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

1,059 篇 会议
282 篇 期刊文献
26 册 图书

馆藏范围

1,367 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

755 篇 工学
- 509 篇 计算机科学与技术...
- 433 篇 软件工程
- 206 篇 信息与通信工程
- 132 篇 电子科学与技术（可...
- 130 篇 控制科学与工程
- 111 篇 电气工程
- 76 篇 生物医学工程（可授...
- 71 篇 生物工程
- 63 篇 光学工程
- 53 篇 机械工程
- 37 篇 动力工程及工程热...
- 36 篇 仪器科学与技术
- 35 篇 化学工程与技术
- 24 篇 材料科学与工程（可...
- 23 篇 建筑学
- 22 篇 交通运输工程
474 篇 理学
- 247 篇 数学
- 195 篇 物理学
- 82 篇 生物学
- 63 篇 统计学（可授理学、...
- 48 篇 系统科学
- 38 篇 化学
189 篇 管理学
- 115 篇 管理科学与工程(可...
- 78 篇 图书情报与档案管...
- 56 篇 工商管理
71 篇 医学
- 61 篇 临床医学
- 55 篇 基础医学(可授医学...
- 37 篇 药学(可授医学、理...
- 21 篇 公共卫生与预防医...
23 篇 法学
22 篇 经济学
- 22 篇 应用经济学
21 篇 教育学
5 篇 农学
5 篇 军事学
1 篇 文学
1 篇 艺术学

主题

42 篇 computer science
29 篇 feature extracti...
24 篇 bandwidth
23 篇 training
22 篇 computational mo...
19 篇 accuracy
18 篇 optimization
18 篇 data mining
17 篇 application soft...
17 篇 computer archite...
17 篇 artificial intel...
16 篇 proton-proton in...
16 篇 hardware
15 篇 routing
15 篇 throughput
15 篇 neural networks
15 篇 machine learning
15 篇 delay
15 篇 robustness
14 篇 signal to noise ...

机构

35 篇 department of ph...
35 篇 faculty of scien...
35 篇 kirchhoff-instit...
35 篇 institute of phy...
34 篇 department of ph...
34 篇 fakultät für phy...
34 篇 institute of phy...
33 篇 department of ph...
33 篇 department for p...
32 篇 department of ph...
32 篇 instituto de fís...
30 篇 departamento de ...
30 篇 physics departme...
29 篇 faculté des scie...
29 篇 yerevan physics ...
29 篇 institut für ast...
29 篇 department of ph...
29 篇 department of ph...
28 篇 infn sezione di ...
28 篇 infn sezione di ...

作者

31 篇 c. alexa
31 篇 j. m. izen
31 篇 a. harvey
31 篇 c. hensel
31 篇 s. michal
31 篇 t. poghosyan
31 篇 k. bos
31 篇 g. bella
31 篇 j. strandberg
31 篇 d. calvet
31 篇 c. amelung
31 篇 b. toggerson
31 篇 g. m. kolachev
31 篇 f. pastore
31 篇 c. geweniger
31 篇 h. a. gordon
31 篇 s. montesano
31 篇 g. spigo
31 篇 f. siegert
31 篇 a. ishikawa

语言

1,327 篇 英文
20 篇 中文
19 篇 其他
1 篇 日文

检索条件"机构=Computer Engineering and Informatics Dept. and Computer Technology Inst."

共 1367 条记录，以下是71-80 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：

Emotion Recognition from Video Frame Sequence using Face Mesh and Pre-Trained Models of Convolutional Neural Network

Emotion Recognition from Video Frame Sequence using Face Mes...

引用

International Seminar on Intelligent technology and Its Applications (ISITIA)

作者： Derry Pramono Adi Eko Mulyanto Yuniarno Diah Puspito Wulandari Dept. of Electrical Engineering Faculty of Intelligent Electrical and Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia Dept. of Electrical Engineering Dept. of Computer Engineering Faculty of Intelligent Electrical and Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia Dept. of Computer Engineering Faculty of Intelligent Electrical and Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia

Emotions are a collection of subjective cognitive experiences and psychological and physiological characteristics that express a wide range of feelings, thoughts, and behaviors in human interaction. Emotions can be represented through several means, such as facial expressions, tone of voice, and behavior. Deep Learning (DL) research has focused on incorporating facial expressions. Images with facial expressions are commonly used as data input for the DL model. Unfortunately, most DL models in Facial Emotion Recognition (FER) use static images. This method does not take into consideration all conceivable facial expressions. The static image of facial expressions is insufficient for recognizing emotions, but a sequential image from a video is required. In this study, we extract MediaPipe’s face mesh feature, the state-of-the-art multidimensional expression key points embedded in the video image sequence. Furthermore, we feed sequence image data into the pre-trained Convolutional Neural Network (CNN) model. The data we used is from The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) with the emotion classes of “Anger,” “Fearful,” “Happy,” and “Sad.” For this specific FER task, we found that the best pre-trained CNN model achieved 92.8% accuracy (using the VGG-19 model), with the fastest runtime of $\sim2.3$ seconds (achieved using the SqueezeNet model).

关键词：

来源：评论

学校读者我要写书评

暂无评论

PhishGuard: A Convolutional Neural Network-Based Model for Detecting Phishing URLs with Explainability Analysis

PhishGuard: A Convolutional Neural Network-Based Model for D...

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： Md Robiul Islam Md Mahamodul Islam Mst. Suraiya Afrin Anika Antara Nujhat Tabassum Al Amin Dept. of Computer Science and Engineering Uttara University Dhaka Bangladesh Dept. of Informatics University of Oslo Oslo Norway Dept. of Building Engineering and Construction Management Khulna University of Engineering and Technology (KUET) Khulna Bangladesh Dept. of Electrical and Electronics Engineering BRAC University Dhaka Bangladesh Dept. of Electrical and Computer Engineering North South University Dhaka Bangladesh Dept. of Computer Science American International University Bangladesh (AIUB) Dhaka Bangladesh

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

Abstract-Cybersecurity is one of the global issues because of the extensive dependence on cyber systems of individuals, industries, and organizations. Among the cyber attacks, phishing is increasing tremendously and affecting the global economy. Therefore, this phenomenon highlights the vital need for enhancing user awareness and robust support at both individual and organizational levels. Phishing URL identification is the best way to address the problem. Various machine learning and deep learning methods have been proposed to automate the detection of phishing URLs. However, these approaches often need more convincing accuracy and rely on datasets consisting of limited samples. Furthermore, these black-box intelligent models’ decision to detect Suspicious URLs needs proper explanation to understand the features affecting the output. To address the issues, we propose a $1 D$ Convolutional Neural Network (CNN) and trained the model with extensive features and a substantial amount of data. The proposed model outperforms existing works by attaining an accuracy of 99.85 %. Additionally, our explainability analysis highlights certain features that significantly contribute to identifying the phishing URL.

关键词： Uniform resource locators Deep learning Analytical models Accuracy Phishing Organizations Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Prediction of Continuous Targets by Explainable Imbalanced Regression from Omics Data in Childhood Obesity 1

Prediction of Continuous Targets by Explainable Imbalanced R...

引用

1st Workshop on Explainable Artificial Intelligence for the Medical Domain, EXPLIMED 2024

作者： Arteaga, María Torres-Martos, Álvaro Anguita-Ruiz, Augusto Alcalá-Fdez, Jesús Alcalá, Rafael Gacto, María José Dept. of Computer Science and Artificial Intelligence Univ. of Granada Granada Spain Center of Biomedical Research Univ. of Granada Inst. de investigación Biosanitaria ibs.GRANADA Granada Spain Inst. de Salud Carlos III Madrid Spain Barcelona Spain Univ. of Granada Granada Spain Dept. of Software Engineering Univ. of Granada Granada Spain

Childhood obesity is a persistent challenge for society since it is highly related to insulin resistance and a wide range of other chronic diseases, which impair not only the health of the people, but also the health system itself due to extra costs of treating them. In this context, it is imperative to consider innovative approaches, like eXplainable Artificial Intelligence, to understand the factors underlying childhood obesity. Data imbalance has been thoroughly studied in classification, but scarcely studied in regression since classes do not exist. However, extreme values in continuous domains, which are usually minority are often the most clinically relevant. Facing the imbalance in regression while obtaining explainable models has never been studied. In this application work, we adopt a Machine Learning approach to obtain explainable regression models for imbalanced continuous targets in childhood obesity, as HOMA-IR and Waist Circumference. We consider 79 variables, including targeted metabolomics, targeted proteomics, exposomic data (e.g., the physical activity subdomain), hematological parameters and anthropometry of Spanish children from 3 to 18 years with significant imbalance ratios around 12% in HOMA-IR and Waist Circumference. Even though we mainly focus on extensions of linguistic fuzzy rule-based systems, particularly designed for explainability, we also consider highly accurate complementary approaches as Random Forest that could additionally provide contrast interesting information by post-hoc SHAP. The models so obtained are better considering the relevant minority information (17% improvements in F1). Moreover, they seem to properly explain biologically meaningful relations, as in the case of physical activity data or the one with the follicle stimulating hormone, among others. © 2024 Copyright for this paper by its authors.

关键词： Nutrition

来源：评论

学校读者我要写书评

暂无评论

Development of a teaching model based on lifelong learning through active methodological strategies 12

Development of a teaching model based on lifelong learning t...

引用

12th International Conference on Virtual Campus, JICV 2022

作者： Trujillo-Aguilera, F D. Blazquez-Parra, E.B. Almendros, J. Calderon Marti-Campoy, A. Plaza-Garcia, I. University of Malaga Dept. Electronic Technology Malaga Spain University of Malaga Dept. Graphic Engineering Design and Projects Malaga Spain Polytechnic University of Valencia Dept. of Computer and Systems Informatics Valencia Spain University of Zaragoza Dept. of Electronic Engineering and Communications Zaragoza Spain

ISBN: (数字)9781665451062

ISBN: (纸本)9781665451062

Based on one of the fundamental principles of the educational model of the European Higher Education Area concerning the development of the capacity to achieve lifelong learning, this project has been developed in which a set of active teaching activities have been implemented for the acquisition of key competences in the challenge of achieving one of the most important goals that any educational system must provide: lifelong learning, thereby facilitating the incorporation of new university graduates into the world of work. This project has been implemented on the subject of Power Electronics. However, to facilitate the transfer to other subjects, the catalogue of active teaching activities is sufficiently varied to make it easy to extrapolate and use in other subjects, thanks to the fact that teachers have a wide variety of activities to choose from the set. Finally, a survey has been drawn to evaluate this new active methodology's satisfaction, impact and improvement to know the students' perspectives once they have worked with this catalogue of activities. © 2022 IEEE.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Language Grounding: Mapping Words to Actions in Human-Robot Interaction 4

Reinforcement Learning for Language Grounding: Mapping Words...

引用

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Adapa, Srinivasa Rao Gupta, Himanshu Mukherjee, Susmoy Mallupalli, Praneeth Reddy Avhad, Priyanka Upreti, Kamal OpenLogix LLC Software Engineer MI United States Software Engineer Meta NJ United States VIT Institute Electrical and Electronics Engg. Tamil Nadu India Arcesium Hyderabad India Veermata Jijabai Technological Inst. Computer Engineering Mumbai India Christ University Dept. of Computer Science Delhi NCR Campus India

ISBN: (纸本)9798350353266

Within the domain of human-robot communication, effective communication is paramount for seamless and smooth collaboration between humans and robots. A promising method for improving language grounding is reinforcement learning (RL), which enables robots to translate spoken commands into suitable behaviors. This paper presents a comprehensive review of recent advancements in RL techniques applied to the task of language grounding in human-robot interaction, focusing specifically on inst.uction following. Key challenges in this domain include the ambiguity of natural language, the complexity of action spaces, and the need for robust and interpretable models. Various RL algorithms and architectures tailored for language grounding tasks are discussed, highlighting their strengths and limitations. Furthermore, real-world applications and experimental results are examined, showcasing the effectiveness of RL-based approaches in enabling robots to understand and execute inst.uctions from human users. Finally, promising directions for future research are identified, emphasizing the importance of addressing scalability, generalization, and adaptability in RL-based language grounding systems for human-robot interaction. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of data from UAVs for surveillance and threat identification in maritime areas

Analysis of data from UAVs for surveillance and threat ident...

引用

Big Data, Cloud Computing, Data Science & engineering (BCD)

作者： Fotis Lampropoulos Ioannis Daramouskas Isidoros Perikos Michael Paraskevas Electrical and Computer Engineering Dept. University of Peloponnese Patras Greece Hellenic Coast Guard Patras Greece Computer Engineering and Informatics Department Computer Technology Institute and Press "Diophantus" University of Patras Patras Greece Electrical and Computer Engineering Dept. Computer Technology Institute and Press "Diophantus" University of Peloponnese Patras Greece

In this paper, we present a methodology for drones for recognizing different types of objects in maritime areas. The concept and the aim is to assist the national maritime surveillance authorities in the identification of treats and the recognition of the exact type of the treat. The methodology relies on the use of deep learning networks and YOLO framework as well as regression models. The YOLO model detects where each object is and which label should be applied. In this way, object detection is subject to the analysis of Machine Learning-based approaches and Deep Learning-based approaches providing more information about the video or an image than traditional approaches to recognition. These approaches are used to identify groups of pixels that may individually belong to an object. This then feeds a regression model with the help of a convolutional neural network and more specifically, R-CNN, Fast R-CNN, Faster R-CNN and after that object detection algorithm approximates the location of the object and gives its label at the same time. The purpose of the application is to detect objects with an emphasis on identifying one or more targets of interest from data of a video or an image capture. An experimental study was conducted in real-world conditions and revealed quite interesting findings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Acoustic measurement framework for audio systems based on structured periodic test signals 12

Acoustic measurement framework for audio systems based on st...

引用

12th IEEE Global Conference on Consumer Electronics, GCCE 2023

作者： Kawahara, Hideki Yatabe, Kohei Sakakibara, Ken-Ichi Mizumachi, Mitsunori Kitamura, Tatsuya Wakayama University Cntr. Innovative Research and Liaison Wakayama Japan Tokyo University of Agriculture and Technology Dept. Electrical Engineering and Computer Science Tokyo Japan Health Sciences University of Hokkaido Dept. Speech-Language-Hearing Therapy Hokkaido Japan Kyushu Institute of Technology Dept. Electrical and Electronic Eng. Kitakyushu Japan Konan University Dept. Intelligence and Informatics Kitakyushu Japan

ISBN: (纸本)9798350340181

We introduce a framework for acoustic measurement that allows everyday sounds into acoustic measurement test signals and standard test signals such as swept-sine and MLS (Maximum Length Sequence). The framework extends our extended Time-Stretched-Pulse generation method and safeguarding method for any signals to make them appropriate for acoustic measurement. The extension uses the periodic nature of discrete Fourier transform combined with orthogonalization based on the Walsh-Hadamerd matrix. This framework enables simultaneous measurement of acoustic attributes such as linear time-invariant response, signal-dependent non-linear and time-invariant components, and random time-varying components. We also discuss and demonstrate practical scenarios in classes and laboratory lessons using tools developed based on the proposed framework. © 2023 IEEE.

关键词： Audio systems

来源：评论

学校读者我要写书评

暂无评论

A Method for Predicting Cardiovascular Disorder using Machine Learning Techniques

A Method for Predicting Cardiovascular Disorder using Machin...

引用

2024 IEEE International Conference on Recent Advances in Science and engineering technology, ICRASET 2024

作者： Hegde, Ramakrishna Pavithra, D.R. Shivashankara, S. Prasanna Kumar, G. Soumyasri, S.M. Nagashree, S. Vidyavardaka College of Engineering Affiliated to Visvesvaraya Technological University Belagavi India Jss Science and Technology University Sri Jayachamarajendra College of Engineering Mysuru India Kr Pete Krishna Government Engineering College Krishnarajapet India The National Institute of Engineering Mysore India Dept. of Computer Applications Vidya Vikas Inst. of Engg. and Tech. Affiliated to Visvesvaraya Technological University Belagavi India Vidya Vikas Institute of Engineering and Technology Mysuru India

ISBN: (纸本)9798350388602

Drastic increase of cardiovascular disease has led to a lot of adult's death. As per 'News 18' very year, 12 million young people in India die from heart disease. In most of these cases people experience cardiac arrest, some of which are normal. First, families of patients are vulnerable because it takes only a few minutes for a person to die of a heart attack, and it is difficult to get medical help in time. Second, most victims are under the age of 45. According to Dr. Maninder Sandhu, cardiologist and cardiologist at Artemis Hospital Gurgaon, 30 percent of people who suffer from heart disease are under the age of 45. This paper proposes a method that maybe used by laboratory technicians, doctors and users to understand whether there are any chances of having cardiovascular disease or not. The proposed system takes live data of patients and their lifestyle attributes these data are processed by the trained model to produce the output. In this model we haveused random forest classifier, linear regression, k-neighbors classifier & x gradient boost classifier. This model has attained maximum accuracy and least type one error in 'X- Gradient Boost'. We have concentrated more on type one error. The developed system shows whether the patient has any chances of cardiovascular disease or not. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality-Based Navigation: Bridging Indoor and Outdoor Environments through Immersal Integration

Augmented Reality-Based Navigation: Bridging Indoor and Outd...

引用

IEEE International Symposium on Consumer Electronics (ISCE)

作者： Zacky Maulana Achmad Sritrusta Sukaridhoto Muhammad Agus Zainuddin Aurent Savila Ardian Firmansyah Septa Mega Saputra Dept. of Informatics and Computer Engineering Politeknik Elektronika Negeri Surabaya Surabaya Indonesia Dept. of Multimedia Creative Technology Politeknik Elektronika Negeri Surabaya Surabaya Indonesia

ISBN: (数字)9798350365191

ISBN: (纸本)9798350365207

A navigation system is an essential tool designed to assist users in determining and following a route from one location to another. Navigation systems are typically categorized into two types: outdoor navigation systems designed for open areas and indoor navigation systems used within enclosed spaces. However, transitioning between indoor and outdoor environments has limitations, often requiring users to switch applications, such as using GPS for outdoor navigation and a different application for indoor navigation. Therefore, we propose the integration of indoor and outdoor navigation based on Augmented Reality. The development of AR navigation system begins with the creation of 3D assets of the Politeknik Elektronika Negeri Surabaya (PENS) campus, which is the site of our research including three buildings for indoor navigation and the connecting roads between the buildings for outdoor navigation. The development of this navigation system uses the Immersal SDK as a library for Spatial Mapping, Localization and System Integration. Several features are included, such as indoor-outdoor navigation, multilevel floor navigation, and zero additional devices. The system testing results are based on user testing, integration testing, and multilevel floor testing. From User Testing with PIECES Framework, 32 respondents expressed satisfaction with the proposed system. Integration Testing showed that the system could navigate between indoor and outdoor environments. And Multilevel Floor Testing demonstrated that the system could navigate within buildings with multiple floors.

关键词： Location awareness Three-dimensional displays Navigation Indoor navigation Buildings Switches Stairs Floors Augmented reality Testing

来源：评论

学校读者我要写书评

暂无评论

Development of a Calibration-Free Brain-computer Interface Utilizing Common Spatial Patterns and Artificial Neural Networks for EEG Signal Analysis 6

Development of a Calibration-Free Brain-Computer Interface U...

引用

6th International Congress on Human-computer Interaction, Optimization and Robotic Applications, HORA 2024

作者： Cengiz, Korhan Shreyas, J. Udayaprasad, P.K. Gururaj, H.L. Kumar, Dilip S.M. College of Information Technology University of Fujairah United Arab Emirates Faculty of Organization and Informatics University of Zagreb Croatia Croatia Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Karnataka Manipal576104 India Department of Artificial Intelligence & Machine Learning Global Academy of Technology Bengaluru India Dept. of Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore India

ISBN: (纸本)9798350394634

A brain computer interface (BCI) system uses a technique known calibration, that takes 20 to 30 minutes to accomplish. For the objective of creating a reliable decoder, the calibration process is challenging and expensive. In order to address the drawbacks of the current system, a spectral-spatial technique has been suggested. The motor imagery (MI) data set, comprising 15 electroencephalography (EEG) signals and fourteen test subjects, is taken into consideration. The two modules are designed to extract characteristics and process data. An artificial neural network (ANN) is used to independently train and test the suggested spectral-spatial algorithm. Based on it, a variety of machine learning techniques, including random forest (RF), neural networks (NN), and XGboost, are used to classify the data, that is then sent to the hidden layer (Lth layer). The obtained results indicates 2% of improvement in comparison with existing methodology. © 2024 IEEE.

关键词： Electroencephalography

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137页 << < 4 5 6 7 8 9 10 11 12 13 > >>

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：