检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Mao, Yulian Ye, Qingqing Du, Rong Wang, Qi Huang, Kai Hu, Haibo Department of Computer Science and Engineering Southern University of Science and Technology China Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Hong Kong School of Computer Science and Engineering Macau University of Science and Technology China

Item mining, a fundamental task for collecting statistical data from users, has raised increasing privacy concerns. To address these concerns, local differential privacy (LDP) was proposed as a privacy-preserving technique. Existing LDP item mining mechanisms primarily concentrate on global statistics, i.e., those from the entire dataset. Nevertheless, they fall short of user-tailored tasks such as personalized recommendations, whereas classwise statistics can improve task accuracy with fine-grained information. Meanwhile, the introduction of class labels brings new challenges. Label perturbation may result in invalid items for aggregation. To this end, we propose frameworks for multi-class item mining, along with two mechanisms: validity perturbation to reduce the impact of invalid data, and correlated perturbation to preserve the relationship between labels and items. We also apply these optimized methods to two multi-class item mining queries: frequency estimation and top-k item mining. Through theoretical analysis and extensive experiments, we verify the effectiveness and superiority of these methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

HomoMGC: Homophily-Enhanced Adaptive Graph Refinement for Multi-View Graph Clustering 24

HomoMGC: Homophily-Enhanced Adaptive Graph Refinement for Mu...

引用

24th IEEE International Conference on Data Mining, ICDM 2024

作者： Chen, Man-Sheng Cai, Xiao-Sha Wang, Chang-Dong Huang, Dong Chen, Min Guizani, Mohsen School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Sun Yat-sen University Zhuhai China College of Mathematics and Informatics South China Agricultural University Guangzhou China School of Computer Science and Engineering South China University of Technology Guangzhou China Pazhou Laboratory Guangzhou China Machine Learning Department Abu Dhabi United Arab Emirates

ISBN: (纸本)9798331506681

Due to the emergency of multi-view graph data, considerable attention is focused on the multi-view graph clustering. Although great efforts have been made in developing the multi-view graph clustering methods, most of them implicitly follow the homophily assumption, where the connected nodes with edges tend to be in the same category. As a matter of fact, such an ideal assumption is hard to be satisfied in the real-world graph data, and there are some heterogeneous edges connecting dissimilar nodes in graph. How to well consider the homophily and refine the noisy/heterogeneous edges in multi-view graph clustering still remains an under-explored challenge. Therefore, in this paper, we propose a Homophily-enhanced Adaptive Graph Refinement for Multi-view Graph Clustering (HomoMGC) method, where an adaptive graph refinement strategy is seamlessly designed. Specifically, a feature-oriented graph is constructed based on the shared feature, and an integrated graph is computed by averagely fusing all the input adjacent graphs. Then, the feature-oriented graph and integrated graph are stacked into a graph tensor with a low-rank tensor constraint, where a refined affinity probability matrix can be adaptively recovered from the integrated graph by considering multiple graph information as well as the semantics features. Extensive experiments on several benchmark datasets demonstrate the superiority of HomoMGC compared with the state-of-the-art graph clustering methods. For the code reproducibility, the source code of HomoMGC is public available at https://***/ManshengChen/Code-for-HomoMGc-master. © 2024 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Antenna Beam forming Technology Based Enhanced Metamaterial Superstrates 3

Antenna Beam forming Technology Based Enhanced Metamaterial ...

引用

3rd IEEE KhPI Week on Advanced Technology, KhPI Week 2022

作者： Bashar, Bashar S. Rhazali, Z.A. Elwi, Taha A. Misran, Halina Ismail, Marwa M. Mahdi, Maki Alanssari, Ali Ihsan Universiti Tenaga Nasional Al-Nisour University College Electrical & Electronic Engineering Department College of Engineering Kajang Malaysia Universiti Tenaga Nasional Electrical & Electronic Engineering Department College of Engineering Kajang Malaysia Al-Ma 'Moon University College Department of Communication Engineering Baghdad Iraq Universiti Tenaga Nasional Nanoarchitectonic Laboratory Department of Mechanical Engineering Kajang Malaysia Computer Technologies Engineering Al-Nisour University College Baghdad Iraq

ISBN: (数字)9798350399202

ISBN: (纸本)9798350399202

The proposed antenna system is designed for modern wireless communication technologies. Therefore, to match the modern applications, the proposed antenna is structured to provide multi-frequency bands with enhanced gain at the frequency band of interest. Consequently, the proposed antenna is consistent of two patches: The first, or the main patch, is a square patch layer is mounted on Taconic FR-30 substrate. The second patch is constructed as a meander ring with two stubs to increase the generated frequency bands. Nevertheless, the proposed patch is shaped as V-shape line to ensure antenna beam splitting at the desired frequency bands. The second patch is excited by the first patch by capacitive coupling;where, the first patch is excited by conduction with 50Ω discrete port. On the other hand, a metasurface layer is introduced to the proposed design mounted on the second antenna patch, as superstrate, to increase the antenna gain toward the bore-sight direction. Thus, it is found that the proposed antenna shows a maximum gain of 8dBi at 4.2GHz with maximum dimensions of 108× 108mm2. The proposed antenna operates at other frequency bands at 2.6GHz, 4.2GHz, and 5.6GHz with acceptable return losses of -16.8dB, -12.3dB and -30.6dB, sequentially. The antenna designed numerically using CST MWS software package. © 2022 IEEE.

关键词： Microstrip antennas

来源：评论

学校读者我要写书评

暂无评论

Encrypted Domain Secret Medical-Image Sharing with Secure Outsourcing Computation in IoT Environment

引用

IEEE Internet of Things Journal 2024年第2期11卷 2382-2393页

作者： Huang, Jingwang Cui, Qi Zhou, Zhili Yu, Keping Yang, Ching-Nung Choo, Kim-Kwang Raymond Institute of Artificial Intelligence and Blockchain Guangzhou University Guangzhou510006 China Nanjing University Information Science and Technology Engineering Research Center of Digital Forensics Ministry of Education Nanjing210044 China Nanyang Technological University School of Electrical and Electronic Engineering Jurong West639798 Singapore Guangzhou University Institute of Artificial Intelligence and Blockchain Guangzhou510006 China Hosei University Graduate School of Science and Engineering Tokyo184-8584 Japan National Dong Hwa University Department of Computer Science and Information Engineering Hualien974301 Taiwan The University of Texas at San Antonio Department of Information Systems and Cyber Security San AntonioTX78249 United States

In existing secret medical-image sharing (SMIS) schemes, to protect and manage secret medical-images (SMIs), the sharing and recovery of each SMI are implemented by local servers of medical institutions. However, since a lot of SMIs are produced by personal smart terminal devices in Internet of Things (IoT) environment, directly implementing the sharing and recovery processes will cause excessive communication and computing burden for those local servers, which makes the existing SMIS schemes not suitable for IoT environment. To address the above issue, we propose an encrypted domain SMIS (Enc-SMIS) scheme with secure outsourcing computation for protecting and managing medical images in IoT environment. In the proposed scheme, the medical images are first encrypted using fully homomorphic encryption (FHE) and then outsourced to a cloud server for generating a set of image shares. Subsequently, these shares are stored separately in different local servers of medical institutions. Furthermore, the recovery process is also outsourced to the cloud server when doctors need to observe the patients' medical images. Compared with the existing SMIS schemes, the proposed Enc-SMIS scheme alleviates the computing and communication burden on local servers significantly with secure outsourcing computation in the semi-honest model, and thus supports the storage and management of medical images well in IoT environment. © 2014 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Improving SVM Performance in Determining Cost and Kernel Parameter Values Through Grid Search

Improving SVM Performance in Determining Cost and Kernel Par...

引用

Technology Innovation and Its Applications (ICTIIA), International Conference on

作者： Visca Sylvia Maya Silvi Lydia Benny Benyamin Nasution Master of Informatics Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Department of Computer Engineering and Informatics Politeknik Negeri Medan Medan Indonesia

ISBN: (数字)9798350351613

ISBN: (纸本)9798350351620

The purpose of this study is to improve the performance of Support Vector Machine (SVM) algorithm in sentiment analysis of trainee reviews through parameter optimization using Grid Search. Trainee reviews were taken from the Vocational and Productivity Training Center (BBPVP) Medan, which is the context of this study. The method used includes collection and preprocessing of review data, followed by the application of SVM for sentiment analysis. Grid Search is used to optimize the cost and kernel parameters of SVM. The results show that after optimization, the resulting SVM model shows significant performance improvement compared to the model before optimization. Accuracy increased from 68.75% to 71.96%, with improvements in other metrics such as precision, recall, and F1 score. These findings suggest that Grid Search is an effective method to optimize SVM parameters in sentiment analysis, providing a more accurate evaluation of the effectiveness of training programs at BBPVP Medan. This research makes an important contribution by applying hyperparameter optimization to SVM and suggests the application of this method for similar analysis in the future.

关键词： Support vector machines Training Productivity Sentiment analysis Analytical models Accuracy Costs Reviews Kernel Optimization

来源：评论

学校读者我要写书评

暂无评论

MLBlock: Harnessing Machine Learning, Blockchain, and XAI for Smarter Land Valuation

MLBlock: Harnessing Machine Learning, Blockchain, and XAI fo...

引用

International Conference on computer and Information Technology (ICCIT)

作者： Alauddin Sabari Md Jakir Hossain Imran Hasan Abdullah All Ahhad Md Shafiqul Islam Feroza Naznin Md Zahidul Islam Department of Computer Science and Engineering Jahangirnagar University Savar Bangladesh Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh Department of Computer Science and Engineering Islamic University Kushtia Bangladesh Department of Tourism and Hospitality Management Islamic University Kushtia Bangladesh Department of Electrical and Electronic Engineering Islamic University Kushtia Bangladesh Department of Computer Science and Engineering Green University of Bangladesh Dhaka Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

Accurate and transparent land valuation is critical for sustainable urban planning, yet traditional methods often lack flexibility and reliability. This study presents ML-Block, a framework integrating blockchain, machine learning (ML), and Explainable AI (XAI) to address these challenges. The methodology begins with secure data validation through blockchain, ensuring tamper-proof and verifiable user data. Advanced ML techniques, including Reinforcement Learning (RL) and polynomial regression, enhance predictive accuracy by 20% over conventional approaches, achieving RMSE values between 200-300 USD and R 2 above 0.8. RL adds a crucial layer of adaptability, enabling the model to learn from dynamic market trends and adjust predictions in real time. XAI provides clear, interpretable insights, fostering trust among stakeholders such as governments, real estate firms, and community planners [22]. Interactive visualization tools, powered by Google Maps API, identify undervalued regions and economic trends, supporting equitable development. This framework demonstrates how secure data handling, adaptable models, and transparent predictions can bridge the gap between technological innovation and real-world applications, promoting informed decision-making across diverse stakeholders, governments, and real estate investors.

关键词： Adaptation models Accuracy Explainable AI Government Reinforcement learning Predictive models Market research Blockchains Stakeholders Cost accounting

来源：评论

学校读者我要写书评

暂无评论

Abridged Neat Key Instance: an Integrity Property for Digital Multimedia Asset of Non-fungible Token

Abridged Neat Key Instance: an Integrity Property for Digita...

引用

International Conference on informatics and Computing (ICIC)

作者： Fardani Annisa Damastuti Moch Fachri Nugrahardi Ramadhani Didit Prasetyo Aliridho Barakbah Mochamad Hariadi Electrical Engineering Department Institut Teknologi Sepuluh Nopember Surabaya Indonesia Informatics and Computer Engineering Dept Politeknik Elektronika Negeri Surabaya Surabaya Indonesia Computer Engineering Department Institut Teknologi Sepuluh Nopember Surabaya Indonesia

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

The non-fungible token (NFT) is a record used to ensure the privilege and ownership of a certain digital asset with a distinctive digital identifier in a blockchain. In digital-multimedia assets i.e. images, videos, audio, etc. NFTs generally retain references to the properties of the asset. Due to the nature of blockchain technology, NFT is oftentimes associated with its immutability. NFTs that represent digital multimedia assets may utilize blockchain-based file servers, but oftentimes time the associated file is stored off-chain. This makes the assets themselves vulnerable to link rot and causes the NFT owner to lose access to their assets since the off-chain storageis not immutable like the NFT. To preserve the integrity of the NFT’s associated digital assets, we introduce Abridged Neat Key Instance (ANKI). ANKI is a property embedded inside NFT that contains the seed number of the digital multimedia asset to be procedurally generated. We are taking advantage of Procedural Content Generation (PCG) technology to reproduce the digital multimedia asset presented by the information available inside the NFT itself. By leveraging Procedural Content Generation(PCG) technology, our approach can regenerate the exact digital asset directly from the information encoded within the *** our experiments, we successfully recreated music files using the ANKI seed and a PCG engine, verifying their accuracy by comparing the MD5 and SHA-512 checksums of the generated files with those of the original NFT assets. All 50 generated musicfiles produced identical checksums to their original counterparts,confirming the integrity of our method.

关键词： Procedural generation Accuracy Streaming media File servers Nonfungible tokens Reliability informatics Engines Phonocardiography Videos

来源：评论

学校读者我要写书评

暂无评论

Solar powered high gain DC-DC converter with FPGA controller for portable devices

引用

e-Prime - Advances in Electrical engineering, electronics and Energy 2024年 9卷

作者： Nanjappan, Vijayalakshmi Ramasamy, Suganthi Gatto, Gianluca Kumar, Amit Department of Computer Science and Engineering (Data Science) Dayananda Sagar College of Engineering Department of Electrical and Electronic Engineering University of Cagliari

A solar-powered converter design is necessary for portable devices with increased gain and reduced ripple in overall operation. This research presents a photovoltaic-powered Field Programmable Gate Array (FPGA) based on increased gain multiple output converter design and analysis. The dynamic panel input makes it difficult to operate the load. To control and make the input static to satisfy the demand, perturb and observe with a load balancing algorithm technique are used. The converter gained output is high, and batteries are used to balance the loads when solar irradiance is low. Simulation results were carried out with the presented converter circuit that can be operated with a 12 V supply as input from a renewable power source. The output gain ratio of 14 to a minimum of 40 % duty cycle operating at a switching frequency of 20 kHz has been achieved. The proposed methodology is transferred to hardware by connecting with the reconfigurable FPGA Spartan-6 development board to manage the dynamic load control system's complex logic and high processing ability. The overall performance is compared with various pre-existing systems, tabulations are made with the analysis, and experimental results are also illustrated at the end. © 2024 The Author(s)

关键词： FPGA High Gain Dual Output (HGDO) converter Load balancing algorithm MPPT algorithm Solar photo-voltaic (PV) panel

来源：评论

学校读者我要写书评

暂无评论

YA-DA: YAng-Based DAta Model for Fine-Grained IIoT Air Quality Monitoring

YA-DA: YAng-Based DAta Model for Fine-Grained IIoT Air Quali...

引用

2022 IEEE GLOBECOM Workshops, GC Wkshps 2022

作者： Yigit, Yagmur Huseynov, Khayal Ahmadi, Hamed Canberk, Berk Istanbul Technical University Department of Computer Engineering Turkey University of York Department of Electronic Engineering United Kingdom Istanbul Technical University Department of Artificial Intelligence and Data Engineering Turkey Edinburgh Napier University School of Computing Engineering and the Build Environment United Kingdom

ISBN: (纸本)9781665459754

With the development of industrialization, air pollution is also steadily on the rise since both industrial and daily activities generate a massive amount of air pollution. Since decreasing air pollution is critical for citizens' health and well-being, air pollution monitoring is becoming an essential topic. Industrial Internet of Things (IIoT) research focuses on this crucial area. Several attempts already exist for air pollution monitoring. However, none of them are improving the performance of IoT data collection at the desired level. Inspired by the genuine Yet Another Next Generation (YANG) data model, we propose a YAng-based DAta model (YA-DA) to improve the performance of IIoT data collection. Moreover, by taking advantage of digital twin (DT) technology, we propose a DT-enabled fine-grained IIoT air quality monitoring system using YA-DA. As a result, DT synchronization becomes fine-grained. In turn, we improve the performance of IIoT data collection resulting in lower round-trip time (RTT), higher DT synchronization, and lower DT latency. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Intelligent QV2X Routing for Traffic Management in Consumer IoV Using STGNN and Reinforcement Learning

引用

IEEE Transactions on Consumer electronics 2025年

作者： Jamal, Syed Saqib Muhammad, Afaq Song, Wang-Cheol Jeju National University Department of Electronic Engineering Jeju Korea Republic of College of Computing and Mathematics Computer Engineering Department and Interdisciplinary Research Center for Intelligent Secure Systems Dhahran Saudi Arabia

In the Consumer Internet of Vehicles (CIoV), reliable and timely data communication is essential for enhancing driver experience and safety. This paper introduces an innovative QV2X routing strategy that uses Spatio-Temporal Graph Neural Networks (STGNN) and Q-learning to optimize packet traffic in CIoV. By predicting network conditions and adapting to real-time data flows, our approach directly addresses consumer needs for efficient data transmission, reduced communication delays, and improved infotainment access. The integration of predictive models with adaptive learning mechanisms not only optimizes packet delivery but also minimizes latency and packet loss, critical for consumer applications like real-time navigation assistance and hazard warnings. Our key contribution is a dynamic packet traffic management system designed for consumer use, enhancing network reliability and efficiency for everyday vehicle users. Experimental results validate that our model surpasses existing benchmarks by improving packet delivery ratios by up to 15% and reducing end-to-end delays by up to 20% in urban traffic scenarios. This advancement demonstrates our strategy's effectiveness in enriching consumer experiences and safety in vehicular communications. © 1975-2011 IEEE.

关键词： Packet loss

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：