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

2,407 篇 会议
1,316 篇 期刊文献
37 册 图书

馆藏范围

3,760 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,305 篇 工学
- 1,636 篇 计算机科学与技术...
- 1,341 篇 软件工程
- 623 篇 信息与通信工程
- 366 篇 控制科学与工程
- 300 篇 生物工程
- 288 篇 电气工程
- 229 篇 生物医学工程（可授...
- 220 篇 电子科学与技术（可...
- 180 篇 光学工程
- 161 篇 机械工程
- 160 篇 网络空间安全
- 135 篇 化学工程与技术
- 129 篇 安全科学与工程
- 115 篇 动力工程及工程热...
- 111 篇 核科学与技术
- 107 篇 交通运输工程
- 102 篇 仪器科学与技术
1,344 篇 理学
- 602 篇 数学
- 472 篇 物理学
- 327 篇 生物学
- 214 篇 统计学（可授理学、...
- 154 篇 化学
- 113 篇 系统科学
691 篇 管理学
- 431 篇 管理科学与工程(可...
- 294 篇 图书情报与档案管...
- 153 篇 工商管理
218 篇 医学
- 161 篇 临床医学
- 160 篇 基础医学(可授医学...
- 111 篇 公共卫生与预防医...
131 篇 法学
- 109 篇 社会学
66 篇 经济学
65 篇 农学
36 篇 教育学
34 篇 文学
20 篇 军事学
5 篇 艺术学
1 篇 哲学

主题

172 篇 accuracy
141 篇 deep learning
105 篇 feature extracti...
100 篇 hadron colliders
98 篇 machine learning
89 篇 computational mo...
88 篇 training
84 篇 convolutional ne...
73 篇 real-time system...
66 篇 support vector m...
63 篇 predictive model...
61 篇 artificial intel...
55 篇 optimization
53 篇 internet of thin...
49 篇 reliability
46 篇 genetic algorith...
46 篇 cloud computing
46 篇 data models
44 篇 semantics
44 篇 security

机构

132 篇 yerevan physics ...
129 篇 national and kap...
129 篇 centro brasileir...
129 篇 istanbul technic...
127 篇 university of sp...
127 篇 indian institute...
126 篇 universidad iber...
125 篇 brunel universit...
125 篇 irfu cea univers...
124 篇 università di to...
124 篇 academy of scien...
124 篇 charles universi...
124 篇 infn sezione di ...
123 篇 department of ph...
123 篇 zhejiang univers...
121 篇 infn sezione di ...
120 篇 university of de...
120 篇 department of ph...
118 篇 imperial college...
118 篇 rwth aachen univ...

作者

125 篇 m. lu
95 篇 g. tonelli
95 篇 d. barney
95 篇 l. valencia palo...
95 篇 t. liu
95 篇 c. hensel
95 篇 a. garcia-bellid...
95 篇 a. steen
95 篇 n. cartiglia
95 篇 d. eliseev
94 篇 a. babaev
94 篇 v. karjavine
93 篇 n. colino
93 篇 f. moortgat
92 篇 b. clerbaux
91 篇 g. sultanov
91 篇 a. mallampalli
91 篇 m. a. ciocci
91 篇 k. lamichhane
91 篇 s. maselli

语言

3,136 篇 英文
584 篇 其他
44 篇 中文
2 篇 日文
1 篇 德文
1 篇 法文

检索条件"机构=Computer Science Engineering and Application"

共 3760 条记录，以下是871-880 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：

Research on intrusion detection algorithm based on dilated convolution and bidirectional gating cyclic unit

Research on intrusion detection algorithm based on dilated c...

引用

2022 International Conference on Algorithms, Microchips and Network applications

作者： Liu, Xingyuan Miao, Xianghua Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Computer Technology Application Key Laboratory of Yunnan Province Kunming650500 China

ISBN: (纸本)9781510653290

Intrusion detection based on machine learning plays an important role in the security protection of the network environment. In order to improve the accuracy of network intrusion detection, intrusion detection algorithm based on dilated convolution and a two-way gating unit is proposed. Firstly, dilated convolution (DCNN) is used to increase the receptive field of information and extract spatial features. Secondly, the bidirectional gated cyclic unit (bigru) model is used to capture the temporal features of data, and the attention mechanism is introduced to increase the calculation of feature importance. Compared with the classical machine learning classifier, this model has a high detection rate. The multi-classification experiments on the famous UNSW-NB15 data set show that the model has leading performance, and its classification accuracy can reach 97.14%. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Efficiency Beyond Limits: LSTM and k-NN Synergy for Forecasting Energy Needs in Data Centers

Efficiency Beyond Limits: LSTM and k-NN Synergy for Forecast...

引用

Innovation in Technology (APCIT), Asia Pacific Conference on

作者： Amit K. Mogal Vaibhav P. Sonaje CH N Santhosh Kumar V. Chithra Devi Prasanthi Gottumukkala Satheesh Kumar D Department of Computer Science & Application School of Computer Science and Engineering Sandip University Nashik Maharashtra India Department of Computer Science & Applications School of Computer Science and Engineering Sandip University Nashik Maharashtra India Department of CSE Anurag Engineering College Kodada Telangana India PSNA College of Engineering and Technology Dindigul Tamilnadu India Department of Information Technology Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad India Department of Computer Science and Engineering Hindusthan College of Engineering and Technology Coimbatore India

ISBN: (数字)9798350361537

ISBN: (纸本)9798350361544

The objective of this study is to examine the effectiveness of a hybrid methodology that combines Long Short-Term Memory (LSTM) and k-Nearest Neighbors (k-NN) models in the context of energy prediction within data centres. The objective of this study is to improve the accuracy of predictions and the efficiency of operations by utilising the combined capabilities of these two machine learning approaches. The proposed LSTM-kNN model has superior performance compared to individual LSTM and k-NN models, as evidenced by a thorough assessment on sample data. It achieves a Mean Absolute Error (MAE) of 9.45, Root Mean Square Error (RMSE) of 12.97, and a coefficient of determination (R 2 ) value of 0.89. The importance of model synergy in enhancing the accuracy of energy forecasts is shown by comparative analysis. The results of this study provide a significant contribution to the advancement of energy management methods in data centres. These findings provide vital insights for stakeholders, enabling them to optimise resource allocation, capacity planning, and sustainability initiatives. Proactive energy optimisation measures and cost-effective operational decisions are examples of practical applications. Potential avenues for future study encompass the exploration of supplementary machine learning techniques and the examination of the influence exerted by external factors on patterns of energy usage. In summary, this work highlights the significance of incorporating machine learning methods to tackle intricate issues in energy prediction and control in data centre settings.

关键词： Data centers Machine learning Predictive models Nearest neighbor methods Data models Resource management Energy management

来源：评论

学校读者我要写书评

暂无评论

Sustainable Self-evolution Adversarial Training 24

Sustainable Self-evolution Adversarial Training

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wang, Wenxuan Wang, Chenglei Qi, Huihui Ye, Menghao Qian, Xuelin Wang, Peng Zhang, Yanning School of Computer Science Northwestern Polytechnical University China Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi'an China School of Automation Northwestern Polytechnical University The BRain and Artificial INtelligence Lab Shaanxi Xi'an China

ISBN: (纸本)9798400706868

With the wide application of deep neural network models in various computer vision tasks, there has been a proliferation of adversarial example generation strategies aimed at deeply exploring model security. However, existing adversarial training defense models, which rely on single or limited types of attacks under a one-time learning process, struggle to adapt to the dynamic and evolving nature of attack methods. Therefore, to achieve defense performance improvements for models in long-term applications, we propose a novel Sustainable Self-Evolution Adversarial Training (SSEAT) framework. Specifically, we introduce a continual adversarial defense pipeline to realize learning from various kinds of adversarial examples across multiple stages. Additionally, to address the issue of model catastrophic forgetting caused by continual learning from ongoing novel attacks, we propose an adversarial data replay module to better select more diverse and key relearning data. Furthermore, we design a consistency regularization strategy to encourage current defense models to learn more from previously trained ones, guiding them to retain more past knowledge and maintain accuracy on clean samples. Extensive experiments have been conducted to verify the efficacy of the proposed SSEAT defense method, which demonstrates superior defense performance and classification accuracy compared to competitors. © 2024 ACM.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Brinjal Leaf Pathology: An Improved Disease Classification in a Federated Learning-CNN Approach

Brinjal Leaf Pathology: An Improved Disease Classification i...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Poonam Gaur Priyanshi Aggarwal Kireet Joshi Shiva Mehta Vinay Kukreja Department of Computer Application CGC Landran Mohali Computer Science and Engineering Graphic Era Hill University Dehradun Uttarakhand India Computer Science and Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

A study about brinjal leaf disease diagnosis using federated learning using CNN is presented here. Based on the data from four clients, we can identify four levels of severity for brinjal leaf disease. As a result of the use of federated learning, it is possible to train a CNN model collaboratively while maintaining data privacy and locality, which are essential when dealing with agricultural data. A federated average algorithm was used in our approach to combine local updates of models into a global model. Using this method, the model gains experience from different data sources, thus becoming more generalized and reliable. As evidenced by enhanced model performance among clients, this approach produces tangible outcomes. There were several significant results from the analysis. The macro average of disease diagnosis accuracy through clients is 97.55% in NA_6 and 89.71% in NA_1. As a result of accounting for disease severity classes, the weighted average (Weighted_average) also displays a rising trend. Also, the Micro Average (Micro_ave) shows this trend, running from 89.55% (na_1) to 97.55% (na_6), which represents a general classification success rate. Federation learning can manage brinjal disease severity strata's intricacies and disparities successfully. For a reliable classification of medical conditions, the model must accommodate various inputs, especially among later clients. The study improves agricultural technology by addressing field infections with a practical, scalable, and privacy-preserving method. This study suggests that federated learning and CNN can be used to diagnose crop diseases, revolutionizing the practice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of a Machine Learning based Data Analytics Engine to Improve Decision Making Processes

Design of a Machine Learning based Data Analytics Engine to ...

引用

International Conference on Smart Systems and Inventive Technology (ICSSIT)

作者： Yoginee Surendra Pethe Pranali Rahul Dandekar Department of Computer Application Shri Ramdeobaba College of Engineering and Management Nagpur India Department of Computer Science and Engineering Shri Ramdeobaba College of Engineering and Management Nagpur India

Analytical Hierarchy Processing (AHP) assists in estimation of input-specific weights for improving system-level decision making operations. The process initially decides a goal, and then uses different criterion & alternatives to achieve it. But original AHP model is not efficient for large-scale systems, which limits its capability under real-time use cases. To overcome this issue, various Machine Learning based techniques are proposed, and each of them has their own set of limitations. Techniques with higher efficiency also showcase high complexity, while simplistic optimization techniques have limited performance levels. To overcome these limitations, this text proposes design of an efficient AHP model with low complexity via integration of (GWO), and iterative learning (IL) operations. The proposed model initially performs context-based correlation between input parameter sets. These correlation values are used to modify the AHP decisions, which are tuned by GWO process. Results of Grey Wolf optimization this GWO process are optimized via IL based tuning, which incrementally modifies the correlation values for optimum efficiency levels. Due to which the proposed model showcases low complexity, while maintaining higher efficiency when compared with the original AHP process. The proposed model was evaluated on multiple datasets including housing, image processing, and employment scenarios. Based on this evaluation it was observed that the proposed model showcased 8.5% higher accuracy, 6.4% higher precision, with 4.5% 1ower delay when compared with original AHP and standard AHP-optimization techniques. Due to this improvement, the proposed model is capable of deployment for a wide variety of real-time scenarios.

关键词： Correlation Image processing Machine learning Real-time systems Complexity theory Large-scale systems Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Explainable Pulmonary Disease Diagnosis with Prompt-Based Knowledge Extraction

Explainable Pulmonary Disease Diagnosis with Prompt-Based Kn...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Zhang, Haodi Xu, Chenyu Li, Jiahong Liang, Peirou Zeng, Xiangyu Ren, Hao Cheng, Weibin Wu, Kaishun Shenzhen University College of Computer Science and Software Engineering Shenzhen China Institute for Healthcare Artificial Intelligence Application Guangdong Second Provincial General Hospital Guangzhou China

ISBN: (纸本)9781665468190

Recent studies show that deep learning models perform well in many medical tasks such as medical imaging and automated diagnosis. With qualified training datasets, some models can achieve or even surpass expert-level performance on some tasks. However, as a typical black-box-style approach, deep learning lacks theoretical interpretability, which is especially important for medical tasks. On the other hand, there are many sources of domain knowledge for medical diagnosis from human experts, such as clinical guidelines. How to sufficiently integrate human knowledge in the model is crucial for explainable diagnosis. In this paper, we propose a novel framework for explainable automated diagnosis that leverages explicit medical knowledge. We automate the knowledge extraction from textual clinical guidelines with prompt-based learning, train a set of weighted first-order logical rules with constructed evidence database, and finally infer the diagnosis result with integrated knowledge and multi-sourced data. We instantiate the framework for pulmonary disease diagnosis, and our experiments on a real dataset show that our method outperforms the state-of-the-art baselines in accuracy and interpretability. © 2022 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

An Efficient AdaBoost and CNN Hybrid Model for Weed Detection and Removal

An Efficient AdaBoost and CNN Hybrid Model for Weed Detectio...

引用

Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering (RMKMATE), International Conference on

作者： Shivam Tiwari Satvik Vats Anurag Kumar Srivastava Ashish Kumar Rastogi Yogesh Singh Rathore Department of Computer Science & Engineering Sharda University Greater Noida Computer Science & Engineering Graphic Era Hill University Dehradun India Department of Computer Science and Engineering GL Bajaj Institute of Technology and Management Greater Noida India Computer Science & Engineering Amity University Rajasthan India Computer Science and Application Sharda University Greater Noida

With the aid of AI-based methods like convolution neural networks, this article seeks to enhance weed detection and removal. A plant that is not wanted and is growing wild, especially one that does so on cultivated land and produces a low crop yield, is referred to as weed. In order to increase production in agriculture, it is essential to have a strong and positive weed identification and removal. This paper suggested a weed control programme for wheat fields indicated on the RGB combination of image elements with essential attributes due to the low weed control rate and availability of inefficient weed removal approaches in the wheat sector. AdaBoost estimation and the CNN model are combined to enhance the performance of the weed distinguishing proof. The approach tests the bounds of the 2D topographical from RGB images while seeing wheat-like grass weeds. The accuracy of the test results displayed by the algorithm during the process was 94.7%. In comparison to previously employed methods, the combination of both algorithms used provides a high degree of accuracy in the estimation of various types of weeds.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Toledic: Tomato Leaf Disease Classification Lite

Toledic: Tomato Leaf Disease Classification Lite

引用

Data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： D. Lita Pansy V. Vidhya S.R. Noble Lourdhu Raj E. DilipKumar P. Malathi T. Kalaivanan Department of Information Technology Chennai Institute of Technology Chennai India Department of Computer Science and Engineering PERI Institute of Technology Chennai India Department of Computer Application Dhanalakshmi Srinivasan College of Engineering and Technology Chennai India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Chennai India Department of Computer Science and Engineering Dhanalakshmi Srinivasan College of Engineering and Technology Chennai India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

Tomatoes are edible berries with the rich umami flavor. Since, identification of diseases in tomato leaves is essential in Indian market to maximize the crop yield and minimize the crop loss. As such, this paper investigates the usage of lightweight Convolution Neural Networks deployed on a Raspberry Pi 4 for real-time diagnosis of tomato leaf diseases. In this paper, I focus on computational constraint on the Raspberry Pi 4 at the cost of accuracy and introduce a novel model, Toledic-Lite. We evaluate and compare various conventional lightweight models based on ResNet 50, EfficientNet v4, DenseNet 121, ConvNext v2_Nano and VGG16 metrics such as accuracy, inference time and memory usage, and identify conventional edge computation performance. Toledic-Lite’s functionality is meant to bring the data processing process in the complex computational tasks of Arm based processors into more efficient and accurate domain by optimizing the accuracy and the result as compared to the conventional model. The objective is to develop a cost effective, efficient and accurate solution for deployment on farms. The work presents models using multiple architectures on the Raspberry Pi platform that balance accuracy and computational efficiency. Overall, it is demonstrated that lightweight CNNs can accurately classify tomato leaf diseases to support the development of intelligent and sustainable agricultural practices. This work demonstrates a significant contribution to the exploration of the application of edge computing for disease management in agriculture, focusing on a need to intervene early to protect crop health and improve agricultural output.

关键词： Deep learning Performance evaluation Accuracy Costs Computational modeling Real-time systems Computational efficiency Diseases Residual neural networks Edge computing

来源：评论

学校读者我要写书评

暂无评论

Federated Learning CNN for Smart Agriculture: A Modeling for Soybean Disease Detection

Federated Learning CNN for Smart Agriculture: A Modeling for...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Mukesh Kumar Manisha Aeri Richa Chandel Vinay Kukreja Shiva Mehta Computer Science and Engineering Graphic Era Hill University Dehradun Uttarakhand India Computer Science and Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Computer Application CGC Landran Mohali Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

With the help of federated learning and CNNs, this research paper aims to identify and categorize soybean leaf diseases. This study uses a federated learning approach to classify disease severity into four classes using four clients. The benefit of this method is that it preserves data privacy during analytics, which is highly important in our digital age. The information we obtain from each local customer is used to conduct our analysis. Using federated averaging, we produce an aggregate global model. It is possible to assess the model's performance on a local and international level by calculating macro, micro, and weighted averages. As a result of the macro standard stressing class equality, clients yu_1 through yu_6 performed well with grades of 91.42%, 91.08%, 90.92%, 93.15%, and 93.40. Based on the weighted average of those clients with class imbalance, 91.43%, 91.07%, 90.92%, 93.13%, 93.41%, and 92.86%, respectively. Finally, the micro average averaging all inputs to the model indicates its overall accuracy with the following percentages for each client: 91.43%, 91.06%, 90.91%, and 93.11%.Using federated averaging to transform local data into a global data model proved this approach feasible in a real-world scenario. Precision, recall, and F1-scores for the studied clients indicate high sensitivity and specificity of the model. A precise agriculture technique can be adapted to control soybean foliar disorders resulting from this study. As a part of our move towards more resilient and safe farm management approaches, this study helps us solve the urgent task of detecting and classifying diseases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Review of Deep Learning Models for Plant Disease Detection with a Focus on Apple Leaf Pathologies

Comprehensive Review of Deep Learning Models for Plant Disea...

引用

Data, Computation and Communication (ICDCC), International Conference on

作者： Nidhi Agrawal Sanjay Singh Bhadoriya Rajesh Kumar Nagar School of Computer Application SAGE University Indore (M.P.) India School of Computer Science & Engineering SAGE University Indore (M.P.) India

ISBN: (数字)9798331532956

ISBN: (纸本)9798331532963

Effective agriculture and the economy are the identification of plant diseases. Conventional means for diagnosing plant disease are laborious since they call for a lot of effort, time, and knowledge. Recently, academics, researchers, and practitioners have given a lot of attention to an important study topic automatic disease spotting of plants. Like a flash, diseases first manifest itself on plant leaf, Machine learning and automated analysis can assist in recognizing it. This cutting-edge review has conducted detailed research to assess the viability of applying AI based models to categorize plant disorders. The pathogens and infections of various crops are examined in this study. A comprehensive study of the many procedures required in classifying and detecting using ML and AI to diagnose plant diseases is presented. Additionally, several online databases for identifying plant diseases have been given. In addition to this, a thorough analysis of a variety of currently used classifying models based on ML and DL proposed by many researchers for different crops is explained. This includes information on how well each model performed, the dataset it was based on, and the technique used to extract features. Lastly, a variety of concerns are highlighted and examined when employing DL & ML to predict plant pathogens.

关键词： Deep learning Plant diseases Pathogens Accuracy Reviews Biological system modeling Crops Feature extraction Real-time systems Reliability

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376页 << < 84 85 86 87 88 89 90 91 92 93 > >>

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：