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

1,721 篇 会议
45 册 图书
12 篇 期刊文献

馆藏范围

1,777 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

1,224 篇 工学
- 1,093 篇 计算机科学与技术...
- 629 篇 软件工程
- 253 篇 信息与通信工程
- 200 篇 电气工程
- 177 篇 生物工程
- 99 篇 控制科学与工程
- 98 篇 生物医学工程（可授...
- 60 篇 光学工程
- 46 篇 化学工程与技术
- 45 篇 电子科学与技术（可...
- 41 篇 机械工程
- 41 篇 仪器科学与技术
- 40 篇 安全科学与工程
- 30 篇 交通运输工程
- 28 篇 动力工程及工程热...
- 27 篇 材料科学与工程（可...
456 篇 理学
- 199 篇 数学
- 197 篇 生物学
- 144 篇 物理学
- 83 篇 统计学（可授理学、...
- 51 篇 系统科学
- 46 篇 化学
233 篇 管理学
- 167 篇 图书情报与档案管...
- 86 篇 管理科学与工程(可...
- 43 篇 工商管理
182 篇 医学
- 160 篇 临床医学
- 72 篇 基础医学(可授医学...
- 39 篇 药学(可授医学、理...
- 32 篇 公共卫生与预防医...
34 篇 法学
- 30 篇 社会学
17 篇 经济学
14 篇 教育学
11 篇 农学
2 篇 艺术学
1 篇 军事学

主题

237 篇 machine learning
182 篇 deep learning
137 篇 pattern recognit...
107 篇 feature extracti...
89 篇 support vector m...
88 篇 data mining
74 篇 accuracy
72 篇 training
57 篇 convolutional ne...
50 篇 machine learning...
46 篇 artificial intel...
45 篇 data models
40 篇 neural networks
39 篇 face recognition
38 篇 computational mo...
36 篇 learning systems
36 篇 adversarial mach...
33 篇 predictive model...
32 篇 classification
32 篇 image recognitio...

机构

6 篇 college of compu...
5 篇 xi'an university...
4 篇 badji mokhtar un...
4 篇 shanghai jiao to...
4 篇 institute of big...
4 篇 chitkara centre ...
4 篇 chitkara univers...
4 篇 library shanghai...
3 篇 school of comput...
3 篇 univ chittagong ...
3 篇 chongqing univer...
3 篇 centre of resear...
3 篇 school of comput...
3 篇 school of comput...
3 篇 school of design...
3 篇 korea univ dept ...
3 篇 school of automa...
3 篇 university of mi...
3 篇 shenyang jianzhu...
3 篇 xi'an university...

作者

5 篇 venkatesh svetha
4 篇 ashwini kodipall...
4 篇 zhang yan
4 篇 srinivasa gowri
4 篇 kamel mohamed s.
4 篇 lall brejesh
4 篇 trupthi rao
3 篇 andersson karl
3 篇 peng yang
3 篇 malerba donato
3 篇 karl andersson
3 篇 chaudhury santan...
3 篇 de-shuang huang
3 篇 sekhar c. chandr...
3 篇 wang shuo
3 篇 kamata sei-ichir...
3 篇 mohammad shahada...
3 篇 azizi nabiha
3 篇 phung dinh
3 篇 krasotkina olga

语言

1,695 篇 英文
74 篇 其他
22 篇 中文

检索条件"任意字段=4th International Conference on Machine Learning and Data Minining in Pattern Recognition"

共 1778 条记录，以下是491-500 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：

Handwritten Digit recognition using Ensemble learning techniques: A Comparative performance Analysis 4

Handwritten Digit Recognition using Ensemble learning techni...

引用

4th international conference on Advances in Computing, Communication Control and Networking, ICAC3N 2022

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

ISBN: (纸本)9781665474368

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. © 2022 IEEE.

关键词： learning systems

来源：评论

学校读者我要写书评

暂无评论

Advances in Adversarial Attacks and Defenses in Intrusion Detection System: A Survey

Advances in Adversarial Attacks and Defenses in Intrusion De...

引用

4th international conference on Science of Cyber Security (SciSec)

作者： Mbow, Mariama Sakurai, Kouichi Koide, Hiroshi Kyushu Univ Dept Informat Grad Sch Informat Sci & Elect Engn Fukuoka Japan Kyushu Univ Res Inst Informat Technol Cyber Secur Ctr Fukuoka Japan

ISBN: (纸本)9789811977688;9789811977695

machine learning is one of the predominant methods used in computer science and has been widely and successfully applied in many areas such as computer vision, pattern recognition, natural language processing, cyber security etc. In cyber security, the application of machine learning algorithms for network intrusion detection system (NIDS) has seen promising results for anomaly detection mostly with the adoption of deep learning and is still growing. However, machine learning algorithms are vulnerable to adversarial attacks resulting in significant performance degradation. Adversarial attacks are security threats that aim to deceive the learning algorithm by manipulating its predictions, and Adversarial machine learning is a research area that studies both the generation and defense of such attacks. Researchers have extensively worked on the adversarial machine learning in computer vision but not many works in Intrusion detection system. However, failure in this critical Intrusion detection area could compromise the security of an entire system, and need much attention. this paper provides a review of the advancement in adversarial machine learning based intrusion detection and explores the various defense techniques applied against. Finally discuss their limitations for future research direction in this emerging area.

关键词： Adversarial attack Cyber security Intrusion detection machine learning Deep learning Poisoning attack Evasion attack

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Graph Neural Networks Fusing Multiple data 4

Spatial-Temporal Graph Neural Networks Fusing Multiple Data

引用

4th international conference on Frontiers Technology of Information and Computer, ICFTIC 2022

作者： Xu, Haonan Xue, Wenfang Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Beijing China

ISBN: (纸本)9798350321951

Recently, quantitative investment has become a new way of investment finance, which combines the model with the computer to predict the investment stock trend more efficiently and accurately. Stock trend forecasting is one of the difficult and important tasks in modern quantitative investment systems. With the development of artificial intelligence technology, many deep learning models have emerged. the application of deep learning in the stock market not only reduces the difficulty of stock analysis and trend prediction, but also introduces new investment methods and ideas for investors. However, most of the models are based on volume and price data, and the consideration of stock relationships are relatively simple, so we propose a Spatial-Temporal Graph Neural Network model fusing Barra factors (BSTGNN), which integrates factor knowledge, mines potential inter-stock relationships, and fully consider the heterogeneity of the relationship. the experiments conducted on the real-world stock market dataset prove that BSTGNN perform better than the baseline methods. © 2022 IEEE.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Detecting Irregular Contexts Using Image recognition and data Analysis for Elderly Monitoring

Detecting Irregular Contexts Using Image Recognition and Dat...

引用

Electronic Communications, Internet of things and Big data (ICEIB), international conference on

作者： Sinan Chen Masahide Nakamura Kiyoshi Yasuda Kobe University Kobe Japan Kobe University RIKEN Center for Advanced Intelligence Project Tokyo Japan Kobe University Kobe Japan Japan

ISBN: (数字)9798350360721

ISBN: (纸本)9798350360738

In developed countries including Japan, the population is rapidly aging, and dealing with the increasing number of people requiring care is an urgent issue. Assistive technology (AT) can solve problems in medical care, welfare, and home care issues with engineering technology. Previous studies proposed sensors and physical devices for the elderly, but individualized detection and analysis have not yet been realized. thus, we developed proposed a method for detecting and analyzing situations in the daily life of the elderly. the time-series data was analyzed using an image recognition pre-trained model with lightweight machine learning. the model helps to improve quality of life (QoL) and promote a stable daily life for the elderly at home.

关键词： Image recognition Sociology Medical services machine learning data models Sensors Internet of things

来源：评论

学校读者我要写书评

暂无评论

Gesture recognition Technology in Smart Gloves Enhanced by machine learning

Gesture Recognition Technology in Smart Gloves Enhanced by M...

引用

Ubiquitous Computing and Intelligent Information Systems (ICUIS), international conference on

作者： thangam S Nithin Kandi Dorai Sai Charan Vijay Gosu J. Jesy Janet Kumari Virupaxappa G Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidhyapeetham Bengaluru India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

Gesture recognition systems are changing how people interact with devices, promising natural and intuitive hands-free control in various applications. Based on the ESP32 microcontroller and machine learning techniques, the proposed work is developing a compact, power-efficient system for recognizing hand gestures from data gathered by flex sensors and accelerometers. the entire system fits within memory constraints, as lightweight machine learning models are first trained on a computer using Python and then ideally deployed in optimized versions onto the ESP32. In this respect, the stream of pre-processed sensor data happens to be fed to the ML model for inference, sending back results to the ESP32, which hence triggers specific actions or commands. this fundamentally new approach shows the feasibility of machine learning on resource-constrained platforms, opening the road for wearable technologies that will be more clever and reactive.

关键词： Hands Flexible printed circuits Heuristic algorithms machine learning Gesture recognition Sensor fusion Real-time systems Sensor systems Reliability Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

RTGBO based Recurrent Neural Network for Sarcasm recognition using Twitter data 4

RTGBO based Recurrent Neural Network for Sarcasm Recognition...

引用

4th international conference on Emerging Research in Electronics, Computer Science and Technology, ICERECT 2022

作者： Madhura, G.K. Pareek, Piyush Kumar Parameshachari, B.D. Nitte Meenakshi Institute of Technology Department of Artificial Intelligence & Machine Learning Bengaluru India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Nitte Meenakshi Institute of Technology Department of Electronics and Communications Engineering Bengaluru India

ISBN: (纸本)9781665456357

Increases in popularity of social media stages have been meteoric in fresh years. through social media, a massive quantity of information is being released to the public. this massive amount of freely accessible data has several potential uses. this work aims to discourse issues with the social media dataset, such as its short text nature (with just 140 to 160 characters of text data), its continuous cyclosis nature, its use of abbreviations and slang, and the growing prevalence of sarcasm in online communications. Sentiment analysis and sarcasm recognition are two of the most important jobs in NLP. To communicate sarcasm, one must provide an outside element that reverses the positive and negative emotions involved. there is a risk that data mining efforts may be misclassified if they are fed sarcastic tweets. In this study, we provide a Recurrent Neural Network-based technique for analysing the tone of tweets (RNNs). the proposed approach combines a memory cell-level and network-level localization system for identifying sarcastic and non-sarcastic tweets with an attention mechanism designed to improve the network's performance. It uses an algorithm called Ring-Toss-Game-Based Optimization (RTGBO) to fine-tune the hyper-parameters. the primary focus of RTGBO is to provide a simulation of player behaviour and rules for the ring toss game. One distinguishing feature of the RTGBO procedure is that it has no tuning knobs. Since newspaper headlines often include sarcasm in an effort to draw in readers, the newspaper sarcasm dataset is used for this research. Existing methods are used to verify the suggested classifier in terms of a number of metrics. the model works quite well and accurately identifies which sentences are sarcastic and which are not. © 2022 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

ShoppingGPT: A GPT-based Product Recommendation Dialogue System

ShoppingGPT: A GPT-based Product Recommendation Dialogue Sys...

引用

pattern recognition and machine learning (PRML), IEEE international conference on

作者： Renjie Yu Yujing Guan Yuancheng Zhan Dept. of Computer and Information Technology Guangxi University of XingJian College of Science and Liberal Arts Nanning China Dept. of School of Big Data and Artificial Intelligence Guangxi University Of Finance and Economics Nanning China Dept. Global Institute of Software Technology of NanNing University NanNing University Nanning China

this article introduces a shopping recommendation dialogue system called ShoppingGPT, which aims to help people get comprehensive product recommendations based on individual needs and preferences. the system can leverage existing large-scale generative pre-trained models with the ability to communicate and understand human language to provide more detailed and comprehensive product recommendations through multiple conversations with users. By constructing the shopping recommendation dataset and using the large-scale language model fine-tuning methods, we successfully fine-tuned on a large-scale language model and transformed the shopping recommendation task into a sequential labeling task to adapt to our shopping recommendation dialogue system. And we design a specific method for unlabeled prompt, which uses the basic language knowledge of large-scale language models to output product information for unsupervised annotation for product recommendation. In the experiment, we evaluate several existing language model fine-tuning techniques and explore the generalization ability of the ShoppingGPT system on unlabeled samples. We also compared models before and after fine-tuning to see what the models learned from the data. In the discussion section, we provide a detailed analysis of the advantages and limitations of ShoppingGPT and its potential applications in the shopping field. In addition, we explore the potential security challenges that ShoppingGPT can pose and discuss how to address them. Finally, we discussed how to improve ShoppingGPT to make it perform better and more secure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on a Mixed Asset Identification Model for Industrial control system of Tobacco Industry 24

Research on a Mixed Asset Identification Model for Industria...

引用

4th international conference on Big data, Artificial Intelligence and Risk Management, ICBAR 2024

作者： Yan, Cheng Yang, Cheng Li, Xinjian Ma, Shengjun Zou, Xinhao Chen, Xiaohu Guangshui Cigarette Factory China Tobacco Hubei Industrial LLC Hubei Suizhou China China Tobacco Hubei Industrial LLC Hubei Wuhan China

ISBN: (纸本)9798400709753

With the rapid development of the tobacco industrial internet and the rapid iteration and expansion of industrial assets, it has become a new topic to clarify asset information and sort out asset status in the tobacco industrial environment. Based on common asset types used in the tobacco industrial internet such as PLC, HMI, tobacco machinery, HDMI, and intelligent robots, this paper studies a solution for identifying industrial mixed assets in the tobacco industry by using network communication traffic between assets as the basic data unit, and achieves precise identification of industrial assets in the tobacco industry industrial internet. © 2024 Copyright held by the owner/author(s).

关键词： asset fingerprint recognition model machine learning tobacco asset classification Tobacco asset discovery tobacco asset fingerprint recognition tobacco asset status

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Deep learning Models for Human Activity recognition in Edge Computing Environments

Privacy-Preserving Deep Learning Models for Human Activity R...

引用

Artificial Intelligence and Signal Processing (AISP), INDIA, international conference on

作者： Kambala Vijaya Kumar Challari Pranitha Annam Tanuja Pagolu Indira PriyaDarsini Eswar Patnala Vinay Kumar Dasari Department of CSE Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur

ISBN: (数字)9798350350654

ISBN: (纸本)9798350350661

the increase of wearable devices and smart sensors led to increase of human activity recognition system; this plays a vital role in various domains like healthcare and mainly we need to take further modifications on education, sports and security. Human activity recognition system raises privacy concerns, it often involves the collection of sensitive data of users, there is an approach to modernizing human activity recognition system by using machine learning techniques and data identification and lattice based methods to ensure privacy while restructuring and managing unwanted data or activities in the recognition process. Human activity recognition system involves the continuous monitoring and analyzing the individual activities. To address this, we can use machine learning approaches like deep learning models which improve the accuracy of activity recognition while minimizing the intrusion on the user privacy. Here we use machine learning for accurate the activity recognition and deepdeep learning techniques for preserving privacy and restructuring of unwanted activities. Combining these techniques we can safeguard user privacy in an increasingly data centric world. In this paper we are seeing as the negligible of human exercises from the pictures or recordings taken from the different public where the high goal can be distinguished and getting the exceptionally low goal and protection can be stowed away from such pictures or recordings.

关键词： Deep learning Privacy data privacy Accuracy Recurrent neural networks Recording Human activity recognition Convolutional neural networks Wearable devices Sports

来源：评论

学校读者我要写书评

暂无评论

Improving Biomedical Claim Detection using Prompt learning Approaches

Improving Biomedical Claim Detection using Prompt Learning A...

引用

pattern recognition and machine learning (PRML), IEEE international conference on

作者： Tong Chen Angelos Stefanidis Zhengyong Jiang Jionglong Su School of AI and Advanced Computing XJTLU Entrepreneur College (Taicang) Xi’an Jiaotong-Liverpool University Suzhou Jiangsu China

Biomedical claim detection is an effective method to uncover negative effects arising from the treatment of disease and detect misinformation about medications from online platforms. Due to the power of pre-trained language models (PLMs), such as BERT, RoBERTa and T5, fine-tuned PLMs perform exceptionally well in biomedical claim detection. However, a gap exists in the text classification task between objective forms used in pre-training and fine-tuning for PLMs methods, preventing these models from taking full advantage of the information for biomedical claim detection. Motivated by the prompt learning approach, we propose a method, in which the classification task is transformed into a masked language modeling task that fully utilizes the mask learning capability of PLMs for better prediction of biomedical claim detection. In our method, a template with a mask representing the label is first constructed, and the mask is then filled and mapped to the corresponding label. We use three PLMs as backbone models, i.e., BERT, RoBERTa, and T5, with both hard and mixed templates which are fully and partially predefined templates. Experimental results using the BioClaim dataset demonstrate the superiority of the prompt learning methods over the BERT and RoBERTa classification baselines. Furthermore, the T5 model with mixed template consistently outperforms the rest of experimented models and achieves state-of-the-art performance with an increase of 5.3% on F1-score compared to previous research on this dataset.

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178页 << < 46 47 48 49 50 51 52 53 54 55 > >>

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：