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

2,938 篇 会议
174 册 图书
25 篇 期刊文献

馆藏范围

3,136 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

2,026 篇 工学
- 1,813 篇 计算机科学与技术...
- 948 篇 软件工程
- 329 篇 电气工程
- 312 篇 信息与通信工程
- 214 篇 控制科学与工程
- 207 篇 生物工程
- 149 篇 生物医学工程（可授...
- 70 篇 光学工程
- 64 篇 机械工程
- 61 篇 化学工程与技术
- 50 篇 电子科学与技术（可...
- 48 篇 仪器科学与技术
- 42 篇 安全科学与工程
- 35 篇 交通运输工程
644 篇 理学
- 350 篇 数学
- 244 篇 生物学
- 138 篇 物理学
- 134 篇 统计学（可授理学、...
- 95 篇 系统科学
- 62 篇 化学
399 篇 管理学
- 240 篇 图书情报与档案管...
- 176 篇 管理科学与工程(可...
- 76 篇 工商管理
261 篇 医学
- 240 篇 临床医学
- 122 篇 基础医学(可授医学...
- 74 篇 药学(可授医学、理...
- 39 篇 公共卫生与预防医...
43 篇 法学
- 40 篇 社会学
37 篇 教育学
- 31 篇 教育学
31 篇 经济学
- 29 篇 应用经济学
23 篇 农学
6 篇 艺术学
4 篇 文学

主题

572 篇 machine learning
563 篇 data mining
320 篇 pattern recognit...
202 篇 deep learning
201 篇 feature extracti...
154 篇 support vector m...
145 篇 artificial intel...
128 篇 machine learning...
120 篇 training
116 篇 accuracy
90 篇 data models
89 篇 data mining and ...
71 篇 neural networks
71 篇 classification
67 篇 predictive model...
66 篇 face recognition
61 篇 learning systems
52 篇 computer imaging...
50 篇 convolutional ne...
48 篇 classification a...

机构

9 篇 school of comput...
9 篇 chinese academy ...
8 篇 zhejiang univers...
8 篇 chitkara univers...
7 篇 guangdong univer...
7 篇 school of inform...
6 篇 xi'an university...
6 篇 indian statistic...
6 篇 central south un...
6 篇 department of co...
6 篇 unsw sydney
6 篇 xi'an university...
6 篇 southern univers...
5 篇 study group aust...
5 篇 peking universit...
4 篇 centre for patte...
4 篇 chongqing univer...
4 篇 national laborat...
4 篇 sun yat sen univ...
4 篇 school of inform...

作者

11 篇 de-shuang huang
8 篇 petra perner
7 篇 krasotkina olga
7 篇 mottl vadim
7 篇 ying tan
6 篇 zheng-guang wu
6 篇 ryszard tadeusie...
6 篇 marcin korytkows...
6 篇 phung dinh
6 篇 venkatesh svetha
6 篇 hongyi li
6 篇 jacek m. zurada
6 篇 chaojie li
6 篇 biao luo
6 篇 ilias maglogiann...
6 篇 lotfi a. zadeh
6 篇 leszek rutkowski
6 篇 lazaros iliadis
6 篇 long cheng
5 篇 vitoantonio bevi...

语言

3,044 篇 英文
79 篇 其他
19 篇 中文
1 篇 土耳其文

检索条件"任意字段=5th International Conference on Machine Learning and Data Mining in Pattern Recognition"

共 3137 条记录，以下是31-40 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：

Transferability feature recognition of university biomedical patent technology based on machine learning 5

Transferability feature recognition of university biomedical...

引用

5th international conference on Computer Engineering and Application (ICCEA)

作者： Tang, Yirui Shao, Xingdong Shanghai Inst Technol Dept Econ & Management Shanghai Peoples R China

ISBN: (纸本)9798350386783;9798350386776

In the era of digitalization and intelligence, identifying the transferability characteristics of biomedical patent technologies in higher education institutions is of great significance. this study takes seven intellectual property demonstration pilot universities in Shanghai as the research subjects, and constructs a biomedical patent technology transferability evaluation index system from three aspects: technical dimension, market dimension, and legal dimension. Four algorithms based on machine learning, including Support Vector machine (SVM), Decision Tree (DT), Random Forest (RF), and Adaptive Boosting (AdaBoost), are respectively used for training and prediction. through comparison and selection, it is finally confirmed that the Random Forest model has the best prediction effect for the constructed index system. It is considered to apply the algorithm model of this research to the massive data of biomedical industry-related patent technologies, to promote the transformation of achievements and intelligent development of the biomedical industry.

关键词： Biomedical Universities Patents Transferability machine learning Random Forest

来源：评论

学校读者我要写书评

暂无评论

Hand Gesture recognition for Smart Television Using GRU 5th

Hand Gesture Recognition for Smart Television Using GRU

引用

5th international conference on data Science, machine learning and Applications

作者： Suresh, Garugu Yaswanth Lakshmi Sravani, Ravinuthala Gayatri Venkata VIT AP Univ Sch Comp Sci & Engn Inavolu AP Secretariat Amaravati Andhra Pradesh India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

Even with the rapid advancement of technology, using a television still requires a physical remote control. Apart from occasionally losing sight of the television remote control, we also sometimes run out of batteries. the goal is to discover an effective way of controlling television and develop 3D hand gesture-based smart television control using Gated Recurrent Unit (GRU). the results of the research show that hand gesture recognition-based interface technology is capable of performing the majority of smart TV operations. It is a comfortable and delightful experience for consumers. the existing research features static image gesture recognition with predefined models for training in addition to the existing research the proposed model features sample video dataset, Custom design with Gated Recurrent Unit. the suggested model is trained using five hand gestures. the camera positioned on the TV continually records the motions. Each gesture is associated with a certain command. the proposed model has achieved an accuracy of about 94% in recognizing the gestures.

关键词： Smart Television Image Processing Deep learning Convolutional Neural Networks Gated Recurrent Unit (GRU)

来源：评论

学校读者我要写书评

暂无评论

Deep learning in Automatic recognition of Mongolian Compound Nouns 5

Deep Learning in Automatic Recognition of Mongolian Compound...

引用

5th IEEE international conference on pattern recognition and machine learning, PRML 2024

作者： Si, Ha La, Du Ding, Yang College of Computer Science and Information Engineering Hohhot Minzu College Hohhot China College of Computer Science and Technology Inner Mongolia Normal University Hohhot China School of Software and Big Data Inner Mongolia Electronic Information Vocational Technical College Hohhot China

ISBN: (纸本)9798350355925

Mongolian compound nouns often become the vehicle for the creation of new concepts and terms due to their diverse combinations and flexible expressive power. In the field of natural language shallow syntactic analysis, the recognition of Mongolian compound nouns plays an important role, and its performance will directly affect the processing effect of related research. In the current academic research, the research on automatic recognition of Mongolian compound nouns is still insufficient, especially in the automatic recognition of Mongolian compound nouns using deep learning technology, which is almost in a blank state. In this study, we firstly construct a Mongolian compound noun annotated corpus, and on the basis of the constructed annotated corpus, we propose a Mongolian compound noun automatic recognition model based on deep learning for the fact that there is no deep learning method for recognising Mongolian compound nouns at present. the model takes Conditional Random Field (CRF) as the basic framework to make full use of contextual information by considering the joint probability distribution of the whole sequence. During the model construction process, the TextCNN model is incorporated and by designing a multi-scale convolutional kernel, the model is able to effectively capture the local features of Mongolian compound nouns. the experimental results show that the automatic Mongolian compound noun recognition model based on deep learning proposed in this study performs well on the Mongolian compound noun recognition task, with an F1 value of 93.40%. © 2024 IEEE.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Meta Transductive Linear Probing for Few-Shot Node Classification 5

Meta Transductive Linear Probing for Few-Shot Node Classific...

引用

5th IEEE international conference on pattern recognition and machine learning, PRML 2024

作者： Lan, Mingjing Huang, Ningbo Zhou, Gang Xia, Yi State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9798350355925

Graph few-shot learning aims to predict well by training with very few labeled data. Meta learning has been the most popular solution for few-shot learning problem. However, transductive linear probing shows that fine-tuning a simple linear classification head after a pretrained graph neural networks can outperforms most of the sophisticated-designed graph meta learning algorithms. therefore, in the paper, we propose a meta transductive linear probing methods named Meta-TLP to incorporate the advantages of graph self-supervised and graph meta learning model. Specifically, the graph neural network is firstly pretrained with graph contrastive learning methods. then we design an unsupervised meta training task construction methods to require meta tasks without relying on labeled data. Finally, we meta training the linear classification head on the meta training tasks to learn to fast adopt to novel classes. Experiment results show that our model can perform better than TLP on three real world datasets. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Review on Fashion Trend Analysis and Forecasting Techniques - A machine learning Approach 5

Review on Fashion Trend Analysis and Forecasting Techniques ...

引用

5th international conference on Innovative Trends in Information Technology (ICITIIT)

作者： Jiju, Amrita Anilkumar, Adithya Krishnan, Gokul K. P. George, Jithu Prasanth, R. S. Govt Engn Coll Barton Hill Dept Informat Technol Thiruvananthapuram Kerala India

ISBN: (纸本)9798350386813;9798350386820

the fashion industry is characterized by its rapid changes involving consumer's ever-changing preferences, whether in color palettes, patterns, seasonal trends, or social and cultural influences. Fashion reflects one's culture, individuality, and societal trends. With technological advancement, the fashion generation and recommendation systems have shown enhancements. the integration of advanced algorithms has emerged as a transformative solution, capable of uncovering concealed insights and effectively addressing color variations and pattern formulation within the intricate landscape of fashion collections. this transformative approach significantly influences production processes and design strategies, fostering an environment where adaptability and responsiveness become pivotal for success. With the rise of machine learning, the industry experiences a paradigm shift, gaining an unprecedented ability to analyze historical and real-time data. the analysis gives a clear idea about the possible combinations and can be efficiently used to create designs that match the upcoming trends. this study examines the use of machine learning as well as deep learning and artificial intelligence in the fashion industry for tasks such as clothing recognition, style understanding, color and style extraction, outfit recommendations, and fashion forecasting. the study highlights various ways of applying machine learning in the fashion domain. However, it's important to note that this review only covers a few methods, as they have shown the best performance in accuracy and efficiency when dealing with a vast amount of fashion data. the limitations mentioned suggest areas that still need exploration for future research.

关键词： machine learning deep learning neural networks object detection fashion item classification feature extraction fashion recommendation fashion dataset trend analysis social media

来源：评论

学校读者我要写书评

暂无评论

Mitigating Credit Card Fraud through Behavior-Based Classification and Anomaly Elimination Using Support Vector machine 5th

Mitigating Credit Card Fraud Through Behavior-Based Classifi...

引用

5th international conference on data Science, machine learning and Applications

作者： Manohari, Katta Gouthami Sravya, Samana Nandini, Vorus Joy, Konkini Vinnie Kumar, Chanda Raj Pagadala, Pavan Kumar Koneru Lakshmaiah Educ Fdn Hyderabad 500075 Telangana India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

With the rise in internet and e-commerce usage, the significance of credit card usage has also increased. However this surge in credit card usage has unfortunately led to an increase in activities. To address this issue various techniques have been developed. In this research paper we propose a behavior-based classification approach that utilizes vector machines along with a to eliminate affect. By monitoring any deviations in business practice, we can identify activities and further analyze the relevant factors involved. It's crucial to find a solution to the growing problem of credit card fraud given the amount of data involved. From this perspective, our method specifically leverages the power of support vector machine (SVMs) to understand large data. SVM is known for its ability to stabilize class objects and is particularly suitable for detecting anomalous behavior that may indicate fraud. Our model examines every transaction when integrated into a credit card. this process focuses on patterns and behaviors that differ from the cardholder's business behavior. SVM provides high accuracy in identifying potential threats by creating a hyperplane that separates legitimate activity from suspicious activity.

关键词： data mining machine learning Support Vector machine Confusion Matrix Classification Regression

来源：评论

学校读者我要写书评

暂无评论

learning Rate Decay Scheduler Using the Loss Operator as Generalization 5

Learning Rate Decay Scheduler Using the Loss Operator as Gen...

引用

5th IEEE international conference on pattern recognition and machine learning, PRML 2024

作者： An, Wenbo Zhang, Juntao Liu, Jianning Shao, Kun Bian, Kun Zhou, Jun Institute of System Engineering AMS Beijing China School of Electronic Engineering Xidian University Xi'an China

ISBN: (纸本)9798350355925

learning rate decay scheduler is the commonly used method in training Deep Neural Networks. Traditional learning rate decay scheduler adjusts the learning rate of decrease based on the number of training iterations or epochs. However, when handling the dataset from different task types during training Large Language Models, the traditional method cannot adaptively adjust the learning rate to help the model converge better. In this paper, We propose to introduce training loss operator gt into the traditional time-based scheduler to adjust the rate of learning rate decay. Our experiments is conducted by using two large models, 'Baichuan2' and 'Qwen' on zero-shot and few-shot task datasets. Compared to primary cos learning rate decay methods, our method achieve state-of-the-art results on In-Context learning and zero-shot tasks. the code are publicly available at https://***/Lunamoon-flow/learning-rate-decay. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Research on Tibetan Voiceprint recognition Methods Under Low-Resource Condition 5

Research on Tibetan Voiceprint Recognition Methods Under Low...

引用

5th IEEE international conference on pattern recognition and machine learning, PRML 2024

作者： Ni, Qiong Gao, Dingguo Ba, Guo School of Information Science and Technology Tibetan Information Technology Innovative Talent Cultivation Demonstration Base Tibet University Lhasa China

ISBN: (纸本)9798350355925

In recent years, research on Chinese and English voiceprint recognition has matured and has been widely ap-plied in various fields. However, research on Tibetan voiceprint recognition is relatively limited, primarily focusing on text-related voiceprint recognition. Research on text-independent Tibetan voiceprint recognition is almost nonexistent, and deep learning-based Tibetan voiceprint recognition has only just begun. Furthermore, existing models rely heavily on large datasets. To address these issues, this paper implements text-independent Tibetan voiceprint recognition using mainstream models and proposes a ResNet model that incorporates multi-scale attention to enhance model performance in low-resource environments. Firstly, diverse data is expanded using the pub-licly available Tibetan speech dataset ertz0y0o, resulting in a dataset of 61,457 audio samples from 112 speakers. Secondly, six sets of comparative experiments were conducted using main-stream models TDNN, ResNet34SE, and the proposed model ResNetSE_Multi on both the complete dataset and a low-resource dataset consisting of 20 % of the audio data randomly sampled from each speaker. Experimental results demonstrate that the proposed model achieves an accuracy improvement of 2% and 3% over the other two models in the low-resource scenario, indicating stronger learning capabilities and laying a foundation for practical applications in Tibetan voiceprint recognition. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

learning and Application of Different machine learning Methods (KNN, SVM, Decision Tree) in Different datasets 5

Learning and Application of Different Machine Learning Metho...

引用

5th international conference on machine learning and Computer Application, ICMLCA 2024

作者： Zhu, Chaoqun School of Computer Science and Technology School of Artificial Intelligence Zhejiang Normal University Zhejiang Jinhua321004 China

ISBN: (纸本)9798331530334

With the continuous development of artificial intelligence, machine learning has shown great ability in classification and regression problems. For example, logistic regression, SVM methods, and neural networks are widely used in credit evaluation, image recognition, and sales forecasting. In this paper, KNN method, SVM method and decision tree method are used for iris data set, aircraft delay data set and diabetes dataset was tested by linear regression and Lasso regression ridge regression. We can conclude that different machine learning methods have different sensitivities to the partitioning of the dataset (controlled by random_state and test-size). When selecting the model parameters, the influence of these factors on the model performance should be considered. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Style Augmentation for Semi-Supervised Domain-Generalized Medical Image Segmentation 5

Cross-Domain Style Augmentation for Semi-Supervised Domain-G...

引用

5th IEEE international conference on pattern recognition and machine learning, PRML 2024

作者： Wang, Jun Wang, Liping School of Information Science and Engineering University of Jinan Jinan China The Fourth People's Hospital of Jinan Department of Gynecology Jinan China

ISBN: (纸本)9798350355925

Medical image segmentation models based on deep learning often experience performance decline when applied to unseen domains, which restricts the use of deep learning models in real-world medical settings. Most existing methods require the use of multiple fully labeled source domain datasets for training, which can be challenging due to the difficulty of obtaining a substantial volume of annotated medical datasets in practical scenarios. In this paper, we focus on semi-supervised domain-generalized medical image segmentation, aiming to achieve gen-eralization to unknown domains by training with limited labeled data from multi-source domain datasets. We propose a novel cross-domain style augmentation method, which augments image style by applying nonlinear transformation functions to low level frequency information from images in different domains and further merging information from different domains. In addition, we propose a confidence-weighted consistency method between teacher and student predictions to better guide consistency regularization learning within the teacher-student framework. Extensive experiments show that our method achieves improved generalization effectiveness on two public benchmarks. © 2024 IEEE.

关键词： Self-supervised learning

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314页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：