检索结果-内蒙古大学图书馆

Emerging Technologies (GlobConET), IEEE IAS Global Conference on

作者： Sanjaya Mallikarachchi Bonnie Ho Iyad Kanj Oshani Seneviratne Isuru S. Godage Jarvis College of Computing & Digital Media School of Computing DePaul University Chicago IL USA Department of Computer Science Rensselaer Polytechnic Institute Troy NY USA Department of Engineering Technology & Industrial Distribution Texas A&M University College Station TX USA

Image data plays a pivotal role in the current data-driven era, particularly in applications such as computer vision, object recognition, and facial identification. Google Maps ® stands out as a widely used platform that heavily relies on street view images. To fulfill the pressing need for an effective and distributed mechanism for image data collection, we present a framework that utilizes smart contract technology and open-source robots to gather street-view image sequences. The proposed framework also includes a protocol for maintaining these sequences using a private blockchain capable of retaining different versions of street views while ensuring the integrity of collected data. With this framework, Google Maps ® data can be securely collected, stored, and published on a private blockchain. By conducting tests with actual robots, we demonstrate the feasibility of the framework and its capability to seamlessly upload privately maintained blockchain image sequences to Google Maps ® using the Google Street View ® Publish API.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Customer Churn Prediction in the Telecom Sector with Machine Learning and Adaptive k-Means Cluster using Imbalance Data

Customer Churn Prediction in the Telecom Sector with Machine...

引用

Distributed computing and Optimization Techniques (ICDCOT), International Conference on

作者： N L Aravinda R Archana Reddy Bala Dhandayuthapani V Jithendra P R Nayak Ahmad Husseen Electronics and Communication Engineering Department Mallareddy Engineering College for Women (Autonomous) Hyderabad Telangana India School of Computer Science and Engineering SR University Warangal Telangana India Department of IT College of Computing and Information Sciences University of Technology and Applied Sciences Shinas branch Oman Department of CSE Srinivas Institute of Technology Valachil Mangalore India The Islamic university Najaf Iraq

A crucial aspect of maintaining a customer-oriented business in the telecommunications sector with machine learning (ML) is understanding the reasons and factors that lead to customer churn. However, the dataset is difficult by noise, misclassifications, duplicated data, and imbalanced customer information complicating the process of identifying ways to split the dataset based on events. The under-sampling method address the imbalance data by decreasing the data quantity of majority class, thereby achieving a balanced dataset. This method, utilizing Adaptive k-means clustering, directly determines the reduction based on that data quality in each class. The datasets are combined with class labels to generate a new balanced dataset used for classification in the SVM algorithm, which distinguishes between customer churn and non-churn in the prediction for the telecom sector. The SVM algorithm can perform linear and non-linear classification with a kernel function to control overfitting improve generalization and handle high-dimensional data. The obtained results demonstrate that the proposed method achieves better accuracy of 95.70%, precision of 56.01%, Recall of 55.05%, and F1-score of 96.05% on the telecom churn dataset. These results ensure superior detection and classification performance compared to other existing methods, such as Random Forest (RF), Decision Tree (DT) and K-Nearest Neighbour (KNN).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optical Anisotropy in van der Waals materials: Impact on Direct Excitation of Plasmons and Photons by Quantum Tunneling

引用

Light(science & Applications) 2021年第12期10卷 2387-2398页

作者： Zhe Wang Vijith Kalathingal Thanh Xuan Hoang Hong-Son Chu Christian A.Nijhuis Department of Chemistry National University of Singapore3 Science Drive 3Singapore 117543Singapore Centre for Advanced 2D Materials National University of Singapore6 Science Drive 2Singapore 117564Singapore Department of Electrical and Computer Engineering National University of Singapore4 Engineering Drive 3Singapore 117583Singapore Department of Electronics and Photonics Institute of High Performance ComputingA*STAR(Agency for ScienceTechnology and Research)1 Fusionopolis WaySingapore 138632Singapore Hybrid Materials for Opto-Electronics Group Department of Molecules and MaterialsMESA+Institute for Nanotechnology and Center for Brain-Inspired Nano SystemsFaculty of Science and TechnologyUniversity of Twente7500 AE EnschedeThe Netherlands

Inelastic quantum mechanical tunneling of electrons across plasmonic tunnel junctions can lead to surface plasmon polariton(SPP)and photon *** far,the optical properties of such junctions have been controlled by changing the shape,or the type of the material,of the electrodes,primarily with the aim to improve SPP or photon emission *** we show that by tuning the tunneling barrier itself,the efficiency of the inelastic tunneling rates can be improved by a factor of *** exploit the anisotropic nature of hexagonal boron nitride(hBN)as the tunneling barrier material in Au//hBN//graphene tunnel junctions where the Au electrode also serves as a plasmonic strip *** this junction constitutes an optically transparent hBN–graphene heterostructure on a glass substrate,it forms an open plasmonic system where the SPPs are directly coupled to the dedicated strip waveguide and photons outcouple to the far *** experimentally and analytically show that the photon emission rate per tunneling electron is significantly improved(~×3)in Au//hBN//graphene tunnel junction due to the enhancement in the local density of optical states(LDOS)arising from the hBN *** the dedicated strip waveguide,SPP outcoupling efficiency is quantified and is found to be∼80%stronger than the radiative outcoupling in Au//hBN//graphene due to the high LDOS of the SPP decay channel associated with the inelastic *** new insights elucidated here deepen our understanding of plasmonic tunnel junctions beyond the isotropic models with enhanced LDOS.

关键词： tunneling strip coupling

来源：评论

学校读者我要写书评

暂无评论

Human Activity Recognition Using Improved Cat Swarm Optimization Algorithm and Convolutional Neural Network

Human Activity Recognition Using Improved Cat Swarm Optimiza...

引用

Network, Multimedia and Information technology (NMITCON) International Conference on

作者： Yerrolla Chanti Ammar Hameed Shnain Ramesh Banoth Rana Veer Samara Sihman Brahmatej Rupavath C. Sushama School of Computer Science & Artificial Intelligence SR University Warangal India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of AI & ML Gokaraju Rangaraju Institute of Engineering and Technology Bachupally Hyderabad India Indiana Wesleyan University Marion USA Department of CSE School of Computing Mohan Babu University Tirupati India

ISBN: (数字)9798350372892

ISBN: (纸本)9798350372908

Widespread computing has a lot of ability to offer users customised services and support, especially as more people use smartphones for everyday tasks. In the past ten years, there has been a significant advancement in Sensor-Based Human Activity Recognition (HAR), which detects the movements of the user and emerged as a crucial component of pervasive computing. Thus, accurate HAR plays a significant role in numerous applications. For accurate HAR, the current research proposes an Improved Cat Swarm Optimization Algorithm based Convolutional Neural Network (ICSO-CNN) for tuning the parameters of CNN for optimal solution. Using various performance measures, the present research examines the performance of the proposed ICSO-CNN algorithm. The test results demonstrated that the ICSO-CNN outperforms the compared methods, including CNN with Long Short-Term Memory (CNN-LSTM), Particle Swarm Optimization based CNN (PSO-CNN), and CNN-BiLSTM with an accuracy of 99.79%.

关键词： Pervasive computing Accuracy Particle measurements Convolutional neural networks Human activity recognition Particle swarm optimization Tuning Optimization Smart phones Sports

来源：评论

学校读者我要写书评

暂无评论

Design of Automated Deep Learning-Based Fusion Model for Copy-Move Image Forgery Detection

引用

Computational Intelligence and Neuroscience 2022年 2022卷 8501738页

作者： Krishnaraj, N. Sivakumar, B. Kuppusamy, Ramya Teekaraman, Yuvaraja Thelkar, Amruth Ramesh Department of Networking and Communications School of Computing SRM Institute of Science and Technology Kattankulathur Chennai603203 India Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Chennai603203 India Department of Electrical and Electronics Engineering Sri Sairam College of Engineering Karnataka Bangalore562106 India Department of Electronic and Electrical Engineering The University of Sheffield SheffieldS1 3JD United Kingdom Faculty of Electrical and Computer Engineering Jimma Institute of Technology Jimma University Jimma Ethiopia

Due to the exponential growth of high-quality fake photos on social media and the Internet, it is critical to develop robust forgery detection tools. Traditional picture- and video-editing techniques include copying areas of the image, referred to as the copy-move approach. The standard image processing methods physically search for patterns relevant to the duplicated material, restricting the usage in enormous data categorization. On the contrary, while deep learning (DL) models have exhibited improved performance, they have significant generalization concerns because of their high reliance on training datasets and the requirement for good hyperparameter selection. With this in mind, this article provides an automated deep learning-based fusion model for detecting and localizing copy-move forgeries (DLFM-CMDFC). The proposed DLFM-CMDFC technique combines models of generative adversarial networks (GANs) and densely connected networks (DenseNets). The two outputs are combined in the DLFM-CMDFC technique to create a layer for encoding the input vectors with the initial layer of an extreme learning machine (ELM) classifier. Additionally, the ELM model's weight and bias values are optimally adjusted using the artificial fish swarm algorithm (AFSA). The networks' outputs are supplied into the merger unit as input. Finally, a faked image is used to identify the difference between the input and target areas. Two benchmark datasets are used to validate the proposed model's performance. The experimental results established the proposed model's superiority over recently developed approaches. © 2022 N. Krishnaraj et al.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A nonconvex framework for structured dynamic covariance recovery

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2022年第1期23卷 9056-9146页

作者： Katherine Tsai Mladen Kolar Oluwasanmi Koyejo Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign Urbana IL University of Chicago Booth School of Business Chicago IL Department of Computer Science Beckman Institute for Advanced Science and Technology and Statistics University of Illinois at Urbana-Champaign Urbana IL

We propose a flexible, yet interpretable model for high-dimensional data with time-varying second-order statistics, motivated and applied to functional neuroimaging data. Our approach implements the neuroscientific hypothesis of discrete cognitive processes by factorizing covariances into sparse spatial and smooth temporal components. Although this factorization results in parsimony and domain interpretability, the resulting estimation problem is nonconvex. We design a two-stage optimization scheme with a tailored spectral initialization, combined with iteratively refined alternating projected gradient descent. We prove a linear convergence rate up to a nontrivial statistical error for the proposed descent scheme and establish sample complexity guarantees for the estimator. Empirical results using simulated data and brain imaging data illustrate that our approach outperforms existing baselines.

关键词： dynamic covariance structured factor model alternating projected gradient descent time series data functional connectivity

来源：评论

学校读者我要写书评

暂无评论

Flux variations of cosmic ray air showers detected by LHAASO-KM2A during a thunderstorm on June 10,2021

引用

Chinese Physics C 2023年第1期47卷 193-203页

作者： F.Aharonian 安琪阿西克古白立新白云翔包逸炜 D.Bastieri 毕效军毕玉江蔡金庭曹喆曹臻常进常劲帆陈恩生陈良陈亮陈龙陈明君陈玛丽陈素弘陈松战陈天禄陈学健陈阳程皓麟程宁程耀东崔树旺崔晓红崔昱东戴本忠代洪亮戴子高单增罗布 D.della Volpe 段凯凯樊军辉范一中范志香方军方堃冯存峰封莉冯少辉丰晓婷冯有亮高博高川东高林青高启高卫高伟康葛茂茂耿利斯龚光华苟全补顾旻皓郭福来郭俊广郭晓磊郭义庆郭莹莹韩毅昂何会海贺昊宁何思乐何新波何钰 M.Heller 贺远强侯超侯贤胡红波胡铨胡森胡世聪呼晓军黄代绘黄文昊黄性涛黄晓渊黄勇黄志成季筱璐贾焕玉贾康江琨姜泽军金敏康明铭柯通 D.Kuleshov 李兵兵李澄李骢李飞李海波李会财李华阳李军李剑李捷李凯李文龙李秀荣李昕李新李一卓李哲黎卓梁恩维梁云峰林苏杰刘冰刘成刘栋刘虎刘海东刘佳刘江来刘佳松刘金艳刘茂元柳若愚刘四明刘伟刘怡刘以农龙文杰鲁睿罗晴吕洪魁马伯强马玲玲马欣华毛基荣 A.Masood 闵振 W.Mitthumsiri 南云程区子维庞彬宇 P.Pattarakijwanich 裴致远齐孟尧祁业情乔冰强秦家军 D.Ruffolo A.Sáiz 邵澄宇邵琅 O.Shchegolev 盛祥东石京燕宋慧超 Yu.V.Stenkin V.Stepanov 苏扬孙秦宁孙晓娜孙志斌谭柏轩唐泽波田文武王博东王超王辉王洪光王建成王界双王利苹王玲玉王冉王润娜王为王祥高王祥玉王阳王玉东王岩谨王亚平王忠海王仲翔王振王铮韦大明魏俊杰魏永健文韬吴超勇吴含荣武莎吴雪峰吴雨生席邵强夏捷夏君集项光漫肖迪泫肖刚辛广广辛玉良邢祎熊峥徐东莲徐仁新薛良闫大海颜景志杨朝文杨冯帆杨何文杨佳盈杨莉莉杨明洁杨睿智杨深邦姚玉华姚志国叶一锰尹丽巧尹娜游晓浩游智勇于艳红袁强岳华曾厚敦曾婷轩曾玮曾宗康查敏翟徐徐张彬彬张丰张海明张恒英张建立张丽霞张力张路张鹏飞张佩佩张瑞张少博张少如张寿山张潇张笑鹏张云峰张月雷张毅张勇赵兵赵静赵雷赵立志赵世平郑福郑应周斌周浩周佳能周平周荣周勋秀祝成光祝凤荣朱辉朱科军左雄 Key Laboratory of Particle Astrophyics&Experimental Physics Division&Computing Center of Sciences Beijing 100049China University of Chinese Academy of Sciences Beijing 100049China TIANFU Cosmic Ray Research Center ChengduSichuanChina Dublin Institute for Advanced Studies 31 Fitzwilliam Place2 DublinIreland Max-Planck-Institut for Nuclear Physics P.O.Box 10398069029 HeidelbergGermany State Key Laboratory of Particle Detection and Electronics China University of Science and Technology of China Hefei 230026China School of Physical Science and Technology&School of Information Science and Technology Southwest Jiaotong UniversityChengdu 610031China College of Physics Sichuan UniversityChengdu 610065China School of Astronomy and Space Science Nanjing UniversityNanjing 210023China Center for Astrophysics Guangzhou UniversityGuangzhou 510006China Key Laboratory of Dark Matter and Space Astronomy&Key Laboratory of Radio Astronomy Purple Mountain ObservatoryChinese Academy of SciencesNanjing 210023China Key Laboratory for Research in Galaxies and Cosmology Shanghai Astronomical ObservatoryChinese Academy of SciencesShanghai 200030China Key Laboratory of Cosmic Rays(Tibet University) Ministry of Education850000 LhasaTibetChina National Astronomical Observatories Chinese Academy of SciencesBeijing 100101China Hebei Normal University Shijiazhuang 050024China School of Physics and Astronomy(Zhuhai)&School of Physics(Guangzhou)&Sino-French Institute of Nuclear Engineering and Technology(Zhuhai) Sun Yat-sen University519000 Zhuhai&510275 GuangzhouGuangdongChina Dipartimento di Fisica dell’Universitàdi Napoli"Federico II" Complesso Universitario di Monte Sant’Angelovia Cinthia80126 NapoliItaly School of Physics and Astronomy Yunnan UniversityKunming 650091China D´epartement de Physique Nucléaire et Corpusculaire Facultéde SciencesUniversitéde Genève24 Quai Ernest Ansermet1211 GenevaSwitzerland Institute of Frontier and Interdisciplinary Science Shandong UniversityQingdao 266237China Depar

The Large High Altitude Air Shower Observatory(LHAASO)has three sub-arrays,KM2A,WCDA,and *** flux variations of cosmic ray air showers were studied by analyzing the KM2A data during a thunderstorm on June 10,*** number of shower events that meet the trigger conditions increases significantly in atmospheric electric fields,with a maximum fractional increase of 20%.The variations in trigger rates(increases or decreases)were found to be strongly dependent on the primary zenith *** flux of secondary particles increased significantly,following a trend similar to that of shower *** better understand the observed behavior,Monte Carlo simulations were performed with CORSIKA and G4KM2A(a code based on GEANT4).We found that the experimental data(in saturated negative fields)were in good agreement with the simulations,assuming the presence of a uniform electric field of-700 V/cm with a thickness of 1500 m in the atmosphere above the observation *** to the acceleration/deceleration by the atmospheric electric field,the number of secondary particles with energy above the detector threshold was modified,resulting in the changes in shower detection rate.

关键词： thunderstorm cosmic rays extensive air showers LHAASO-KM2A

来源：评论

学校读者我要写书评

暂无评论

Modeling Fine-Grained Relations in Dynamic Space-Time Graphs for Video-Based Facial Expression Recognition

引用

IEEE Transactions on Affective computing 2025年

作者： Huang, Changqin Jiang, Fan Han, Zhongmei Huang, Xiaodi Wang, Shijin Zhu, Yanlai Jiang, Yunliang Hu, Bin Zhejiang Normal University Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Jinhua321004 China Charles Sturt University School of Computing Mathematics and Engineering AlburyNSW2640 Australia State Key Laboratory of Cognitive Intelligence Anhui Hefei230088 China Hangzhou Hikvision Digital Technology Co. Ltd Education Business Department Hangzhou310051 China Zhejiang Normal University School of Computer Science and Technology Jinhua321004 China Beijing Institute of Technology School of Medical Technology Beijing10081 China

Facial expressions in videos inherently mirror the dynamic nature of real-world facial events. Consequently, facial expression recognition (FER) should employ a dynamic graph-based representation to effectively capture the relational structure of facial expressions rather than relying on conventional grid or sequence methods. However, existing graph-based approaches have their limitations. Frame-level graph methods provide a coarse representation of the facial graph across time and space, while landmark-based graph methods need to introduce additional facial landmarks, resulting in a static graph structure. To address these challenges, we propose spatial-temporal relation-aware dynamic graph convolutional networks (ST-RDGCN). This fine-grained relation modeling approach enables the dynamic modeling of evolving facial expressions in videos through dynamic space-time graphs, eliminating the need for facial landmarks. ST-RDGCN encompasses three graph construction paradigms: dynamic independent space graph, dynamic joint space-time graph, and dynamic cross space-time graph. Furthermore, we propose a relation-aware space-time graph convolution (RSTG-Conv) operator to learn informative spatiotemporal correlations in dynamic space-time graphs. In extensive experimental evaluations, our ST-RDGCN demonstrates state-of-the-art performance on the five popular video-based FER datasets, achieving overall accuracy scores of 99.69%, 91.67%, 56.51%, 69.37%, and 49.03% on the CK+, Oulu-CASIA, AFEW, DFEW, and FERV39 k datasets, respectively. In particular, our ST-RDGCN outperforms the current best method by 3.6% in UAR on the most challenging FERV39 k dataset. Furthermore, our analysis reveals that the dynamic cross space-time graph scheme is the most effective among the three dynamic graph construction schemes. © 2010-2012 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Analysis of Text Mining Tools in Disease Prediction 20th

Analysis of Text Mining Tools in Disease Prediction

引用

20th International Conference on Hybrid Intelligent Systems, HIS 2020 and 12th World Congress on Nature and Biologically Inspired computing, NaBIC 2020

作者： Kumari, Shabnam Vani, V. Malik, Shaveta Tyagi, Amit Kumar Reddy, Sravanti SRMIST University ChennaiTamilnadu603203 India School of Computer Science and Engineering Vellore Institute of Technology ChennaiTamilnadu600127 India Terna Engineering College MumbaiMaharshtra India Center for Advanced Data Science Vellore Institute of Technology ChennaiTamilnadu600127 India VJIET HyderabadTelangana India

ISBN: (纸本)9783030730499

Due to rapid creation of digital data by Internet of Things devices or smart devices, many new modern mining strategies/techniques require to handle/analyse this large amount of data. Note that more than 90% of today’s data is in present (generated) unstructured or semi-structured data format (most of part of this data is being generated only in the past decade). The discovery of appropriate patterns and trends to analyse the text documents from this large big data (i.e., large volume of data) is a big issue. Text mining is a process of extracting interesting and non- trivial patterns from huge amount of text documents. There exist different techniques and tools to mine the text (also other data format) and discover valuable information for future prediction and decision making process. Basically, there are two terms used in making or extracting some relevant information from a data-set, i.e., prediction modelling, and text mining. Predictive models are often used to detect crimes and identify suspects, after the crime has taken place/to detect an email, how likely that it is spam. Similarly, text mining used in applications like digital libraries, academic research field, life science, social media, business intelligence, etc. Today’s different text mining techniques are available for analysing the text patterns and their mining process, some of them are included here as: document classification (text classification, document standardization), information retrieval (keyword search/querying and indexing), document clustering (phrase clustering), natural language processing (spelling correction, lemmatization, grammatical parsing, and word sense disambiguation), information extraction (relationship extraction/link analysis), and web mining (web link analysis), etc. This article discusses and analyse the text mining techniques and their applications in diverse fields of life. This work discusses about several use-cases, efficient algorithms like apriori algorithm, ass

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Outlier Processing for Disease Diagnosis in Real-World Medical Data

SSRN

引用

SSRN 2024年

作者： Li, Yucheng Li, Chengyun Ouyang, Xinyue Nie, Hu Ren, Yazhou Yue, Guang Pu, Xiaorong School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen China Emergency Department West China Hospital Sichuan University Chengdu China Department of Neonatology Chengdu Women’s and Children’s Central Hospital Chengdu China Tandon School of Engineering New York University New YorkNY United States

Objective: Machine learning has increasingly been applied to clinical diagnosis, providing valuable insights for rapid decision-making. However, the presence of outliers in the medical data can cause biased or inaccurate predictions, leading to misdiagnosis when applying machine learning models in real-world diagnostic environments. Proper handling of outliers is thus crucial in clinical diagnosis. This paper introduces a novel data preprocessing method to balance the sensitivity of machine learning models to outliers while mitigating their negative ***: In order to handle outlier instances, the method first employs the Mean Shift algorithm to detect outlier instances. Since this algorithm does not explicitly quantify the deviation of outliers from normal clusters, we define a metric called the Outlier Degree (OD) to measure this extent. Next, the influence of outlier instances is reduced by scaling the value of each feature in outlier instances based on their OD. Finally, the weight of each outlier instance is also increased based on its OD to preserve the model’s predictive ***: Three real-world medical datasets were preprocessed with the proposed method and subsequently used to train machine learning models separately. Experimental results on all three datasets indicate that our method effectively improve the model’s predictive ability for abnormal samples by an average of 41% without compromising predictive performance. Furthermore, it shows a 97.7% similarity with the commonly used preprocessing method in the feature importance ranking obtained from the machine learning ***: In the context of handling outlier instances in the real-world medical data, we proposed a novel preprocessing method. Our approach not only significantly enhances the prediction accuracy for outlier instances but also maintains the overall accuracy for the entire dataset. By enabling a more realistic appraisal of feature importance, our method effect

关键词： Adversarial machine learning

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：