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

1,730 篇 会议
45 册 图书
11 篇 期刊文献

馆藏范围

1,785 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

1,223 篇 工学
- 1,093 篇 计算机科学与技术...
- 628 篇 软件工程
- 254 篇 信息与通信工程
- 199 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
- 40 篇 仪器科学与技术
- 40 篇 安全科学与工程
- 29 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...
455 篇 理学
- 199 篇 数学
- 196 篇 生物学
- 144 篇 物理学
- 83 篇 统计学（可授理学、...
- 51 篇 系统科学
- 45 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

239 篇 machine learning
184 篇 deep learning
140 篇 pattern recognit...
110 篇 feature extracti...
91 篇 support vector m...
88 篇 data mining
79 篇 accuracy
75 篇 training
59 篇 convolutional ne...
51 篇 machine learning...
48 篇 data models
46 篇 artificial intel...
41 篇 computational mo...
40 篇 neural networks
39 篇 face recognition
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

1,587 篇 英文
190 篇 其他
26 篇 中文

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

共 1786 条记录，以下是581-590 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：

Enhancing OCR Model Training with Synthetic data: A Case Study with SROIE dataset

Enhancing OCR Model Training with Synthetic Data: A Case Stu...

引用

Smart Information Systems and Technologies (SIST), IEEE international conference on

作者： Yuriy Yashchuk Yuliana Yurchenko Nataliia Yurchenko Yurii Andrashko Ivan Franko National University of Lviv Lviv Ukraine Uzhhorod National University Uzhhorod Ukraine

ISBN: (数字)9798350374865

ISBN: (纸本)9798350374872

this paper investigates the impact of synthetic data on the training effectiveness of optical character recognition (OCR) models. With the rapid advancement in machine learning, the availability of diverse and extensive datasets has become crucial for developing robust OCR systems. However, the scarcity of annotated real-world data poses significant challenges. this study focuses on performing an OCR task using the SROIE dataset, which presents a real-world challenge due to prevalent issues such as paper and ink corruption, inconsistent lighting conditions, variable fonts, colors, background noise, and imaging distortions. We introduce an approach to generating synthetic data, aiming to mimic those peculiarities. By conducting thorough experiments using the SROIE dataset and a custom synthetic training dataset, we demonstrate substantial improvements in model performance, thereby underscoring the potential of synthetic data in OCR applications.

关键词： Training Recurrent neural networks Computational modeling Optical character recognition Transfer learning Optical distortion Distortion

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Method for Marine Engine under Variable Working Conditions Based on Adversarial Subdomain Adaptation

Fault Diagnosis Method for Marine Engine under Variable Work...

引用

machine learning and Intelligent Systems Engineering (MLISE), international conference on

作者： Xiaorong Zhang Mingshun Zhou Peng Wang Qingdao Ocean Shipping Mariners College Qingdao Shandong

ISBN: (数字)9798350375077

ISBN: (纸本)9798350375084

Marine engines have a high risk of failure during navigation and face issues such as varying operating conditions and complex faults. Existing research mainly focuses on fault diagnosis of marine engines under single operating conditions, neglecting the applicability of these methods under other conditions. To address this issue, this paper employs domain adaptation techniques to study cross-condition fault diagnosis of marine engines. Firstly, a self-calibrating convolutional neural network is used to extract health state features from engine operation data. Meanwhile, by integrating adversarial and subdomain adaptation techniques, the distribution differences in global domains and local subdomains under different operating conditions are reduced, thereby improving the fault diagnosis accuracy under variable conditions. Finally, the effectiveness of the diagnostic model is validated based on simulated marine engine fault data. For the designed one-to-one and one-to-many condition transfer tasks, the average fault diagnosis accuracy reaches approximately 90%, achieving higher recognition accuracy compared to other methods. the research results can provide theoretical reference for fault diagnosis of marine engines under variable operating conditions.

关键词： Fault diagnosis Adaptation models Accuracy Navigation Face recognition machine learning Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Micro-Expression recognition Method Based on Transformer with Separable Self-Attention

Micro-Expression Recognition Method Based on Transformer wit...

引用

machine learning and Intelligent Systems Engineering (MLISE), international conference on

作者： Peng Yang Zhifeng Zeng Tianyuan Zhu Department of Computer Science Zhuhai College of Science and Technology Zhuhai China Department of Aliyun Big Data Zhuhai College of Science and Technology Zhuhai China

ISBN: (数字)9798350375077

ISBN: (纸本)9798350375084

Micro-expressions, which are brief facial movements reflecting an individual's emotions and psychological state, are crucial in fields like psychological counseling and trust evaluation. However, they are challenging to capture, and traditional methods struggle with effective recognition. While neural networks are a primary tool for this task, they are limited by their large number of parameters and slow processing speeds. Transformer architectures have shown promise in micro-expression recognition but face similar challenges. To address these issues, an improved HTNet model, called Lightweight HTNet (LWHTNet), has been proposed. Specifically, by using a Separable Self-Attention mechanism to replace the multi-head attention mechanism in Transformer layers and incorporating depthwise separable convolutions in the block aggregation layers, the model reduces the number of training parameters. In experiments, LWHTNet demonstrated strong performance on composite datasets, achieving an Unweighted F1 Score (UF1) of 0.8498 and an Unweighted Average Recall (UAR) of 0.8307. Additionally, the optimized model showed significant improvements in inference speed and parameter efficiency.

关键词： Training Employee welfare Computer vision Face recognition Neural networks Psychology Transformers

来源：评论

学校读者我要写书评

暂无评论

Image recognition Using machine learning for Classifying Finger Print recognition using direction filtering

Image Recognition Using Machine Learning for Classifying Fin...

引用

international conference on Computation, Automation and Knowledge Management (ICCAKM)

作者： Neeraj Bhargava Ritu Bhargava Swapnesh Taterh Pramod Singh Rathore Apoorva Bhowmick MDS University Ajmer India Sophia Girls' College (Autonomous) Ajmer India Amity University Rajasthan India Manipal University Jaipur Jaipur India United Nations Secretariate New Yourk NY USA Baghdad Iraq

Image processing is the new trend of implementing the image classification and many kinds of researchers are being working on this kind of implementation to process the data in the form of images. the current paper is focusing on identifying the images and processing the fingerprints which hold the secret information. We learn about steganography preparation, that involves the images which consists of secret information, and we need to decrypt that kind of information with some tools and techniques. Here in this article, we are focusing on the new concept of image processing which can consider the fingerprint of the human to hide secret information. this kind of information is very sensitive and can be shared with anyone and the concept behind photo-response non- uniformity is the way of linking pictures to the camera sensors which are having well established finger printing information. the information we transform from one user to the other user in the government organizations must be confidential and we are performing better PRNU with machine learning and the implementation consists of different neural network approaches and these approaches are more likely to work with existing approaches of PRNU. machine learning and image processing will lead the concept of highest secured data transmission with the data encrypted in the form of fingerprint.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Spectrum Busting: A Federated learning Approach for Radio Fingerprinting for Defence Forces

Enhancing Spectrum Busting: A Federated Learning Approach fo...

引用

international conference on Applied Electromagnetics, Signal Processing and Communication (AESPC)

作者： Jyoti Ranjan Satapathy John Ayeelyan Rajesh M Bodade Faculty of Communication Engineering Military College of Telecommunication Engineering Indore India

ISBN: (数字)9798331528171

ISBN: (纸本)9798331528188

Each transmitter has a unique transmission pattern due to semiconductor variations. Using Software Defined Radio (SDR) and Artificial Intelligence (AI), transmitters can be identified through their Radio Frequency patterns. With the growing number of transmitters, ensuring security, availability, and data privacy is crucial for military and civilian applications. this paper introduces a novel hybrid method for radio fingerprinting via RF classification and proposes a Federated learning (FL) model, achieving 86% accuracy in the client model and 89% in the universal model. the solution addresses spectrum sensing, signal classification, spoofing countermeasures and ensures security, low latency, and resource optimisation.

关键词： Radio frequency Semiconductor device measurement Heuristic algorithms Radio transmitters pattern classification Fingerprint recognition Sensors Security Artificial intelligence Software radio

来源：评论

学校读者我要写书评

暂无评论

Consistency-based semi-supervised learning for point cloud classification 4

Consistency-based semi-supervised learning for point cloud c...

引用

4th international conference on pattern recognition and Artificial Intelligence, PRAI 2021

作者： Chen, Lingli Zhang, Yan Lin, Yanan Jiang, Mengxi Huang, Yunan Lei, Yunqi Xiamen University Department of Computer Science and Technology Xiamen China

ISBN: (纸本)9781665413220

Under the strong supervision information of a large number of training samples with ground-truth labels, the point cloud classification techniques have achieved great success. However, in real tasks, it is difficult to get strong supervision information like fully ground-truth labels due to the high cost of the data labeling process. thus, it is desirable to work with weak supervision. this paper presents a semi-supervised learning framework based on consistency constraints on the point cloud to solve the classification task. the key to the framework mainly includes consistency constraints and pseudo-label generation. the former uses consistency constraints to encourage the model to output consistent predictions on the original and the perturbed point cloud, which avoids overfitting due to limited labeled data. the latter generates high-quality pseudo-labels for unlabeled point clouds to strengthen the discriminative supervision of the model. By fully mining the labeled and unlabeled point clouds, the generalization ability of the model is improved. On the 3D point cloud benchmark ModelNet40 [19], with only 10% labeled data, our proposed approach performs comparable results to the supervised approaches. © 2021 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Enhanced Medicinal Plant Identification: Leveraging machine learning and Image Processing for Accurate Raw Material recognition

Enhanced Medicinal Plant Identification: Leveraging Machine ...

引用

Intelligent Technologies (CONIT), international conference on

作者： G. Fayaz Hussain Sayeeda Sameera Mahnaaz Sheema Parveen Shaik Shazia Tazeen Arigela Sravika Dept. of CSE Ravindra College of Engineering for Women Kurnool India Dept. of CSE(AI) Ravindra College of Engineering for Women Kurnool India

ISBN: (数字)9798350349900

ISBN: (纸本)9798350349917

data on medicinal plants and raw materials encompasses details about diverse botanical resources employed for their healing attributes in both traditional and contemporary medical practices. the difficulties in improving the identification of medicinal plants include fluctuations in image quality caused by elements such as lighting, background clutter, and camera angles, which affect the accuracy of algorithms, as well as the shortage of varied training data, potentially resulting in biases or inaccuracies during recognition. To address the challenges mentioned earlier, utilize customized Extended Convolutional Neural Network (CNN) techniques capable of managing variations in image quality and utilizing diverse training data to enhance the precision of medicinal plant identification. the Extended CNN approach provides better flexibility in handling varied image attributes and heightened precision in medicinal plant recognition, thanks to its specialized architecture and utilization of extensive training datasets.

关键词： Medicinal plants Training Image quality Accuracy Image recognition Computational modeling Training data

来源：评论

学校读者我要写书评

暂无评论

A Novel Image Deep learning for recognition of Silicon Photonics Redistribution Layer

A Novel Image Deep Learning for Recognition of Silicon Photo...

引用

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

作者： Jen-Kuang Fang Chao-Kai Hung Peng Yang Wen-Long Lu Chien-Wei Chang Advanced Semiconductor Engineering Inc. Kaohsiung Taiwan

ISBN: (数字)9798350360721

ISBN: (纸本)9798350360738

Due to the design requirements for miniaturization and high-density placement of silicon photonics (SiPh) components in integrated circuit (IC) packaging, the system in package (SiP) process and equipment have become important but challenging. Automatic optical inspection (AOI) detection equipment in IC packaging lines is also important in identifying redistribution layer (RDL) anomalies that affect signal transmission. If the AOI misrecognition rate is too high, the production yield and overall equipment performance are lowered. To solve the above problems, we proposed a novel Pix2Pix generative adversarial network (GAN) algorithm based on machine learning methods. the new feature extraction method has demonstrated highly sensitive image detection capabilities after processing tens of thousands of huge SiPh RDL image databases.

关键词： Deep learning System-in-package Image recognition Production Generative adversarial networks Silicon photonics Optical imaging

来源：评论

学校读者我要写书评

暂无评论

Leveraging Semi-Supervised learning to Enhance data Mining for Image Classification under Limited Labeled data

Leveraging Semi-Supervised Learning to Enhance Data Mining f...

引用

Electronic Information Engineering and Computer Communication (EIECC), international conference on

作者： Aoran Shen Minghao Dai Jiacheng Hu Yingbin Liang Shiru Wang Junliang Du University of Michigan Ann Arbor USA Columbia University New York USA Tulane University New Orleans USA Northeastern University Seattle USA Dartmouth College Hanover USA Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798331534622

ISBN: (纸本)9798331534639

In the 21st-century information age, with the development of big data technology, effectively extracting valuable information from massive data has become a key issue. Traditional data mining methods are inadequate when faced with large-scale, high-dimensional and complex data. Especially when labeled data is scarce, their performance is greatly limited. this study optimizes data mining algorithms by introducing semi-supervised learning methods, aiming to improve the algorithm's ability to utilize unlabeled data, thereby achieving more accurate data analysis and pattern recognition under limited labeled data conditions. Specifically, we adopt a self-training method and combine it with a convolutional neural network (CNN) for image feature extraction and classification, and continuously improve the model prediction performance through an iterative process. the experimental results demonstrate that the proposed method significantly outperforms traditional machine learning techniques such as Support Vector machine (SVM), XGBoost, and Multi-Layer Perceptron (MLP) on the CIFAR-10 image classification dataset. Notable improvements were observed in key performance metrics, including accuracy, recall, and F1 score. Furthermore, the robustness and noise-resistance capabilities of the semi-supervised CNN model were validated through experiments under varying noise levels, confirming its practical applicability in real-world scenarios.

关键词： Support vector machines Visualization Accuracy Semisupervised learning Feature extraction Classification algorithms Behavioral sciences data mining Convolutional neural networks Image classification

来源：评论

学校读者我要写书评

暂无评论

A machine learning Approach for Detection of Heart Diseases Using Wearable Devices

A Machine Learning Approach for Detection of Heart Diseases ...

引用

Smart Information Systems and Technologies (SIST), IEEE international conference on

作者： Spandiyar Abutalip Meirzhan Baikuvekov Duisen Zanggar Department of Information Systems Al-Farabi Kazakh National University Almaty Kazakhstan Kazakh National Agrarian Research University Almaty Kazakhstan

ISBN: (数字)9798350374865

ISBN: (纸本)9798350374872

this research paper delves into the integration of wearable devices and deep learning techniques to enhance heart disease detection and monitoring. the study highlights the importance of continuous cardiac health assessment and the transformative potential of wearable technology in the healthcare landscape. Our investigation showcases their efficacy in processing intricate physiological data for early heart disease recognition. Key variables such as age, maximum heart rate, blood pressure, cholesterol levels, and various electrocardiography (ECG) metrics are explored as pivotal factors in predicting and comprehending heart disease risk factors. Furthermore, we emphasize the significance of data normalization methodologies and secure data storage solutions to ensure data reliability and accessibility. Correlation analyses elucidate the intricate interplay among these variables, providing valuable insights into their collective influence on cardiac health. As the realm of machine learning and healthcare technology continues to evolve, this research lays a solid foundation for advancing heart disease detection and management, ultimately aiming to enhance patient outcomes and elevate the quality of healthcare delivery.

关键词： Deep learning Measurement Memory Medical services Electrocardiography Reliability Biomedical monitoring

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179页 << < 55 56 57 58 59 60 61 62 63 64 > >>

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：