algorithm performs a little better than the other algorithms. Finally, to achieve a lightweight malware detection system, we reduced the number of permissions or the features on a two-step process, and found only a slight difference in results. In the first step, even after reducing the number of permissions by about 9

关键词：

来源：评论

学校读者我要写书评

暂无评论

Epilepsy Detection through EEG Signal Classification Using machine learning Methods

Epilepsy Detection Through EEG Signal Classification Using M...

引用

international conference on ICT in Business Industry & Government (ICTBIG)

作者： Vivek Deshpande P. Gajendran Varun Ojha Latha B Ishika Soni Arunkumar D T Department of Computer Engineering Vishwakarma Institute of Technology Pune India Department of Electrical and Electronics Engineering Karpagam College of Engineering Coimbatore Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of IT Prince Shri Venkateshwara Padmavathy Engineering College Chennai Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India School of Engineering and Technology Mechaical Engineering JAIN (Deemed to be University) Bangalore Karnataka India

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518998

In this exertion demonstrates the application of a deep learning algorithm to the analysis of focal and non-focal EEG data for the finding of epilepsy. this research presents a strategy for automating the diagnosis of epilepsy by making use of a soft computing resource. By using the ANFIS classification technique, focal and non-focal samples may be distinguished. Structures computation, features classification, and features transformation are the three pillars upon which this technique rests. For an electroencephalogram (EEG) data, the Approximate and Directional bands are produced when the suggested NSCT is used. NSDF and Non-Subsampled Pyramid Filter are the two main components of this NSCT. these fall into two categories: low pass, which includes power frequencies, and high pass, which includes high frequency noise. To do this, we construct directed subbands and reroute the high-pass signal using NSDF. Step two of decomposition involves creating high and low frequency sub bands by passing the low pass sub band signal via the Non-Sub Sampled Pixel Frequency (NSPF). the directed sub bands that are created are achieved by retransmitting the high-frequency sub band signal via NSDF. Using the statistical properties obtained from these sub-bands, the ANFIS classification method divides the overall EEG signal into focal and non-focal samples. Applying the proposed method to a collection of EEG signal extraction measurements allows for validation.

关键词： Deep learning Analytical models Time-frequency analysis Sensitivity Noise Epilepsy Pattern classification Brain modeling Electroencephalography Data models

来源：评论

学校读者我要写书评

暂无评论

Analytical review of existing techniques IoT based Home Automation and securing its data over Edge Computing using machine learning 22

Analytical review of existing techniques IoT based Home Auto...

引用

proceedings of the 4th international conference on Information Management & machine Intelligence

作者： Abhishek Dadhich Dinesh Goyal Computer Engineering Poornima University India

ISBN: (纸本)9781450399937

Future home designs heavily rely on the smart home concept. the primary goal of Home automation is to provide pleasant, secure, efficient, and easy management or monitoring of home appliances, using sensors that save energy too. For controlling the home appliances, existing systems use Bluetooth, Zigbee, GSM Module, WLAN, or Internet Technology. Home automation systems have been further enhanced using Arduino, Node MCU, Raspberry Pi, and WIFI Module. When billions of devices are online and this data-rich world enabled by the Internet of things is fully operational, cloud computing won't be able to handle the workload. Every IoT sensor produces a significant amount of data. Data is promptly transferred to a central cloud database in cloud computing, where it is managed and stored. But occasionally, a response may be interrupted or delayed owing to a network error or a poor internet connection simply because the data centre is too far away from the device. this problem is solved by the use of edge computing, IoT device itself or the nearby node network is behind the data processing and can response in an exact manner if a specific action is needed. In the proposed paper a detailed review conducted regarding existing technologies and existing home automation system (HAS). With the same reference to IoT, new architecture needs to be developed and providing data security using the edge computing instead of Cloud Computing.

关键词： Home Automation System Edge Computing Security Cloud Computing Internet of things

来源：评论

学校读者我要写书评

暂无评论

application and prospect of brain computer interface technology in the future war 22

Application and prospect of brain computer interface technol...

引用

proceedings of the 2022 4th international conference on Robotics, Intelligent Control and Artificial Intelligence

作者： Xiao Chen School of life science Jilin university China

ISBN: (纸本)9781450398343

As one of the most popular cutting-edge technologies at present, brain computer interface technology has important research significance and great application prospects in bio-medicine, educational technology, electronic information and other fields, achieving a series of considerable scientific research results, its application fields continue to expand. this paper firstly describes the working process of BCI, by collecting the original EEG signals and preprocessing them, inputting into one or more feature extraction algorithms to encode information and commands and then establishing a classifier to classify their features, this process is to realize the analysis of human behavior and intention, BCI application is responsible for the specific expression of them. Secondly, we prospectively predict the application of this technology in the future war, such as the coordinated operation of brain-controlled robot forces and UAV groups, even utilizing BCI for reverse operations to defeat enemy forces through enemy forces, realizing a fully unmanned and highly intelligent combat mode. Finally, we summarized the shortcomings and ethical problems caused by BCI, for example, over-developed this technology will affect human physical and mental quality and personal privacy, even threaten social security. Due to the great uncertainty of war, there will be some certain risks, such as the instability of wireless technology and once important EEG signals are intercepted, it will bring huge risks and even disasters to military operations under brain control technology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Investigation and Development into the Use of AI-Based Analytical Methods for Forecasting the Stock Market

An Investigation and Development into the Use of AI-Based An...

引用

Smart Electronics and Communication (ICOSEC), international conference on

作者： M. Sheeba D. Ranjith Kumar S. Kirubakaran Ila Dixit D. Leela Rani Ajay Singh Yadav Department of B. Com Information System Management Guru Nanak College (Autonomous) Chennai Tamil Nadu India Department of B. Com Corporate Secretaryship Guru Nanak College (Autonomous) Chennai Tamil Nadu India Department of Computer Science and Engineering CMR College of Engineering and Technology Hyderabad Telangana India Department of Management Maharaja Agarsen International College Raipur Chhattisgarh India Department of Electronics and Communication Engineering School of Engineering Mohan Babu University Tirupati Andhra Pradesh India Department of Mathematics SRM Institute of Science and Technology Ghaziabad Utter Pradesh India

Forecasting the stock market is difficult due to the fact that a number numerous factors, including the current situation of economy, current politics, and market sentiment. Traditional analytical methods have limitations in accurately predicting stock prices, leading to increased curiosity about using algorithms based on artificial intelligence (AI) and machine learning (ML) stock market forecasting. this paper investigates the use of AI-based analytical methods for forecasting the stock market and presents a detailed analysis of various algorithms used in AI-based stock market forecasting. the use of AI-based analytical methods for forecasting the stock market has several benefits. Firstly, AI-based models can analyse vast amounts of financial data much faster than traditional methods, allowing for more accurate and timely predictions. Secondly, AI-based models can handle complex relationships between different factors affecting stock prices, such as market trends, news events, and economic indicators, which can be challenging to capture using traditional methods. this study also discusses about the challenges and limitations of using AI-based models for stock market forecasting research in the future research. Here, this study uses a novel theory of recurrent neural networks and a random forest model to enable prediction with more accuracy. One of the commonly used algorithms in AI-based stock market forecasting is the recurrent neural network (RNN), which model that uses deep learning. RNNs are very helpful for modelling time-series information, like stock prices, just because they may ensnare the temporal data dependencies. In addition, RNNs can be used to generate forecasts by predicting the next value in a set of timestamps based on previous values. Another popular algorithm for stock market forecasting is the Random Forest (RF) ensemble model. RF models are a type of decision tree-based algorithm that can generate accurate predictions by combining the output

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419页 << < 344 345 346 347 348 349 350 351 352 353 > >>

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：