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

2,603 篇 会议
179 册 图书
30 篇 期刊文献

馆藏范围

2,811 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

1,873 篇 工学
- 1,691 篇 计算机科学与技术...
- 833 篇 软件工程
- 322 篇 信息与通信工程
- 274 篇 电气工程
- 191 篇 生物工程
- 170 篇 控制科学与工程
- 153 篇 生物医学工程（可授...
- 67 篇 安全科学与工程
- 65 篇 光学工程
- 64 篇 化学工程与技术
- 57 篇 机械工程
- 50 篇 交通运输工程
- 44 篇 仪器科学与技术
- 38 篇 电子科学与技术（可...
- 33 篇 网络空间安全
554 篇 理学
- 293 篇 数学
- 222 篇 生物学
- 113 篇 统计学（可授理学、...
- 104 篇 物理学
- 80 篇 系统科学
- 55 篇 化学
398 篇 管理学
- 268 篇 图书情报与档案管...
- 183 篇 管理科学与工程(可...
- 63 篇 工商管理
260 篇 医学
- 201 篇 临床医学
- 121 篇 基础医学(可授医学...
- 70 篇 药学(可授医学、理...
- 33 篇 公共卫生与预防医...
47 篇 法学
- 42 篇 社会学
39 篇 教育学
- 35 篇 教育学
29 篇 经济学
27 篇 农学
7 篇 文学
5 篇 艺术学
2 篇 军事学

主题

483 篇 machine learning
482 篇 data mining
272 篇 pattern recognit...
160 篇 feature extracti...
152 篇 deep learning
148 篇 artificial intel...
112 篇 support vector m...
106 篇 machine learning...
94 篇 data mining and ...
85 篇 training
76 篇 data models
74 篇 accuracy
59 篇 computer imaging...
56 篇 learning systems
55 篇 neural networks
47 篇 information syst...
47 篇 convolutional ne...
46 篇 computer applica...
45 篇 predictive model...
44 篇 big data

机构

15 篇 national univers...
15 篇 the islamic univ...
15 篇 fujian provincia...
13 篇 medical technica...
13 篇 school of inform...
13 篇 altoosi universi...
11 篇 guangdong univer...
10 篇 indian statistic...
10 篇 school of manage...
10 篇 department of bu...
9 篇 institute of env...
9 篇 department of to...
8 篇 xi'an university...
8 篇 al-zahraa univer...
8 篇 college of mecha...
8 篇 chinese academy ...
7 篇 school of inform...
7 篇 zhejiang univers...
7 篇 institute of aut...
7 篇 unsw sydney

作者

17 篇 chang kuo-chi
12 篇 de-shuang huang
10 篇 chu kai-chun
10 篇 mottl vadim
9 篇 chang fu-hsiang
9 篇 wang hsiao-chuan
8 篇 zheng-guang wu
8 篇 hongyi li
8 篇 chaojie li
8 篇 biao luo
8 篇 petra perner
8 篇 long cheng
7 篇 yuhui shi
7 篇 krasotkina olga
7 篇 alexander gelbuk...
7 篇 sung tien-wen
7 篇 ying tan
7 篇 lin yuh-chung
6 篇 ryszard tadeusie...
6 篇 marcin korytkows...

语言

2,724 篇 英文
73 篇 其他
34 篇 中文
1 篇 土耳其文

检索条件"任意字段=6th International Conference on Machine Learning and Data Mining in Pattern Recognition"

共 2812 条记录，以下是61-70 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：

Web Development and Evaluation of Instructional Objectives’ Quality Using Natural Language Processing 6th

Web Development and Evaluation of Instructional Objectives’...

引用

6th international conference on Computational Intelligence in pattern recognition, CIPR 2024

作者： Mohanta, Jyotiprava Jain, Mahim Jain, Mahim M. Mandal, Shyamal Kumar Das Advance Technology Development Centre Indian Institute of Technology Kharagpur India Aerospace Engineering Indian Institute of Technology Kharagpur India

ISBN: (纸本)9789819780891

Outcome-based education is currently recommended in every field of education by the accreditation bodies. Outcome-based education is the process of developing the curriculum in a well-defined framework. the stated outcome or the instructional objective should be properly defined for successful implementation. Here, a methodology is proposed where the curriculum designer can check whether the instructional objective is properly designed. the methodology consists of website development and a machine learning model (ML) using natural language processing. the input to the model is an instructional objective statement, and the result will be in three categories: poor, good, and perfect. the website consists of a Flask-written backend and a Next. js-developed frontend. the backend was integrated with the ML model. For the model, the Bidirectional Encoder Representations from Transformers model is used. the designed model was applied to 50 instructional objective datasets for training the model and 40 datasets for testing the prediction. the BERT model was found to be effective. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

An Approach Towards learning K-Means-Friendly Deep Latent Representation 27th

An Approach Towards Learning K-Means-Friendly Deep Latent Re...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Roy, Debapriya Institute of Engineering and Management Kolkata India

ISBN: (纸本)9783031781650

Clustering is a long-standing problem area in data mining. the centroid-based classical approaches to clustering mainly face difficulty in the case of high dimensional inputs such as images. With the advent of deep neural networks, a common approach to this problem is to map the data to some latent space of comparatively lower dimensions and then do the clustering in that space. Network architectures adopted for this are generally autoencoders that reconstruct a given input in the output. To keep the input in some compact form, the encoder in AE’s learns to extract useful features that get decoded at the reconstruction end. A well-known centroid-based clustering algorithm is K-means. In the context of deep feature learning, recent works have empirically shown the importance of learning the representations and the cluster centroids together. However, in this aspect of joint learning, recently a continuous variant of K-means has been proposed;where the softmax function is used in place of argmax to learn the clustering and network parameters jointly using stochastic gradient descent (SGD). However, unlike K-means, where the input space stays constant, here the learning of the centroid is done in parallel to the learning of the latent space for every batch of data. Such batch updates disagree with the concept of classical K-means, where the clustering space remains constant as it is the input space itself. To this end, we propose to alternatively learn a clustering-friendly data representation and K-means based cluster centers. Experiments on some benchmark datasets have shown improvements of our approach over the previous approaches. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

A Review of Deep learning Techniques for Early Detection and Categorization of Lung Cancer 6th

A Review of Deep Learning Techniques for Early Detection and...

引用

6th international conference on Intelligent Communication, Control and Devices, ICICCD 2024

作者： Joshi, Swati Mishra, Raj Gaurav Sivagaminathan, P.G. School of Engineering Ajeenkya D Y Patil University MH Pune India Deemed-to-be-University MP Indore India

ISBN: (纸本)9789819783281

Lung cancer becomes critical to human wellness because of its fast-rising rates of disease and loss of life. As a valuable method for increasing the diagnosis precision and detecting cancer earlier, low-dose computed tomography (LDCT) assessment is developed, which leads to decreasing death rates. Designing a computer-aided detection (CADe) method is of great medical significance when using CT data because of its unpredictable nature. Such system would benefit radiologists by helping them to automatically analyze nodules, increasing accuracy of their diagnoses, and enabling prompt patient interventions. An outline of artificial intelligence (AI) systems for pulmonary nodule detection is presented in this work. Findings show the increasing usage of machines and deep learning methods, demonstrating their effectiveness in detecting, classifying, and are tested in. this study confirms that AI helps identify and analyze lung cancer and reduces exposure. With remarkable advances in deep learning, medical imaging studies have occurred as a major research field. this paper provides a broad review of the richness of lung image evaluation by means of deep learning techniques, focusing on different pattern recognition tasks such as classification and local/identification, distribution, and registration. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

PostAugment: Adversarial data Augmentation with Hard Sample Suppression by Incorrect Class Likelihood 27th

PostAugment: Adversarial Data Augmentation with Hard Sample...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Sawada, Azusa Shibata, Takashi Yokoyama, Keiko Yachida, Shoji Hosoi, Toshinori NEC Corporation Nakahara-ku Shimonumabe Kawasaki1753 Japan

ISBN: (纸本)9783031781919

We propose an adversarial automatic data augmentation with hard sample suppression by incorrect class likelihood for time series data. Automatic data augmentation (ADA) is a practical framework when the number of training data is small. In particular, an ADA based on adversarial loss, such as TeachAugment, can improve classification accuracy in optimizing complex transformation parameters with class and instance dependencies. In this paper, we aim to extend adversarial ADA for image recognition to time series data. the critical challenge is that data augmentation for time series data is more difficult than that for images in designing a transformation function that does not cross the discriminant class boundary. When existing ADA frameworks are naively applied to time series data, the transformation function often generates augmented data similar to the incorrect class. As a result, this overly hard-to-identify data degrades the accuracy of a target classifier. In general, this hard-to-identify data near the class boundary has a high likelihood both in the correct and incorrect classes. the proposed method can reduce this hard-to-identify data by introducing a novel fidelity loss that suppresses only the likelihood of the incorrect class. Comprehensive experiments on two datasets demonstrate the effectiveness of the proposed method. the project code is included in the supplemental material. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

On Trace of PGD-Like Adversarial Attacks 27th

On Trace of PGD-Like Adversarial Attacks

引用

27th international conference on pattern recognition, ICPR 2024

作者： Zhou, Mo Patel, Vishal M. Johns Hopkins University BaltimoreMD21218 United States

ISBN: (纸本)9783031781216

Adversarial attacks pose security concerns to deep learning applications, but their characteristics are under-explored. Yet largely imperceptible, a strong trace could have been left by PGD-like attacks in an adversarial example. Recall that PGD-like attacks trigger the "local linearity" of a network, which implies different extents of linearity for benign or adversarial examples. Inspired by this, we construct an Adversarial Response Characteristics (ARC) feature to reflect the model’s gradient consistency around the input to indicate the extent of linearity. Under certain conditions, it qualitatively shows a gradually varying pattern from benign example to adversarial example, as the latter leads to Sequel Attack Effect (SAE). To quantitatively evaluate the effectiveness of ARC, we conduct experiments on CIFAR-10 and ImageNet in a challenging setting. the results suggest that SAE, reflected through the ARC feature, is an effective and unique trace of PGD-like attacks. Our method is designed to generalize with a scarce amount of data, which remains feasible even when access to the full training dataset is impossible. Code: https://***/cdluminate/advtrace. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Exploring the Role of Artificial Intelligence for pattern recognition of Textile Sorting and Recycling for Circular Economy 6

Exploring the Role of Artificial Intelligence for Pattern Re...

引用

6th international conference on Industry 4.0 and Smart Manufacturing, ISM 2024

作者： Karmali, Irfan Mohammed Valilai, Omid Fatahi Constructor University Bremen Campus Ring 1 Bremen28759 Germany

In an era where sustainability is a vital concern, the textile industry is a major obstacle that stands in the way of addressing environmental challenges, climate change, pollution, and biodiversity loss. the integration of Artificial Intelligence (AI) into the textile recycling process holds significant promise for advancing the circular economy agenda. AI technologies offer innovative solutions for automating pattern recognition tasks, thereby enhancing the efficiency and accuracy of textile sorting and recycling processes. this paper endeavors to explore AI algorithms specifically tailored for soiled cloth detection in textile products. through a comprehensive analysis of existing literature studies, the paper aims to propose an approach that addresses the unique challenges associated with identifying and classifying soiled cloth. this research focuses on investigating and developing unsupervised computer vision techniques for the initial detection and segmentation of stains on textile materials. the paper focuses on the capabilities of two methods, (1) Otsu's thresholding and (2) K-Means clustering, which do not require extensive training data or deep learning models. Practical conditions are examined for complex backgrounds and uneven lighting conditions and capability for accurate separation of stains from fabrics with similar colors or textures. the results show that for both methods to work efficiently, they require even and bright lighting conditions on the textiles. Moreover, the paper has discussed the challenges faced for real implementation of models for textiles being sorted on factory line. © 2025 the Authors. Published by Elsevier B.V.

关键词： Circular economy

来源：评论

学校读者我要写书评

暂无评论

Automating the labeling of industrial data: A challenge and an opportunity to boost the development of Condition-Based Monitoring in Industry 4.0 6

Automating the labeling of industrial data: A challenge and ...

引用

6th international conference on Industry 4.0 and Smart Manufacturing, ISM 2024

作者： Lepetit, Philippe Belmerhnia, Leïla Peysson, Flavien Predict 19 avenue Foret de la Haye Vandoeuvre-lès-Nancy54500 France

this paper addresses a critical challenge hindering the widespread adoption of smart manufacturing and Condition-Based Maintenance: the contextualization step for behavioral indicator extraction. Contextualization is an essential step for a reliable and robust assessment of the health condition of an operating machine. this process involves identifying and labeling patterns from raw data prior to the extraction of behavioral indicators. From a machine learning perspective, this problem corresponds to pattern matching and time series classification. However, traditional machine learning techniques only address the later and suffers from a scarcity of labeled data. To highlight this issue, we present an industrial-focused problem formulation and demonstrate it through two use cases, applying a modified Dynamic Time Warping (DTW) algorithm. the results show that while the DTW-based method is one of the few, if not the only, that addresses industry-specific constraints, its performance varies significantly across applications and lacks scalability for complex manufacturing processes. the paper concludes by discussing potential research directions to overcome DTW's limitations by leveraging AI-based methods. © 2024 the Authors. Published by Elsevier B.V.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

FL-PSeC: Federated learning-Pseudo Labeled Medical Image Segmentation with Personalized Class Balancing Semi-supervised Approach 27th

FL-PSeC: Federated Learning-Pseudo Labeled Medical Image Seg...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Priya, Ishu Mohan, C. Krishna Indian Institute of Technology Hyderabad Hyderabad India

ISBN: (纸本)9783031781919

Medical image segmentation plays a pivotal role in modern healthcare applications, significantly assisting healthcare professionals in making accurate diagnosis. However, limited annotated data hinders the development of robust medical image segmentation models due to strict patient privacy regulations. Semi-supervised learning offers a solution by leveraging both labeled and unlabeled data, enabling models to learn from larger datasets while capitalizing on limited labeled data. Despite its benefits, semi-supervised learning continues to face concerns related to data privacy. Federated learning (FL) addresses these concerns by enabling multiple parties to collaboratively train a model without sharing their local data. As the need for data-efficient and privacy-preserving machine learning techniques grows, semi-supervised federated learning emerges as a potential paradigm to tackle this issue. Our work underscores the importance of semi-supervised federated learning approaches that can effectively leverage both labeled and unlabeled data distributed across multiple sites. However, non-Independent and Identically Distributed (non-IID) data and class data imbalance remain significant challenges in semi-supervised federated learning, hindering overall performance. To address these issues, we propose the Federated learning-Pseudo labeled Segmentation with Class balance (FL-PSeC) framework, which focuses on tackling class imbalance across clients’ local data by assigning higher weightage to underrepresented classes when generating annotations from unlabeled data. this strategy not only improves the IID nature of the data but also leads to enhanced global model performance. Our experiments on HAM10000, BUS, BUSIS, and UDIAT datasets demonstrate the efficacy of FL-PSeC in adapting to a class imbalance in FL, outperforming existing methods. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Advancing 3D Mesh Analysis: A Graph learning Approach for Intersecting 3D Geometry Classification 27th

Advancing 3D Mesh Analysis: A Graph Learning Approach for I...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Böhm, Stefan Andreas Neumayer, Martin Zagar, Bare Luka Riß, Fabian Kortüm, Christian Knoll, Alois Technical University of Munich Boltzmannstraße 3 Garching85748 Germany Rosenheim Technical University of Applied Sciences Hochschulstraße 1 Rosenheim83024 Germany

ISBN: (纸本)9783031781650

Driven by increasing customer demands, manufacturing processes now encompass increasingly intricate workflows. the industry uses computer-aided process planning to manage these complex manufacturing processes effectively. A crucial task here is to analyze product data and determine the required machining features, represented as 3D mesh geometries. However, a notable challenge arises, particularly with custom products, where the interpretation of the 3D mesh geometry varies significantly depending on the available machinery and expert preferences. this study introduces a configurable automated feature recognition framework based on expert knowledge. Experts can use a configurable synthetic data generator to encode their requirements within this framework via the training data. A machine-learning graph classification approach is used to recognize the 3D geometries of machining features in the generated data, based on to the user requirements. the system accomplishes this without requiring for data conversion into alternative formats, such as voxel or pixel representations, like other approaches are forced to. © the Author(s) 2025.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Neural Topic Model with Distance Awareness 27th

Neural Topic Model with Distance Awareness

引用

27th international conference on pattern recognition, ICPR 2024

作者： Chen, Shangyu Zhao, He Huynh, Viet Phung, Dinh Cai, Jianfei FIT-DSAI Monash University Exhibition Walk ClaytonVIC3168 Australia CSIRO’s Data61 Garden St EveleighNSW2015 Australia School of Science Edith Cowan University 270 Joondalup Dr JoondalupWA6027 Australia

ISBN: (纸本)9783031781889

Neural topic models (NTMs) have shown their success in topic modeling with a wide range of applications in text analysis. NTMs based on generative models prioritize document representations with good reconstruction capabilities, but they are they are insufficient in preserving distances between documents in the topic space. To bridge this gap, inspired by manifold learning, we propose a neural topic model that enables the reflection of word-to-word relationships onto topic-to-topic associations. this is achieved by approximating the distances between documents in the word space within the topic space. Extensive experiments demonstrate that the proposed model outperforms state-of-the-art NTMs in improving the quality of learned topics, as evidenced by metrics such as purity, diversity, coherence. Beyond that, the model can provide more interpretable low dimensional visualizations of documents. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine 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282页 << < 3 4 5 6 7 8 9 10 11 12 > >>

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：