检索结果-内蒙古大学图书馆

DRTNet: Dual-route transformer network for thyroid ultrasound segmentation based on Bbox-supervised learning

Knowledge-Based Systems 2025年 324卷

作者： Bi, Hui Cai, Chengjie Sun, Jiawei Ge, Shihao Shu, Huazhong Ni, Xinye School of Computer Science and Artificial Intelligence Changzhou University Changzhou213164 China The Affiliated Changzhou NO.2 People's Hospital of Nanjing Medical University Changzhou213003 China Key Laboratory of Computer Network and Information Integration Southeast University Nanjing211096 China Jiangsu Province Engineering Research Center of Medical Physics Changzhou213003 China Center of Medical Physics Nanjing Medical University Changzhou213003 China Laboratory of Image Science and Technology Southeast University Nanjing210096 China Centre de Recherche en Information Biomédicale Sino-Français RennesF-35000 France

Background and Objective: Accurate nodule delineation plays a significant role in the intelligent diagnosis of thyroid disease. However, the labels accessing is difficult since it is time-consuming and laborious. To mitigate the over-dependence of the segmentation accuracy on the labels, we proposed a dual-route transformer network (DRTNet) based on Bbox-supervised learning that only requires the rough bounding rectangle as labels instead of a precise boundary for thyroid ultrasound segmentation. Methods: DRTNet incorporates double-branch foreground class activation mappings (CAMs) into Transformers to combine key areas. Meanwhile, double-branch architecture dynamically adjusts the feature distribution of nodules of different sizes in frequency channels and spatial dimensions, effectively addressing the localization of nodules of different sizes. Moreover, ultrasound prior background-aware pooling (UPBAP) is proposed in both branches to deal with the ambiguous boundary of thyroid nodules. Finally, adaptive uncertainty estimate multi-scale consistency (AUEMC) is proposed to help mitigate the risk of excessive over-fitting because of pseudo annotations, which further guarantees consistency among nodules with diverse resolutions. Results: Substantial improvement of segmentation accuracy is shown on the public thyroid dataset of TN3k and DDTI dataset with Dice similarity coefficient (DSC) of 84.94% and 83.98%, with 95% of the asymmetric Hausdorff distance (HD95) of 27.69 and 29.18, respectively. And our private dataset has a DSC of 84.39% and HD95 of 14.53. Conclusions: The proposed DRTNet used rectangular box labeled for thyroid ultrasound images based on Bbox-supervised learning. The experimental results show that the DRTNet is comparable to these fully supervised methods. Code is available at https://***/ccjcv/DRTNet. © 2025 Elsevier B.V.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Retraction Notice to:New Solution Generation Strategy to Improve Brain Storm Optimization Algorithm for Classification

引用

Journal on Internet of Things 2021年第4期3卷 183-183页

作者： Yu Xue Yan Zhao School of Computer and Software Nanjing University of Information Science and TechnologyNanjingChina Jiangsu Key Laboratory of Data Science and Smart Software Jinling Institute of TechnologyNanjingChina

The published article titled“New Solution Generation Strategy to Improve Brain Storm Optimization Algorithm for Classification”has been retracted from the Journal on Internet of Things,Vol.3,No.3,109-118,***:10.32604/jiot.2021.014980 URL:https://***/jiot/v3n3/46020/pdf After the publication of the above article,the authors Xue et *** that due to the following reasons,they have to retract the published article from Journal on Internet of Things:*** authors need to conduct more indepth experiments to verify the proposed method regarding problematic experimental setup,which leads to an unfair comparison with the comparison algorithm.

关键词： Storm Strategy Imp

来源：评论

学校读者我要写书评

暂无评论

Pareto-wise Ranking Classifier for Multi-objective Evolutionary Neural Architecture Search

arXiv

引用

arXiv 2021年

作者： Ma, Lianbo Li, Nan Yu, Guo Geng, Xiaoyu Cheng, Shi Wang, Xingwei Huang, Min Jin, Yaochu College of Software Northeastern University Shenyang110819 China The Institute of Intelligent Manufacturing Nanjing Tech University Nanjing211816 China The School of Computer Science Shaanxi Normal University Xi’an710062 China The College of Computer Science Northeastern University Shenyang110819 China The College of Information Science and Engineering State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China The Faculty of Technology Bielefeld University Bielefeld33619 Germany The Department of Computer Science University of Surrey GuildfordGU2 7XH United Kingdom

In multi-objective evolutionary neural architecture search (NAS), existing predictor-based methods commonly suffer from the rank disorder issue that a candidate high-performance architecture may have a poor ranking compared with the worse architecture in terms of the trained *** alleviate the above issue, we aim to train a Pareto-wise end-to-end ranking classifier to simplify the architecture search process by transforming the complex multi-objective NAS task into a simple classification task. To this end, a classifier-based Pareto evolution approach is proposed, where an online classifier is trained to directly predict the dominance relationship between the candidate and reference architectures. Besides, an adaptive clustering method is designed to select reference architectures for the classifier, and an α-domination assisted approach is developed to address the imbalance issue of positive and negative samples. The proposed approach is compared with a number of state-of-the-art NAS methods on widely-used test datasets, and computation results show that the proposed approach is able to alleviate the rank disorder issue and outperforms other methods. Especially, the proposed method is able to find a set of promising network architectures with different model sizes ranging from 2M to 5M under diverse objectives and constraints. © 2021, CC BY.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Data-driven Surplus Material Prediction in Steel Coil Production

Data-driven Surplus Material Prediction in Steel Coil Produc...

引用

International Conference on Wireless and Optical Communications ( WOCC)

作者： Ziyan Zhao Xiaoyue Yong Shixin Liu Mengchu Zhou State Key Laboratory of Synthetical Automation for Process Industries College of Information Science and Engineering Northeastern University Shenyang China Shanghai Baosight Software Co. Ltd Shanghai China Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark USA

ISBN: (数字)9781728161242

ISBN: (纸本)9781728161259

A steel enterprise is currently trying to avoid the presence of surplus materials since they can greatly increase its operational cost. The complicated production process of steel products makes it difficult to find the causes of surplus materials. In this work, we propose a surplus material prediction problem and solve it based on statistical analysis and machine learning methods. In the concerned problem, we predict whether there are surplus materials under a given group of production parameters. The dataset used in this work is from a real-world three-month steel coil production process. First, data cleaning is conducted to standardize the industrial dataset. Then, the production parameters highly correlated with surplus material prediction results are selected by a series of feature selection methods. Finally, two prediction models based on extreme gradient boosting and logistic regression are presented according to the selected features. The experimental results reveal that the proposed prediction models have similar effectiveness. A visible regression function makes the logistic regression method more suitable for practical application.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Overview of the recent experimental research on the J-TEXT tokamak

引用

Nuclear Fusion 2024年第11期64卷 112005-112005页

作者： Ding, Yonghua Wang, Nengchao Chen, Zhongyong Xia, Donghui Yang, Zhoujun Chen, Zhipeng Zheng, Wei Yan, Wei Li, Da Zhou, Song Xu, Xin Zhang, Xiaoyi Mao, Feiyue Fang, Jiangang Ren, Zhengkang Chen, Xixuan Zhang, Junli Zhang, Xiaobo He, Ying Zhang, Qi Li, You Bai, Wei Mou, Lingke Li, Feng Long, Ting Ke, Rui Gao, Li Shi, Peng Shen, Chengshuo Liu, Jiaxing Guo, Weixin Wang, Lu Li, Hanhui Jiang, Zhonghe Zhang, Xiaoqing Li, Jianchao Rao, Bo Cheng, Zhifeng Zhu, Ping Liu, Minghai Xu, Tao Ma, Shaoxiang Yang, Yong Li, Chuan Wang, Zhijiang Zhang, Ming Yu, Kexun Hu, Xiwei Liang, Y. Yu, Q. Gentle, K.W. Pan, Yuan Gentle, Kenneth William Yu, Qingquan Liang, Yunfeng Jiang, Wei Yi, Lin Zhang, Ya Hu, Qiming Li, Jianchao Huang, Mingxiang Li, Haolong Huang, Zhuo Huang, Jie Wang, Weijun He, Mei Zhao, Qing Xu, Jiayu Zhou, Gangyi Ba, Weigang Yang, Cheng Yao, Junjie Wang, Chuliang He, Bo Hu, Yongzhen Deng, Mingyang Fu, Jingwei Liang, Meiling Guan, Yehong Wu, Hongyan Zhuang, Ge Ding, Weixing Lan, Tao Zeng, Shiyong Hussain, Malik Sadam Lin, Zhifang Liu, Hai Sun, Youwen Zeng, Long Liu, Shaocheng Liao, Liang Zhong, Wulyu Shi, Zhongbing Jiang, Min Dong, Yunbo Xu, Min Wang, Aike Zhang, Xiaolong Liu, Linzi Tong, Ruihai Cheng, Jun Nie, Lin Li, Hui Xu, Jianqiang Yang, Zengchen Wen, Jie Liang, Anshu Zhang, Yipo Wu, Yifan Chen, Chengyuan Zhao, Kaijun Shi, Yuejiang Huang, He Austin, Max Lee, Sanggon Luhmann, Neville C. Domier, Calvin W. Zhu, Yilun Brower, David L. Chen, Jie Ida, K. Takemura, Y. Suzuki, Y. Nagasaki, K. Drews, P. Knieps, A. Han, Xiang Krämer-Flecken, A. Henkel, M. He, Jiyang Zhou, Yinan Jia, Ruo Peng, Yue Wang, Pengyu Li, Jiawei Yang, Jie Lu, Conghui Lu, Yiwei Wang, Rumeng Zhang, Hongqi Zeng, Yingqin Zhang, Guodong Ma, Fangyuan Bala, Abba Alhaji Li, Dingchen Hua, Jiankun Ai, Xinkun Tao, Qinlin Zhong, Yu Li, Yangbo He, Xiangrui Wan, Sui Huang, Shanni Ma, Yiming Qu, Zitong Yu, Shimin Huang, Zhangsheng Lei, Chi School of Electric and Electronic Engineering Huazhong University of Science and Technology Wuhan430074 China Southwestern Institute of Physics Chengdu China Institute of Plasma Physics Chinese Academy of Sciences Hefei China Guizhou University of Commerce Guiyang China Wuhan Institute of Technology Wuhan China ITER Organization Route de Vinon-sur-Verdon CS 90 046 Saint-Paul-lez-DuranceCedex 13067 France Forschungszentrum Jülich GmbH IEK-Plasmaphysik Jülich Germany Max-Planck-Institut für Plasmaphysik Garching Germany Institute of Fusion Studies University of Texas at Austin AustinTX United States University of Texas at Austin AustinTX78712 United States School of Physics Huazhong University of Science and Technology Wuhan430074 China Department of Physics Wuhan University of Technology Wuhan430070 China Princeton Plasma Physics Laboratory PO Box 451 PrincetonNJ08543 United States Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of Technology Wuhan430205 China College of Computer Science South-Central University for Nationalities Wuhan430074 China Shenzhen University Shenzhen518060 China University of Science and Technology of China Hefei230026 China School of Electrical Engineering & Automation Jiangsu Normal University Xuzhou221116 China Southwest Jiaotong University Chengdu China College of Nuclear Science and Engineer East China University of Technology PO Box Nanchang330013 China ENN Science and Technology Development Co. Ltd Hebei Key Laboratory of Compact Fusion Langfang065001 China National Fusion Research Institute Daejeon305-333 Korea Republic of University of California DavisCA95616 United States University of California Los Angeles Los AngelesCA90095 United States National Institute for Fusion Science Toki509-5292 Japan Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima739-8527 Japan Institute of Advanced Energy Kyoto University Gokasho Ky

The J-TEXT capability is enhanced compared to two years ago with several upgrades of its diagnostics and the increase of electron cyclotron resonance heating (ECRH) power to 1 MW. With the application of electron cyclotron wave (ECW), the ECW assisted plasma startup is achieved;the tearing mode is suppressed;the toroidal injection of 300 kW ECW drives around 24 kA current;fast electrons are generated with toroidal injected ECW and the runaway current conversion efficiency increases with ECRH power. The mode coupling between 2/1 and 3/1 modes are extensively studied. The coupled 2/1 and 3/1 modes usually lead to major disruption. Their coupling can be either suppressed or avoided by external resonant magnetic perturbation fields and hence avoids the major disruption. It is also found that the 2/1 threshold of external field is significantly reduced by a pre-excited 3/1 mode, which can be either a locked island or an external kink mode. The disruption control is studied by developing prediction methods capable of cross tokamak application and by new mitigation methods, such as the biased electrode or electromagnetic pellet injector. The high-density operation and related disruptions are studied from various aspects. Approaching the density limit, the collapse of the edge shear layer is observed and such collapse can be prevented by applying edge biasing, leading to an increased density limit. The density limit is also observed to increase, if the plasma is operated in the poloidal divertor configuration or the plasma purity is increased by increasing the pre-filled gas pressure or ECRH power during the start-up phase. © 2024 The Author(s).

关键词： Tokamak devices

来源：评论

学校读者我要写书评

暂无评论

Regret and cumulative constraint violation analysis for online convex optimization with long term constraints

arXiv

引用

arXiv 2021年

作者： Yi, Xinlei Li, Xiuxian Yang, Tao Xie, Lihua Chai, Tianyou Johansson, Karl H. School of Electrical Engineering and Computer Science and Digital Futures KTH Royal Institute of Technology Stockholm Sweden Department of Control Science and Engineering College of Electronics and Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems Institute for Advanced Study Tongji University Shanghai China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore

This paper considers online convex optimization with long term constraints, where constraints can be violated in intermediate rounds, but need to be satisfied in the long run. The cumulative constraint violation is used as the metric to measure constraint violations, which excludes the situation that strictly feasible constraints can compensate the effects of violated constraints. A novel algorithm is first proposed and it achieves an O(Tmax{c,1-c}) bound for static regret and an O(T (1-c)/2) bound for cumulative constraint violation, where c ϵ (0, 1) is a user-defined trade-off parameter, and thus has improved performance compared with existing results. Both static regret and cumulative constraint violation bounds are reduced to O(log(T )) when the loss functions are strongly convex, which also improves existing results. In order to achieve the optimal regret with respect to any comparator sequence, another algorithm is then proposed and it achieves the optimal O( p T (1 + PT )) regret and an O(√T) cumulative constraint violation, where PT is the path-length of the comparator sequence. Finally, numerical simulations are provided to illustrate the effectiveness of the theoretical results. Copyright © 2021, The Authors. All rights reserved.

关键词： Comparators (optical)

来源：评论

学校读者我要写书评

暂无评论

SAR Image Time Series for Land Cover Mapping via Sparse Local-Global Temporal Transformer Network

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Ni, Kang Yuan, Chunyang Zheng, Zhizhong Wang, Peng Nanjing University of Posts and Telecommunications School of Computer Science Nanjing210023 China Ministry of Natural Resources of the People's Republic of China Key Laboratory of China-ASEAN Satellite Remote Sensing Applications Nanning530221 China Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan430079 China Ministry of Education Key Laboratory of Radar Imaging and Microwave Photonics Nanjing University of Aeronautics and Astronautics Nanjing211106 China Jiangsu Province Engineering Research Center of Airborne Detecting and Intelligent Perceptive Technology Nanjing210049 China Nanjing University of Aeronautics and Astronautics Shenzhen Research Institute Shenzhen518110 China

Due to the effective embedding of temporal information, time-series SAR images can acquire more abundant land covers information, thereby effectively enhancing the accuracy of land cover mapping. However, the significant introduction of temporal features greatly increases the redundancy of deep features. Simultaneously, capturing the global-local features of time-series SAR images effectively while considering temporal features has a significant influence on time-series SAR land cover mapping. Motivated by these, a sparse 3D Transformer network based on joint learning of temporal-spatial features, named Sparse Local-Global Temporal Transformer Network (SL-GT2Net), is proposed for SAR land cover mapping, which has the ability to learn sparse global-local temporal-spatial features of SAR land covers. To emphasize crucial spatiotemporal features and suppress noise features, we propose a Spatial-Temporal Channel Refinement Block (STCRB) to mitigate feature redundancy. Additionally, we develop novel and effective Sparse Multi-scale Local Window Multi-Head Self-Attention (SMLW-MHSA) and Sparse Multi-scale Global Window Multi-Head Self-Attention (SMGW-MHSA) blocks. Both incorporate parallel multi-scale window partitioning and Top-K sparsification strategies to robustly model discriminative spatiotemporal features of land covers with vast scale variations, while maintaining linear complexity with respect to the number of tokens. The experimental results on three challenge time-series SAR datasets demonstrate that our SL-GT2Net exhibits outstanding competitiveness compared to other related networks. © 1965-2011 IEEE.

关键词： Photomapping

来源：评论

学校读者我要写书评

暂无评论

Multi-level graph convolutional network with automatic graph learning for hyperspectral image classification

arXiv

引用

arXiv 2020年

作者： Wan, Sheng Gong, Chen Pan, Shirui Yang, Jie Yang, Jian PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Faculty of Information Technology Monash University ClaytonVIC3800 Australia

Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification. However, the current GCN-based methods treat graph construction and image classification as two separate tasks, which often results in suboptimal performance. Another defect of these methods is that they mainly focus on modeling the local pairwise importance between graph nodes while lack the capability to capture the global contextual information of HSI. In this paper, we propose a Multi-level GCN with Automatic Graph Learning method (MGCN-AGL) for HSI classification, which can automatically learn the graph information at both local and global levels. By employing attention mechanism to characterize the importance among spatially neighboring regions, the most relevant information can be adaptively incorporated to make decisions, which helps encode the spatial context to form the graph information at local level. Moreover, we utilize multiple pathways for local-level graph convolution, in order to leverage the merits from the diverse spatial context of HSI and to enhance the expressive power of the generated representations. To reconstruct the global contextual relations, our MGCN-AGL encodes the long range dependencies among image regions based on the expressive representations that have been produced at local level. Then inference can be performed along the reconstructed graph edges connecting faraway regions. Finally, the multi-level information is adaptively fused to generate the network output. In this means, the graph learning and image classification can be integrated into a unified framework and benefit each other. Extensive experiments have been conducted on three real-world hyperspectral datasets, which are shown to outperform the state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Targeting macrophages in cancer immunotherapy: Frontiers and challenges

引用

Journal of Advanced Research 2025年

作者： Liu, Yu'e Tan, Huabing Dai, Jingyuan Lin, Jianghua Zhao, Kaijun Hu, Haibo Zhong, Chunlong Department of Neurosurgery Shanghai East Hospital School of Medicine Tongji University Shanghai 200120 China Department of Pediatric Hematology-Oncology Boston Children's Hospital Dana Farber Cancer Institute Harvard Medical School Boston 02115 MA United States Department of Infectious Diseases Hepatology Institute Renmin Hospital Hubei University of Medicine Shiyan Key Laboratory of Virology Hubei University of Medicine Hubei Province Shiyan 442000 China General internal medicine Wuhan Jinyintan Hospital Tongji Medical College of Huazhong University of Science and Technology Wuhan 430048 China School of Computer Science and Information Systems Northwest Missouri State University Maryville 64468 MO United States Department of Cardiothoracic Surgery The Affiliated Huai'an Hospital of Xuzhou Medical University Jiangsu Huai'an China

Background: Cancer immunotherapy has emerged as a groundbreaking approach in cancer treatment, primarily realized through the manipulation of immune cells, notably T cell adoption and immune checkpoint blockade. Nevertheless, the manipulation of T cells encounters formidable hurdles. Macrophages, serving as the pivotal link between innate and adaptive immunity, play crucial roles in phagocytosis, cytokine secretion, and antigen presentation. Consequently, macrophage-targeted therapies have garnered significant attention. Aim of review: We aim to provide the most cutting-edge insights and future perspectives for macrophage-targeted therapies, fostering the development of novel and effective cancer treatments. key scientific concepts of review: To date, the forefront strategies for macrophage targeting encompass: altering their plasticity, harnessing CAR-macrophages, and targeting phagocytosis checkpoints. Macrophages are characterized by their remarkable diversity and plasticity, offering a unique therapeutic target. In this context, we critically analyze the innovative strategies aimed at transforming macrophages from their M2 (tumor-promoting) to M1 (tumor-suppressing) phenotype. Furthermore, we delve into the design principles, developmental progress, and advantages of CAR-macrophages. Additionally, we illuminate the challenges encountered in targeting phagocytosis checkpoints on macrophages and propose potential strategies to overcome these obstacles. © 2024

关键词： Cancer immunotherapy CAR macrophage Macrophage polarization Phagocytosis checkpoints

来源：评论

学校读者我要写书评

暂无评论

Measurement-level fusion for OTHR network using message passing

arXiv

引用

arXiv 2020年

作者： Lan, Hua Wang, Zengfu Bai, Xianglong Pan, Quan Lu, Kun School of Automation Northwestern Polytechnical University Key Laboratory of Information Fusion Technology Ministry of Education Xi’anShaanxi710072 China Nanjing Reasearch Insitute of Electronics Technology Nanjing Jiangsu210039 China Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft2826 CD Netherlands

Tracking an unknown number of targets based on multipath measurements provided by an over-the-horizon radar (OTHR) network with a statistical ionospheric model is complicated, which requires solving four subproblems: target detection, target tracking, multipath data association and ionospheric height identification. A joint solution is desired since the four subproblems are highly correlated, but suffering from the intractable inference problem of high-dimensional latent variables. In this paper, a unified message passing approach, combining belief propagation (BP) and mean-field (MF) approximation, is developed for simplifying the intractable inference. Based upon the factor graph corresponding to a factorization of the joint probability distribution function (PDF) of the latent variables and a choice for a separation of this factorization into BP region and MF region, the posterior PDFs of continuous latent variables including target kinematic state, target visibility state, and ionospheric height, are approximated by MF due to its simple MP update rules for conjugate-exponential models. With regard to discrete multipath data association which contains one-to-one frame (hard) constraints, its PDF is approximated by loopy BP. Finally, the approximated posterior PDFs are updated iteratively in a closed-loop manner, which is effective for dealing with the coupling issue among target detection, target tracking, multipath data association, and ionospheric height identification. Meanwhile, the proposed approach has the measurement-level fusion architecture due to the direct processing of the raw multipath measurements from an OTHR network, which is benefit to improving target tracking performance. Its performance is demonstrated on a simulated OTHR network multitarget tracking scenario. Copyright © 2020, The Authors. All rights reserved.

关键词： Target tracking

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：