检索结果-内蒙古大学图书馆

A Comparative Study of Validation Methods for Sensor-Based Human Activity Recognition Using Deep Learning Models

A Comparative Study of Validation Methods for Sensor-Based H...

International ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications Engineering (ECTI-NCON)

作者： Sakorn Mekruksavanich Narit Hnoohom Wikanda Phaphan Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Department of Computer Engineering Faculty of Engineering Image Information and Intelligence Laboratory Mahidol University Nakhon Pathom Thailand Department of Applied Statistics Faculty of Applied Science Research Group in Statistical Learning and Inference King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Mathematics Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543273

ISBN: (纸本)9798331543280

With the rise of wearable sensors and smart devices, human activity recognition (HAR) has become a vital research area in ubiquitous computing. Although many studies report high accuracy using k-fold cross-validation, these results often do not reflect actual generalization interpretation due to subject-dependent data leakage, where models test on activities from the subjects they were trained. This study compares traditional k-fold cross-validation with leave-one-subject-out (LOSO) validation using the WISDM dataset, highlighting the importance of proper validation techniques in HAR systems. We implemented and evaluated five advanced deep learning models – convolutional neural network (CNN), long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and bidirectional GRU (BiGRU) – on windowed raw sensor data. Our experiments showed significant differences between validation methods. The BiGRU model achieved 97.91% accuracy with k-fold cross-validation and 98.02% with LOSO validation, while the CNN model achieved only 92.55% and 93.44%, respectively. These results underscore the impact of both model architecture and validation approach on performance. Our findings stress the need for subject-independent validation strategies like LOSO to develop truly generalizable HAR systems.

关键词： Deep learning Accuracy Bidirectional long short term memory Ubiquitous computing Data models Human activity recognition Convolutional neural networks Smart devices Wearable sensors Stress

来源：评论

学校读者我要写书评

暂无评论

Orthopedic Walker Fall Detection and Motion Classification Using Bidirectional Gated Recurrent Unit Neural Network

Orthopedic Walker Fall Detection and Motion Classification U...

引用

International ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications Engineering (ECTI-NCON)

作者： Sakorn Mekruksavanich Narit Hnoohom Wikanda Phaphan Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of Phayao Thailand Department of Computer Engineering Faculty of Engineering Image Information and Intelligence Laboratory Mahidol University Nakhon Pathom Thailand Department of Applied Statistics Faculty of Applied Science Research Group in Statistical Learning and Inference King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Mathematics Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543273

ISBN: (纸本)9798331543280

Accurate fall detection for orthopedic walker users is essential for timely medical intervention and enhancing safety for elderly and mobility-impaired individuals. This paper introduces a new method using a bidirectional gated recurrent unit (BiGRU) neural network to detect falls and classify motion patterns in walker usage. We use the Walker dataset, which includes inertial measurement unit sensor data for four motion classes: idle, motion, step, and fall. The dataset consists of 6-axis IMU readings (3-axis accelerometer and 3-axis gyroscope) from sensors mounted on orthopedic walkers, with around 620 samples per class. Our BiGRU model leverages temporal dependencies in both forward and backward directions to improve classification accuracy. We assess the model’s performance in two scenarios: binary classification (fall vs. non-fall) and multi-class classification of all four motion types. The proposed architecture shows strong performance, achieving 99.79% accuracy and a 99.73% F1-score in binary classification, and 98.51% accuracy and a 98.50% F1-score in multi-class classification. It outperforms traditional deep learning models like CNN, LSTM, and GRU. The experimental results confirm the effectiveness of bidirectional processing in capturing temporal motion patterns, indicating significant potential for realtime fall detection in walker-assisted mobility. The high precision and recall values in both scenarios demonstrate the model’s reliability for practical healthcare monitoring applications.

关键词： Deep learning Accuracy Measurement units Neural networks Medical services Safety Reliability Fall detection Older adults Monitoring

来源：评论

学校读者我要写书评

暂无评论

Implementation and Evaluation of 0.6 µm CMOS Complex RCPF for Accurate Frequency Response Measurement

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, information and systems 2025年第1期145卷 25-37页

作者： Sato, Lina Fukagawa, Kanta Shouno, Kazuhiro Tanimoto, Hiroshi Muto, Cosy Moriyama, Seijiro Takahashi, Chikau Yoshino, Michitaka Graduate School of Science and Technology Degree Programs in Systems and Information Engineering Master’s Program in Computer Science University of Tsukuba Japan Division of Information Engineering University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8573 Japan Kitami Institute of Technology 165 Koen-cho Hokkaido Kitami090-8507 Japan Faculty of Education Nagasaki University 1-14 Bunkyo-machi Nagasaki852-8521 Japan Anagix Corporation 3-22-27 Numama Kanagawa Zushi249-0004 Japan Takamori Corporation Japan Research Center for Micro-Nano Technology Hosei University 3-11-15 Midori-cho Koganei Tokyo184-0003 Japan

This paper describes the implementation and evaluation of an RC polyphase filter (RCPF) and circuitry for measuring its frequency characteristics. The integrated circuit is fabricated on a 0.6 µm CMOS process and its supply voltage is 5 V. The integrated circuit includes a filter under test (FUT), a four-phase square wave generator, several analog switches and differential amplifiers to amplify the high-impedance signals of the RCPF. This FUT is a third-order complex RCPF whose passband is 8 − 40 MHz. This paper describes the design of these circuits in detail. This integrated circuit can select two measurement methods by means of external control signals. The first method uses a four-phase square wave. The frequency characteristics are measured by using an on-chip four-phase square wave generator driven by an external clock generator and by a spectrum analyzer tuned to the fundamental frequency. The second method uses an external network analyzer. Furthermore, this integrated circuit is equipped with a calibration circuit to measure the frequency characteristics of the circuitry except FUT by passing through the input / output signals of the FUT. As a result, the frequency characteristics of the FUT itself can be accurately measured. The effectiveness is confirmed through evaluation of the fabricated integrated circuit. © 2025 The Institute of Electrical Engineers of Japan.

关键词： Differential amplifiers

来源：评论

学校读者我要写书评

暂无评论

Secure and fast mobility handover scheme for IoMT in 5 G and future 6 G networks

引用

Alexandria Engineering Journal 2025年 128卷 127-143页

作者： Shayla Islam S.M. Topazal Mohammad Kamrul Hasan Raenu AL Kolandaisamy Huda Saleh Abbas Nguyen Vo Rahul Thakkar Muhammad Attique Khan Deepak Gupta Dina Abdulaziz AlHammadi Institute of Computer Science and Digital Innovation UCSI University Kuala Lumpur 56000 Malaysia Center for Cyber Security Faculty of Information Science and Technology the National University of Malaysia 43600 Bangi Selangor Malaysia Department of computer science College of Computer Science and Engineering Taibah University Madina Saudi Arabia Victorian Institute of Technology Melbourne Australia Center of AI College of Computer Engineering and Science Prince Mohammad Bin Fahd University Al-Khobar Saudi Arabia Maharaja Agrasen Institute of Technology Delhi India Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O.Box 84428 Riyadh 11671 Saudi Arabia

The emergence of 5 G and 6 G networks promises significant advancements in the Internet of Medical Things (IoMT) by enabling real-time medical data transmission and continuous connectivity for mobile healthcare devices. However, traditional Handover (HO) mechanisms face latency, security, energy consumption, and scalability challenges when supporting fast-moving and dense IoMT environments. This paper presents a secure and fast mobility handover scheme for IoMT in 5 G and future 6 G networks, incorporating a predictive algorithm, Blockchain-Based (BC-B) decentralized authentication mechanism, and AI-driven anomaly detection. The predictive algorithm anticipates device movement and pre-allocates resources at the target Base Station (BS), reducing HO latency by 20–30 % in 5 G and up to 40 % in 6 G. Meanwhile, blockchain-based authentication ensures tamper-proof and decentralized security, reducing vulnerability to cyberattacks by 90 % compared to traditional methods. Additionally, the energy consumption during HO events is reduced by 20–35 %, dropping from 15 mJ in traditional schemes to 12 mJ in 5 G and further to 10 mJ in 6 G. The scheme also incorporates AI-driven anomaly detection, achieving an accuracy of 96.7 %, ensuring proactive identification and mitigation of potential security threats. The analyzed scheme maintains consistent throughput with less than 5 % reduction and scales effectively for up to 300 devices per cell. The simulation results demonstrate significant improvements across key performance metrics, including latency, security, energy efficiency, and scalability, making this approach highly suitable for critical IoMT applications such as telesurgery, remote patient monitoring, and innovative healthcare environments. These advancements position the analyzed framework as a cornerstone for next-generation (NG) healthcare networks.

关键词： 4G Fourth-Generation 5G Fifth-Generation 6G Sixth-Generation AR Augmented Reality NG Next-Generation IoT Internet of Things IoMT Internet of Medical Things TPBs Terabit Per Second BC-B Blockchain-Based URLLC Ultra-Reliable Low Latency Communications EMBB Enhanced Mobile Broadband MMTC Massive Machine-Type Communications AI Artificial Intelligence MIoT Massive Internet of Things DoS Denial-of-Service MIMO Multiple-Input Multiple-Output HOBP Handover Blocking Probability HOSR Handover Success Rate ADA Anomaly Detection Accuracy SLA Service Level Agreement VR Virtual Reality HO Handover BC Blockchain Ms millisecond KM kilometer THz Terahertz B5G Beyond-5G ML Machine Learning DL Deep Learning EC Energy Consumption BS Base Station ECC Elliptic Curve Cryptography QS Quality of Server E2E End-to-End MJ megaJoule XR Extended Reality D2D Device to Device PLR Packet Loss Ratio Handover Internet of Medical Things (IoMT) 5G networks 6G technology Security concerns Blockchain Digital healthcare Internet of Things Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Prevalence of Menstrual Dysfunction and Hormonal Contraceptive Use Among Elite Female Athletes from Different Sports in Germany

引用

Sports Medicine - Open 2025年第1期11卷 1-16页

作者： Kirschbaum, Elisabeth M. Fischer, Katharina Speiser, Dorothee Lautenbach, Franziska Schwenkreis, Friedemann Dathan-Stumpf, Anne Legerlotz, Kirsten Movement Biomechanics Institute of Sport Science Humboldt-Universität zu Berlin Berlin Germany Research Group Elite Female Athletes Institute for Applied Training Science Leipzig Germany Sports Psychology Faculty of Sports Science University of Leipzig Leipzig Germany Department of Gynecology with Breast Center Charité - Universitätsmedizin Berlin Berlin Germany Sports Psychology Institute of Sport Science Humboldt-Universität zu Berlin Berlin Germany Business Information Systems Baden-Wuerttemberg Cooperative State University Stuttgart Stuttgart Germany Department of Obstetrics University Hospital of Leipzig Leipzig Germany Department of Movement and Training Science Institute of Sport Science University of Wuppertal Wuppertal Germany

Background: While a regular menstrual cycle is an indicator of good health, menstrual dysfunction (MD) and wrong beliefs regarding hormonal contraceptives (HC) are quite common among elite female athletes and threaten their health. This study aimed to (1) identify the prevalence of current and lifetime MD in various sports disciplines, (2) investigate variables that are associated with the prevalence of MD, (3) study the current practice of HC use among elite German female athletes. Methods: 584 German elite female athletes (mean 20.7 ± 4.9 years) from 64 different sports completed an online questionnaire to assess gynecological health characteristics, history of MD, and the use of HC. Results: Sixty-nine percent of athletes not using HC reported a regular menstrual cycle, while oligomenorrhea was currently reported in 13%, secondary amenorrhea in 8%, primary amenorrhea in 2% and polymenorrhea in 8%. The current prevalence of primary amenorrhea differed between sports disciplines (p = 0.002), while oligomenorrhea (p = 0.828) and secondary amenorrhea (p = 0.848) did not. The lifetime prevalence of primary amenorrhea (10%) and oligomenorrhea (74%) differed significantly between sports disciplines (p < 0.001 and p = 0.001), while secondary amenorrhea (40%) did not (p = 0.298). The current and lifetime prevalence of primary amenorrhea was higher in aesthetic sports disciplines, while the lifetime prevalence of oligomenorrhea was higher in endurance disciplines. Factors associated with lower prevalences of MD were menstrual cycle tracking (p < 0.001), higher gynecological age (p < 0.001), regular gynecological health screenings (p = 0.008), and a diagnosed eating disorder (p = 0.037). Twenty-nine percent of these elite athletes used HC, of whom 15% claimed to use HC as a treatment for MD. Conclusion: Elite female athletes from a variety of sports disciplines, not just from endurance and aesthetic sports, are at high risk of developing MD. Given the high percentage of ath

关键词： Amenorrhea Gynecological health Menstrual cycle Oligomenorrhea Prevalence Sports disciplines Women

来源：评论

学校读者我要写书评

暂无评论

A novel pythonic paradigm for image encryption using axis-aligned bounding boxes

引用

Scientific Reports 2025年第1期15卷 1-27页

作者： Banga, Abdulbasid Abbas, Akifa Ali, Danish Innab, Nisreen Alluhaidan, Ala Saleh Iqbal, Nadeem Diab, Hossam College of Computing and Informatics (CCI) Saudi Electronic University Riyadh 11673 Saudi Arabia School of Computing Bath Spa University Academic Center Ras Ul Khaima United Arab Emirates Department of Computer Science and Information Systems College of Applied Sciences AlMaarefa University Riyadh 13713 Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh 11671 Saudi Arabia Department of Computer Science & IT The University of Lahore Lahore 54000 Pakistan Math and Computer Science Department Faculty of Science Menoufia University Menoufia Shibin El Kom 32511 Egypt Computer Science Department Applied College Taibah University Madinah 41477 Saudi Arabia

In the digital age, images permeate every facet of our lives, often carrying critical information for organizations, institutions, and even nation-states. Ensuring their security against unauthorized access is paramount. This research introduces a novel image encryption algorithm designed to safeguard the integrity and confidentiality of sensitive gray-scale digital images. The algorithm leverages the theory of axis-aligned bounding boxes, translating the input image into a 3D representation. Within this 3D space, two identically sized boxes are generated and assessed for overlap. If the boxes do not overlap, the pixels within them are swapped. This pixel-swapping process, guided by random numbers generated from a 5D multi-wing hyper-chaotic map, is repeated numerous times to infuse confusion into the image. To further enhance security, diffusion effects are introduced by performing an XoR operation between the confused image and random numbers provided by the piece-wise linear chaotic map. This study employs private key cryptography and utilizes four gray-scale images to validate the feasibility and effectiveness of the proposed method. Simulation has been carried out in the Pythonic ecosystem. So, the algorithms presented in this study are designed to closely resemble Python code. Comprehensive validation metrics attest to the robustness of the cipher, achieving an information entropy of 7.99985 and a computational speed of 0.3987 seconds. These results underscore the potential of this encryption approach for practical, real-world applications. These applications span military, diplomacy & government, commerce, showbiz, industry, and social life etc. © The Author(s) 2025.

关键词： Chaotic map Non-linearity Random numbers S-Box Smart cities Wireless communication security

来源：评论

学校读者我要写书评

暂无评论

Correction: Divine Religions algorithm: a novel social-inspired metaheuristic algorithm for engineering and continuous optimization problems

引用

Cluster Computing 2025年第5期28卷 1-2页

作者： Mozhdehi, Ali Toufanzadeh Khodadadi, Nima Aboutalebi, Mohaddeseh El-kenawy, El-Sayed M. Hussien, Abdelazim G. Zhao, Weiguo Nadimi-Shahraki, Mohammad H. Mirjalili, Seyedali Faculty of Computer and Information Technology Engineering Qazvin Branch Islamic Azad University Qazvin Iran Department of Civil Architectural and Environmental Engineering University of Miami Coral Gables USA Department of Computer Engineering Azad University of Lahijan Lahijan Iran School of ICT Faculty of Engineering Design and Information & Communications Technology (EDICT) Bahrain Polytechnic Isa Town Bahrain Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer and Information Science Linköping University Linköping Sweden Faculty of Science Fayoum University Fayoum Egypt School of Water Conservancy and Hydropower Handan China Faculty of Computer Engineering Najafabad Branch Islamic Azad University Najafabad Iran Centre for Artificial Intelligence Research and Optimization Torrens University Australia Fortitude Valley Australia University Research and Innovation Center (EKIK) Obuda University Budapest Hungary

来源：评论

学校读者我要写书评

暂无评论

Experimental implementation of chaos-based video encryption using visible light communication technology

引用

applied Optics 2025年第9期64卷 C101-C118页

作者： Fotso, Sorel Bagio Nono Mbé, Jimmi Hervé Talla Takotue, Jean Ernest Takougang, Armand Cyrille Nzeukou Ndjiongue, Alain Richard Research Unit of Condensed Matter Electronics and Signal Processing Department of Physics University of Dschang P.O. Box 67 Dschang Cameroon Research Unit of Automation and Applied Computer Department of Electrical Engineering IUT-FV Bandjoun University of Dschang P.O. Box: 134 Bandjoun Cameroon Laboratory of Industrial Systems and Environmental Engineering Fotso Victor University Institute of Technology University of Dschang P.O. Box 134 Bandjoun Cameroon School of Electrical and Information Engineering Faculty of Engineering and the Built Environment University of the Witwatersrand Johannesburg South Africa

Simulations are commonly used to develop and evaluate video encryption algorithms. Although these approaches are useful for demonstrating theoretical feasibility and algorithm performance, they neglect practical challenges and real-world communication conditions. This oversight creates a critical gap in evaluating their effectiveness and security in practical applications. In this paper, we describe a novel, to the best of our knowledge, video encryption scheme that employs a modified chaotic Colpitts oscillator, a customized Josephus problem, and ribonucleic acid (RNA) operations, and is implemented in visible light communication (VLC) environment. The modified Colpitts oscillator reveals significant phenomena, the most prominent for this study being chaos. The encryption scheme involves block scrambling and pixel-level permutation employing a customized Josephus problem and a column and row shifting technique. Diffusion is then achieved through a custom Josephus problem-oriented RNA operation combined with basic RNA operations and cipher block chaining (CBC). Based on the results, we found that the customized Josephus problem-based permutation performed more efficiently than traditional methods, whereas the column and row shifting permutation was more robust. By eliminating key sequence coding and item-to-item operations, the proposed RNA operation reduces computational overhead. This video encryption scheme is proven to be effective and resilient at securing video data transmitted over the VLC channel, and it constitutes a significant advancement in areas such as surveillance, medical imaging, and military communication requiring robust secured video data. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Joint Hybrid Beamforming and RIS Phase Shift Design for RIS-Enabled Mmwave ISAC System

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Wang, Lu Abanto-Leon, Luis F. Asadi, Arash Ruhr University Bochum Faculty of Electrical Engineering and Information Technology Bochum Germany Technical University of Darmstadt Department of Computer Science Darmstadt64289 Germany TU Delft Embedded Systems Group DelftCD 2628 Netherlands

Empowering cellular networks with augmented sensing capabilities is a key research area in sixth generation (6 G) communication systems. Recently, we have witnessed a plethora of efforts to devise solutions that integrate sensing capabilities into communication systems, i.e., integrated sensing and communication (ISAC), especially at millimeter-wave (mmWave) frequencies with large bandwidths. Despite the challenges posed by severe path loss and blockage at mmWave bands, this work incorporates reconfigurable intelligent surfaces (RISs) into ISAC systems to enhance both sensing and communication. To comply with the waveform utilized in current cellular systems, this paper studies mmWave orthogonal frequency-division multiplexing (OFDM) ISAC systems in the presence of RISs. Specifically, we jointly design the hybrid beamforming and RIS phase shifts to guarantee the sensing functionalities via minimizing the beampattern mean squared error at RIS, subject to signal-to-interference-plus-noise (SINR) and power constraints. The non-convexity of the investigated problem poses a challenge which we address by proposing a solution based on the penalty method and manifold-based alternating direction method of multipliers (ADMM). Simulation results demonstrate that both sensing and communication capabilities improve when the RIS is adequately designed. In addition, we discuss the tradeoff between sensing and communication. © 2025 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

What Drives the Use of Generative Artificial Intelligence to Promote Educational Sustainability? Evidence from SEM-ANN Approach

引用

TechTrends 2025年 1-15页

作者： Arpaci, Ibrahim Al-Emran, Mostafa Al-Qaysi, Noor Al-Sharafi, Mohammed A. Management Information Systems College of Business Administration Gulf University for Science and Technology Mishref Kuwait Department of Software Engineering Faculty of Engineering and Natural Sciences Bandirma Onyedi Eylul University Balikesir Turkey Department of Computer Science and Engineering College of Informatics Korea University Seoul 02841 South Korea Faculty of Engineering & IT The British University in Dubai Dubai United Arab Emirates Engineering Technical College Al-Bayan University Baghdad Iraq Information and Communication Technology Research Group Scientific Research Center Al-Ayen University Thi-Qar Iraq IRC for Finance and Digital Economy KFUPM Business School King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia

The literature on generative “Artificial Intelligence” (AI) in education primarily focuses on its immediate benefits and applications, such as personalized learning, student engagement, and content generation. However, there is a notable absence of empirical research concerning the holistic use of generative AI within educational institutions and its long-term impact on educational sustainability. This study investigates the factors that predict the use of generative AI and its subsequent influence on educational sustainability. This study enhanced the extended “Unified Theory of Acceptance and Use of Technology” (UTAUT-2) by including personal innovativeness as an external variable and educational sustainability as an outcome. A hybrid methodology, integrating “Structural Equation Modeling” (SEM) and “Artificial Neural Network” (ANN), was used to evaluate the research model using data collected from 1,011 university students. The SEM analysis confirmed all hypotheses. Specifically, a positive relationship was found between use behavior and educational sustainability. These results show that the combined variables collectively account for 63% and 66% of the variance in use behavior and educational sustainability, respectively. The sensitivity analysis identified habit as the most important predictor of use behavior. The findings offer both theoretically important and practically valuable implications for designing user-centered AI integration in education. © Association for Educational Communications & Technology 2025.

关键词： Artificial intelligence Educational sustainability SEM-ANN UTAUT-2

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：