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

3,133 篇 会议
171 册 图书
28 篇 期刊文献

馆藏范围

3,331 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

2,241 篇 工学
- 2,038 篇 计算机科学与技术...
- 1,086 篇 软件工程
- 402 篇 信息与通信工程
- 358 篇 电气工程
- 249 篇 生物工程
- 169 篇 控制科学与工程
- 157 篇 生物医学工程（可授...
- 73 篇 光学工程
- 73 篇 化学工程与技术
- 68 篇 机械工程
- 63 篇 仪器科学与技术
- 59 篇 电子科学与技术（可...
- 58 篇 安全科学与工程
- 47 篇 交通运输工程
- 38 篇 材料科学与工程（可...
- 38 篇 动力工程及工程热...
718 篇 理学
- 378 篇 数学
- 273 篇 生物学
- 168 篇 物理学
- 147 篇 统计学（可授理学、...
- 104 篇 系统科学
- 70 篇 化学
460 篇 管理学
- 298 篇 图书情报与档案管...
- 200 篇 管理科学与工程(可...
- 96 篇 工商管理
300 篇 医学
- 273 篇 临床医学
- 125 篇 基础医学(可授医学...
- 70 篇 药学(可授医学、理...
- 53 篇 公共卫生与预防医...
64 篇 法学
- 57 篇 社会学
32 篇 经济学
31 篇 教育学
28 篇 农学
6 篇 艺术学
3 篇 军事学
1 篇 文学

主题

545 篇 data mining
543 篇 machine learning
286 篇 pattern recognit...
239 篇 deep learning
188 篇 feature extracti...
160 篇 support vector m...
156 篇 artificial intel...
120 篇 training
118 篇 accuracy
115 篇 machine learning...
95 篇 data models
91 篇 data mining and ...
75 篇 classification
72 篇 neural networks
70 篇 convolutional ne...
68 篇 predictive model...
67 篇 big data
64 篇 computational mo...
57 篇 sentiment analys...
55 篇 learning systems

机构

10 篇 chinese academy ...
9 篇 chitkara centre ...
8 篇 zhejiang univers...
7 篇 guangdong univer...
7 篇 centre of resear...
6 篇 central south un...
6 篇 unsw sydney
6 篇 college of compu...
5 篇 badji mokhtar un...
5 篇 xi'an university...
5 篇 indian statistic...
5 篇 southwest jiaoto...
5 篇 kobe university ...
5 篇 southern univers...
4 篇 columbia univers...
4 篇 chitkara univers...
4 篇 shanghai jiao to...
4 篇 institute of big...
4 篇 centre for patte...
4 篇 shandong institu...

作者

12 篇 de-shuang huang
12 篇 venkatesh svetha
8 篇 petra perner
7 篇 phung dinh
7 篇 jacek m. zurada
7 篇 krasotkina olga
7 篇 mottl vadim
6 篇 zheng-guang wu
6 篇 ryszard tadeusie...
6 篇 marcin korytkows...
6 篇 hongyi li
6 篇 chaojie li
6 篇 biao luo
6 篇 lotfi a. zadeh
6 篇 kang-hyun jo
6 篇 leszek rutkowski
6 篇 long cheng
6 篇 zhongzhi shi
5 篇 zhang yan
5 篇 vitoantonio bevi...

语言

3,198 篇 英文
117 篇 其他
32 篇 中文

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

共 3332 条记录，以下是341-350 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：

Feature-Based Explainable Reinforcement learning in Environments with Multiple Sources of Risk 4th

Feature-Based Explainable Reinforcement Learning in Environ...

引用

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

作者： Davoodi, Omid Komeili, Majid Carleton University OttawaON Canada

ISBN: (纸本)9789819787012

Explainable Reinforcement learning is key in bringing the current neural network-based state-of-the-art reinforcement learning methods to real-world environments. In particular, explaining the risks of the agent’s decision-making process is critical to deploying such models in safety-critical tasks. the previous feature-based methods for characterizing risk in reinforcement learning settings were not well suited for handling situations when there are multiple sources of risk. this work attempts to address this shortcoming by providing a post-hoc method that can explain multiple sources of risk. Our experiments show that the proposed method can provide more insights into the workings of the agent while avoiding the issues faced by the previous work in multi-risk environments. © the Editor(s) (if applicable) and 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

Deep learning with Conditional Generative Adversarial Network Based Intrusion Detection System on Balanced data 4

Deep Learning with Conditional Generative Adversarial Networ...

引用

4th international conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Hemavathi, K. Latha, R. St. Peter's Institute of Higher Education and Research Dept. of Computer Science Chennai India

ISBN: (纸本)9798350300093

Networks have an important role to play in modern life, and cyber security is an active research area. An Intrusion Detection System (IDS) becomes a crucial cyber security method that monitored the state of hardware and software running in the network. IDS can find attacks in available environments. the machine learning (ML) method is one among the emerging approaches that have better performance in the situation they have encountered already, and enjoy a wide variety of applications in outlier analysis speech recognition, pattern detection, and so on. With unbalanced data, the predictive model established utilizing ML method might produce an unacceptable classifier that affects the accuracy of predicting intrusion. Conventionally, researcher workers applied oversampling and undersampling to balance data in the dataset for overcoming these problems. therefore, this article presents a Deep learning with Conditional Generative Adversarial Network-based Intrusion Detection System (DLCGAN-IDS) technique on Balanced data. the goal of the DLCGAN-IDS technique lies in the proper balancing of the network samples and identify the intrusions accurately. To accomplish this, the presented DLCGAN-IDS approach primarily normalizes the input data by employing min-max normalization. For imbalanced data handling, the CGAN approach is used for balancing the sample numbers in the dataset. Finally, DL based Long Short-Term Memory (LS TM) method is enforced for detecting and classifying intrusions in the network. the results of the DLCGAN-IDS method execute on the IDS dataset. the comprehensive outcomes pointed out the superior achievement of the DLCGAN-IDS model over other current algorithms. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

A Review on the Applications of Natural Language Processing in Healthcare 4

A Review on the Applications of Natural Language Processing ...

引用

4th international conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Warbhe, Mohan K. Verma, Prateek Faculty of Engineering and Technology Department of Computer Science and Design Sawangi Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Sawangi Maharashtra Wardha442001 India

ISBN: (纸本)9798331529635

In healthcare, Natural Language Processing (NLP) is a technique to improve clinical decision support, patient care, and medical research. By automating clinical recording, NLP enhances the calibre of medical records and professional communication. It makes Electronic Health Records (EHRs) easier to use by facilitating quick and easy data entry, retrieval, and access to vital patient data that helps with precise diagnosis and efficient treatment planning. through the analysis of patient-specific data, NLP supports clinical decision support by delivering prompt recommendations. Chatbots and virtual assistants managing repetitive duties like booking appointments also improve patient connection. NLP makes it easier to analyse vast amounts of literature for medical research, facilitating the extraction and summary of important discoveries. Healthcare data processing requires text preparation, sentiment analysis, Named Entity recognition (NER), semantic parsing, and Natural Language Generation (NLG). However, there are obstacles to overcome, like bias, ethical concerns, system integration, privacy, and data quality. the healthcare industry can use NLP to enhance patient outcomes, promote personalized medication, and streamline healthcare delivery by guaranteeing interoperability and setting standards. © 2024 IEEE.

关键词： Challenges of NLP in Healthcare Future treads of NLP for healthcare Healthcare NLP

来源：评论

学校读者我要写书评

暂无评论

Efficient Vehicle Tracking and Authentication with YOLOv8: Integrating Deep learning and OCR for Real-Time License Plate Detection 4

Efficient Vehicle Tracking and Authentication with YOLOv8: I...

引用

4th international conference on Sustainable Expert Systems, ICSES 2024

作者： Kalaimathi, B. Jayanthy, S. Bharathkumar, G. Akshaya, A.V.R. Dharanya, P. Sri Ramakrishna Engineering College Department of Electronics and Communication Engineering Coimbatore India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540364

Computer vision plays an important role in this technology-driven world. Using computer vision, the images can be acquired and processed to achieve the high dimensional data of the images. In late 1960s computer vision was start emerging which is considered as the colonist for the latest technology Artificial intelligence. the machine learning and deep learning comes under the artificial intelligence as the subsets. the object detection falls under the category of computer vision. Tracking of each license plate is considered as a most difficult task as the population increases massively day by day. Also, to identify whether a vehicle is authorized or unauthorized in distinct environment is a challenging one. When the population becomes higher and higher leads to many complications such as vehicle theft, misusing vehicles, and unauthorized accessing of vehicles. To overcome these issues many algorithms are handled and the best method is done with the deep learning algorithm. the project aims at designing a system by training the model using deep learning which allows to detect the number plate accurately using open cv module and then the text of number plate is extracted using optical character recognition (OCR) and thus fixed database is compared with the code written in python and thus the vehicle can be detected whether it is authorized or unauthorized. By implementing this project, the complications associated with the detection of vehicles can be overcome. this project aims at designing a most efficient and conceded way for detecting the license plates. For this purpose, the deep learning method is handled which follows the basic algorithm CNN (convolution neural networks) and the model created using the deep learning method follows the YOLOv8, the latest version used for the object detection. In this process the YOLOv8 (you only look once) is handled to make the detection easier since it follows the single neural network to identify the boundary boxes and the c

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

4th EAI international conference on data Information in Online Environments, DIONE 2023

4th EAI International Conference on Data Information in Onli...

引用

4th EAI international conference on data Information in Online Environments, DIONE 2023

ISBN: (纸本)9783031807121

the proceedings contain 21 papers. the special focus in this conference is on data Information in Online Environments. the topics include: Deep Image Inpainting Incorporating Texture Prior Based on Gabor Filter;the Improved XdeepFM Algorithm Based on Attention Mechanism and Factorization machine;deep learning-Based Glaucoma Diagnostic Assistance System on Mobile Devices;using Alignment Chain to Boost Genetic Sequence Alignment Process;analysis of the Industrial Internet Industry Chain and Supply Capability Analysis of Key Links Within Jiangxi Province;a Lithium-Ion Battery Cathode Material Literature Entity recognition Method Based on Deep learning;design and Implementation of Improved Multi-objective Genetic Algorithm Based on Uniform Distribution;Wavelet and Kalman Filter-Empowered Traffic Detection for Secure QUIC Network Communication;hyFed: A Hybrid Blockchain Empowered Federated learning Privacy Fair Framework;research on the Capability Status of Industrial Internet Security Supervision Platform;solar System Dynamics with Jet Propulsion Laboratory Ephemeris;elderly Health Care data Integration Framework: Design and Implementation;challenges and Prospects of Power Network Security Protection in the Context of a New Power System: A Case Study of Jiangxi;enhancing Sequence Alignment Efficiency through Concurrent Utilization of Multiple Arm Processors in a Sequential Processing Framework;Fusion of Multiscale Convolution and LSTM for Stock Price Prediction;development of a Web Application for the Sociocultural Diffusion of the Municipality of Lamas, Peru;A Solution Against Selective Jamming Attack in IEEE 802.15.4e Wireless Networks;TDFM and TAFM: Time-Aware and Feature Fusion-Based Deep Recommendation Models for Short Videos;blockchain Based Access Control: A Review and Future Perspectives.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient and Flexible Sublabel-Accurate Energy Minimization 26

Efficient and Flexible Sublabel-Accurate Energy Minimization

引用

26th international conference on pattern recognition / 8th international Workshop on Image mining - theory and Applications (IMTA)

作者： Nurlanov, Zhakshylyk Cremers, Daniel Bernard, Florian Univ Bonn Bonn Germany Tech Univ Munich Munich Germany

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

We address the problem of minimizing a class of energy functions consisting of data and smoothness terms that commonly occur in machine learning, computer vision, and pattern recognition. While discrete optimization methods are able to give theoretical optimality guarantees, they can only handle a finite number of labels and therefore suffer from label discretization bias. Existing continuous optimization methods can find sublabel-accurate solutions, but they are not efficient for large label spaces. In this work, we propose an efficient sublabel-accurate method that utilizes the best properties of both continuous and discrete models. We separate the problem into two sequential steps: (i) global discrete optimization for selecting the label range, and (ii) efficient continuous sublabel-accurate local refinement of a convex approximation of the energy function in the chosen range. Doing so allows us to achieve a boost in time and memory efficiency while practically keeping the accuracy at the same level as continuous convex relaxation methods, and in addition, providing theoretical optimality guarantees at the level of discrete methods. Finally, we show the flexibility of the proposed approach to general pairwise smoothness terms, so that it is applicable to a wide range of regularizations. Experiments on the illustrating example of the image denoising problem demonstrate the properties of the proposed method. the code reproducing experiments is available on https://***/nurlanov-zh/sublabel-accurate-alpha-expansion.

关键词： Computer vision Codes Memory management Optimization methods machine learning Minimization Relaxation methods

来源：评论

学校读者我要写书评

暂无评论

Skin Disease Classification using machine learning based Proposed Ensemble Model 4

Skin Disease Classification using Machine Learning based Pro...

引用

4th international conference for Emerging Technology, INCET 2023

作者： Ram Sahu, Bisahu Kumar Shrivas, Akhilesh Shukla, Abhinav Dr. C.V. Raman University Kota Department of IT & CS C.G. Bilaspur India Guru Ghasidas Vishwavidyalaya Department of CSIT C.G. Bilaspur India

ISBN: (纸本)9798350335750

Skin disease is a major issue of global health problem affecting a large amount of persons. the advancement of dermatological diseases categorization has grown more accurate in recent years due to the rapid growth of technology and the use of various machine learning techniques. therefore the creation of machine learning methods that can accurately differentiate between the classifications of skin diseases is one of the great importance. this research work focuses on the classification of different kinds of skin diseases using machine learning techniques. In this research, we introduce a novel approach that makes use of four distinct data mining techniques like support vector machine (SVM), k-nearest neighbor (KNN), random forest (RF) and, naive bayes (NB) algorithm. this research work proposed an ensemble model that is combination of SVM, KNN, RF and NB using voting scheme. the proposed model classified the skin disease into five different classes that are Acne, Skin allergy, Nail fungus, Hair loss, and Normal skin. the proposed ensemble model used on skin disease classification that gives better performance over other classifier algorithms. the proposed ensemble model achieved highest 97.33% of accuracy as compared to others. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Classification of Dermoscopic Images using Deep learning 4

Skin Cancer Classification of Dermoscopic Images using Deep ...

引用

4th international conference on Advancement in Electronics and Communication Engineering, AECE 2024

作者： Madhavi, G Bindu Sumithra, M. Devi, P Yamini Mahalaxmi, U.S.B.K. Saravanan, T. Shaker Reddy, Pundru Chandra Geethanjali College of Engineering and Technology Department of Cse -AI &ml Telangana Hyderabad India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Computer Science and Engineering School of Computing Tamil Nadu Chennai India Computer Science and Engineering Vignana Bharathi Institute of Technology Telangana Hyderabad India Electronics Communication Engineering Aditya University Andhra Pradesh Surampalem India P. S. R. Engineering College Department of Information Technology Tamil Nadu Sivakasi India School of Computer Science and Artificial Intelligence Sr University Telangana Warangal India

ISBN: (纸本)9798350364729

Pigmented skin lesions must be identified in order to detect hazardous skin-related disorders, especially cancer. To improve the correctness of skin cancer recognition, image detection strategies and classification abilities can be utilized. Based on the HAM10000 dataset, which contains 10015 photos, this research paper makes use of the dataset. An augmentation has been carried out on a subset of the dataset in the proposed work. Compared to an approach with &without data augmentation, is more likely to learn unique traits and attributes. To make the model more accurate, data augmentation is often used. However, until the model is strong, it will not be able to produce meaningful results when tested with the testing data. this work's model is robust since it makes use of the k-fold cross-validation technique. machine learning methods and models from Convolutional Neural Networks have been evaluated for their classification accuracy. After comparing the suggested work's use of several machine learning methods, we found that Convolutional Neural Network produced the best results in terms of accuracy. We achieved a maximum accuracy of 95.53% using the CNN in the suggested setup. Early detection of seven types of skin illness is made easier by the suggested work, which may be authenticated and treated properly by medicinal professionals. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Real-Time Transaction Classification and Fraud Detection in Banking using AI and Advanced data Processing 4

Real-Time Transaction Classification and Fraud Detection in ...

引用

4th international conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Beeram, Divya Logeshwaran, J. San Jose State University United States Christ University Department of Computer Science Karnataka Bengaluru560029 India

ISBN: (纸本)9798331529635

Banks need real-time transaction classification and fraud detection to secure end-to-end financial transactions. However, the time it currently takes to classify and detect manually is too slow for an industry that can lead to financial loss if done incorrectly or lead customers in some forward-oriented industries. Artificial Intelligence (AI) and Advanced data Processing techniques have sharpened the speed and accuracy of transaction classification and fraud detection in banking systems. By analyzing transaction history, customer behaviour, and the geographical location of a shop overplayed in tens to hundreds of different real-time data sources, an AI algorithm can accurately classify the level of fraud risk on card transactions. With that data in place, problematic patterns suggestive of fraud can be identified immediately. Sophisticated data processing techniques like data mining and machine learning can identify fraudulent patterns hidden in large amounts of actions, and even the most complex fraud cases will be detected. Moreover, these technologies constantly learn, and with new fraud patterns, they adapt on the go, giving banks a 'pre-fraud' approach to detection. Banks can now classify transactions and detect fraud in real-time using AI and Advanced data Processing, significantly reducing financial losses and eliminating the frustration of yet another chargeable transaction. As technology advances, these strategies will continue to strengthen and adapt to fight against new types of fraud, leading transactions towards more safety. © 2024 IEEE.

关键词： data handling

来源：评论

学校读者我要写书评

暂无评论

A Region-Based Approach for Layout Analysis of Music Score Images in Scarce data Scenarios 18th

A Region-Based Approach for Layout Analysis of Music Score I...

引用

18th international conference on Document Analysis and recognition (ICDAR)

作者： Castellanos, Francisco J. Martinez-Esteso, Juan P. Galan-Cuenca, Alejandro Gallego, Antonio Javier Univ Alicante Univ Inst Comp Res Alicante 03690 Spain

ISBN: (纸本)9783031705458;9783031705465

this work presents a novel region-based layout analysis (LA) method for Optical Music recognition (OMR) systems, aimed at overcoming the data scarcity challenge. Contemporary OMR techniques, grounded in machine learning principles, have a critical requirement: a labeled dataset for training. this presents a practical challenge due to the extensive manual effort required, coupled with the fact that the availability of suitable data for creating training sets is not always guaranteed. Unlike other approaches, our method focuses on adapting the training and sample extraction processes within an existing neural network framework. Our approach incorporates a labeled data-driven oversampling technique, a masking layer to enable training with partial labeling, and an adaptive scaling process to improve results for varying score sizes. through comprehensive experimentation, we established the minimal labeled data necessary for an effective model and demonstrated that our method could achieve a performance comparable with the state-of-the-art with just 8 to 32 labeled samples. the implications of our research extend beyond improving LA, providing a scalable and practical solution for digitizing and preserving musical documents.

关键词： Few-shot learning Deep learning Layout Analysis Object Detection Optical Music recognition

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334页 << < 31 32 33 34 35 36 37 38 39 40 > >>

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：