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

6,150 篇 会议
5,208 篇 期刊文献
126 册 图书

馆藏范围

11,484 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,436 篇 工学
- 5,354 篇 计算机科学与技术...
- 4,415 篇 软件工程
- 1,755 篇 信息与通信工程
- 1,070 篇 控制科学与工程
- 905 篇 生物工程
- 891 篇 电气工程
- 682 篇 电子科学与技术（可...
- 601 篇 生物医学工程（可授...
- 577 篇 光学工程
- 541 篇 机械工程
- 366 篇 仪器科学与技术
- 347 篇 化学工程与技术
- 320 篇 动力工程及工程热...
- 315 篇 网络空间安全
- 265 篇 交通运输工程
- 250 篇 安全科学与工程
4,131 篇 理学
- 2,041 篇 数学
- 1,310 篇 物理学
- 1,014 篇 生物学
- 682 篇 统计学（可授理学、...
- 416 篇 系统科学
- 379 篇 化学
2,072 篇 管理学
- 1,227 篇 管理科学与工程(可...
- 925 篇 图书情报与档案管...
- 578 篇 工商管理
611 篇 医学
- 528 篇 临床医学
- 465 篇 基础医学(可授医学...
- 291 篇 公共卫生与预防医...
- 257 篇 药学(可授医学、理...
398 篇 法学
- 309 篇 社会学
189 篇 经济学
156 篇 教育学
142 篇 农学
36 篇 文学
35 篇 艺术学
27 篇 军事学
7 篇 哲学
3 篇 历史学

主题

298 篇 deep learning
261 篇 machine learning
260 篇 feature extracti...
221 篇 computational mo...
192 篇 accuracy
185 篇 semantics
171 篇 predictive model...
168 篇 internet of thin...
168 篇 training
144 篇 real-time system...
117 篇 data mining
110 篇 support vector m...
110 篇 artificial intel...
109 篇 neural networks
109 篇 security
108 篇 computer science
108 篇 optimization
95 篇 visualization
88 篇 data models
87 篇 cloud computing

机构

172 篇 university of ch...
122 篇 key laboratory o...
113 篇 university of sc...
97 篇 tianfu cosmic ra...
96 篇 school of comput...
91 篇 hebei normal uni...
89 篇 state key labora...
87 篇 department of ph...
87 篇 school of comput...
86 篇 yunnan observato...
73 篇 key laboratory f...
59 篇 karnataka bangal...
56 篇 school of inform...
56 篇 school of inform...
54 篇 school of comput...
54 篇 college of compu...
54 篇 school of comput...
54 篇 college of intel...
48 篇 institute for nu...
47 篇 department of co...

作者

97 篇 niyato dusit
82 篇 axikegu
78 篇 fang j.
78 篇 feng c.f.
77 篇 jiang k.
76 篇 bastieri d.
71 篇 kuleshov d.
71 篇 li cheng
70 篇 li xin
70 篇 liu d.
69 篇 chen m.j.
69 篇 liu s.m.
68 篇 huang d.h.
67 篇 dai h.l.
63 篇 min z.
61 篇 guo y.q.
58 篇 liu b.
57 篇 bao y.w.
56 篇 heller m.
56 篇 hu h.b.

语言

10,384 篇 英文
959 篇 其他
127 篇 中文
13 篇 日文
2 篇 德文
1 篇 法文

检索条件"机构=School of Computing and Information Technology Feculty of Science and Technology"

共 11484 条记录，以下是581-590 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Generative Adversarial Networks for Self-Supervised Transfer Learning in Medical Image Classification 5th

Generative Adversarial Networks for Self-Supervised Transfer...

引用

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Kumar, Rohit Yogeetha, B.R. Savita Mehta, Deepak School of Engineering and Computing Dev Bhoomi Uttarakhand University Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bengaluru India

ISBN: (纸本)9789819780426

Self-supervised transfer mastering for clinical picture analysis is a method that uses deep getting-to-know procedures to research large units of medical imaging facts without using guide labels. By way of using switch getting to know, the version can come across diffused patterns from the facts that are not easily located with the aid of the medical doctors or researchers. This method can diffuse clinical imaging packages consisting of type, segmentation, and item detection. The self-supervised transfer studying technique involves educating an artificial intelligence (AI) model on a set of scientific picas with available labels. Further, the model can detect small capabilities and patterns that may be ignored through manual labeling, leading to more excellent correct outcomes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Improved Honey Encryption to Protect the Internet users from Various Attacks 3

Improved Honey Encryption to Protect the Internet users from...

引用

3rd International Conference on Electronics and Sustainable Communication Systems, ICESC 2022

作者： Nirmalraj, T. Jebathangam, J. Vistas School of Computing Science Department of Computer Science Chennai India Vistas School of Computing Science Department of Information Technology Chennai India

ISBN: (数字)9781665479714

ISBN: (纸本)9781665479714

In recent months, there has been a rise in security issues as well as data breaches, which has led to increased anxiety regarding the safety of online banking. The existing authentication method for internet banking, which is entirely dependent on a password, is not robust enough to withstand the recent wave of successful password guessing and cracking attacks due to the fact that it is solely dependent on a password. As a potential remedy to this problem, the authors of this paper proposed a method known as Honey Encryption (HE), which adds another layer of protection on top of the user authentication measures that are already in place. When a malicious user guesses the password for a cloud account, the HE algorithm immediately generates false bank data that is impossible to distinguish and then directs the attacker to an account that has a fake password. This prevents the attack from being able to determine whether or not the password that was guessed is valid. As a direct consequence of this, cracking attacks and guessing passwords have become increasingly challenging. In addition to that, this research investigates different attack models and potential defences for password-based authentication schemes. © 2022 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Innovative Image Processing Techniques for Automating Cosmetic Inspection 5th

Innovative Image Processing Techniques for Automating Cosmet...

引用

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Panwar, Govind Singh Murthy, D.H.R. Agarwal, Trapty Jaison, Feon Department of Computer Science and Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India

ISBN: (纸本)9789819780426

Progressive photograph processing techniques were developed for automating the technique of beauty inspection. These techniques make use of the wealthy, unique image records of the inspected objects to hastily become aware of diverse product defects. Specifically, object features including coloration, texture, size, shape, and location are first extracted from the photograph, and every function is then evaluated to come across cosmetic defects. Following the detection technique, the extracted capabilities are used to at once alter the manufacturing technique, enabling faster production turnaround times and progressed product quality. The strategies are designed to make certain rapid and accurate product inspection and also provide a bendy adjustment of parameters for various types of cosmetic merchandise. With these techniques, producers are capable of reduce cosmetically based totally product defects and supply improved great merchandise in a shorter time frame. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

Defending Against Vishing Attacks: A Comprehensive Review for Prevention and Mitigation Techniques

Defending Against Vishing Attacks: A Comprehensive Review fo...

引用

International Conference on Recent Developments in Cyber Security, ReDCySec 2023

作者： Ashfaq, Shaikh Chandre, Pankaj Pathan, Shafi Mande, Uday Nimbalkar, Madhukar Mahalle, Parikshit Information Technology Department M H Saboo Siddik College of Engineering Mumbai India Computer Science and Engineering Department MIT School of Computing MIT Art Design and Technology University Loni Kalbhor Pune India Artificial Intelligence and Data Science Department Vishwakarma Institute of Information Technology Kondhwa Pune India

ISBN: (纸本)9789819998104

Vishing attacks, or voice phishing attacks, are a type of social engineering attack in which attackers use voice communication channels, such as phone calls, to trick victims into divulging sensitive information or performing actions that compromise their security. Vishing attacks have become increasingly common in recent years and can have severe consequences for individuals, businesses, and organizations. In this review, we examine various prevention and mitigation techniques that can be used to defend against vishing attacks. We start by discussing the common tactics used by attackers and how they exploit vulnerabilities in human behaviour to achieve their goals. We then present an overview of different prevention and mitigation techniques, including education and awareness campaigns, technical solutions such as authentication mechanisms and policy-based approaches. We also evaluate the effectiveness of different techniques, highlighting their strengths and weaknesses, and provide guidance on how to implement a comprehensive vishing defence strategy. Finally, we discuss emerging trends and challenges in vishing attacks and defence, such as the use of artificial intelligence and deepfake technology, and suggest directions for future research and development. Overall, this review provides a comprehensive and up-to-date overview of the current state of vishing attacks and defence, and should be of interest to researchers, practitioners, and individuals who want to enhance their knowledge and understanding of this important topic. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Detecting Brain Cancer Using Explainable AI 7

Detecting Brain Cancer Using Explainable AI

引用

7th International Conference on Signal Processing and information Security, ICSPIS 2024

作者： Rahman, Abdul Sohail, Shahab Saquib Alam, Mohammad Sultan Sharma, Anil Mansoor, Wathiq VIT Bhopal University School of Computing Science Engineering and Artificial Intelligence MP Sehore466114 India VIT Bhopal University School of Computing Science and Engineering MP Sehore466114 India Amity School of Engineering & Technology UP Noida201313 India University of Dubai College of Engineering and Information Technology Dubai United Arab Emirates

ISBN: (纸本)9798350368673

The accurate and early diagnosis of brain tumors that is one of the deadly cancers may save many humans. Proposed research focused on primary types of tumors detection (i.e. gliomas, meningiomas, and pituitary tumors). Further, the research is meticulous in fine-tuning the model's parameters - including the loss function, optimizer, learning rate, epochs, and batch size - to optimize performance and achieve high accuracy in tumor detection. While the findings of this work mark a significant advancement in medical imaging and brain tumor detection, it acknowledges the prevailing limitations, such as the constraints imposed by hardware resources and the challenges of model generalization across diverse and more extensive datasets. Recognizing these limitations, the work sets the stage for future research, emphasizing the exploration of larger and more heterogeneous datasets, the adoption of more sophisticated deep learning models, with the aim of enhancing the precision, reliability, and clinical applicability of brain tumor detection methodologies. In essence, this research not only contributes to the field of medical imaging analysis but also represents a transformative step towards the realization of more accurate, timely, and personalized healthcare solutions, powered by the advancements in artificial intelligence and machine learning. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Machine Learning Techniques for Yemeni Universities Admission Examinations Predictions 1

A Comparison of Machine Learning Techniques for Yemeni Unive...

引用

1st International Conference on Emerging Technologies for Dependable Internet of Things, ICETI 2024

作者： Al-Hagree, Salah Al-Sanabani, Maher Al-Gaphari, Ghaleb Al-Shalabi, Ahmed Abdullah Alawdi, Ala'a Al-Dilami, Redwan Mohsen, Ayedh Abdulaziz Alfahad, Khalil T. Computer Science Department Faculty of Computer and Information Technology Sana’a University Yemen Computer Science Department Faculty of Sciences Ibb University Yemen Aljazeera University Yemen Computer Science Department Faculty of Computer and Information Technology Thamar University Yemen Faculty of Computing and IT University of Science and Technology Sana’a Yemen School of Mathematics and Computer Science Wuhan Textile University China

ISBN: (纸本)9798331533557

Admissions examinations are crucial in shaping students' academic and career paths. Machine learning (ML) offers a promising avenue for transforming the assessment process in universities, schools, and colleges. This paper presents a new ML-based method to evaluate high school graduates seeking admission to eleven colleges across nine Yemeni universities, applicable to both scholarship and self-financing students. The proposed approach leverages several ML techniques, including Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), K-Nearest Neighbors (KNN), Gradient Boosting (GB), Extra Trees (ET), Decision Tree (DT), AdaBoost, and XGBoost. In this study, ML algorithms were applied to admissions examinations at nine Yemeni universities, including Sana’a, Ibb, Dhamar, Amran, Jiblah, Mihwit, Al-Dhalea, Saada, and Hajjah. The dataset comprised 15,898 student applications for eleven colleges, encompassing both scholarship and self-financing programs. Experiment one evaluated the performance of various ML techniques. Gradient Boosting (GB) and Random Forest (RF) demonstrated superior results, achieving the highest accuracy, precision, recall, and F-score. Specifically, GB and RF attained 91.00% and 90.00% accuracy, 87.60% and 88.80% precision, 89.90% and 87.50% recall, and 89.30% and 87.60% F-score, respectively. Experiment two further refined the analysis, comparing ET and RF to other ML methods. ET and RF consistently outperformed LR, KNN, SVM, DT, GB, AdaBoost, and XGBoost. In this experiment, ET and RF achieved exceptional accuracy, precision, recall, and F-score rates of 99.00% and 99.00%, 97.50% and 97.20%, 98.00% and 97.80%, and 97.80% and 97.50%, respectively. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for ECG-Based Cardiac Anomaly Detection with Improved Feature Extraction 2

A Deep Learning Approach for ECG-Based Cardiac Anomaly Detec...

引用

2nd IEEE Global Conference on Communications and information Technologies, GCCIT 2024

作者： Thanjaivadivel, M. Purandhar, N. Bhasker, B. Ganesh, A. Reva University School of Computing and Information Technology Karnataka Bengaluru India Madanapalle Institute of Technology & Science School of Computers Andhra Pradesh Madanapalle India Sri Venkateswara College of Engineering Department of Cse Andhra Pradesh Tirupati India

ISBN: (纸本)9798350388916

Heart disease is a global health concern that requires accurate and timely prediction tools for successful management and treatment. Electrocardiogram (ECG) data analysis helps discover cardiac anomalies by revealing heart function and risk factors. ECG data is complicated and variable, making interpretation and prediction difficult. Researchers have used preprocessing, feature extraction, and machine learning algorithms to enhance heart disease prediction. Ensemble learning can improve predictive performance by combining model predictions. This study attempts to improve cardiac risk assessment and patient outcomes by merging multiple *** goal of this paper is to improve heart disease prediction accuracy by evaluating ECG data using machine learning techniques. To improve cardiac abnormality identification, preprocess ECG images, extract key characteristics, and use ensemble learning. The work investigates signal contour extraction and dimensionality reduction to provide a comprehensive cardiac risk assessment *** study uses a multi-step technique to improve heart disease prediction using ECG data. Preprocessing ECG pictures with signal contour extraction, grayscale conversion, and Gaussian blurring improves data quality and clarity. To find predictive modelling features, feature extraction methods like PCA dimensionality reduction are used. Ensemble learning methods like the Voting Classifier combine predictions from numerous machine learning models to increase predictive performance. Hyperparameter adjustment improves model performance, achieving 98% testing set correctness. This study's methods give a complete foundation for precise and fast cardiac risk assessment. © 2024 IEEE.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Enhanced Speech Emotion and Gender Recognition Using Hybrid CNN-LSTM Models 4

Enhanced Speech Emotion and Gender Recognition Using Hybrid ...

引用

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

作者： Priyadharshini, S. Sundar, G. Naveen Narmadha, D. Thangavel, Senthil Kumar Ajibesin, Adeyemi Abel Kolandapalayam Shanmugam, Selvanayaki Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Coimbatore India Amrita School of Computing Department of Computer Science and Engineering Coimbatore India Cape Peninsula University of Technology Faculty of Informatics and Design Department of Information Technology South Africa Ashland University Department of Mathematics and Computer Science United States

ISBN: (纸本)9798331523923

The current paper proposes a new approach for peripheral speech emotion analysis and gender estimation incorporating the best machine learning architectures such as CNNs and LSTMs. Its correct depiction of emotions and the variation of the gendered speech to indicate manifold signal-to-noise ratio make the approach accommodate the difficulty inherent in recognizing emotions from the recording of voices as well as predicting the gender of a speaker. It is then able to ally with preprocessing and collection of a vast range of different speech samples, feature extraction of pitch, tone and spectral data. These features serve as input to the CNNs and LSTMs: LSTMs work well at temporal regular features and the CNNs work well in feature extraction by location (spatio feature). The approach is tested on the RAVDESS and IEMOCAP datasets and establishes a near perfect match to prior approaches with reference to recognition accuracy of emotion analysis and gender prediction. Thus, applying the identified dual method approach, which could be described by such characteristics as highly accurate data pre-preprocessing, clear indication of the features of interest, a different CNN-LSTM model joint training, it offers a reasonably good platform to gain certain insights into such characteristics of the speech as our experiment demonstrates. This work offers satisfactory configurations on concerns such as human computer relation, customer relation and mental health surveillance to suggest that other applications could be achieved in future. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Amyotrophic Lateral Sclerosis with Time Collection Evaluation 5th

Early Detection of Amyotrophic Lateral Sclerosis with Time C...

引用

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Mehar, Palavancha Tirumala Krishna Agarwal, Trapty Suneetha, K. Ahmad, Naseem School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bengaluru India Department of Computer Science and Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Dehradun India

ISBN: (纸本)9789819780426

This paper discusses the usage of time series analysis for the early detection of Amyotrophic Lateral Sclerosis (ALS). A time series approach was used to expand a set of rules that may detect the early stages of ALS via analyzing symptomatic changes in signs and symptoms consisting of muscle energy, taking walks potential, speech, swallowing, and different bodily motion. This technique become examined on a retrospective dataset, and proven if you want to come across changes in the circumstance of ALS in a well-timed way. The outcomes suggest that this technique has ability as a tool for early detection in ALS sufferers. The proposed algorithm ought to potentially be used to improve the present day standard of care and help lead to in advance analysis and higher scientific effects. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Motion Potential Swallowing

来源：评论

学校读者我要写书评

暂无评论

How to Train Your Neural Network for Molecular Structure Generation from Mass Spectra?

How to Train Your Neural Network for Molecular Structure Gen...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhao, Kai Liu, Yanmin Dian, Longyang Sun, Shiwei Cui, Xuefeng Shandong University School of Computer Science and Technology Qingdao China Shandong University State Key Laboratory of Microbial Technology Qingdao China Chinese Academy of Sciences Key Lab of Intelligent Information Processing Institute of Computing Technology Beijing China

ISBN: (纸本)9798350386226

Mass spectrometry serves as a pivotal tool for the analysis of small molecules through an examination of their mass-to-charge ratios. Recent advancements in deep learning have markedly enhanced the analysis of mass spectrometric data, facilitating the prediction of novel small molecule structures without the necessity of extensive databases. Nonetheless, the paucity of annotated datasets impedes the efficacious training of molecular generation models predicated on MS2 spectra. To mitigate this limitation, we introduce ctMSNovelist, an avant-garde method that amalgamates pre-training, fine-tuning, and co-training techniques to construct a more precise model for the generation of molecular structures from tandem mass spectrometry data. This novel approach augments both the training regimen and the predictive accuracy of the MSNovelist model, thereby surmounting the obstacle of limited data. The methodology commences with the pretraining of a Variational Autoencoder (VAE) to generate molecular fingerprints derived from SMILES strings. Subsequently, it undergoes fine-tuning to emulate noisy fingerprints originating from mass spectrometry (MS) data. Concurrently, MSNovelist is co-trained utilizing these simulated fingerprints, inclusive of the highly noisy variants produced in the early stages of VAE training. The incorporation of a substantial volume of noisy data serves to enhance model accuracy and avert overfitting. We evaluated ctMSNovelist using the GNPS dataset and attained a SMILES prediction accuracy of 48.8%, representing a 4.1% enhancement over MSNovelist. It is pertinent to note that the sole distinction between ctMSNovelist and MSNovelist in this experiment was the training process. The code and models are publicly available at https://***/xfcui/ctMSNovelist. © 2024 IEEE.

关键词： Neural networks

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

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：