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321-330 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：

Influence of Water Droplet Contamination for Transparency Segmentation 4th

Influence of Water Droplet Contamination for Transparency ...

引用

4th international conference on pattern recognition and Artificial Intelligence, ICPRAI 2024

作者： Knauthe, Volker Weitz, Paul Pöllabauer, thomas Wirth, Tristan Rak, Arne Kuijper, Arjan Fellner, Dieter W. Technical University of Darmstadt Darmstadt Germany Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany CGV Institute Graz University of Technology Graz Austria

ISBN: (纸本)9789819787043

Computer vision techniques are on the rise for industrial applications, like process supervision and autonomous agents, e.g., in the healthcare domain and dangerous environments. While the general usability of these techniques is high, there are still challenging real-world use-cases. Especially transparent structures, which can appear in the form of glass doors, protective casings or everyday objects like glasses, pose a challenge for computer vision methods. this paper evaluates the combination of transparent objects in conjunction with (naturally occurring) contamination through environmental effects like hazing. We introduce a novel publicly available dataset containing 489 images incorporating three grades of water droplet contamination on transparent structures and examine the resulting influence on transparency handling. Our findings show, that contaminated transparent objects are easier to segment and that we are able to distinguish between different severity levels of contamination with a current state-of-the art machine-learning model. this in turn opens up the possibility to enhance computer vision systems regarding resilience against, e.g., datashifts through contaminated protection casings or implement an automated cleaning alert. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Image Domain Translation for Few-Shot learning 27th

Image Domain Translation for Few-Shot Learning

引用

27th international conference on pattern recognition, ICPR 2024

作者： Chen, Liangyuan He, Zhenan Zhang, Hai College of Computer Science Sichuan University Chengdu China

ISBN: (纸本)9783031781827

Few-shot learning is crucial in machine learning and computer vision. It enables models to recognize new objects with limited labeled data, addressing the challenge of data scarcity and expanding the application of machine learning to domains with scarce data. Previous methods built metric space using labeled data from the base set and then classified queried images from the novel set by finding the nearest class prototype. However, due to the presence of poor-quality data in the novel set, the class prototype often exhibits instability. In response to this challenge, this paper proposes a Semantic Conditional Translation Network for reconstructing stable class prototypes. Specifically, images are first divided into edge domain (i.e., images at the cluster edge) and prototype domain (i.e., images at the cluster center). then, an Enhanced Generative Adversarial Network is introduced to learn the translation from edge toward prototype, where a Non-parametric Classification Regularizer is designed to enlarge the discriminability of the translated samples. Meanwhile, class definitions are exploited as semantics providing precise descriptions and enhancing translation performance. Experimental results demonstrate that the proposed method obtains competitive results on four benchmark datasets. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Zero-shot Automated Class Imbalanced learning 27th

Zero-shot Automated Class Imbalanced Learning

引用

27th international conference on pattern recognition, ICPR 2024

作者： Wang, Zhaoyang Wang, Shuo School of Computer Science University of Birmingham BirminghamB15 2TT United Kingdom

ISBN: (纸本)9783031783821

Given a new class imbalanced dataset D and limited computational resources, the challenge arises of selecting promising class imbalanced learning (CIL) pipelines that include resampling methods, classification models, and their corresponding hyperparameters. To address this challenge, we study Zero-shot Automated machine learning and propose a new approach aiming at class imbalanced data, called Zero-shot Automated Class Imbalance learning (ZAutoCIL). ZAutoCIL employs domain-independent meta-learning to develop a zero-shot surrogate model for automated class imbalanced learning. this model aims to recommend effective CIL pipelines for new unseen imbalanced datasets without requiring additional search. Specifically, we meta-train a two-tower model to serve as the surrogate model, adapted from recommender systems, using a pairwise ranking loss on the meta-dataset gained from collecting performance data across a wide range of CIL pipelines and a comprehensive repository of class imbalance datasets. We perform extensive experiments on 100 datasets grouped in 4 parts based on their imbalance ratio. the experimental results demonstrate the efficacy of our approach in automating the recommendation of CIL pipelines given any target imbalanced datasets. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

4th international conference on Trends in Cognitive Computation Engineering, TCCE 2022

4th International Conference on Trends in Cognitive Computat...

引用

4th international conference on Trends in Cognitive Computation Engineering, TCCE 2022

ISBN: (纸本)9789811994821

the proceedings contain 43 papers. the special focus in this conference is on Trends in Cognitive Computation Engineering. the topics include: Descriptive Analysis for Electric Bus During Non-Operational Stage;the Effectiveness Level on the Electric Buses Operation: Case Study for Affordability and Accessibility;IoMT-based Android Application for Monitoring COVID-19 Patients Using Real-Time data;A Cost-Effective Unmanned Ground Vehicle (UGV) Using Swarm Robotics Technology for Surveillance and Future Combat;neural Network-Based Obstacle and Pothole Avoiding Robot;a Comparative Study of Psychiatric Characteristics Classification for Predicting Psychiatric Disorder;Material Named Entity recognition (MNER) for Knowledge-Driven Materials Using Deep learning Approach;An Improved Optimization Algorithm-Based Prediction Approach for the Weekly Trend of COVID-19 Considering the Total Vaccination in Malaysia: A Novel Hybrid machine learning Approach;analyzing the Effectiveness of Several machine learning Methods for Heart Attack Prediction;Ensemble machine learning Technique for Identifying COVID-19 from CT Scan Images;solving the Royalty Payment Problem through Shooting Method;ECG Signal Classification Using Transfer learning and Convolutional Neural Networks;partitional Technique for Searching Initial Cluster Centers in K-means Algorithm;a Novel Ensemble Methodology to Validate Fuzzy Clusters of Big data;Model Analysis for Predicting Prostate Cancer Patient’s Survival: A SEER Case Study;quantum-Inspired Neural Network on Handwriting datasets;an Efficient and Secure data Deduplication Scheme for Cloud Assisted Storage Systems with Access Control;priority-Based Intelligent Reflecting Surface for Uplink 6G Communication;identifying Duplicate Questions Leveraging Recurrent Neural Network;stegoPix2Pix: Image Steganography Method via Pix2Pix Networks;machine learning-Based Tomato Leaf Disease Diagnosis Using Radiomics Features;low-Cost Energy Efficient Encryption Algorithm for P

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification of Faults in Dynamically Controlled Systems using Gaussian Process Regression with Hidden Markov Model 4

Detection and Classification of Faults in Dynamically Contro...

引用

4th IEEE international conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Almusawi, Muntadher Muhssan Karuna, Gotlur Suganya, E. Yenugu, Bhanu Chandar thamizhkani, B. College of Technical Engineering The Islamic University of Al Diwaniyah Department of Computers Techniques Engineering Al Diwaniyah Iraq Gokaraju Rangaraju Institute of Engineering and Technology Department of Artificial Intelligence and Machine Learning Hyderabad India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India Srkr Engineering College Department of Electrical and Electronics Engineering Bhimavaram India New Prince Shri Bhavani College of Engineering and Technology Department of Electrical and Electronics Engineering Chennai India

ISBN: (纸本)9798350352931

Nowadays, cyber security has evolved over decades in response to increasing complexity and frequency of cyber threats. Traditional protection methods are related to firewalls, anti-virus programs, and intrusion detection systems, rely on pattern matching to counter known attacks. However, these methods are limited in detecting unknown threats, highlighting the need for advanced cyber security measures. In addressing emerging and unknown threats, emphasizing the need for more proactive and adaptive security approaches. To overcome these drawbacks, a Gaussian Process Regression with Hidden Markov Model (GPR-HMM) is proposed for fault detection and classification of faults in dynamically controlled systems using Electrical Fault Detection and Classification (EFDCD) dataset. Initially, for preprocessing, data cleaning, normalization, and scaling are performed using Short-Time Fourier Transform (STFT). then, for feature extraction Multi Scale Entropy (MSE) is considered to quantify the complexity of time series data at multiple scales. At last, GPR-HMM is employed as classifier for detection and classification of faults. From the results, it clearly shows that the proposed GPR-HMM obtained accuracy value in the context faults detection when compared to existing data Entry and Office Automation (DEOA). © 2024 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Rapid pattern recognition of Electric Submersible Pump Ammeter Card Based on Artificial Neural Network 28th

Rapid Pattern Recognition of Electric Submersible Pump Ammet...

引用

28th international conference on Computational and Experimental Engineering and Sciences, ICCES 2022

作者： Wang, Biao Han, Guoqing Lu, Xin Tan, Shuai Key Laboratory of Petroleum Engineering China University of Petroleum – Beijing Beijing102249 China

ISBN: (纸本)9783031020964

Ammeter card diagnosis is a typical diagnostic method for ESP working conditions. the traditional ammeter card pattern recognition method needs to be completed manually, which contains certain technical barriers and induces subjective errors. As a machine learning algorithm, artificial neural network (ANN) can make up for these errors. For the purpose of realizing fast, accurate and objective pattern recognition. We use the relationships between the current characteristics of the collected ammeter card data after pre-processing and the actual working conditions, establishes the ANN models. Using the established ANN models to diagnose the working condition, which has the advantages that the traditional ammeter card manual identification is incomparable. In this paper, the ANN model is established and then used for the pattern recognition by the method mentioned above. By extracting the ammeter card data not involved in the training stage, the diagnostic model of the working condition is verified, and reached high accuracy, which proved the feasibility and reliability of the diagnosis of the working condition using the ANN model in quickly identifying the ammeter cards. © 2023, the Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Teacher Teaching Posture Evaluation Model: Based on OpenPose Posture recognition in the Context of Digitalization and Intelligence Integration 4

Comprehensive Teacher Teaching Posture Evaluation Model: Bas...

引用

4th international conference on machine learning and Computer Application, ICMLCA 2023

作者： Yu, Zengyi Jin, Zhou Xue, Qinda Liu, Yingchun College of Educational Science and Technology Zhejiang University of Technology Hangzhou China

ISBN: (纸本)9798400709449

In the contemporary landscape, the assessment of teaching postures among educators traditionally relies on manual techniques, such as micro-teaching sessions and peer evaluations. However, these methods are often characterized by their inefficiency. Consequently, there is a pressing demand for automated approaches to evaluate and intervene in teaching postures. In the age of data-driven intelligence, this paper introduces the development of an intelligent teaching posture evaluation model. this model is constructed upon the foundation of the OpenPose posture recognition framework, which transforms unstructured video data into structured, analyzable data. Subsequent analysis of this structured data yields valuable metrics for the assessment of teaching postures. Ultimately, through the application of a fuzzy comprehensive evaluation method, this model enables quantitative assessments of teaching postures for both pre-service and in-service educators. the experimental results demonstrate that the evaluations generated by this model closely align with traditional manual assessments. this finding holds substantial implications for enhancing the efficiency and precision of teacher skill evaluations. Additionally, it offers innovative insights and methodologies for supporting educators in improving their teaching postures. © 2023 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Transfering RGB-D Models to RGB by Multi-View Embedding Space learning for Object Detection 4

Transfering RGB-D Models to RGB by Multi-View Embedding Spac...

引用

4th international conference on Artificial Intelligence and Advanced Manufacturing, AIAM 2022

作者： Liu, Jinde Zhang, Zhang University of Chinese Academy of Sciences Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665463997

In this paper, we propose a new framework for detecting objects in RGB images captured by conventional cameras by leveraging a set of labeled RGB-D data. We formulate this problem into a new multi-view learning problem, where we have the depth information in the training set that is not available in the testing set. To solve this problem, we use a three-view CCA learning method which combines visual features, depth features, and label information together to get the projection matrices. Sufficient experiments are done to demonstrate the effectiveness of our method, and improvement measures in the future are also proposed. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

5E Teaching Model Based on Neural Network data Sampling and Clustering 4

5E Teaching Model Based on Neural Network Data Sampling and ...

引用

4th international conference on Intelligent Computing and Human-Computer Interaction, ICHCI 2023

作者： Ye, Jingjing Architecture and Design College Nanchang University Nanchang Jiangxi330031 China

ISBN: (纸本)9798350343113

Clustering analysis plays a decisive role in data processing in information exchange system. Select internal connection to make database data. Internal connections for in-group database data should be as large as possible, and internal connections for non-in-group database data should be as small as possible. through the way of teaching-Testing-Analysis and summary, students' scores are taken as the only reference index. this mode only gets the results on the final scores, which can not predict and arrange the knowledge mastery of different types of students, and also causes the uncertainty of professional courses. through the introduction of 5E teaching model, taking into account the basic indicators such as reading rate, it is easy to capture students' interest habits. In this paper, based on the basic indicators of professional courses, data sampling is carried out from the information of students' interest in courses. the indicators of self-mastery ability and learning time are the comprehensive performance of students' thinking ability and the attractiveness of professional courses. then the least square method of clustering analysis is adopted to divide the students into different types according to their interest. Finally, the clustering subdivision of data sampling is achieved. 224 pattern works were selected for experimental analysis. After the experimental test, comparative analysis of the algorithm effect, this algorithm can measure the results of the students' pattern works algorithm recognition, and judge the degree of coincidence of the test situation. Compared with random forest algorithm, genetic algorithm and traditional mode, it is obvious that the test accuracy of this algorithm is more than 97%, while the test accuracy of traditional mode is the lowest-less than 95%. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Balancing Label Imbalance in Federated Environments Using Only Mixup and Artificially-Labeled Noise 4th

Balancing Label Imbalance in Federated Environments Using O...

引用

4th international conference on pattern recognition and Artificial Intelligence, ICPRAI 2024

作者： Rabbani, Tahseen Sang, Kyle Huang, Furong University of Maryland College ParkMD20742 United States

ISBN: (纸本)9789819787043

Clients in a distributed or federated environment will often hold data skewed towards differing subsets of labels. this scenario, referred to as heterogeneous or non-iid federated learning, has been shown to significantly hinder model training and performance. In this work, we explore the limits of a simple yet effective augmentation strategy for balancing skewed label distributions: filling in underrepresented samples of a particular label class using pseudo-images. While existing algorithms exclusively train on pseudo-images such as mixups of local training data, our augmented client datasets consist of both real and pseudo-images. In further contrast to other literature, we (1) use a DP-Instahide variant to reduce the decodability of our image encodings and (2) as a twist, supplement local data using artificially labeled, training-free ‘natural noise’ generated by an untrained StyleGAN. these noisy images mimic the power spectra patterns present in natural scenes which, together with mixup images, help homogenize label distribution among clients. We demonstrate that small amounts of augmentation via mixups and natural noise markedly improve label-skewed CIFAR-10 and MNIST training. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated 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178页 << < 29 30 31 32 33 34 35 36 37 38 > >>

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：