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

1,258 篇 会议
264 篇 期刊文献
1 册 图书

馆藏范围

1,523 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

769 篇 工学
- 599 篇 计算机科学与技术...
- 519 篇 软件工程
- 194 篇 信息与通信工程
- 151 篇 控制科学与工程
- 128 篇 电气工程
- 115 篇 生物医学工程（可授...
- 114 篇 生物工程
- 82 篇 光学工程
- 81 篇 电子科学与技术（可...
- 67 篇 网络空间安全
- 66 篇 安全科学与工程
- 57 篇 机械工程
- 52 篇 仪器科学与技术
- 51 篇 交通运输工程
- 40 篇 化学工程与技术
426 篇 理学
- 209 篇 数学
- 130 篇 生物学
- 116 篇 物理学
- 85 篇 统计学（可授理学、...
- 60 篇 化学
- 38 篇 系统科学
247 篇 管理学
- 165 篇 管理科学与工程(可...
- 101 篇 图书情报与档案管...
- 95 篇 工商管理
141 篇 医学
- 108 篇 临床医学
- 107 篇 基础医学(可授医学...
- 86 篇 公共卫生与预防医...
- 58 篇 药学(可授医学、理...
57 篇 法学
- 49 篇 社会学
46 篇 经济学
- 46 篇 应用经济学
36 篇 农学
20 篇 教育学
7 篇 文学
3 篇 艺术学
1 篇 哲学
1 篇 历史学
1 篇 军事学

主题

185 篇 accuracy
119 篇 real-time system...
114 篇 deep learning
81 篇 convolutional ne...
79 篇 machine learning
77 篇 predictive model...
75 篇 training
69 篇 feature extracti...
59 篇 support vector m...
59 篇 computational mo...
55 篇 internet of thin...
55 篇 machine learning...
54 篇 medical services
53 篇 data models
50 篇 optimization
47 篇 reviews
41 篇 reliability
41 篇 prediction algor...
40 篇 artificial intel...
36 篇 technological in...

机构

50 篇 nitte meenakshi ...
42 篇 department of ar...
39 篇 lovely professio...
31 篇 department of co...
21 篇 department of ar...
19 篇 east west instit...
19 篇 department of co...
18 篇 department of ar...
18 篇 division of arti...
17 篇 department of ar...
17 篇 machine learning...
16 篇 new horizon coll...
15 篇 college of techn...
15 篇 department of ar...
13 篇 institute of aer...
12 篇 artificial intel...
12 篇 datta meghe inst...
12 篇 department of ar...
12 篇 division of comp...
12 篇 vector institute...

作者

42 篇 prateek verma
42 篇 piyush kumar par...
41 篇 pareek piyush ku...
29 篇 mohsen guizani
28 篇 verma prateek
17 篇 guizani mohsen
14 篇 uma reddy
14 篇 swapnil gundewar
13 篇 amandeep nagpal
12 篇 aditya barhate
12 篇 madhura g.k.
11 篇 utkarsha pachara...
11 篇 xiaojiang du
11 篇 abhay tale
11 篇 rushikesh burle
10 篇 tale abhay
10 篇 reddy uma
10 篇 sundaravadivel p...
9 篇 von lilienfeld o...
9 篇 n v uma reddy

语言

1,278 篇 英文
242 篇 其他
3 篇 中文

检索条件"机构=Artificial Intelligence and Machine Learning Faculty of Engineering and Technology"

共 1523 条记录，以下是521-530 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：

High-Dimensional Data Processing Using Quantum-Inspired Evolutionary Algorithms for Homeland Security Imaging Systems

High-Dimensional Data Processing Using Quantum-Inspired Evol...

引用

2024 International Conference on Communication, Computer Sciences and engineering, IC3SE 2024

作者： Alekhya, V. Reddy, N. V. Uma Singh, Jay Boddu, Bhasker Sobti, Rajeev Hameed, Ali Abduhussien Institute Of Aeronautical Engineering Dundigal Hyderabad India New Horizon College Of Engineering Department Of Artificial Intelligence And Machine Learning Bangalore India Gl Bajaj Institute Of Technology & Management U.P. Greater Noida India Mlr Institute Of Technology Department Of Information Technology Telangana Hyderabad India Lovely Professional University Phagwara India College Of Medical Technology The Islamic University Radiology Techniques Department Najaf Iraq

ISBN: (纸本)9798350366846

This research study explores the emerging area of quantum-inspired evolutionary algorithms (QIEAs) applied to high-dimensional data processing, with a focus on homeland security imaging systems. This work attempts to close the paradigm gap in image processing methodologies caused by the growing complexity of security threats. By combining the adaptive processes of evolutionary algorithms with the probabilistic reasoning inherent in quantum computing, the proposed technique creates a potent tool for managing the inherent difficulties of high-dimensional data. The main contribution of this study is the creation of a brand-new QIEA framework that is specifically designed for image analysis in security contexts and exhibits higher accuracy and efficiency than traditional techniques. The quantum bit representation and quantum gate operations, which have been cleverly tailored to the evolutionary algorithm structure, provide the methodological basis, and improve the search capacity in multidimensional data fields. An unparalleled degree of clarity and detail in security photography is made possible by this fusion, which is essential for threat identification and prevention. Experiments conducted on a variety of difficult datasets show that the suggested method is reliable for identifying important characteristics in complicated photos, which is a crucial component of homeland security applications. Beyond only addressing short-term security issues, this study establishes a standard for next investigations into quantum-inspired computing for image processing. © 2024 IEEE.

关键词： Imaging systems

来源：评论

学校读者我要写书评

暂无评论

Internet of Animal Health Things (IoAHT) Framework for Clinical Mastitis Detection in Dairy Cows

Internet of Animal Health Things (IoAHT) Framework for Clini...

引用

Recent Advances in Information technology for Sustainable Development (ICRAIS), International Conference on

作者： Ankitha K Venugopala P S Harish Kunder Ankitha Shetty Dept. of Artificial Intelligence and Data Science NMAMIT Nitte Karkala India Dept. of Artificial Intelligence and Machine Learning Alvas Institute of Engineering and Technology Moodbidri India

The Earth serves as a shared habitat not just for humans but also for an array of animal species and organisms. Throughout history, animals have played a crucial role in preserving the natural ecosystem balance and meeting diverse human needs. They contribute significantly to various sectors, such as Agriculture, Dairy, Poultry, and animal husbandry, thus bolstering a country's economy. Human responsibility lies in ensuring the well-being of these animals, which is overseen by Veterinary Science. In India, a major milk and milk product producer, the dairy industry actively contributes to the nation's economy. Among the primary milk sources-cows, buffaloes, goats, and sheep-cows hold a revered place in different faiths. Particularly in the dairy industry, cows are vital for milk production. However, monitoring cow health poses challenges. Clinical Mastitis, an inflammation affecting cows' mammary glands, hampers milk production. Automatic milking machines are commonly used, but identifying and segregating mastitis-infected cows from healthy ones remains difficult. The contagious nature of the disease increases the risk of widespread infection among cows. To combat this issue, we propose a solution called the Internet of Animal Health Things (IoAHT), based on the Internet of Things (IoT). IoAHT employs IoT technology for animal health, aiming to accurately identify cases of clinical mastitis in cows. The implementation of IoAHT has the potential to revolutionize health monitoring in the dairy industry, safeguarding cow well-being and ensuring sustainable milk production.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diabetes Prediction using Different machine learning Classifiers

Diabetes Prediction using Different Machine Learning Classif...

引用

engineering and technology (PICET), Parul International Conference on

作者： Mansvi Kishorrao Daigavhane Swapnil Gundewar Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (Deemed to be University) Wardha India dept. of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (Deemed to be University) Wardha India

ISBN: (数字)9798350369748

ISBN: (纸本)9798350369755

Diabetes mellitus is a prevalent global health concern, necessitating proactive approaches for early detection and intervention. This paper explores the application of diverse machine learning classifiers for predicting diabetes onset, with the aim of identifying the most effective model. A comprehensive dataset encompassing clinical and demographic features is employed to train and evaluate the classifiers, including Support Vector machines, Random Forest, Decision Trees, Naive Bayes, and k-Nearest Neighbors. The study incorporates feature engineering and selection techniques to enhance model performance and reduce dimensionality. Through rigorous evaluation metrics such as accuracy, precision, recall, and F1-score, the classifiers’ performances are compared. Results reveal nuanced variations in predictive accuracy among the classifiers, emphasizing the significance of tailored algorithm selection for diabetes prediction. The findings contribute to the optimization of predictive models in healthcare contexts, providing valuable insights for clinicians to identify individuals at higher risk for diabetes. This research serves as a stepping stone for refining machine learning applications in healthcare, underscoring the importance of selecting appropriate models for effective diabetes prediction and fostering advancements in personalized patient care.

关键词： Accuracy machine learning algorithms Medical services Predictive models Prediction algorithms Diabetes Classification algorithms Random forests Medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

The Role of technology in Modern Education

The Role of Technology in Modern Education

引用

artificial intelligence in Education and Industry 4.0 (IDICAIEI), DMIHER International Conference on

作者： Priya Kate Utkarsha Pacharaney Abhay Tale Aditya Barhate Nishad Sheikh Chinmaya Khadse Department of Computer Science and Engineering Faculty of Engineering & Technology Datta Meghe Institute of Higher Education & Research Wardha Maharashtra India Department of Artificial Intelligence and Machine Learning Faculty of Engineering & Technology Datta Meghe Institute of Higher Education & Research Wardha Maharashtra India Department of Artificial Intelligence and Data Science Faculty of Engineering & Technology Datta Meghe Institute of Higher Education & Research Wardha Maharashtra India

ISBN: (数字)9798331528713

ISBN: (纸本)9798331528720

It can be seen that technology has played a big role in today’s education through the use of smart boards and AI. Some of the advantages are that it affords students better access and opportunity for participation and brings more flexibility and efficiency to the teaching process and allows students to experience learning in new ways. However, there are also disadvantages such as digital divides, screen time, privacy concerns, and technical limitations. After highlighting the implications, the article analyses potential developments such as AI tutors and 5G connectivity as potential frontier technologies for the next era of learning technologies. Concisely, technology is an enhancement resource that should be embraced and complement quality teaching. The appropriate policy and continuous enhancement are the two crucial strategies for the education systems to implement technology to foster students with competencies required in the twenty-first century. Further research is needed regarding such matters as time spent in front of screens, media education, and implementation of new technologies in schools.

关键词： Training Industries Privacy Education Medical services learning (artificial intelligence) Media Stakeholders Security Digital divide

来源：评论

学校读者我要写书评

暂无评论

Automated Crack Detection in Pipelines Using Advanced Image Processing

Automated Crack Detection in Pipelines Using Advanced Image ...

引用

machine learning and Autonomous Systems (ICMLAS), International Conference on

作者： Nandhagopal Subramani Jithesh M D Harish R Rithish Hari G Department of Artificial Intelligence and Machine Learning KPR Institute of Engineering and Technology Coimbatore India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Mechanical Engineering KPR Institute of Engineering and Technology Coimbatore India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

The automated detection of pipeline cracks is vital for maintaining the safety and operational lifespan of this crucial infrastructure. Early crack detection prevents costly repairs and minimizes the risk of catastrophic failures and environmental damage. Existing methods primarily rely on manual inspections and traditional image processing techniques, which often lead to inaccuracies and inefficiencies. These methods suffer from high false-negative rates and poor adaptability to different environmental conditions. This study proposes a deep learning framework utilizing YOLOv10 to automate the detection of pipeline cracks with enhanced accuracy. Studies using deep learning report detection accuracies between 80% and 92%, although performance varies across different studies. The range reflects the influence of factors such as dataset and model specifics.

关键词： Deep learning Accuracy Image processing Pipelines Refining Object detection Manuals Real-time systems Safety Monitoring

来源：评论

学校读者我要写书评

暂无评论

Smart Healthcare: Harnessing the Power of machine learning for Predictive Analysis

Smart Healthcare: Harnessing the Power of Machine Learning f...

引用

engineering and technology (PICET), Parul International Conference on

作者： Aditya Barhate Praveen Kumar Prateek Verma Nayan Jikar Abhay Tale Vaibhav Hikre Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Computer Science and Medical Engineering Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India

ISBN: (数字)9798350369748

ISBN: (纸本)9798350369755

Smart healthcare employs cloud computing, the Internet of Things (IoT), and supercomputers to manage the healthcare system. Medical data storage volume is increasing, necessitating the adoption of machine learning (ML) models for predicting outcomes, particularly in the treatment of chronic illnesses. The trend of care personalization and technological integration is highlighted by the development of ML applications for clinical decision support systems, including real-time predictive analytics. Predictive analytics applications employ ML and artificial intelligence (AI) to forecast patient risks, outcomes, and treatment responses. Predictive analytics is more important in healthcare when it comes to detecting Alzheimer's disease, cardiovascular events, radiology, and other conditions. Therefore, the current study highlights the change in illness identification, medical imaging, and personalized medication brought about by ML and Predictive Analytics in Precision Medicine (PM). However, ethical concerns and the deployment of transparent AI models still need more research. This study anticipates a time when healthcare will be quicker, better informed, and more patient-centered by using the insights provided by intelligent healthcare data. By effectively saving patient lives, the use of ML in healthcare ushers in a new era for the industry.

关键词： Ethics Solid modeling Medical services machine learning Radiology Supercomputers Real-time systems Internet of Things Predictive analytics Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Stock Market Forecasting Using LSTM

Stock Market Forecasting Using LSTM

引用

Communication & Computing (WCONF), World Conference on

作者： J. Aswini Dinesh S C. Lakshmipriya Lokesh Krishnaa M Siva Subramanian R Dept of Artificial Intelligence & Machine Learning Saveetha Engineering College(Autonomous) Department of Artificial Intelligence and Data Science Saveetha Engineering College(Autonomous) Department CSE S.A. Engineering College Department CSE R.M.K College of Engineering and Technology

ISBN: (数字)9798350395327

ISBN: (纸本)9798350395334

In this research paper, a novel methodology for forecasting stock market trends is presented: the utilization of Long Short-Term Memory networks, which are a part of RNN network. This model effectively incorporates the delivery of dynamic datasets, model training, and the immediate distribution of the learned TensorFlow model through the utilization of deep learning. The Long Short-Term Memory is a highly effective tool for understanding complex stock market behaviors, as it captures sequential dependencies and effortlessly adapts to changing market conditions. Transparency, collaboration, scalability, user experience, and security are given top priority in the project to guarantee accessibility for users of all levels of expertise. By outperforming conventional neural network architecture in prediction and by capturing dependencies over extended time periods, the LSTM model demonstrates its value. This research may pave the way for additional financial forecasting applications, thereby enhancing the efficacy of decision-making instruments in dynamic stock market environments.

关键词： Deep learning Training Adaptation models Decision making Computer architecture Predictive models User experience Stock markets Forecasting Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Black Fungus Using Deep learning Models for Efficient Medical Diagnosis

Early Detection of Black Fungus Using Deep Learning Models f...

引用

Emerging Techniques in Computational intelligence (ICETCI), International Conference on

作者： Esraa Hassan Abeer Saber El-Sayed M. El-kenawy Roheet Bhatnagar Mahmoud Y. Shams Dept. of Machine Learning Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh Egypt Information technology Dept. Faculty of Computers and Artificial intelligence Damietta University Damietta Egypt Dept. of Communications and Electronics Delta Higher Institute of Engineering and Technology Mansoura Egypt Department of Computer Science and Engineering Manipal University Jaipur Rajasthan India

ISBN: (数字)9798350387063

ISBN: (纸本)9798350387070

Mucormycosis, also known as black fungus, is a rare infection caused by mould that can affect the lungs, brain, skin, and sinuses. People with weakened immune systems due to underlying health conditions (e.g., organ transplant, uncontrolled diabetes, cancer, neutropenia, AIDS, and COVID-19) or drug use are more likely to contract the infection. Recent reports have indicated that a small number of COVID-19 survivors with co-morbidities are particularly vulnerable to black fungus. Therefore, recovered COVID-19 patients should seek medical attention immediately if they experience any mucormycosis symptoms. Patients with COVID-19 have numerous concerns regarding this life-threatening infection, particularly those with immunocompromised states such as solid organ transplant (SOT) and hematopoietic stem cell transplant (HSCT) or tumors, who are more likely to be infected. Early diagnosis and treatment are essential to prevent patient mortality. In this paper, we present the Multi-Class Black Fungus (MCBF) dataset, which consists of three compressed folders containing images. The first folder includes 66 images of eye black fungus after data preprocessing, while the second folder contains 63 images of mouth black fungus after data preprocessing. The third contains 62 images of the mouth after applying data preprocessing, and the last one contains 79 images of black skin fungus after applying data preprocessing. The MCBF dataset contains images that aid in training and validation when using deep learning algorithms to recognise and classify black fungus diseases, then we apply a resnet(50) pretrained model by using MCBF accuracy reaches 96.12%.

关键词： COVID-19 Deep learning Training Computational modeling Data preprocessing Mouth Skin Organ transplantation Immune system Tumors

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep learning for International Trading: Integrating LSTM and Transformer Models 4

Hybrid Deep Learning for International Trading: Integrating ...

引用

4th International Conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Akhila, T.S. Relin Francis Raj, J. Kani Jesintha, D. Santhana Krishnan, R. Vinoth Kumar, V. Sundaravadivel, P. Dhanalakshmi College of Engineering Department of Electronics and Communication Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Scad College of Engineering and Technology Department of Computer Science and Engineering Cheranmahadevi India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India Saveetha Engineering College Department of Artificial Intelligence and Machine Learning Chennai India

ISBN: (纸本)9798331523923

This research proposes a hybrid deep learning model combining Long Short-Term Memory (LSTM) networks and Transformers to enhance decision-making in international trading. The model leverages advanced techniques such as RoBERTa for text tokenization, FinBERT for sentiment analysis, and XLM-Roberta for multilingual language processing. LSTM is employed to analyze sequential numerical data like historical prices and trading volumes, providing accurate price and volatility forecasts. The Transformer component processes textual data to extract sentiment classifications and event-driven market impacts, facilitating a comprehensive understanding of market conditions. A fully connected fusion layer integrates insights from both components, enabling the model to classify market conditions holistically. The optimization process utilizes the Adam optimizer with learning rate scheduling to ensure efficient and effective training. Loss functions like Mean Squared Error (MSE) and Cross-Entropy Loss are employed to optimize numerical predictions and categorical outcomes, respectively. By combining temporal analysis with sentiment-driven insights, this hybrid model offers improved price forecasting, advanced multilingual sentiment analysis, and event-driven market condition predictions. The proposed approach aims to provide traders with actionable insights, enabling more informed decision-making in the highly dynamic and multilingual environment of international trading. © 2025 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Web-Based Smart Healthcare System

Web-Based Smart Healthcare System

引用

artificial intelligence in Education and Industry 4.0 (IDICAIEI), DMIHER International Conference on

作者： Mansvi Kishorrao Daigavhane Swapnil Gundewar Ayush Pravin Gadkari Sakshi Prakash Anpan Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (Deemed to be University) Wardha India Dept. of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (Deemed to be University) Wardha India

ISBN: (数字)9798331528713

ISBN: (纸本)9798331528720

In today’s healthcare sector, utilizing information technology is essential for improving hospital operations. This study presents the creation and deployment of a web-based Smart Healthcare system (SHS) aimed at optimizing various administrative and clinical tasks within a healthcare setting. Some of the components are patient portal for signing in, practice calendar, assessment tools, invoicing, and reporting using webbased platform. Web based technologies and keeping a centralized database leads to secure data management, real time information and effective communication between different departments. This paper focuses on the description of the system’s layout, structure and basic operations identifying it as a tool for raising organizational productivity, improving data accuracy and promoting patient care benefits.

关键词： Productivity Privacy Hospitals Manuals Real-time systems Mobile applications Stakeholders Security Standards Portals

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153页 << < 49 50 51 52 53 54 55 56 57 58 > >>

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：