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

85,797 篇 会议
2,719 册 图书
1,775 篇 期刊文献
4 篇 学位论文
2 篇 科技报告

馆藏范围

90,291 篇 电子文献
8 种 纸本馆藏

日期分布

学科分类号

46,659 篇 工学
- 38,357 篇 计算机科学与技术...
- 31,920 篇 软件工程
- 6,345 篇 控制科学与工程
- 6,278 篇 信息与通信工程
- 5,538 篇 电气工程
- 3,208 篇 机械工程
- 2,944 篇 电子科学与技术（可...
- 2,051 篇 生物工程
- 1,600 篇 生物医学工程（可授...
- 1,479 篇 安全科学与工程
- 1,407 篇 动力工程及工程热...
- 1,373 篇 仪器科学与技术
- 1,265 篇 建筑学
- 1,198 篇 土木工程
- 1,149 篇 材料科学与工程（可...
- 1,034 篇 光学工程
- 1,025 篇 交通运输工程
13,133 篇 理学
- 7,331 篇 数学
- 2,658 篇 物理学
- 2,362 篇 系统科学
- 2,237 篇 生物学
- 1,757 篇 统计学（可授理学、...
11,136 篇 管理学
- 7,838 篇 管理科学与工程(可...
- 4,104 篇 工商管理
- 4,077 篇 图书情报与档案管...
2,139 篇 教育学
- 2,113 篇 教育学
1,376 篇 法学
- 1,075 篇 社会学
1,376 篇 医学
- 1,176 篇 临床医学
- 1,031 篇 基础医学(可授医学...
1,312 篇 经济学
- 1,303 篇 应用经济学
382 篇 农学
256 篇 文学
194 篇 军事学
62 篇 艺术学
3 篇 哲学
2 篇 历史学

主题

8,330 篇 application soft...
7,092 篇 software enginee...
5,888 篇 computer archite...
5,249 篇 software
5,220 篇 computer science
4,407 篇 software systems
4,153 篇 hardware
3,534 篇 computer aided s...
3,258 篇 control systems
2,641 篇 computational mo...
2,216 篇 costs
2,087 篇 programming
1,804 篇 artificial intel...
1,774 篇 computer softwar...
1,740 篇 real time system...
1,607 篇 testing
1,438 篇 real-time system...
1,415 篇 software design
1,370 篇 protocols
1,350 篇 information syst...

机构

196 篇 college of compu...
114 篇 school of comput...
60 篇 school of comput...
56 篇 college of compu...
54 篇 school of comput...
49 篇 department of co...
40 篇 college of compu...
37 篇 department of el...
37 篇 school of comput...
36 篇 school of electr...
36 篇 department of el...
33 篇 institute of inf...
33 篇 state key labora...
32 篇 school of comput...
32 篇 department of el...
31 篇 department of co...
31 篇 department of el...
29 篇 department of co...
28 篇 school of comput...
27 篇 department of co...

作者

49 篇 anon
38 篇 bernady o. apduh...
36 篇 bosch jan
34 篇 o'connor rory v.
28 篇 shaoying liu
28 篇 li yang
26 篇 dubinsky yael
26 篇 ebrahim babaei
22 篇 zhu huibiao
21 篇 lei wang
21 篇 dong jin song
20 篇 katz guy
19 篇 zhang lei
17 篇 levent yilmaz
17 篇 rui wang
17 篇 wenyun zhao
17 篇 shahar maoz
17 篇 vardi moshe y.
16 篇 weiming shen
16 篇 noraziah a.

语言

88,862 篇 英文
959 篇 其他
437 篇 中文
32 篇 西班牙文
18 篇 葡萄牙文
17 篇 德文
14 篇 土耳其文
13 篇 俄文
9 篇 法文
4 篇 捷克文
4 篇 日文
2 篇 乌克兰文
1 篇 朝鲜文

检索条件"任意字段=Israel Conference on Computer Systems and Software Engineering"

共 90297 条记录，以下是241-250 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：

An Empirical Comparison of Machine and Deep Learning Algorithms for Predicting Maternal Health Risk 5th

An Empirical Comparison of Machine and Deep Learning Algorit...

引用

5th EAI International conference on Cognitive Computing and Cyber Physical systems, IC4S 2024

作者： N, Srinivasa Gupta Valarmathi, B. Kavitha, A. Gopini, Sai Bhuvan Seela, Hari Kumar Department of Manufacturing Engineering School of Mechanical Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Department of Mathematics School of Advanced of Sciences Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9783031770777

Maternal health is among the greatest challenges in the world, especially in rural areas as there lack medical practitioners, they do not have easily accessible publics clinics and transport is difficult. Therefore, high rates of maternal as well as infant morbidity and mortalities are recorded. This research utilizes Artificial Intelligence (AI) with machine learning algorithms to forecast and address maternal health hazards right at their onset stage. The current research utilizes the concept of AI along with many Machine Learning (ML) methods like the Ensemble Learning Model (ELM), Random Forest (RF), K-Nearest Neighbour (KNN), Decision-Tree (DT), XG-Boost (XGB), Cat Boost (CB), and Gradient Boosting (GB), along with Synthetic Minority Over-sampling Technique (SMOTE) algorithm used for dealing with the problem class imbalance within the data set. SMOTE algorithm is utilized for the dataset balancing process. The handling system involves refining data preprocessing with the help of feature engineering and robust data cleaning which makes sure that anomalies do not erode the reliability of the predictive model. The existing methods [1] used RF (90%), DT (87%), XGB (85%), CB (86%), and GB (81%) algorithms and were compared with the accuracies of the proposed models like Logistic Regression (LR), Ensemble Learning Bagging (ELB), Ensemble Learning Stacking (ELS), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). The existing methods used only imbalance dataset. The accuracies of the proposed models with using SMOTE algorithm (balanced dataset) are LR (61.33%), KNN (81%), ELB (92.33%), ELS (90.66%) CNN (40.67%), RNN (59.67%), LSTM (54%), GRU (56%) respectively. Among these methods, ELB achieved 92.33% of accuracy with using SMOTE algorithm using imbalanced dataset. Whereas the accuracies of the proposed models without using SMOTE algorithm (imbalanced dataset) are LR (66.09%), KNN (68.47%)

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

8th EAI International conference on Future Access Enablers of Ubiquitous and Intelligent Infrastructures, FABULOUS 2024

8th EAI International Conference on Future Access Enablers o...

引用

8th EAI International conference on Future Access Enablers of Ubiquitous and Intelligent Infrastructures, FABULOUS 2024

ISBN: (纸本)9783031723926

The proceedings contain 14 papers. The special focus in this conference is on Future Access Enablers of Ubiquitous and Intelligent Infrastructures. The topics include: Enhanced Relaxed Loop Free Updates in software Defined Network;an Empirical Analysis of Machine Learning Approaches for Phishing Detection;SARF: Stock Market Prediction with Sentiment-Augmented Random Forest;impact of Service Time Distributions and Server Utilization on Tandem Queueing System Performance;improvement of the Teaching Process Using the Genetic Algorithm;Sustainable Productivity Improvement in CPM Through Building Information Modeling in the Context of Circular Construction;integration of Electromobility into Public Transport systems: A Case Study;monitoring the Surface Treatment Effect on the Polyvinyl Butyral Samples in the Context of Industry 4.0;methods and Practices of Integrated Construction Process Management – Minimizing Environmental Impacts and Promoting Efficient Resource Management;CIO in the Organizational Hierarchy;use of Product Lifecycle Management in Preparation for Simulation of Logistic Processes;a Model of Cloud-Based System for Monitoring Air Quality in Urban Traffic Environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Machine Learning-Based Approach for Detecting Malicious Websites Using URL Features 3rd

An Ensemble Machine Learning-Based Approach for Detecting Ma...

引用

3rd International conference on Trends in Electronics and Health Informatics, TEHI 2023

作者： Uddin, Khandaker Mohammad Mohi Islam, Md. Ashraful Hasan, Md. Nahid Ahmad, Kawsar Haque, Mir Aminul Department of Computer Science andEngineering Southeast University Dhaka1208 Bangladesh Department of Computer Science and Engineering Dhaka International University Dhaka1205 Bangladesh Department of Computer Science and Engineering Jahangirnagar Univerisity Dhaka Bangladesh Department of Computer Science and Engineering Daffodil International University Dhaka1216 Bangladesh

ISBN: (纸本)9789819739363

The Internet has transformed into a hub for a wide array of illegal activities, ranging from annoying spam ads to financial scams, all thanks to advancements in modern technology. With the constant enhancements in network technology, data traffic on the Internet is ballooning in both volume and scope. Consequently, the complexity and prevalence of cyber threats and attacks are on the rise, with websites becoming the prime targets for hackers. These intruders, or hackers, embed harmful content into web pages with the intent of carrying out nefarious activities. They employ various tactics, such as hacking into computers or trying to harvest information through compromised or malicious websites. Some of these tactics involve injecting malicious software into web links. Therefore, it has become more critical than ever to identify and block such websites before the average user can stumble upon them. In this paper, we propose a method that utilizes machine learning techniques to detect fraudulent websites. We evaluate the prediction accuracy of different machine learning classification methods in this study. We trained our model using various algorithms, including Naive Bayes, Support Vector Machines (SVM), K-Nearest Neighbors (K-NN), Decision Trees, Random Forests, and AdaBoost. Ultimately, we employed an ensemble approach and achieved an outstanding accuracy rate of 99.98%, surpassing other methods in effectiveness. © 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

YFLM: An Improved Levenberg-Marquardt Algorithm for Global Bundle Adjustment 41st

YFLM: An Improved Levenberg-Marquardt Algorithm for Global ...

引用

41st computer Graphics International conference, CGI 2024

作者： Peng, Jiaxin Li, Tao Jiang, Qin Liu, Jie Wang, Ruibo Laboratory of Software Engineering for Complex Systems School of Computer Science National University of Defense Technology Hunan Changsha410073 China Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Hunan Changsha410073 China

ISBN: (纸本)9783031820205

The conventional Levenberg-Marquardt (LM) algorithm is a state-of-the-art trust-region optimization method for solving bundle adjustment problems in the Structure-from-Motion community, which not only takes advantage of the fast convergence of the Gauss-Newton method, but also the stability of the gradient descent method when approaching optimal solutions. However, the damping ratio of LM is simply provided by trial-and-error, which causes slow convergence rate for large-scale problems. This paper proposes the Yamashita-Fukushima LM (YFLM) algorithm to reduce the time complexity for global bundle adjustment, where the damping factor is determined by Yamashita and Fukushima’s method. YFLM dynamically calculates a more reasonable and optimal damping ratio according to the newest reprojection error. The experimental results show that the YFLM algorithm outperforms the conventional LM algorithm for most public bundle adjustment datasets. Besides this, the convergence of the YFLM algorithm is also evaluated with different σ∈(0,2]. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

A Mini Review on Purchaser Security in the Metaverse: Challenges and Solutions

A Mini Review on Purchaser Security in the Metaverse: Cha...

引用

PhD Symposium, Posters, Demos, and A Web for more inclusive, sustainable and prosperous societies, WEB-for-GOOD 2024 and 1st International Workshop on AI and Web Data Analytics, AIWDA 2024 form the 25th International conference on Web Information systems engineering, WISE 2024

作者： Aloudat, Mohammad Barhamgi, Mahmoud Yaacoub, Elias Department of Computer Science and Engineering Qatar University Doha Qatar

ISBN: (纸本)9789819614820

This mini review examines the security challenges faced by purchasers in the metaverse, focusing on issues such as data protection, privacy, identity theft, financial fraud, and software vulnerabilities. The metaverse, characterized by its immersive, decentralized, and interactive nature, presents unique risks due to extensive data collection, real-time user tracking, and the integration of digital and physical worlds. This mini review highlights specific threats such as unauthorized access, exploitation of biometric data, and fraudulent activities involving blockchain-based assets like non-fungible tokens (NFTs). Mitigation strategies, including advanced encryption, multi-factor authentication, decentralized identity solutions, and regulatory frameworks, are discussed as essential to safeguarding purchasers. The paper concludes by identifying gaps in current research and proposing directions for future studies, emphasizing the need for interdisciplinary approaches to enhance metaverse security. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Circuit-Based Numerical Solutions of Transmission Lines: Application to Korteweg-de Vries Equations 4th

Circuit-Based Numerical Solutions of Transmission Lines: Ap...

引用

4th International conference on Numerical Computations: Theory and Algorithms, NUMTA 2023

作者： Alì, Giuseppe Bertacchini, Francesca Bilotta, Eleonora Demarco, Francesco Pantano, Pietro Vena, Stefano Department of Physics University of Calabria Rende Italy Department of Mechanical Energy and Management Engineering University of Calabria Rende Italy Altrama Rende Italy

ISBN: (纸本)9783031812460

Transmission lines, devices employed for the transmission of electrical signals, can be used for the approximation of non-linear partial differential equations (PDEs) also in the nonlinear case. To this end, transmission lines are used to spatially discretize PDEs allowing the problem to be solved numerically even for intricate boundary conditions - e.g. at intersection of many wires in the system. Using transmission lines to solve the Korteweg-de Vries Equation (KdV) allows for efficient and accurate numerical solutions, as it provides a method to investigate the propagation of wave-like information in nonlinear and dispersive media with multiple dimensions. In the present paper a software developed in C# is presented, the latter employs discretization by transmission lines and the Runge-Kutta 4–5 integration algorithm to numerically solve the KdV equation in the one-dimensional case. The implemented program, named "WireExplorer," is able to simulate the propagation of solitonic pulses on different types of circuits composed of one or more wires, even in the case of intersections. Such conditions are not canonically solvable by resolution of the KdV equations, while approximate numerical resolution allowed the evaluation of these intricate cases. In particular, the obtained results showed the subdivision of the wave into smaller components, at intersections between wires, which propagate in different directions showing also the formation of dispersive tails propagating in the direction opposite to that of the main wave. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Solitons

来源：评论

学校读者我要写书评

暂无评论

Wavelet and Kalman Filter-Empowered Traffic Detection for Secure QUIC Network Communication 4th

Wavelet and Kalman Filter-Empowered Traffic Detection for Se...

引用

4th International conference on Data and Information in Online Environments

作者： Shan, Liang Wu, Junyi Gu, Keyang Nie, Jinquan Xu, Riqing Jiangxi Normal Univ Sch Software Nanchang 330022 Jiangxi Peoples R China Jiangxi Prov Engn Res Ctr Blockchain Data Secur & Nanchang 330022 Jiangxi Peoples R China

ISBN: (纸本)9783031807121;9783031807138

HTTP/3.0 is an application layer protocol built on top of QUIC, which utilizes its characteristics to provide faster and more reliable data transmission. The combi-nation of HTTP/3.0 and QUIC is considered an important development direction for the next generation of internet transmission protocols. QUIC (Quick UDP In-ternet Connection), as an efficient data transmission protocol, can provide better data transmission quality and user experience with its low latency and high data transmission speed characteristics. However, various new network attacks such as LDDoS attacks constantly threaten the transmission capability and robustness of QUIC transmission systems. To solve this problem, based on the Self-similarity and randomness of QUIC network traffic, a traffic detection model of QUIC network communication based on wavelet and Kalman filter is proposed. First, simulate LDDoS attack through NS3, then use wavelet transform to pre-process the jitter signal after the attack, and then use Kalman filter to denoise. At last, it is compared with the jitter signal which is processed only by Kalman filter. The experiment proves that this method can be used for attack detection and pre-vention of network nodes.

关键词： QUIC LDDoS attack Wavelet transform Wavelet transform

来源：评论

学校读者我要写书评

暂无评论

I2C Bridge on FPGA to Facilitate Vast Connection of Heterogeneous IoT Devices in Agriculture Applications 24

I2C Bridge on FPGA to Facilitate Vast Connection of Heteroge...

引用

8th International conference on Algorithms, Computing and systems, ICACS 2024

作者： Patsianotakis, Charalampos Xenakis, Apostolos Chaikalis, Costas Kosmanos, Dimitrios Stamoulis, George Kakarontzas, George Electrical and Computer Engineering University of Thessaly Volos Greece Digital Systems University of Thessaly Larissa Greece

ISBN: (纸本)9798400718304

The integration of sensor devices into an IoT network is experiencing significant growth. Along with the rise of several application demands, it is necessary to continuously develop new designs to accommodate these changes. To facilitate the integration of new features into the IoT system, the electronics of end - node devices are comprised of the parts related to the Main board (MCU unit), various Radio - Frequency (RF) modules and other essential components. These include the peripheral units, designed specifically to meet the user's application requirements. The goal is to maintain a single Main Board for all devices, thereby reducing logistics management effort and costs. To this end, this paper presents a solution, tailored at consolidating the production parts diversity, within the Agriculture IoT applications domain, thereby streamlining manufacturing processes and enhancing logistics personnel productivity. The proposed approach revolves around the initialization of a communication protocol translator, between the Integrated Circuits (ICs) of Peripheral - Boards and the Main - Board, effectively simplifying the interface, across all productions. Finally, we design and test a software drive, to facilitate the integration at firmware level. Our energy efficient experiments prove the applicability of our proposed solution. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

Unlocking potential: Critical success factors for AI integration in remote patient monitoring systems for post-cardiac surgery care 16

Unlocking potential: Critical success factors for AI integra...

引用

16th International conference on ENTERprise Information systems, CENTERIS 2024 - 12th International conference on Project MANagement, ProjMAN 2024 - 14th International conference on Health and Social Care Information systems and Technologies, HCist 2024

作者： Schmocker, Roberto Sampaio, Suzana Cormican, Kathryn Enterprise Research Centre and LERO The Irish Software Research Centre School of Engineering University of Galway H91 TK33 Ireland Federal Rural University of Pernambuco PE Recife Brazil

Rising healthcare costs have led to a shift towards cost-effective medical technologies that enhance clinical outcomes. Remote Patient Monitoring (RPM) systems enable real-Time data collection, reducing hospital stays, reducing healthcare providers' workload, and improving patient satisfaction. Artificial Intelligence (AI) holds promise in transforming healthcare tasks by uncovering hidden patterns and trends. Despite its potential, AI adoption faces several multifaceted challenges such as data quality, privacy and security, interpretability of AI algorithms, and ethical and regulatory considerations. To successfully implement digital advancements these challenges must be addressed and critical success factors must be defined and prioritized. This study adopts a narrow perspective;it focuses on a context-specific domain and explores critical success factors (CSFs) for AI implementation in RPM systems for post-cardiac surgery patient care. A qualitative approach was used to collect data. Two sets of structured interviews were employed to elicit deep insights and experiences with end users and medical workers. Findings emphasize the importance of stakeholder input, revealing valuable insights into CSFs relevant to post-cardiac patient care. We found that technical aspects such as system reliability, ease of use, and data quality are particularly important and warrant attention. This research is crucial for the scientific and academic community as it addresses the multifaceted barriers to AI integration in healthcare. Illuminating and addressing these issues is critical for enhancing AI applications in healthcare. © 2025 The Author(s).

关键词： Cardiovascular surgery

来源：评论

学校读者我要写书评

暂无评论

Posture Recognition-Based Robot Control Using Media Pipe Pose

Posture Recognition-Based Robot Control Using Media Pipe Pos...

引用

2025 International conference on Electronics, Information, and Communication, ICEIC 2025

作者： Woo Kim, Jong Yeong Mun, Seo Park, BoJeong Choi, Younglim Kim, Hyunseok Dong-A University Dept. of Electronic Engineering Busan Korea Republic of Dong-A University Dept.of Mechanical Engineering Busan Korea Republic of Dong-A University Dept. of Software Innovation Center Busan Korea Republic of Dong-A University Dept. of Computer Engineering Busan Korea Republic of

ISBN: (纸本)9798331510756

This study proposed a body movement-based system for efficiently controlling robots in large indoor environments. Traditional hand gesture recognition systems experience significant accuracy loss in large indoor spaces, particularly as the distance between the user and the camera grows. To address this issue, clear and large body movements were used as control signals instead of hand movements. For example, participants could give commands to the robot by raising both hands or lifting one hand in a specific direction. The system utilized MediaPipe Pose to track the user's posture in real time and communicated commands from the server to the robot via TCP/IP socket communication. This structure ensured stable data transmission, enabling smooth robot control even in expansive spaces. Consequently, this research demonstrated the feasibility of effective robot control in large indoor areas, such as screen golf courses, and suggested the potential for system expansion in various indoor environments. © 2025 IEEE.

关键词： Human robot interaction

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500页 << < 21 22 23 24 25 26 27 28 29 30 > >>

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：