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

716 篇 会议

馆藏范围

716 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

324 篇 工学
- 186 篇 计算机科学与技术...
- 180 篇 控制科学与工程
- 168 篇 软件工程
- 46 篇 机械工程
- 41 篇 电气工程
- 29 篇 信息与通信工程
- 26 篇 交通运输工程
- 21 篇 生物医学工程（可授...
- 16 篇 电子科学与技术（可...
- 16 篇 航空宇航科学与技...
- 14 篇 光学工程
- 13 篇 石油与天然气工程
- 11 篇 安全科学与工程
- 10 篇 动力工程及工程热...
- 10 篇 土木工程
- 10 篇 船舶与海洋工程
- 10 篇 生物工程
- 9 篇 仪器科学与技术
- 9 篇 建筑学
- 9 篇 化学工程与技术
148 篇 理学
- 83 篇 数学
- 57 篇 系统科学
- 20 篇 统计学（可授理学、...
- 17 篇 物理学
- 11 篇 生物学
28 篇 管理学
- 22 篇 管理科学与工程(可...
- 10 篇 图书情报与档案管...
- 9 篇 工商管理
9 篇 医学
- 9 篇 基础医学(可授医学...
- 9 篇 临床医学
4 篇 经济学
4 篇 教育学
4 篇 农学
3 篇 法学
2 篇 军事学
1 篇 文学

主题

179 篇 learning systems
83 篇 control systems
67 篇 accuracy
59 篇 simulation
53 篇 adaptation model...
50 篇 predictive model...
48 篇 data models
40 篇 training
36 篇 process control
34 篇 stability analys...
34 篇 heuristic algori...
32 篇 uncertainty
29 篇 neural networks
29 篇 numerical simula...
29 篇 feature extracti...
28 篇 observers
26 篇 adaptive systems
25 篇 reinforcement le...
24 篇 noise
22 篇 deep learning

机构

24 篇 school of electr...
14 篇 school of mathem...
12 篇 school of electr...
12 篇 school of automa...
11 篇 faculty of infor...
9 篇 college of contr...
9 篇 kunming universi...
9 篇 college of contr...
8 篇 college of artif...
8 篇 school of artifi...
8 篇 college of artif...
8 篇 faculty of mecha...
8 篇 beijing key labo...
8 篇 yunnan key labor...
8 篇 school of electr...
7 篇 school of automa...
7 篇 college of infor...
7 篇 state key labora...
6 篇 school of electr...
6 篇 school of automa...

作者

18 篇 wang li
18 篇 li wang
11 篇 deqing huang
11 篇 ji honghai
11 篇 liu shida
11 篇 shida liu
11 篇 honghai ji
10 篇 huang deqing
8 篇 darong huang
7 篇 xiaoli li
6 篇 kang wang
6 篇 feng li
6 篇 song zhihuan
6 篇 ruikun zhang
6 篇 zhou zhou
5 篇 ye ren
5 篇 fan lingling
5 篇 liu yang
5 篇 ren ye
5 篇 zengqiang chen

语言

632 篇 英文
84 篇 其他

检索条件"任意字段=13th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2024"

共 716 条记录，以下是281-290 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：

Recognition of Scalp Psoriasis Dermoscopic Patterns Signs Based on Histogram Equalization and Convolutional Neural Networks 13

Recognition of Scalp Psoriasis Dermoscopic Patterns Signs Ba...

引用

13th ieee data driven control and learning systems conference, ddcls 2024

作者： Ji, Honghai Li, Jiaqi Jiang, Weiwei Wang, Li Liu, Shida Chen, Yang School of Electronics & Control Engineering North China University of Technology Beijing100144 China 72nd Group Army Hospital of Pla Department of Dermatology Zhejiang313000 China

ISBN: (纸本)9798350361674

Scalp psoriasis is a common chronic autoimmune inflammatory skin disease that affects a large number of people worldwide. Although scalp psoriasis is not physically a serious life-threatening condition for patients, the itchiness, inflammation, and social distress it causes have a significant negative impact on their quality of life. Currently, the urgent need for accurate diagnosis of scalp psoriasis has driven researchers to explore efficient diagnostic techniques utilizing deep learning techniques, among which dermoscopy is widely used as a simple and easy-to-use non-invasive testing device. In this paper, a convolutional neural network (HE-CNN) based on histogram equalization is proposed to solve the problem of automatic recognition of different dermoscopic patterns of scalp psoriasis. In this, histogram equalization is used to perform global brightness enhancement of dermoscopic images to ensure that important lesion features in the image are not obscured by hair shadows leading to neglect. CBAM is added to the CNN and the enhanced images are used to train a classification model for automated recognition of scalp psoriasis for clinical detection. We conducted experiments on a scalp psoriasis dataset provided by 72nd Group army hospital of PLA. In order to verify the effectiveness of the method, we use the unenhanced image as a control group and compare it with the image that has undergone enhancement, and the results after five-fold cross-validation show that the recognition effect of HE-CNN outperforms that of the control group in terms of accuracy, specificity, sensitivity and youden index. It is verified that HE-CNN has better effect in assisting doctors in the diagnosis of scalp psoriasis. © 2024 ieee.

关键词： Equalizers

来源：评论

学校读者我要写书评

暂无评论

Design of a Full-Space Tracking and Measurement System Based on the Light Pen with Deep learning Methods 13

Design of a Full-Space Tracking and Measurement System Based...

引用

13th ieee data driven control and learning systems conference, ddcls 2024

作者： Cui, Yu Li, Xu Na, Jing Gao, Guanbin Xing, Yashan Faculty of Mechanical and Electrical Engineering Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Intelligent Control and Application Kunming650500 China Luzhou Laojiao Co.Ltd Luzhou646000 China

ISBN: (纸本)9798350361674

Visual measurement, a critical component in industrial production, often faces accuracy challenges due to image distortion at the edges of the field of view, particularly in large spaces. this paper capitalizes on the robust feature-learning capabilities of deep-learning algorithms tailored for industrial robots in factory settings, and introduces a comprehensive tracking and measurement system, grounded in deep learning, specifically designed for light pen industrial robots. the approach begins with an analysis of the industrial robot's workspace, leading to the installation of a binocular vision sensor on a rotating platform. this setup forms the basis for a novel full-space tracking and measurement device for industrial robots, utilizing a light pen. the system integrates a target detection algorithm with a rotation platform control algorithm, ensuring the light pen remains centered in the camera's field of view in real-time. this innovation addresses the limitations of traditional light pens, particularly their restricted measurement range and reduced accuracy. Furthermore, the transformation matrix between the pixel and world coordinate systems is established by analyzing the relationship between the binocular vision sensor and the precision rotating platform. In the process of pinpointing the sphere center coordinates of the light pen probe, the system establishes a mapping relationship between the marker point and the probe's sphere center. It then employs the cross-ratio invariance principle and the least squares method for precise calculations. Finally, the system's accuracy is validated using the actual dimensions of standard gauge blocks and balls as references. Experimental results demonstrate that the geometric measurement error in the proposed tracking and measurement system on these standard objects is less than 0.1mm. these results offer an alternative for full-space tracking and measurement in complex industrial environments. © 2024 ieee.

关键词： Binocular vision

来源：评论

学校读者我要写书评

暂无评论

Anti-Windup Active Power control for Wind Turbines Considering Loads Reduction 13

Anti-Windup Active Power Control for Wind Turbines Consideri...

引用

13th ieee data driven control and learning systems conference, ddcls 2024

作者： Wang, Guozhong Luo, Hao Jiao, Xuguo Yang, Zhibo Zhao, Xinxin School of Information and Control Engineering Qingdao University of Technology Qingdao266520 China College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China

ISBN: (纸本)9798350361674

In recent years, the proportion of wind power in electricity contribution is increasing, and wind power generation technology has developed rapidly. How to enhance the stability of wind turbine systems and extend their service life are still challenging problems due to uncertain and intermittent characteristics of natural wind. In order to ensure that variable speed wind turbines track the active power instructions released by the power system, an improved anti-windup rotor speed control strategy is designed to switch different control strategies according to the wind turbine rotor speed value, with the aim of optimizing the mechanical loads of pitch systems. Firstly, in the low wind speed region, the maximum wind energy capture is achieved by optimal torque control. When the rotor speed increases to a critic value, torque control determined by the turbine's rated output power and rotor speed is adopted. In the high wind speed region, the pitch controller is used to adjust the wind energy capture coefficient to maintain the rotor speed at its rated value. Moreover, in order to solve the problem of integral saturation in traditional rotor speed control methods, this paper proposes a bounded constraints assisted Proportional-Integral (PI) pitch angle control scheme to optimize the operation of pitch system. this control method can effectively eliminates integral saturation, mitigate fatigue loads of wind turbines, reduces overshoot of rotor speed and ensures safe and stable operation of wind turbines. Finally, the proposed method is simulated on OpenFAST platform to verify its advancement. © 2024 ieee.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

Capacity Configuration Model for Power Dispatch and Clean Energy Peak Shaving with Large-Scale Liquid Flow Batteries 13

Capacity Configuration Model for Power Dispatch and Clean En...

引用

13th ieee data driven control and learning systems conference, ddcls 2024

作者： Li, Dianyang Cui, Dai Xiao, Nan Li, Jiaze Jiang, Huijie Yang, Feiran State Grid Liaoning Electric Power Co. Ltd Power Dispatching Control Center Shenyang China College of Information Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9798350361674

the rapid development of renewable energy has brought us closer to achieving carbon peak and carbon neutrality goals, but it has also exacerbated the challenge of load fluctuation in power grids. To enhance grid stability and security, it is essential to implement effective peak shaving measures. Relying solely on various types of power generation to complement each other has limitations. In this paper, we propose a model and method for configuring the capacity requirements of large-scale liquid flow batteries involved in grid peak shaving, within the context of increasing demand for renewable energy integration. Our model utilizes an optimization approach with the objective of minimizing the operational costs of the peak shaving system. the model not only considers the technical constraint index of the system, but also innovatively introduces the reliability constraint of the probability of insufficient peak regulation and the reliability constraint of the mean value of insufficient peak regulation, and forms the optimal configuration model of peak regulation capacity of large-capacity flow battery assisted power system. the model takes the 24-hour load time series and wind power time series as inputs, employs the YALMIP toolbox, and utilizes the CPLEX solver to optimize the capacity and power requirements for large-scale liquid flow batteries assisting in renewable energy dispatch. A simulation analysis is conducted using a case study with a 24-hour load time series and wind power time series as inputs to evaluate the proposed model. © 2024 ieee.

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

A Bottom-Up Human Pose Estimation Correction Method Based on Object Detection 13

A Bottom-Up Human Pose Estimation Correction Method Based on...

引用

13th ieee data driven control and learning systems conference, ddcls 2024

作者： Zhang, Xiaoping Meng, Xiangpeng Chu, Kai-Fung Wang, Li School of Electrical and Control Engineering North China University of Technology Beijing100144 China University of Cambridge Department of Engineering Cambridge United Kingdom

ISBN: (纸本)9798350361674

As computer vision technology is widely applied in various domains, it inevitably faces complex and crowded scenes. However, human images in these scenes are more susceptible to occlusion, which degrades the performance of human pose estimation. Since human pose estimation methods typically represent the human pose feature as the skeleton of the human keypoints, the keypoint set estimation significantly influences the overall accuracy. To improve the human pose estimation accuracy in crowded scenes, a bottom-up human pose estimation correction method based on object detection is proposed in this paper. the keypoint set estimated by the bottom-up human pose estimation is corrected by introducing an object detection algorithm to reduce estimation errors and fill in missing keypoints, so as to alleviate the decline of detection effect caused by superimposed multilevel errors in occlusion scenes. the method is verified by our self-built human pose dataset in the bus compartment scene. the results show that the OpenPose human pose estimation algorithm with the method in this paper can obtain 4.41 mAP improvement, especially for the keypoints with strong local information. © 2024 ieee.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

data-driven Active Power Dispatch for Wind Farms 13

Data-Driven Active Power Dispatch for Wind Farms

引用

13th ieee data driven control and learning systems conference, ddcls 2024

作者： Jiao, Xuguo Zhang, Daoyuan Wang, Xin Ma, Zhaoxing Zhang, Zhenyong Liu, Wenfeng School of Information and Control Engineering Qingdao University of Technology Qingdao266520 China College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China College of Computer Science and Technology Guizhou University State Key Laboratory of Public Big Data Guiyang550025 China School of Civil Engineering Qingdao University of Technology Qingdao266520 China

ISBN: (纸本)9798350361674

Active power dispatch of wind farms plays an important role in power grid scheduling. In this paper, a data-driven active power dispatch strategy for wind farms is proposed, which uses the key point of minimizing the standard deviation of wind turbines' output power series to reduce their fluctuations. First, to build the optimization problem, the historical active power output data of each wind turbine is collected from the Supervisory control And data Acquisition (SCADA) system. then, the objective function is developed based on the idea of minimizing the standard deviation of the output power time series. Meanwhile, considering the constraints of wind turbines' output power and active power balance of the grid, the feasible domain of the cost function is constructed. Further, to solve the proposed nonlinear optimization problem with equality and inequality constraints, the trust region interior point method (TRIPM) is employed to explore optimal solution within the feasible domain. Finally, actual data collected from wind farms is used to test effectiveness of the designed approach and experimental results show that our method can achieve better output power smoothing performance than conventional Proportional Dispatch (PD) method. © 2024 ieee.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Soft Sensor Modeling for Industrial Dynamic Information Mining Based on Two-Path Weight Comparison 13

Semi-Supervised Soft Sensor Modeling for Industrial Dynamic ...

引用

13th ieee data driven control and learning systems conference, ddcls 2024

作者： Jia, Ruining Jin, Xinyi Ni, Xinru Ruan, Mengjiao Yang, Zeyu Wang, Peiliang School of Engineering Huzhou University Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems Huzhou313000 China

ISBN: (纸本)9798350361674

Deep learning methods can extract reliable feature representations from massive process data to build accurate soft sensor models. However, the data in actual industrial production is often nonlinear, dynamic, and even limited in label samples due to untimely sampling and analysis. Aiming at the above problems, this paper proposes a semi-supervised soft sensor modeling method (SSACF-LSTM) for industrial dynamic information mining based on two-path weight comparison. An unsupervised long short-term memory network (LSTM) encoder-decoder is utilized to extract the hidden dynamic nonlinear information in unlabeled samples. this information is then spliced and masked with the initial input, which is subsequently fed into a deep neural network encoder-decoder for pretraining to learn a self-supervised task that mines correlation information between sequences as well as between samples that is useful for the model. In addition, the LSTM with attentional convolutional fusion serves as an auxiliary path that mines correlation information between variables directly from the initial input to complement the information extracted by self-supervision. Finally, the results of both are linearly weighted to obtain the final prediction. the method is validated in a debutanizer process. the results show that SSACF-LSTM can utilize both labeled and unlabeled data to extract quality-related features for soft sensor modeling, which is better than the semi-supervised LSTM network with historical feature fusion (HFF-ssLSTM), semi-supervised stacked auto-encoder (SSAE), and variational auto-encoder regression (SVAER). © 2024 ieee.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Lidar-Inertial and Downward Vision Based Mobile Robot SLAM in Digital Workshops 13

Lidar-Inertial and Downward Vision Based Mobile Robot SLAM i...

引用

13th ieee data driven control and learning systems conference, ddcls 2024

作者： Zhang, Yanchao Geng, Hao Liu, Bin Zhang, Yinlong Yuan, Xudong Zhang, Sichao School of Information Science and Engineering Shenyang University of Technology Shenyang110020 China Guangzhou Institute of Industrial Intelligence Guangzhou511458 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China

ISBN: (纸本)9798350361674

In order to solve the problems of long-term cumulative error and the absence of absolute pose in the existing Lidar-Inertial Measurement Unit (IMU) fusion methods for Automated Guided Vehicle (AGV) Simultaneous Localization and Mapping (SLAM), we propose a new SLAM method for mobile robot, integrating Lidar, IMU, and a downward vision camera. Firstly, we tightly couple Lidar-IMU and downward vision camera using a multimodal fusion framework. Downward visual measurements are integrated as QR factors into the factor graph, providing absolute pose information to correct cumulative error in the Lidar-IMU system and enable the joint pose estimation of the AGV. Secondly, an enhanced Iterative Closest Point (ICP) point cloud matching algorithm has been developed to correct the incorrect pose. this approach achieves Scan-to-Map alignment by employing a coarse-to-fine matching strategy, thereby enhancing the accuracy of point cloud alignment. Finally, the extended Kalman filter is used to optimize the Lidar pose drift, as well as the Lidar mapping effectively by using the Lidar-IMU as the measurements and the downward visual measurements as the updates. the algorithm has been extensively evaluated on the developed AGV experimental platform. the experimental results show that the position error is less than 0.02 meters and the orientation error is less than 1°, which solves the problems of long-term error accumulation and the lack of absolute pose information for AGV navigation. © 2024 ieee.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Design of a Cough Detection System Based on Vibration and Audio Signals for Post- thoracic Surgery Patients 13

Design of a Cough Detection System Based on Vibration and Au...

引用

13th ieee data driven control and learning systems conference, ddcls 2024

作者： Qiu, Zhilin Liu, Quan Gao, Guanbin Peng, Jun Xing, Yashan Kunming University of Science and Technology Faculty of Mechanical and Electrical Engineering Kunming650500 China Kunming University of Science and Technology Yunnan International Joint Laboratory of Intelligent Control and Application of Advanced Equipment Kunming650500 China First People's Hosp. of Yunnan Province Affiliated to Kunming University of Science and Technology Department of Thoracic Surgery Kunming650100 China

ISBN: (纸本)9798350361674

Cough is a vital rehabilitation indicator which can exhibit many complications after thoracic surgical procedures. In this paper, a portable bimodal cough detector that can achieve consecutive detection is designed to recognize postoperative cough. the detector collects vibration and audio signals of cough and sends the raw data to the base station for data processing. the time domain and frequency domain features of vibration data are extracted. Meanwhile, 13 dimensions of Mel-frequency Cepstral Coefficients (MFCC) features and two dimensions of physical features are extracted from audio data. the threshold distinguish method and the bagged tree model are applied to classify the vibration and audio signals features respectively. the fusion discrimination method determines the result of the two signals and then gives the final judgment based on the two classifiers. the bagged tree model training results show that the audio classifier achieved an accuracy of 94.20% with an Area Under the Receiver Operating Characteristics Curve (AUC) of 0.984. We evaluate the performance of the fusion discrimination in actual use scenarios. the experiment results show that the detector achieved a sensitivity of 85.54% and a specificity of 98.76% in the silent environment. the detector in the interference environment can achieve a sensitivity of 83.44% and a specificity of 98.50% which exhibits a strong interference resisting ability. © 2024 ieee.

关键词： Patient rehabilitation

来源：评论

学校读者我要写书评

暂无评论

Prediction of Ship Propulsion Power based on Bayesian optimized LightGBM Using Ship In-Service data 13

Prediction of Ship Propulsion Power based on Bayesian optimi...

引用

13th ieee International conference on Communications, Circuits and systems (ICCCAS)

作者： Liu Xu Zhang Antong Sun Qiang Guo Yu Yin Wenhui Yang Yunfan Bao Jiawei China Ship Sci Res Ctr Wuxi Jiangsu Peoples R China

ISBN: (数字)9798350386271

ISBN: (纸本)9798350386288;9798350386271

In maritime operations, accurate prediction and control of the propulsion power of the ship's main engine are crucial, as they directly impact the fuel economy, speed performance and carbon emission control. To enhance prediction accuracy, this paper proposes a regression prediction method for ship propulsion power based on the LightGBM model, specifically designed for vessels equipped with air lubrication drag reduction systems. First, domain knowledge is used to select sensor monitoring data related to main engine propulsion power, preprocess it as input variables, and use main engine propulsion power as output. Bayesian optimization is then used to adjust the hyper-parameters of the model. Finally, in order to evaluate the performance of this method, comparisons are made with multiple linear regression and support vector machine (SVM) regression in predicting ship propulsion power. the results show that the LightGBM model based on Bayesian optimization has strong generalization ability, short training time and superior performance.

关键词： ship propulsion power VLCC machine learning LightGBM Bayesian optimization

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72页 << < 25 26 27 28 29 30 31 32 33 34 > >>

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：