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

2,600 篇 会议
177 册 图书
30 篇 期刊文献

馆藏范围

2,806 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

1,871 篇 工学
- 1,693 篇 计算机科学与技术...
- 831 篇 软件工程
- 330 篇 信息与通信工程
- 270 篇 电气工程
- 191 篇 生物工程
- 176 篇 控制科学与工程
- 149 篇 生物医学工程（可授...
- 67 篇 安全科学与工程
- 65 篇 光学工程
- 63 篇 机械工程
- 63 篇 化学工程与技术
- 50 篇 交通运输工程
- 43 篇 仪器科学与技术
- 39 篇 网络空间安全
- 37 篇 电子科学与技术（可...
552 篇 理学
- 292 篇 数学
- 222 篇 生物学
- 112 篇 统计学（可授理学、...
- 103 篇 物理学
- 80 篇 系统科学
- 54 篇 化学
397 篇 管理学
- 266 篇 图书情报与档案管...
- 184 篇 管理科学与工程(可...
- 64 篇 工商管理
256 篇 医学
- 201 篇 临床医学
- 117 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
26 篇 农学
7 篇 文学
5 篇 艺术学
3 篇 军事学

主题

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

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

2,717 篇 英文
75 篇 其他
35 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 2807 条记录，以下是51-60 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：

the Hidden Influence of Latent Feature Magnitude When learning with Imbalanced data 4th

The Hidden Influence of Latent Feature Magnitude When Learn...

引用

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

作者： Dablain, Damien A. Chawla, Nitesh V. Department Computer Science and Lucy Family Institute for Data and Society University of Notre Dame Notre DameIN46553 United States

ISBN: (纸本)9789819787012

machine learning (ML) models have difficulty generalizing when the number of training class instances are numerically imbalanced. the problem of generalization in the face of data imbalance has largely been attributed to the lack of training data for under-represented classes and to feature overlap. the typical remedy is to implement data augmentation for classes with fewer instances or to assign a higher cost to minority class prediction errors or to undersample the prevalent class. However, we show that one of the central causes of impaired generalization when learning with imbalanced data is the inherent manner in which ML models perform inference. these models have difficulty generalizing due to their heavy reliance on the magnitude of encoded signals. During inference, the models predict classes based on a combination of encoded signal magnitudes that linearly sum to the largest scalar. We demonstrate that even with aggressive data augmentation, which generally improves minority class prediction accuracy, parametric ML models still associate a class label with a limited number of feature combinations that sum to a prediction, which can affect generalization. © the Editor(s) (if applicable) and 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

ESL: Explain to Improve Streaming learning for Transformers 27th

ESL: Explain to Improve Streaming Learning for Transformer...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Ayyar, Meghna P. Benois-Pineau, Jenny Zemmari, Akka LaBRI CNRS Univ. Bordeaux UMR 5800 Talence33400 France

AI systems in real-world scenarios must be able to60;learn continuously from a stream of data while adapting quickly to concept drift. We propose a training strategy called Explain to improve Streaming learning (ES... 详细信息

ISBN: (纸本)9783031781889

AI systems in real-world scenarios must be able to learn continuously from a stream of data while adapting quickly to concept drift. We propose a training strategy called Explain to improve Streaming learning (ESL) for the online streaming learning setting where the models have to learn from data on the fly in a single pass. ESL leverages model explanations to identify salient input regions, guiding the streaming learner to focus on these regions by masking the non-salient ones during training. In this work, we focus on using transformers for streaming learning and adapt our CNN-based Feature Explanation Method (FEM) [13] to propose Rollout-FEM with ESL for transformers. We validate the ESL strategy for our streaming learners Entropy-based Move-To-data (EMTD), its variant EMTD with re-targetting (EMTDR), and the state-of-the-art streaming learning method ExStream [14] and benchmark it on two streaming learning datasets and a real-world egocentric video dataset. Our experiments demonstrate that training with the explanation-based ESL strategy has a better performance than standard training, and EMTDR with ESL achieves the best performance compared to ExStream across the datasets. © 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

DQN Trader: Reinforcement learning for Automated Trading 6th

DQN Trader: Reinforcement Learning for Automated Trading

引用

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

作者： Bhati, Avesh Kumar Kumbhar, Vidya Singh, T.P. Shah, Sahil K. Maharashtra Pune India

ISBN: (纸本)9789819780891

Stock markets have witnessed a surge in interest in automated trading systems, driven by their potential to enhance investment decisions and increase returns. this study explores the application of the Deep Q-Network (DQN) Trader, a reinforcement learning algorithm, in the domain of automated trading. the primary objective is to evaluate the efficacy and performance of the DQN Trader in real financial markets. the research delves into the theoretical foundations of DQN, implementation challenges, training, and evaluation methodologies, presenting comprehensive outcomes. the extensive numerical experiments on historical data sets of GOOGL, TSLA, AMZN, AAPL, and NSEI reveal that the DQN Trader exhibits a notable ability to generate profitable trading decisions. these outcomes provide valuable insights for both traders and researchers as the model gave a profit of 28% on the overall period, highlighting the model’s adaptability to dynamic market conditions and its potential contribution to automated trading strategies. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Reinforcement 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

Convolutional Neural Network Segmentation for Satellite Imagery data to Identify Landforms Using U-Net Architecture 6th

Convolutional Neural Network Segmentation for Satellite Imag...

引用

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

作者： Goswami, Mitul Mohanty, Suneeta Dey, Sainath Mukherjee, Aniruddha Pattnaik, Prasant Kumar School of Computer Engineering KIIT Deemed To Be University Odisha Bhubaneswar India

ISBN: (纸本)9789819780891

this study demonstrates a novel use of the U-Net architecture in the field of semantic segmentation to detect landforms using preprocessed satellite imagery. the study applies the U-Net model for effective feature extraction by using convolutional neural network (CNN) segmentation techniques. Dropout is strategically used for regularization to improve the model’s perseverance, and the Adam optimizer is used for effective training. the study thoroughly assesses the performance of the U-Net architecture utilizing a large sample of preprocessed satellite topographical images. the model excels in semantic segmentation tasks, displaying high-resolution outputs, quick feature extraction, and flexibility to a wide range of applications. the findings highlight the U-Net architecture’s substantial contribution to the advancement of machine learning and image processing technologies. the U-Net approach, which emphasizes pixel-wise categorization and comprehensive segmentation map production, is helpful in practical applications such as autonomous driving, disaster management, and land use planning. this study not only investigates the complexities of U-Net architecture for semantic segmentation but also highlights its real-world applications in image classification, analysis, and landform identification. the study demonstrates the U-Net model’s key significance in influencing the environment of modern technology. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Detecting Toxic Comments in Bengali Language 6th

Detecting Toxic Comments in Bengali Language

引用

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

作者： Mondal, Abir Roy, Kingshuk Das, Susmita Dutta, Arpita Techno Main Salt Lake Kolkata India School of Computer Science Engineering and Technology Bennett University Greater Noida Uttar Pradesh India

ISBN: (纸本)9789819780891

An increasing number of users utilize public platforms to communicate. the languages used by general public are diverse and varied. Detection of the offensive words utilized by people on these online platforms is challenging. Unstructured texts, inappropriate models combined with low-resource datasets, cause the research on less prevalent languages quite arduous. In this chapter, we have attempted to address the problem of offensive comments detection in Bengali, which is a low-resource language with limited approaches. Our approach is a binary classification model that successfully classifies toxic comments from nontoxic comments. Natural Language Processing techniques have been implemented for preprocessing of the unstructured data. Deep learning model with a modified version of BERT architecture has been applied. this model has been pretrained on a large corpus of Bengali text and efficiently detects the offensive words in the social media Bengali comments. the proposed approach is performing effectively when compared with different baselines. © 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

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

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281页 << < 2 3 4 5 6 7 8 9 10 11 > >>

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：