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

1,269 篇 会议
261 篇 期刊文献
1 册 图书

馆藏范围

1,531 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

766 篇 工学
- 599 篇 计算机科学与技术...
- 516 篇 软件工程
- 194 篇 信息与通信工程
- 151 篇 控制科学与工程
- 125 篇 电气工程
- 115 篇 生物医学工程（可授...
- 115 篇 生物工程
- 83 篇 光学工程
- 80 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
422 篇 理学
- 205 篇 数学
- 131 篇 生物学
- 114 篇 物理学
- 84 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...
56 篇 法学
- 48 篇 社会学
46 篇 经济学
- 46 篇 应用经济学
35 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

190 篇 accuracy
123 篇 real-time system...
118 篇 deep learning
81 篇 convolutional ne...
80 篇 machine learning
78 篇 predictive model...
77 篇 training
71 篇 feature extracti...
60 篇 support vector m...
60 篇 computational mo...
56 篇 internet of thin...
56 篇 machine learning...
55 篇 medical services
53 篇 data models
50 篇 optimization
47 篇 reviews
42 篇 reliability
41 篇 prediction algor...
41 篇 artificial intel...
36 篇 technological in...

机构

52 篇 nitte meenakshi ...
43 篇 department of ar...
39 篇 lovely professio...
32 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
15 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 abhay tale
11 篇 rushikesh burle
10 篇 xiaojiang du
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

1,128 篇 英文
401 篇 其他
6 篇 中文
1 篇 斯洛文尼亚文

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

共 1531 条记录，以下是641-650 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：

Image Captioning-A Comprehensive Encoder-Decoder Approach on Flickr8K

Image Captioning-A Comprehensive Encoder-Decoder Approach on...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Mithilesh Mahajan Saanvi Bhat Madhav Agrawal Gitanjali Shinde Rutuja Rajendra Patil Gagandeep Kaur Dept. of Computer Science Engineering (Artificial Intelligence and Machine Learning) Vishwakarma Institute of Information Technology Pune India Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

This paper proposes a new encoder-decoder frame-work based on Convolutional Neural Networks (CNN) for feature extraction and Long Short-Term Memory (LSTM) networks for image caption generation. Image captioning, the process of generating descriptive textual content for images, has diverse applications, including accessibility tools for the visually impaired, virtual assistants, social media automation, and satellite imagery analysis in critical domains like defense and disaster management. The proposed model will leverage the power of CNNs for extracting high-level image features and LSTMs for generating semantically coherent captions. Rigorously evaluated on the Flickr8k dataset, the model achieved competitive BLEU scores, showing its efficacy in generating accurate and meaningful descriptions. The methodology integrates advanced preprocessing techniques and efficient training strategies, ensuring robustness and scalability. This re-search focuses on the need to use state-of-the-art machine learning techniques in the solving of real challenges, and some of the potential routes to improving image captioning systems are suggested to include multilingual capabilities and integration with larger datasets. Contributions include a clear explanation of the encoder-decoder approach, detailed metrics for evaluation, and insights into correcting limitations including dataset size and complex scene representation. This work is a step toward further progress in automated image-to-text systems, integrating precision, relevance, and adaptability.

关键词： Measurement Training Adaptation models Automation Accuracy Social networking (online) Virtual assistants Feature extraction Convolutional neural networks Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Bird Species Classification and Prediction Using machine learning Algorithms

Bird Species Classification and Prediction Using Machine Lea...

引用

IEEE Punecon

作者： Penchala Abhinav Sunitha Dhavale Department of Artificial Intelligence & Machine Learning Vardhaman College of Engineering Hyderabad Telangana India School of Computer Engg. & Mathematical Sciences Defence Institute of Advanced Technology Pune

ISBN: (数字)9798331527822

ISBN: (纸本)9798331527839

The BirdClef-2024 dataset, which includes acoustic recordings of 182 Western Ghats species, was used to classify and predict bird species in this study. Three machine learning algorithms were analyzed for their accuracy, precision, recall, and F1 score – K Nearest Neighbors (KNN), Random Forest, and Support Vector machine (SVM). The Random Forest model outperformed the other models in all metrics. The paper contains sections on dataset composition, preprocessing steps, algorithm implementations as well comparisons of the model’s performances. Such issues have been successfully addressed through advanced pre-processing techniques coupled with complex machine-learning algorithms despite the intricate nature of the sound signals. A Streamlit GUI that is user-friendly has been developed to facilitate real-time recognition of birds by breed; this can contribute to surveillance for environmental biodiversity conservation efforts.

关键词： Support vector machines machine learning algorithms Accuracy Biological system modeling Computational modeling Nearest neighbor methods Birds Recording Random forests Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Empowering Early Diagnosis: Optimizers Revolutionizing Breast Cancer Detection with DenseNet 3

Empowering Early Diagnosis: Optimizers Revolutionizing Breas...

引用

3rd International Conference on Technological Advancements in Computational Sciences, ICTACS 2023

作者： Pranati, V. Khatri, Narendra Sharma, Harish Shukla, Praveen Kumar Manipal Institute of Technology Manipal Academy of Higher Education Department of Biomedical Engineering Manipal576104 India Manipal Institute of Technology Manipal Academy of Higher Education Department of Mechatronics Manipal576104 India School of Computer Science and Engineering Manipal University Jaipur Department of Artificial Intelligence and Machine Learning Jaipur India School of Computer and Communication Engineering Manipal University Jaipur India

ISBN: (纸本)9798350342338

Breast cancer, a highly lethal disease with a significant global impact, requires early detection to reduce its mortality rate. The emergence of pre-trained Deep learning (DL) algorithms, commonly utilized for object detection, image classification, and image segmentation, has advanced early breast cancer detection. Several researchers have explored early breast cancer detection using pre-trained DL algorithms in conjunction with classifiers or other existing methods. However, existing research lacks a thorough examination of optimizers and their potential influence on the behaviour of these pre-trained algorithms. This study aims to comprehensively investigate the behaviour of the pre-trained DenseNet201 model under various optimizer and learning rate configurations. The analysis reveals that the DenseNet model achieved superior performance (100% accuracy) with the SGD (Stochastic Gradient Descent), and RMSProp optimizers at a learning rate of 10-2 and 10-3, respectively. However, at a learning rate of 10-4, the Adam optimizer demonstrated the highest accuracy of 99%. © 2023 IEEE.

关键词： Breast Cancer Detection DenseNet201 learning Rates Optimizers Pre-trained DL algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhanced Automatic Number Plate Recognition for High-Speed Vehicles: Leveraging YOLO and Haar Cascade

Enhanced Automatic Number Plate Recognition for High-Speed V...

引用

Pervasive Computing and Social Networking (ICPCSN), International Conference on

作者： K. Kumaran Tharani. R G. Saranya V. Prashanthi G. Manoj Kumar K. Manoj Sagar Department of Information Technology Easwari Engineering College Chennai Tamil Nadu India Department of Artificial Intelligence & Machine Learning Sri Sairam College of Engineering Bengaluru Karnataka India Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Computing Technologies SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Artificial Intelligence and Machine Learning Malla Reddy University Hyderabad

ISBN: (数字)9798350386349

ISBN: (纸本)9798350386356

The integration of artificial intelligence (AI) into advanced Automatic Number Plate Recognition (ANPR) systems offers a state-of-the-art approach for precise identification of license plates on vehicles. This system employs sophisticated techniques including template matching and connected component analysis to efficiently extract characters from input images. Plate extraction, character segmentation, and template matching are integral parts of the process, ensuring reliable operation across diverse outdoor environments with a focus on rapid identification during daylight hours. ANPR systems find wide applications in automated toll collection, parking access control, traffic law enforcement, and road traffic monitoring. Leveraging AI, the approach utilizes multiple templates and character identification methods to enhance accuracy and efficiency. Following character recognition, the identified characters are validated against a license plate database, achieving an accuracy of about 91.8%. Renowned for its simplicity and rapidity in character recognition and plate segmentation across various weather conditions, this model represents a significant advancement in high-speed ANPR technology enabled by AI.

关键词： YOLO Access control Accuracy Systematics Social networking (online) Transportation Robustness

来源：评论

学校读者我要写书评

暂无评论

An Involuntary Liver Cancer Recognition in Abdominal Liver Imageries with Soft Optimization Methods in Biomedical Application

An Involuntary Liver Cancer Recognition in Abdominal Liver I...

引用

2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023

作者： Kumar, M. Vinodh Kumar Patra, Raj Veena, R. Siva Kumar Reddy, A. Sunil Kumar, V. Inventuriz Labs Pvt Ltd Bengaluru India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaadeswaram India Hyderabad Institute of Technology and Management Department of Computer Science and Engineering Telangana India K L University Vadeeshwaram Department of Computer Science & Engineering Vijayawada India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9798350398465

A medical image recovery system can be used for a variety of useful purposes, one of which is the classification of medical images. When numerous different types of medical imaging evidence are accessible, it is essential to have accurate categorization models. Because of the CT paradigm in clinical diagnosis, radiologists are able to properly detect and monitor changes in the body's physiological state. The ability to differentiate between different types of tissues in a CT image based on the various grey rates along each line contributes significantly to the accuracy of a medical diagnosis. The standard practice for diagnosing cancer relies on scientific and histological data, both of which have the potential to lead to incorrect or erroneous findings. The liver, which may be found in the upper abdominal region of the external human form, is responsible for filtering the blood and getting rid of any toxins it discovers in the process. The distinction between the two types of cancer is taught through an artificial neural network in this method. A number of different parameters, including accuracy, area, correlation, entropy, homogeneity, contrast, and the similarity index, are employed to conduct an analysis of the impact. After that, researchers tried to enhance the early identification and treatment of liver cancer by segmenting and classifying liver tumors from CT images. This was done in order to gain a better understanding of the disease. The accuracy of the identification was raised to 99.63 percent thanks to the classifier and optimizer that was proposed. © 2023 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Optimal Resource Management for Hierarchical Federated learning over HetNets with Wireless Energy Transfer

Optimal Resource Management for Hierarchical Federated Learn...

引用

作者： Hamdi, Rami Said, Ahmed Ben Baccour, Emna Erbad, Aiman Mohamed, Amr Hamdi, Mounir Guizani, Mohsen AFG College with the University of Aberdeen Doha Qatar Qatar University College of Engineering Doha Qatar Hamad Bin Khalifa University Qatar Foundation Division of Information and Computing Technology College of Science and Engineering Doha Qatar Mohamed Bin Zayed University of Artificial Intelligence Machine Learning Department Abu Dhabi United Arab Emirates

Remote monitoring systems analyze the environment dynamics in different smart industrial applications, such as occupational health and safety, and environmental monitoring. Specifically, in Industrial Internet of Things (IIoT) systems, the huge number of devices and the expected performance put pressure on resources, such as computational, network, and device energy. Distributed training of machine and deep learning (ML/DL) models for intelligent industrial IoT applications is very challenging for resource limited devices over heterogeneous wireless networks (HetNets). Hierarchical federated learning (HFL) performs training at multiple layers offloading the tasks to nearby multiaccess edge computing (MEC) units. In this article, we propose a novel energy-efficient HFL framework enabled by wireless energy transfer (WET) and designed for heterogeneous networks with massive multiple-input-multiple-output (MIMO) wireless backhaul. Our energy-efficiency approach is formulated as a mixed-integer nonlinear programming (MINLP) problem, where we optimize the HFL device association and manage the wireless transmitted energy. However due to its high complexity, we design a heuristic resource management algorithm, namely, H2RMA, that respects energy, channel quality, and accuracy constraints, while presenting a low-computational complexity. We also improve the energy consumption of the network using an efficient device scheduling scheme. Finally, we investigate device mobility and its impact on the HFL performance. Our extensive experiments confirm the high performance of the proposed resource management approach in HFL over HetNets, in terms of training loss and grid energy costs. © 2014 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Lung Carcinoma Taxonomy: Differentiating Adenocarcinoma, Small Cell Carcinoma, and Squamous Cell Carcinoma 1

Lung Carcinoma Taxonomy: Differentiating Adenocarcinoma, Sma...

引用

1st International Conference on Innovations in Communications, Electrical and Computer engineering, ICICEC 2024

作者： Ayyappan, G. Gopinath, M. Yuktha Varshika, J. Rohan Kumar, S. Sakthi, S. Karthikraja, M. Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai602105 India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Information Technology Chennai602105 India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Artificial Intelligence and Machine Learning Chennai602105 India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Agriculture Engineering Chennai602105 India

ISBN: (数字)9798350376517

ISBN: (纸本)9798350376517

Lung carcinoma represents a diverse group of malignancies that originate in the respiratory epithelium. The primary histological subtypes include adenocarcinoma, small cell carcinoma, and squamous cell carcinoma, each exhibiting distinct clinical, morphological, and genetic characteristics. This classification is critical for determining appropriate treatment strategies and predicting patient outcomes. This article provides an overview of the histopathological features, molecular profiles, and clinical implications of each subtype, highlighting the importance of accurate classification in the management of lung carcinoma. This study also explores various deep-learning algorithms applied to radiological imaging data for the classification of lung carcinoma. We analyze a dataset comprising Computed Tomography (CT) scans annotated with histopathological findings to distinguish between malignant and benign lung nodules. In deep learning models, Convolutional Neural Networks (CNNs) and their variants, have shown promising results in automated detection and classification tasks. Traditional Data augmentation and Gaussian blur techniques are used to enlarge the dataset and to smoothing the image by reducing noise. This model achieves an accurate classification accuracy of 97.74%, 98.96% precision, and 0.98 AUC-ROC compared to various deep learning algorithms used for classification. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation in V2V Communication via Federated Multi-Agent Reinforcement learning

Resource Allocation in V2V Communication via Federated Multi...

引用

Consumer Communications and Networking Conference, CCNC IEEE

作者： Shilong Zhang Cheng Yang Tao Yu Tong Liu Jinhua Chen Keping Yu Mohsen Guizani Graduate School of Science and Engineering Hosei University Japan School of Electrical and Electronic Engineering Chongqing University of Technology China Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) UAE

ISBN: (数字)9798331508050

ISBN: (纸本)9798331508067

With the increasing number of vehicles, the Internet of Vehicles (IoV) exhibits significant dense deployment characteristics, resulting in severe overlaps of communication areas among vehicles and complex interference. To address these issues, the resource allocation problem under complex interference in densely deployed IoV is investigated in this paper. Specifically, an interference hypergraph model is constructed to simultaneously analyze the complex interference relationships among multiple vehicles. Subsequently, the resource allocation problem is transformed into a vertex coloring problem on the hypergraph. Furthermore, a federated double dueling deep Q-Network algorithm is proposed to achieve conflict-free resource allocation while maximizing network throughput. Simulation experiments demonstrate that the proposed method achieves an average network throughput improvement of more than 17.93% compared to the baseline algorithms, showcasing superior network performance in densely deployed IoV scenarios.

关键词： Analytical models Interference Reinforcement learning Throughput Resource management Internet of Vehicles

来源：评论

学校读者我要写书评

暂无评论

Dual-Level Contrastive learning with Reverse Translation for Summarisation

Dual-Level Contrastive Learning with Reverse Translation for...

引用

Smart Technologies for Sustainable Development Goals (ICSTSDG), International Conference on

作者： S Joanna Lois Maruboina Nithyanjali I N Nandithaa Deva Hema D Department of Computer Science Engineering with Specialization in Artificial Intelligence and Machine Learning SRM Institute of Science and Technology Ramapuram Chennai India Department of Computer Science Engineering SRM Institute of Science and Technology Ramapuram Chennai India

ISBN: (数字)9798331516284

ISBN: (纸本)9798331516291

Text summarisation aims to create brief and precise summaries from large amounts of textual information. Although recent advancements have improved summary brevity, significant room remains for enhancing ROUGE scores, especially with increase in beam width. We present a novel model, Dual Level Contrastive learning with Reverse Translation (DC-RT), which utilizes contrastive learning with data augmentation, including reverse translation, to improve accuracy. Reverse translation serves as a key augmentation strategy by translating summaries to another language and back resulting in enriched training data and enhanced robustness of the model. Additionally, we introduce a new scoring function during training to further refine output quality. Exceptional ROUGE scores are achieved using this framework, ensuring concise and readable summaries even with increased beam width. Experiments on the CNN/DailyMail (achieving a47.82 ROUGE-1 score with a 0.017 variance) dataset demonstrates that there is a significant improvement in the precision and succinctness of summaries. Notably, our model surpasses the output of BRIO, the cutting edge model, setting a new benchmark in the field.

关键词： Training Translation Training data Text summarization Contrastive learning Benchmark testing Data augmentation Data models Robustness Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Block Chain based Malware Detection System for Smartphone Application 8

Block Chain based Malware Detection System for Smartphone Ap...

引用

8th International Conference on Communication and Electronics Systems, ICCES 2023

作者： Robert, P. Senkamalavalli, R. Vedanarayanan, V. Manivannan, D. Cmr Institute of Technology Department of Artificial Intelligence and Machine Learning Karnataka Bengaluru India East Point College of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India Sathyabama Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Vel Tech Rangarajan Dr.Sagunthala R & D Institute of Science and Technology Department of Computer Science Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350396638

The quick rise of smartphone malware indicates that cybercriminals are switching from traditional personal computer systems to mobile devices. For adequate security, technology specialists are currently creating new anti-malware techniques. This study proposes the use of a block chain to identify malicious smartphone applications. Two internal and external proprietary block chains are combined to create a private dual block chain and a block chain alliance for the decision-making process in the system. While the external block chain stores the blocks for apps of existing models, the private internal block chain stores include blocks drawn from both statically and dynamically driven function removers. Additionally, the proposed system blocks the outside parties, enabling anti-malware vendors to provide more precise solutions. Because cloud resources can control loads and durability, resource monitoring may be dynamic in nature. The additional feature of the proposed system is that authentication techniques like cryptography and digital signature can be integrated. Finally, the effectiveness of the suggested structure is assessed in terms of throughput and precision rate for malware detection. © 2023 IEEE.

关键词： Personal computers

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154页 << < 61 62 63 64 65 66 67 68 69 70 > >>

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：