检索结果-内蒙古大学图书馆

6th international conference on Mobile computing and Sustainable Informatics, ICMCSI 2025

作者： Langote, Meher Zade, Nikita Gundewar, Swapnil Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Sawangi India Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Sawangi India

ISBN: (纸本)9798331522667

A key difficulty of dealing with imbalanced datasets is that machine learning models are trained to favor the majority class and therefore perform poorly when it comes to a minority class classification. In this paper, we consider the following methods of tackling the issue of the over-representation of a class;random oversampling, undersampling, SMOTE, cost-sensitive learning, and ensemble methods. Comparing them, we assess the performance of each of these techniques within different classifiers. Techniques including SMOTE together with combined methods including Random Forests also show higher capacity in minority class predictions. However, problems such as overfitting and the increase in the computational load are not escapable yet. We briefly recap the strengths and weaknesses of each approach and propose potential refinements including a combination of both methods and dynamic resampling methods to serve as the next steps toward improving the model. Thereby, our results draw attention to the necessity of accurate methods for handling the class imbalance, which will further yield more accurate and fair machine learning solutions across a variety of applications. © 2025 ieee.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Deep Energy Optimization in IRS-Assisted UAV-Based Edge computing Systems

引用

ieee TRANSACTIONS ON MOBILE computing 2025年第1期24卷 449-465页

作者： Wu, Jianqiu Yu, Zhongyi Guo, Jianxiong Tang, Zhiqing Wang, Tian Jia, Weijia BNU HKBU United Int Coll Dept Comp Sci Guangdong Key Lab AI & Multimodal Data Proc Zhuhai 519087 Peoples R China Beijing Normal Univ Adv Inst Nat Sci Zhuhai 519087 Peoples R China

Integrating wireless-powered Mobile Edge computing (MEC) with Unmanned Aerial Vehicles (UAVs) leverages computation offloading services for mobile devices, significantly enhancing the mobility and control of MEC networks. However, current research has not focused on customizing system designs for Terahertz (THz) communication networks. When dealing with THz communication, one must account for blockage vulnerability due to severe THz wave propagation attenuation and insufficient diffraction. The Intelligent Reflecting Surface (IRS) can effectively address these limitations in the model, enhancing spectrum efficiency and coverage capabilities while reducing blockage vulnerability in THz networks. In this paper, we introduce an upgraded MEC system that integrates IRS and UAVs into THz communication networks, focusing on a binary offloading policy for studying the computation offloading problem. Our primary objective is to optimize the energy consumption of both UAVs and User Electronic Devices, alongside refining the phase shift of the IRS reflector. The problem is a Mixed Integer Non-Linear Programming problem known as NP-hard. To tackle this challenge, we propose a two-stage deep learning-based optimization framework named Iterative Order-Preserving Policy Optimization (IOPO). Unlike exhaustive search methods, IOPO continually updates offloading decisions through an order-preserving quantization method, thereby accelerating convergence and reducing computational complexity, especially when handling complex problems with extensive solution spaces. The numerical results demonstrate that the proposed algorithm significantly improves energy efficiency and achieves near-optimal performance compared to benchmark methods.

关键词： Terahertz communications Autonomous aerial vehicles Optimization Resource management Servers computational modeling Costs Mobile edge computing deep learning unmanned aerial vehicles intelligent reflective surface terahertz communications

来源：评论

学校读者我要写书评

暂无评论

research on human pose and action detection algorithm based on YOLOv8 2

Research on human pose and action detection algorithm based ...

引用

2nd international conference on Big Data, computational intelligence, and Applications, BDCIA 2024

作者： Cheng, Weizhong Wang, Xuefei School of Information Engineering Suihua University Heilongjiang Suihua China School of Electrical Engineering Suihua University Heilongjiang Suihua China

ISBN: (纸本)9781510689053

Human pose and action detection technology has significant applications in areas such as smart security, sports monitoring, and human-computer interaction. The development of deep learning has driven the demand for real-time and efficient detection algorithms in this domain. Although existing human action detection algorithms have improved accuracy, their model complexity and computational demands hinder practical use in portable devices and edge computing platforms. To address this, the paper presents a lightweight human pose and action detection algorithm based on the YOLOv8 framework, designed to meet the high-precision, low-latency needs of edge computing and portable devices. In the feature extraction phase, GhostNet's lightweight structure is used to reduce model parameters, while the CBAM attention mechanism, applied in the feature fusion phase, enhances the model's attention to critical features. This approach significantly decreases computational load while maintaining high accuracy. Experimental results indicate that the algorithm achieves a real-time detection rate exceeding 40 frames per second on edge computing platforms, demonstrating high accuracy and robustness across various human action scenarios. This offers strong technical support for human pose detection in smart security and wearable devices. © 2025 SPIE.

关键词： Portable equipment

来源：评论

学校读者我要写书评

暂无评论

Collaborative and Integrated Platform to Support Distributed Manufacturing System Using a Service-Oriented Approach Based on Cloud computing Paradigm

Collaborative and Integrated Platform to Support Distributed...

引用

2025 ieee international conference on computational, Communication and Information Technology, ICCCIT 2025

作者： Nainwal, Ankita Sharma, Vishal Varshney, Neeraj Shirish Boob, Nandini Reddy, N.V. Uma Reddy, K. Jyothsna Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Lovely Professional University Phagwara India GLA University Department of Computer Engineering and Applications Mathura India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India New Horizon College of Engineering Department of Artificial Intelligence & Machine Learning Bangalore India MLR Institute of Technology Department of CSE-AI&ML Telangana Hyderabad India

ISBN: (纸本)9798331512965

Increasing interest in distributed manufacturing systems is a result of the dynamic nature of today's business environment and with that comes the popularity of their use. This has given rise in the interest in distributed manufacturing systems. The indirect consequence of this has led to much higher use of distributed manufacturing systems. A large number of production processes, dispersed across a multitude of locations geographically separate, must be controlled and integrated in order to achieve production agility, flexibility and efficiency of costs. In our most recent project, we developed an integrated, collaborative manufacturing platform, the centerpiece of which was LAYMOD. To address the issues posed by such systems, this research presents a collateral and integrated platform based on a service oriented approach that can operate within the cloud computing paradigm. These systems present problems which the study is conducted in order to solve. Utilising the features of cloud computing, it aims to serve as a platform in solving process coordination and hence improving efficiency and scalability of distant manufacturing processes and potential real time communications among various stake holders. Furthermore, statistical research on the rates of platform module adoption in different settings provides specifics of (a) use patterns of some platform modules and (b) what capabilities are provided by some platform modules. When extrapolated to a wider size, our work is applied towards the creation of collaborative and integrated platforms for a number of the various manufacturing processes which are currently in use. © 2025 ieee.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Security of Healthcare Data in Cloud computing Environments 2

Enhancing the Security of Healthcare Data in Cloud Computing...

引用

2nd international conference on computational intelligence, Communication Technology and Networking, CICTN 2025

作者： Sajwan, Himani Kumari, Anjali Chauhan, Garima Kumar, Raj School of Computer Applications Manav Rachna International Institute of Research & Studies Faridabad India

ISBN: (纸本)9798331530389

Cloud computing has completely evolved the way health care data is managed, but it also introduces critical security vulnerabilities that can compromise the privacy of patient information and threaten regulatory compliance. Herein, we present one of the most severe challenges: securing EHRs in a cloud environment with access to data while maintaining HIPAA compliance. We introduce a novel hybrid framework combining homomorphic encryption with blockchain-based access control and dynamic audit logging. The framework was used with a three-phase experimental approach and was deployed over five major healthcare institutions while being analyzed for 2.3 million patient records over 18 months. Results showed a high success rate of 99.97% against denial-of-service attacks while showing reductions in latency time about data retrieval up to 3 4 % compared to traditional methods of encryption. Security-incident-based variation was reduced up to 78%, and 99.99% data integrity was achieved during concurrent access scenarios. Cost analysis shows that overheads in security management amount to a reduction of 4 5 % against conventional systems. Our results show that the proposed framework is far better for healthcare data security, along with improved operational efficiency and regulatory compliance. This work contributes to the literature by providing a scalable and cost-efficient solution addressing the most complex security requirements of modern health care systems in cloud environments. The fact that the framework is implemented successfully in real life seems to reflect its effectiveness for mass-scale implementation in health organizations. © 2025 ieee.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimization of Resource Efficiency for Federated Edge intelligence in AAV-Enabled IoT Networks

引用

ieee INTERNET OF THINGS JOURNAL 2025年第8期12卷 9449-9464页

作者： Li, Yingyu Rao, Jiangying Wang, Lian Xiao, Yong Ge, Xiaohu Shi, Guangming China Univ Geosci Sch Mech Engn & Elect Informat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Elect Informat & Commun Wuhan 430074 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China Pazhou Lab Huangpu Guangzhou 510555 Guangdong Peoples R China Huazhong Univ Sci & Technol Sch Elect Informat & Commun Wuhan 430074 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China Xidian Univ Sch Artificial Intelligence Xian 710071 Shaanxi Peoples R China

Autonomous aerial vehicles (AAV)-enabled IoT networks have shown promising potential in a range of novel applications and service scenarios, such as extending the network coverage, extending the battery lifetime of IoT networks, and also supporting temporary data collecting and processing needs in various emergency situations. This article studies a federated edge intelligence (FEI) network based on the data collected and uploaded by a AAV-enabled IoT network. More specifically, a set of AAVs has periodically collected and uploaded the data generated by an IoT network to a set of edge servers. Edge servers will then collaboratively construct shared models based on the uploaded datasets. The data uploading performance of a AAV-enabled IoT network and the computational capacity of edge servers are entangled with each other in influencing the overall model training process. We propose a new framework called AAV-enabled IoT network for FEI (U-FEI). This framework enables edge servers to assess how many data samples need to be collected based on the energy costs of the AAV-enabled IoT network. It also considers the local data processing capacity of the edge servers. As a result, the edge servers can request just the right amount of data from the AAVs, which is enough to train a satisfactory model. We evaluate the energy cost for data uploading of AAVs when the data can be uploaded from two different types of frequencies: 1) licensed bands (e.g., using 5G) and 2) unlicensed bands (e.g., using Wi-Fi, ZigBee, or 5G NR-U). We prove that the cost minimization problem of the entire AAV-enabled IoT network is separable and can be divided into a set of subproblems, each of which can be solved by an individual edge server. We also introduce a mapping function to quantify the computational load of edge servers under the combinations of three key parameters: 1) size of the dataset;2) local batch size;and 3) number of local training passes. Finally, we adopt an alternative direction

关键词： Internet of Things Servers Costs Edge computing Autonomous aerial vehicles Training Resource management Optimization Data models computational modeling 6G autonomous aerial vehicles (AAV) distributed optimization edge intelligence federated learning (FL) IoT

来源：评论

学校读者我要写书评

暂无评论

Evolution and Future Trends in Wireless Communication: From 2G to 6G Technologies 2

Evolution and Future Trends in Wireless Communication: From ...

引用

2nd international conference on computational intelligence, Communication Technology and Networking, CICTN 2025

作者： Goel, Deepanshu Jaiwal, Deepanshu Dhruv Chopra, Taruna School of Computer Applications Manav Rachna International Institute of Research & Studies Faridabad India

ISBN: (纸本)9798331530389

The journey from 2G to emerging 6G is impressive, mirroring the long evolutionary path of wireless communication technology. We address critical transitions in cellular networks in light of architectural transformation, performance metrics, and the enablers of new technologies. Key trends identified: from Kbps data rate growth exponentially in 2G to Tbps in 6G;a fall of latency from the 500-ms level to sub-millisecond latency;and more importantly, from human-centric communication to machine-centric communication. It will bring some breakthrough technologies, like terahertz communications, intelligent reflecting surfaces, and quantum computing integration, revolutionizing the network configuration and capability. 6G networks will highlight many unprecedented applications such as holographic communications and extended reality;however, that is not possible without addressing various challenges related to spectrum efficiency, energy optimization, and security challenges. This report synthesized technical literature, standardization documents, and industry insights to propose a roadmap of future wireless networks with innovative and AI-integrated spectrum utilization concepts and sustainable designs. The results are critical to researchers, policymakers, and industry stakeholders in the shaping of the next generation of wireless communication systems. © 2025 ieee.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Application and research of particle swarm optimization algorithm in cloud data backup 2

Application and research of particle swarm optimization algo...

引用

2nd international conference on Big Data, computational intelligence, and Applications, BDCIA 2024

作者： Song, Tao Liu, Na Liaoning Economic Vocational Technological Institute Shenyang110122 China

ISBN: (纸本)9781510689053

With the rapid development of cloud computing technology, data security and backup have become an important guarantee for enterprises. The purpose of this study is to optimize the data allocation, storage strategy and resource management of cloud data backup through particle swarm optimization algorithm. In this paper, the basic principle and flow of Particle Swarm Optimization algorithm are introduced in detail, and a cloud data backup model based on Particle Swarm Optimization algorithm is proposed to solve the problems of resource allocation, unreasonable selection of storage nodes and optimization of backup time strategy in data backup. Through experimental comparison and performance analysis, this paper verifies the effectiveness and feasibility of Particle Swarm Optimization algorithm in improving cloud data backup efficiency, reducing backup cost and optimizing resource utilization. This study proves the important application value of Particle Swarm Optimization in cloud data backup optimization, which can improve backup efficiency and reduce resource consumption. This study also provides theoretical basis and practical guidance for further exploring the application of intelligent algorithms in cloud computing. © 2025 SPIE.

关键词： Particle swarm optimization Data backup Clouds Particles Data storage Mathematical optimization Machine learning Cloud computing Data modeling Data processing

来源：评论

学校读者我要写书评

暂无评论

research on GSEm-Net detection method of embroidery pattern lightweight operator for digital protection of Gansu intangible cultural heritage Long Embroidery 2

Research on GSEm-Net detection method of embroidery pattern ...

引用

2nd international conference on Big Data, computational intelligence, and Applications, BDCIA 2024

作者： Ba, Yuanxiao Lanzhou Vocational Technical College Gansu Lanzhou China

ISBN: (纸本)9781510689053

The digital image of embroidery has complex edge structure and high repetition rate texture features. Post-processing such as region detection is a challenging task. A long embroidery image data set for learning and training is constructed. Based on the deep network and multi-scale detection structure, the lightweight detection network model GSEm-Net is introduced to detect the long embroidery pattern in real time. Experiments show that compared with yoloV8, the detection accuracy of this method is equivalent, and the detection speed is 1.5 times that of yoloV8, but the generated model is smaller, and it is easier to deploy to low-computing edge devices, which effectively improves the target detection efficiency. © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploring Factors Using Statistical Approach to Analyse Purchase Intention for Electronic Products: A UTAUT-Based SEM Perspective 2

Exploring Factors Using Statistical Approach to Analyse Purc...

引用

2nd international conference on computational intelligence, Communication Technology and Networking, CICTN 2025

作者： Srivastava, Aditi Verma, Subhash Kumar Singh, Ajay ABES Business School Ghaziabad India School of Business Management Noida International University Greater Noida India

ISBN: (纸本)9798331530389

The research paper aims to examine and understand the determinants that impact user behaviour and intention when utilizing e-commerce applications to purchase electronic products using the conceptual framework. UTAUT model is employed as the research framework for this research. This theory examines the application of consumers and their purchase Intention for various electronic products applicable. This study examines EE, PE, FC, and Si's predictive role in Behavioural Intention and User Behaviour. The research study also studies the moderating role of task anxiety on Behavioural Intention to Purchase. The study found that PE increases users' propensity to buy electronics on e-commerce apps. EE strongly influences users' intentions, emphasizing the need for user-friendly interfaces. © 2025 ieee.

关键词： Marketplaces

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：