检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hou, Qingshan Cheng, Shuai Cao, Peng Yang, Jinzhu Liu, Xiaoli Zaiane, Osmar R. Tham, Yih Chung Computer Science and Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Shenyang110819 China Alberta Machine Intelligence Institute University of Alberta Edmonton Canada Yong Loo Lin School of Medicine National University of Singapore Singapore

Representation learning offers a conduit to elucidate distinctive features within the latent space and interpret the deep models. However, the randomness of lesion distribution and the complexity of low-quality factors in medical images pose great challenges for models to extract key lesion features. Disease diagnosis methods guided by contrastive learning (CL) have shown significant advantages in lesion feature representation. Nevertheless, the effectiveness of CL is highly dependent on the quality of the positive and negative sample pairs. In this work, we propose a clinical-oriented multi-level CL framework that aims to enhance the model's capacity to extract lesion features and discriminate between lesion and low-quality factors, thereby enabling more accurate disease diagnosis from low-quality medical images. Specifically, we first construct multi-level positive and negative pairs to enhance the model's comprehensive recognition capability of lesion features by integrating information from different levels and qualities of medical images. Moreover, to improve the quality of the learned lesion embeddings, we introduce a dynamic hard sample mining method based on self-paced learning. The proposed CL framework is validated on two public medical image datasets, EyeQ and Chest X-ray, demonstrating superior performance compared to other state-of-the-art disease diagnostic methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Bayesian optimization Framework for Efficient Fleet Design in Autonomous Multi-Robot Exploration

arXiv

引用

arXiv 2024年

作者： Concha, David Molina Li, Jiping Yin, Haoran Park, Kyeonghyeon Lee, Hyun-Rok Lee, Taesik Sirohi, Dhruv Lee, Chi-Guhn The Dynamic Optimization and Reinforcement Learning Laboratory The Department of Mechanical & Industrial Engineering University of Toronto TorontoONM5S3G8 Canada The Department of Electrical & Computer Engineering University of Toronto TorontoONM5S3G8 Canada The Division of Engineering Science The Faculty of Applied Science and Engineering University of Toronto TorontoONM5S3G8 Canada The Complex System Design Laboratory The Department of Industrial and Systems Engineering Korea Advanced Institute of Science and Technology Daejeon34141 Korea Republic of The Department of Industrial Engineering Inha University Incheon22212 Korea Republic of

This study addresses the challenge of fleet design optimization in the context of heterogeneous multi-robot fleets, aiming to obtain feasible designs that balance performance and costs. In the domain of autonomous multi-robot exploration, reinforcement learning agents play a central role, offering adaptability to complex terrains and facilitating collaboration among robots. However, modifying the fleet composition results in changes in the learned behavior, and training multi-robot systems using multi-agent reinforcement learning is expensive. Therefore, an exhaustive evaluation of each potential fleet design is infeasible. To tackle these hurdles, we introduce Bayesian optimization for Fleet Design (BOFD), a framework leveraging multiobjective Bayesian optimization to explore fleets on the Pareto front of performance and cost while accounting for uncertainty in the design space. Moreover, we establish a sub-linear bound for cumulative regret, supporting BOFD’s robustness and efficacy. Extensive benchmark experiments in synthetic and simulated environments demonstrate the superiority of our framework over state-of-the-art methods, achieving efficient fleet designs with minimal fleet evaluations. Copyright © 2024, The Authors. All rights reserved.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Inpainting of ultrasound cardiac tissues with consistent anatomical structures

引用

Biomedical Signal Processing and Control 2025年 110卷

作者： Honghe Li Jinzhu Yang Mei Wei Mingjun Qu Yong Feng Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Shenyang China

Image inpainting techniques play a crucial role in restoring occluded regions in medical images, ultimately enhancing the consistency of clinical diagnoses. Traditional inpainting methods often face challenges when attempting to restore complex anatomical structures and large occluded areas in medical ultrasound images. While recent deep learning-based techniques show promise, they still encounter issues such as loss of edge information and inconsistent reconstruction in occluded regions. In this paper, we introduce a Segmentation-guided Medical Ultrasound Inpainting framework designed to overcome these limitations. Our framework integrates segmentation-derived edge priors to guide the inpainting process, ensuring anatomical consistency and enhancing the recovery of fine details. We propose a Multi-Scale Mixed Residual Block to improve the model’s ability to restore large masked regions and a Deformable Edge Attention mechanism to preserve critical edge details during downsampling while minimizing the introduction of noise. Extensive experiments on two publicly available echocardiography datasets show that our method significantly outperforms state-of-the-art inpainting models in terms of PSNR, MAE, and SSIM metrics. The results highlight the potential of our approach to provide accurate, consistent ultrasound image reconstruction, making it a valuable tool for clinical diagnostics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A learning-based solution method for practical slab allocation problem in multiple hot rolling lines

A I I E Transactions

引用

A I I E Transactions 2024年第9期56卷

作者： Ying Meng Qingxin Guo Qingyang Wang Haichao Wang a National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang Chinab Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Ministry of Education China b Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Ministry of Education Chinac Liaoning Engineering Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University Shenyang China b Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Ministry of Education Chinad Liaoning Key Laboratory of Manufacturing System and Logistics Optimization Northeastern University Shenyang China

Steel slabs are key in-process products in the steel production process. The slab allocation problem is to allocate slabs to suitable orders by considering complicated technical restrictions and multiple management requirements. In practice, thousands of slabs in multiple production lines should be allocated to orders. Due to the complexity and large scale of the problem, it takes planners a long time to make decisions, and the obtained allocation schemes are usually ineffective because of the myopic nature of the rule-based methods. In this article, we present a learning-based solution method for solving a practical slab allocation problem in multiple hot rolling lines. We formulate the problem as an integer programming model, then a data-based method is adopted to evaluate the mismatching cost between slabs and orders. To effectively solve the large-sized problem, a learning-based decomposition strategy is proposed to decompose the original problem into several small-sized subproblems. Then, a branch-and-price algorithm is proposed to optimally solve the subproblems. To further speed up the solution process, a primal heuristics based on column generation is designed to solve the large-sized subproblems. The solution methods have been implemented in a steel company and effectively increased slab utilization and reduced production cost.

关键词： Slab allocation combinatorial optimization branch-and-price learning

来源：评论

学校读者我要写书评

暂无评论

A green multi-period request assignment problem for road freight transport

引用

Journal of Cleaner Production 2025年 519卷

作者： Elham Jelodari Mamaghani Yousef Ghiami Emrah Demir Tom Van Woensel Logistics and Optimization of Industrial Systems Laboratory of Computer Science University of Technology of Troyes Troyes France Institute of Sustainable Business and Organizations Sciences and Humanities Confluence Research Center UCLY ESDES France Department of Operations Analytics Vrije Universiteit Amsterdam Amsterdam The Netherlands Business & Economics Artificial Intelligence Research Network Cardiff Business School Cardiff University Cardiff UK School of Industrial Engineering Eindhoven University of Technology Eindhoven The Netherlands

This paper addresses a multi-period pickup and delivery problem with time windows, where carriers must fulfill committed transport requests while deciding whether to accept additional requests to enhance their financial and environmental performance. Given the increasing focus on sustainability, the objective is to balance profitability and CO 2 e emissions. To tackle this bi-objective problem, we propose a mixed-integer linear programming formulation that accounts for heterogeneous vehicles and both hard and soft time windows. To efficiently solve large-scale instances, we introduce a Hybrid Adaptive Large Neighborhood Search (HALNS) algorithm, which integrates population-based Tabu Search with a mutation operator within an ALNS framework. The proposed HALNS is benchmarked against multiple existing methods to assess its effectiveness and efficiency. Computational experiments demonstrate that HALNS efficiently solves large-scale instances, outperforming existing approaches. In addition, our numerical analysis provides key managerial insights for companies that want to achieve environmentally sustainable transport operations. Our numerical results indicate that imposing stricter emission targets can reduce CO 2 e emissions by up to 40% while decreasing profits by approximately 21%. In contrast, increasing the size of the fleet leads to an increase in profits 15% and improves the performance of the delivery, but at the cost of higher emissions. Furthermore, relaxing the time window constraints improves operational flexibility, resulting in an increase in average profits of 5% while reducing emissions by approximately 7%. These findings highlight the trade-offs involved in sustainable logistics planning and offer actionable insights for managers.

关键词： Green logistics Pickup and delivery problem Multi period planning Bi-objective optimization Reserved and selective requests

来源：评论

学校读者我要写书评

暂无评论

Dynamic Topic Analysis in Academic Journals using Convex Non-negative Matrix Factorization Method

arXiv

引用

arXiv 2025年

作者： Yang, Yang Zhang, Tong Wu, Jian Su, Lijie National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China China Criminal Police University Shenyang China Center for Advanced Process Decision-making Carnegie Mellon University PittsburghPA United States Beijing Institute for General Artificial Intelligence Beijing China Liaoning Key Laboratory of Manufacturing System and Logistics Optimization Northeastern University ChinaShenyang Shenyang110819 China Liaoning Engineering Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University Shenyang China

With the rapid advancement of large language models, academic topic identification and topic evolution analysis are crucial for enhancing AI’s understanding capabilities. Dynamic topic analysis provides a powerful approach to capturing and understanding the temporal evolution of topics in large-scale datasets. This paper presents a two-stage dynamic topic analysis framework that incorporates convex optimization to improve topic consistency, sparsity, and interpretability. In Stage 1, a two-layer non-negative matrix factorization (NMF) model is employed to extract annual topics and identify key terms. In Stage 2, a convex optimization algorithm refines the dynamic topic structure using the convex NMF (cNMF) model, further enhancing topic integration and stability. Applying the proposed method to IEEE journal abstracts from 2004 to 2022 effectively identifies and quantifies emerging research topics, such as COVID-19 and digital twins. By optimizing sparsity differences in the clustering feature space between traditional and emerging research topics, the framework provides deeper insights into topic evolution and ranking analysis. Moreover, the NMF-cNMF model demonstrates superior stability in topic consistency. At sparsity levels of 0.4, 0.6, and 0.9, the proposed approach improves topic ranking stability by 24.51%, 56.60%, and 36.93%, respectively. The source code is available at https://***/meetyangyang/CDNMF. © 2025, CC BY.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Open Innovations for Tourism logistics Design: A Case Study of a Smart Bus Route Design for the Medical Tourist in the City of Greater Mekong Subregion

引用

Journal of Open Innovation: Technology, Market, and Complexity 2022年第4期8卷

作者： Ngeoywijit, Sumalee Kruasom, Tawamin Ugsornwongand, KiengKwan Pitakaso, Rapeepan Sirirak, Worapot Nanthasamroeng, Natthapong Kotmongkol, Thachada Srichok, Thanatkij Khonjun, Surajet Kaewta, Chutchai Department of International Business Management Faculty of Management Science Ubon Ratchathani University 85 Sathonlamark Muang SriKai Warin Chamrap Ubon Ratchathani 34190 Thailand Department of Financial and Investment Faculty of Management Science Ubon Ratchathani University 85 Sathonlamark Muang SriKai Warin Chamrap Ubon Ratchathani 34190 Thailand Artificial Intelligence Optimization SMART Laboratory Department of Industrial Engineering Faculty of Engineering Ubon Ratchathani University 85 Sathonlamark Muang SriKai Warin Chamrap Ubon Ratchathani 34190 Thailand Department of Industrial Engineering Faculty of Engineering Rajamangala University of Technology Lanna Chiang Rai 50300 Thailand Artificial Intelligence Optimization SMART Laboratory Department of Engineering Technology Faculty of Industrial Technology Ubon Ratchathani Rajabhat University 2 Ratchathani Nai Muang Ubon Ratchathani 34000 Thailand Department of Logistics Management Faculty of Industrial Technology Ubon Ratchathani Rajabhat University 2 Ratchathani Nai Muang Ubon Ratchathani 34000 Thailand Artificial Intelligence Optimization SMART Laboratory Department of Computer Science Faculty of Computer Science Ubon Ratchathani Rajabhat University 2 Ratchathani Nai Muang Ubon Ratchathani 34000 Thailand

One of the industries with the fastest growth rates worldwide, and notably in Thailand, is medical tourism. With connections to Cambodia and Laos, Ubon Ratchathani is located in lower northeastern Thailand, close to Vietnam and Myanmar. Therefore, there is a significant chance that this region will welcome medical travelers. High-quality medical facilities are available in Ubon Ratchathani to fulfill the needs of medical tourists. A visitor’s decision to travel to Ubon Ratchathani for medical treatment is influenced by factors other than the high-level medical facilities, such as lodging, accessibility to public transportation, and tourist attractions. The public transportation services in Ubon Ratchathani, especially the public bus system, are poorly designed and may let down visitors. The purpose of this study is to develop a smart public bus route design that will meet tourists’ demands. The concept of open innovation will be utilized to develop the model. We surveyed 400 visitors to Ubon Ratchathani. The tourists’ opinions and views of public transportation will be made public and used as an input parameter when designing bus routes. The bus route can then be constructed using the differential evolution algorithm (DE). A web-based smart public transportation system was built. In order to construct an efficient smart public bus system (SPBS), open innovation was used in the development phase. According to the computational results, the new routes using DE lead to a 5.97% reduction in travel distance when compared to the output of the more well-known genetic method. More than 98.5% of visitors are satisfied with the new routes, and once they start running, 99.5% of all respondents plan to use public transit. © 2022 by the authors.

关键词： differential evolution algorithm environmentally friendly GPS monitoring public transportation system SMART bus system

来源：评论

学校读者我要写书评

暂无评论

Utilization of machine learning and neural networks to optimize the enclosure angle, magnetic field, and radiation parameter for mixed convection of hybrid nanofluid flow next to assess environmental impact

引用

Engineering Analysis with Boundary Elements 2023年 146卷 252-262页

作者： Tao Hai Hayder A. Dhahad Masood Ashraf Ali Vishal Goyal Sattam Fahad Almojil Abdulaziz Ibrahim Almohana Abdulrhman Fahmi Alali Khaled Twfiq Almoalimi Farah Qasim Ahmed Alyousuf School of Computer and Information Qiannan Normal University for Nationalities Duyun Guizhou 558000 China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Duyun Guizhou 558000 China Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Universiti Teknologi MARA Shah Alam Selangor 40450 Malaysia Mechanical Engineering Department University of Technology Baghdad Iraq Department of Industrial Engineering College of Engineering Prince Sattam bin Abdulaziz University Alkharj 16273 Saudi Arabia Department of Electronics and Communication Engineering GLA University Mathura India Department of Civil Engineering College of Engineering King Saud University P.O. Box 800 Riyadh 11421 Saudi Arabia Department of Information Technology College of Engineering and Computer Science Lebanese French University Kurdistan Region Iraq

This paper examines the mixed convective heat transfer (HTR) of nanofluid (NFD) flow in a rectangular enclosure with the upper moving wall numerically. The lower wall has a high temperature and a number of semi-circular obstacles with the same temperature are installed on it. The upper moving wall has a low temperature and the other two walls are insulated. The enclosure can change from horizontal to vertical. Radiation HTR is considered in the enclosure and there is a magnetic field (MGF) that can change the angle from horizontal to vertical affecting the NFD. This study is carried out for different angles of the enclosure and MGF from horizontal to vertical for radiation parameters (RDP) of 0 to 3 and a constant MGF with Hartmann number of 20 and Richardson number of 10. The aim is to estimate the Nusselt number (Nu), entropy generation (ETG), and Bejan number (Be). The SIMPLE algorithm is utilized using FORTRAN software, and optimization is done using artificial intelligence to find the maximum and minimum output values. The results demonstrate that the maximum value of Nu and Bes corresponds to the MGF angle and enclosure angle of 90°. The minimum value of the Nu and the maximum amount of ETG corresponds to the horizontal MGF and horizontal enclosure when the RDP is 1.5. An increment in the RDP enhances the amount of Nu. The maximum amount of ETG, i.e. 12.87, corresponds to the enclosure with an angle of 45° for the horizontal MGF and the absence of RDP. corresponds to the enclosure with an angle of 45° for the horizontal MGF and the absence of RDP. It was also found that most environmental impacts, and hence values for different environmental factors, arise from the production of nanoparticles; thus, it is a significant contributor to environmental impacts.

关键词： Machine learning Entropy generation Numerical calculations Convection Nanofluid

来源：评论

学校读者我要写书评

暂无评论

Operational Research: Methods and Applications

arXiv

引用

arXiv 2023年

作者： Petropoulos, Fotios Laporte, Gilbert Aktas, Emel Alumur, Sibel A. Archetti, Claudia Ayhan, Hayriye Battarra, Maria Bennell, Julia A. Bourjolly, Jean-Marie Boylan, John E. Breton, Michèle Canca, David Charlin, Laurent Chen, Bo Cicek, Cihan Tugrul Cox, Louis Anthony Currie, Christine S.M. Demeulemeester, Erik Ding, Li Disney, Stephen M. Ehrgott, Matthias Eppler, Martin J. Erdogan, Güneş Fortz, Bernard Franco, L. Alberto Frische, Jens Greco, Salvatore Gregory, Amanda J. Hämäläinen, Raimo P. Herroelen, Willy Hewitt, Mike Holmström, Jan Hooker, John N. Işık, Tugçe Johnes, Jill Kara, Bahar Y. Karsu, Özlem Kent, Katherine Köhler, Charlotte Kunc, Martin Kuo, Yong-Hong Letchford, Adam N. Leung, Janny Li, Dong Li, Haitao Lienert, Judit Ljubić, Ivana Lodi, Andrea Lozano, Sebastián Lurkin, Virginie Martello, Silvano McHale, Ian G. Midgley, Gerald Morecroft, John D.W. Mutha, Akshay Oguz, Ceyda Petrovic, Sanja Pferschy, Ulrich Psaraftis, Harilaos N. Rose, Sam Saarinen, Lauri Salhi, Said Song, Jing-Sheng Sotiros, Dimitrios Stecke, Kathryn E. Strauss, Arne K. Tarhan, Istenç Thielen, Clemens Toth, Paolo Van Woensel, Tom Vanden Berghe, Greet Vasilakis, Christos Vaze, Vikrant Vigo, Daniele Virtanen, Kai Wang, Xun Weron, Rafal White, Leroy Yearworth, Mike Yıldırım, E. Alper Zaccour, Georges Zhao, Xuying School of Management University of Bath Bath United Kingdom Makridakis Open Forecasting Center University of Nicosia Nicosia Cyprus Department of Decision Sciences HEC Montréal Montreal Canada Molde University College Molde Norway Cranfield School of Management Cranfield University Cranfield United Kingdom Department of Management Sciences University of Waterloo Waterloo Canada ESSEC Business School in Paris Department of Information Systems Decision Sciences and Statistics Cergy France H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta United States Centre for Decision Research Leeds University Business School University of Leeds Leeds United Kingdom Université du Québec à Montréal Montreal Canada Centre for Marketing Analytics and Forecasting Lancaster University Management School Lancaster University Lancaster United Kingdom School of Engineering Department of Industrial Engineering and Management Science I University of Seville Seville Spain Mila-Quebec AI Institute Montreal Canada Warwick Business School University of Warwick Coventry United Kingdom Department of Industrial Engineering Atilim University Ankara Turkey Department of Business Analytics University of Colorado School of Business Denver United States Cox Associates Denver United States Mathematical Sciences University of Southampton Southampton United Kingdom Faculty of Economics and Business Research Center for Operations Management KU Leuven Leuven Belgium Durham University Business School Durham University Durham United Kingdom Center for Simulation Analytics and Modelling University of Exeter Business School Exeter United Kingdom Department of Management Science Lancaster University Management School Lancaster University Lancaster United Kingdom University of St. Gallen St. Gallen Switzerland HEC - Management School of the University of Liège Liège Belgium Département d'Informatique Université Libre de Bruxelles Bruss

Throughout its history, Operational Research has evolved to include a variety of methods, models and algorithms that have been applied to a diverse and wide range of contexts. This encyclopedic article consists of two main sections: methods and applications. The first aims to summarise the up-to-date knowledge and provide an overview of the state-of-the-art methods and key developments in the various subdomains of the field. The second offers a wide-ranging list of areas where Operational Research has been applied. The article is meant to be read in a nonlinear fashion. It should be used as a point of reference or first-port-of-call for a diverse pool of readers: academics, researchers, students, and practitioners. The entries within the methods and applications sections are presented in alphabetical order. The authors dedicate this paper to the 2023 Turkey/Syria earthquake victims. We sincerely hope that advances in OR will play a role towards minimising the pain and suffering caused by this and future catastrophes. © 2023, CC BY.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

IMPLEMENTING A SMOOTH EXACT PENALTY FUNCTION FOR EQUALITY-CONSTRAINED NONLINEAR optimization∗

arXiv

引用

arXiv 2019年

作者： Estrin, Ron Friedlander, Michael P. Orban, Dominique Saunders, Michael A. Institute for Computational and Mathematical Engineering Stanford University StanfordCA United States Department of Computer Science University of British Columbia VancouverBCV6T 1Z4 Canada GERAD Department of Mathematics and Industrial Engineering École Polytechnique MontréalQC Canada Systems Optimization Laboratory Department of Management Science and Engineering Stanford University StanfordCA United States

We develop a general equality-constrained nonlinear optimization algorithm based on a smooth penalty function proposed by Fletcher (1970). Although it was historically considered to be computationally prohibitive in practice, we demonstrate that the computational kernels required are no more expensive than other widely accepted methods for nonlinear optimization. The main kernel required to evaluate the penalty function and its derivatives is solving a structured linear system. We show how to solve this system efficiently by storing a single factorization each iteration when the matrices are available explicitly. We further show how to adapt the penalty function to the class of factorization-free algorithms by solving the linear system iteratively. The penalty function therefore has promise when the linear system can be solved efficiently, e.g., for PDE-constrained optimization problems where efficient preconditioners exist. We discuss extensions including handling simple constraints explicitly, regularizing the penalty function, and inexact evaluation of the penalty function and its gradients. We demonstrate the merits of the approach and its various features on some nonlinear programs from a standard test set, and some PDE-constrained optimization problems. Copyright © 2019, The Authors. All rights reserved.

关键词： Factorization

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：