检索结果-内蒙古大学图书馆

2024 IET International Conference on engineering Technologies and Applications, ICETA 2024

作者： Lin, Yu-Chuan Chiu, Po-Kai Suryajaya, Benny Department of Computer Science and Information Engineering Chinese Culture University Taipei Taiwan Institute of Manufacturing Information and Systems National Cheng Kung University Tainan Taiwan Intelligent Manufacturing Research Center National Cheng Kung University Tainan Taiwan

ISBN: (纸本)9781837242672

In the era of digital transformation, containerized systems and digital twins are vital technologies in intelligent manufacturing. Our previous research, the Implementation Framework of Digital Twins for Intelligent Manufacturing (IF-DTiM), lacks comprehensive security features[1]. To address this critical gap, we propose the Advanced Security Approach for Building Secure Containerized Manufacturing Digital Twins (ASABS-CMDT), integrating automated tools for detecting vulnerabilities, container image creation, and secure digital signing, all within DevSecOps practices. Case studies show that ASABS-CMDT significantly enhances system security and reduces development time, offering valuable insights for practitioners in intelligent manufacturing. © The Institution of engineering & Technology 2024.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Developing a Cloud information Monitoring and Recommendation Multi-agent System based on Artificial Intelligence Technology for Smart Energy-saving 3

Developing a Cloud Information Monitoring and Recommendation...

引用

3rd IEEE Eurasia Conference on Biomedical engineering, Healthcare and Sustainability, ECBIOS 2021

作者： Yang, Sheng-Yuan Department of Computer Information and Network Engineering Lunghwa University of Science and Technology

ISBN: (纸本)9781728193045

Smart energy-saving is one of the important topics of applied science. Artificial intelligence (AI) is also worth paying attention to for intelligent systems. This study aimed to develop a cloud multi-agent system that integrates multiple intelligent technologies for quickly, accurately, and effectively obtaining useful cloud energy-saving information on time for applying science. The proposed system was successfully built by ontology, Web services, and big data analytic technologies based on many practical developments in the Dr. What-Info system. To build the system, we surveyed the related techniques for constructing a Web service platform and explored how to broadly combine cloud interactions among all sub-agents. The preliminary system shows that the proposed system architecture and operation have met the system design requirements. © 2021 ECBIOS 2021. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

DQPS: An Intelligent Multi-Hop Computation Offloading Scheme for Workflow Applications in Vehicular Edge Computing networks

引用

IEEE Transactions on Consumer Electronics 2024年第1期71卷 2202-2216页

作者： Lin, Bing Chen, Qiaoxin Chen, Xing Jia, Wen-Kang Lu, Yu Xiong, Neal N. Fujian Normal University College of Physics and Energy Fujian Provincial Key Laboratory of Quantum Manipulation and New Energy Materials Fuzhou350117 China Fujian Provincial Collaborative Innovation Center for Advanced High-Field Superconducting Materials and Engineering Fuzhou350117 China Peking University School of Computer Science 100871 China Xiamen University Department of Informatics and Communication Engineering Xiamen361005 China Fuzhou University College of Computer and Data Science Fuzhou350118 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350118 China Fujian Normal University College of Photonic and Electronic Engineering Fuzhou350117 China Fujian Normal University Concord University College Fuzhou350117 China Sul Ross State University Department of Computer Mathematical and Physical Sciences AlpineTX79830 United States

Vehicular Edge Computing (VEC) is a feasible solution for autonomous driving as it can offload latency-sensitive and computation-intensive tasks from vehicle terminals to roadside units (RSUs) for real-time processing. Due to the high computational resource the workflow applications (i.e., autonomous driving) required, the small vehicle-to-RSUs communication range, and the scarce available resources for each vehicle, it might be difficult to accomplish complex workflow applications through the single-hop offloading paradigm in the Internet of Vehicles (IoV). In this paper, we propose a reinforcement learning (RL) based multi-hop computation offloading scheme for workflow applications to reduce their execution latency in the VEC networks, which considers the data dependency in workflow applications as well as the trust relationship and communication interference among RSUs. Firstly, a preprocessing method is employed to merge the cut-edges in a workflow to reduce the offloading scale of tasks and compress the encoding dimension of offloading solutions. Then, a Deep Q-network algorithm using Phase-optimal State update (DQPS) is proposed to update the offloading policy distribution, in which the deviation of the phase-optimal state from the current state is estimated as the reward of RL to promote the algorithm's convergence to adapt the dynamic VEC networks. Simulation results show that DQPS has the best performance compared to other benchmark schemes. Moreover, the latency of the identical applications can be reduced by 2.5%-25.3% through our offloading scheme with a multi-hop model compared to that with the single-hop paradigm in IoV. © 1975-2011 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Light Fidelity and Internet of Things for Medical Applications 4

Light Fidelity and Internet of Things for Medical Applicatio...

引用

4th International Conference of science and information Technology in Smart Administration, ICSINTESA 2024

作者： Adi, Puput Dani Prasetyo Sariningrum, Ros Rahmatullah, Rizky Novita, Hessy Situngkir, Tiar Lina Adji, Priyo Hartono Lusiastuti, Angela Mariana Wibowo, Antonia Rahayu Rosaria Prastiyono, Yudi Adiprabowo, Tjahjo Yassir, Muhammad Maulana, Fairuz Iqbal Department of Telecommunication Bandung Indonesia Veterinary Research Center Bandung Indonesia Singaperbangsa University Faculty of Economics Department of Management Karawang Indonesia Bandung Indonesia Langlangbuana University Faculty of Engineering Department of Electrical Engineering Bandung Indonesia Institut Teknologi Dan Bisnis Nobel Department of System and Information System Makassar Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350376111

This study focuses on transmitting data utilizing medical sensors that are vital for patients in hospitals and other settings. In this situation, Light Fidelity refers to transmitting medical sensor data or other data comprising the Transmitter (Tx) and the Receiver (Rx). If the Light Fidelity Principle is used, the Transmitter transmits LEDs or light to the Receiver. At the same time, the Receiver contains a receiver or light detection component known as the Light Dependent Resistor (LDR);using programming and this basic working principle, data can be sent from the LED Transmitter to the LDR Receiver using C++ Programming and its Library to send Medical sensor data. Sensors can include pulse sensors, like in prior research, and additional sensors such as SPO2 or blood pressure sensors. For medical data, a modest bit rate is sufficient, but LiFi applications can be created in such a way that they can be hybridized with WiFi and other RF devices such as LoRa and the Internet of Things. © 2024 IEEE.

关键词： C++ (programming language)

来源：评论

学校读者我要写书评

暂无评论

Risk-Aware Sensitive Property-Driven Resource Management in Cloud Datacenters

arXiv

引用

arXiv 2025年

作者： Felemban, Muhamad Almutairi, Abdulrahman Ghafoor, Arif Computer Engineering Department The Information and Computer Science Department The Interdisciplinary Research Center for Intelligent Secure Systems KFUPM Saudi Arabia Purdue University West LafayetteIN United States Computer Engineering Department The College of Computer and Information Science in King Saud University Riyadh Saudi Arabia

Organizations are increasingly moving towards the cloud computing paradigm, in which an on-demand access to a pool of shared configurable resources is provided. However, security challenges, which are particularly exacerbated by the multitenancy and virtualization features of cloud computing, present a major obstacle. In particular, sharing of resources among potentially untrusted tenants in access controlled cloud datacenters can result in increased risk of data leakage. To address such risk, we propose an efficient risk-aware sensitive property-driven virtual resource assignment mechanism for cloud datacenters. We have used two information-theoretic measures, i.e., KL-divergence and mutual information, to represent sensitive properties in the dataset. Based on the vulnerabilities of cloud architecture and the sensitive property profile, we have formulated the problem as a cost-drive optimization problem. The problem is shown to be NP-complete. Accordingly, we have proposed two heuristics and presented simulation based performance results for cloud datacenters with multiple sensitivity. © 2025, CC BY.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic-Based Deep Reinforcement Learning Pre-Training: A Case Study in MEC Task Offloading

Fuzzy Logic-Based Deep Reinforcement Learning Pre-Training: ...

引用

Cyber science and Technology Congress (CyberSciTech), IEEE

作者： Jiujie Zhang Yangfei Lin Zhaoyang Du Wugedele Bao Department of Computer and Network Engineering The University of Electro-Communications Tokyo Japan Department of Information Science and Technology Baotou Teachers' College Baotou China Department of Computer Science and Information Engineering Hohhot Minzu College Hohhot China

ISBN: (数字)9798331532093

ISBN: (纸本)9798331532109

The joint optimization of task offloading in mobile edge computing (MEC) presents significant challenges due to the complex interaction between computation, communication, and resource constraints. Deep reinforcement learning (DRL) algorithms offer promising solutions for optimizing task offloading decisions in dynamic environments. However, these algorithms often face drawbacks, such as arbitrary or random parameter initialization, which lacks semantic and behavioral relevance. Thus, extensive exploration is required to identify optimal policies, particularly at the early learning stages. To address this issue, a pre-training framework for DRL algorithms is proposed, which utilizes fuzzy logic to guide initial policy exploration. The proposed approach incorporates a fuzzy logic-based module for task offloading, enabling the framework to collect valuable experiential data related to task offloading decisions. These experiences are then used to pre-train the DRL algorithm offline, facilitating the rapid acquisition of more meaningful initial parameters. Simulations in an MEC task offloading scenario with multiple mobile devices and edge servers demonstrate that the proposed framework enhances early-stage performance and improves long-term stability of the DRL algorithm by reducing average task processing time and increasing average task completion rates. Additionally, the fuzzy logic-based task offloading module performs effectively even when it is applied independently.

关键词： Fuzzy logic Performance evaluation Multi-access edge computing Heuristic algorithms Semantics Refining Deep reinforcement learning Stability analysis Servers Thermal stability

来源：评论

学校读者我要写书评

暂无评论

Double-Blockchain Assisted Secure and Anonymous Data Aggregation for Fog-Enabled Smart Grid

引用

engineering 2022年第1期8卷 159-169页

作者： Siguang Chen Li Yang Chuanxin Zhao Vijayakumar Varadarajan Kun Wang Jiangsu Key Lab of Broadband Wireless Communication and Internet of Things Nanjing University of Posts and TelecommunicationsNanjing 210003China Jiangsu Engineering Research Center of Communication and Network Technology Nanjing University of Posts and TelecommunicationsNanjing 210003China Anhui Provincial Key Laboratory of Network and Information Security Anhui Normal UniversityWuhu 241000China School of Computer Science and Engineering Vellore Institute of TechnologyChennai 600127India Department of Electrical and Computer Engineering University of CaliforniaLos AngelesCA 90095USA

As a future energy system,the smart grid is designed to improve the efficiency of traditional power systems while providing more stable and reliable ***,this efficient and reliable service relies on collecting and analyzing users’electricity consumption data frequently,which induces various security and privacy *** address these challenges,we propose a double-blockchain assisted secure and anonymous data aggregation scheme for fog-enabled smart grid named ***,we design a three-tier architecture-based data aggregation framework by integrating fog computing and the blockchain,which provides strong support for achieving efficient and secure data collection in smart ***,we develop a secure and anonymous data aggregation mechanism with low computational overhead by jointly leveraging the Paillier encryption,batch aggregation signature and anonymous *** particular,the system achieves fine-grained data aggregation and provides effective support for power dispatching and price adjustment by the designed double-blockchain and two-level data ***,the superiority of the proposed scheme is illustrated by a series of security and computation cost analyses.

关键词： Blockchain Fog computing Homomorphic encryption Smart grid Anonymity

来源：评论

学校读者我要写书评

暂无评论

A New Portfolio Optimization Model Considering Hybrid Trading Strategies

A New Portfolio Optimization Model Considering Hybrid Tradin...

引用

2023 IEEE Congress on Evolutionary Computation, CEC 2023

作者： Kuo, Shu-Yu Jiang, Yu-Chi Lai, Yun-Ting Chou, Yao-Hsin Center for Quantum Science and Engineering National Taiwan University Department of Physics Taiwan National Taiwan University Department of Electrical Engineering Taiwan National Chi Nan University Department of Computer Science and Information Engineering Taiwan

ISBN: (纸本)9798350314588

Computational intelligence (CI) has been extensively used in financial technology areas to help make smart decisions within enormous solution spaces. This study proposes a new portfolio optimization model using hybrid strategies to concurrently consider long and short investments and compose effective portfolios assessed by an emerging indicator to reach an excellent balance between return and risk. It exploits the trend ratio investment strategy to a detailed extent to evaluate the steady uptrend and downtrend portfolios and provides an in-depth discussion of the U.S. stock market. The proposed method combines long and short selling through a single fund to enhance investment efficiency. Quantum-inspired CI is adopted to construct a near-optimal portfolio efficiently and effectively, and sliding windows are applied to rebalance the portfolio and dynamically discover appropriate periods. The experiment conducts comprehensive statistical tests to show that hybrid strategies significantly improve traditional approaches. The comparison with other traditional methods shows outstanding performances in MDD, PF, RoMaD, return, and trend ratio. The proposed hybrid portfolio optimization application can be complementary, offset the volatility and increase the return, and show great potential in the financial industry. © 2023 IEEE.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Performance of Power Allocation Under Priority User in CR-NOMA 3

Performance of Power Allocation Under Priority User in CR-NO...

引用

3rd IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and computer engineering, MI-STA 2023

作者： Elmadina, Nahla Nur Saeid, Elsadig Mokhtar, Rania A. Saeed, Rashid A. Ali, Elmustafa Sayed Khalifa, Othman O. Alzaiem Alazhari University Department of Electrical Engineering Khartoum Sudan Taif University College of Computers and Information Technology Department of Computer Engineering Taif21944 Saudi Arabia Sudan University of Science and Technology Department of Electronics Engineering Khartoum Sudan International Islamic University Malaysia Gombak Malaysia Libyan Center for Engineering Resarch and Information Technology Department of Electrical and Computer Engineering Bani Waleed Libya

ISBN: (纸本)9798350319897

A promising 5G communications technology was already known as CR-Non-Orthogonal Multiple Access (CR- NOMA). Power allocation (PA) and user pairing both affect how well NOMA systems perform. For the PA problem, the majority of recent studies offer suboptimal solutions with high computing complexity that prioritize rate maximization over performance fairness. Furthermore, a thorough search is required for the combined optimization of PA and UP. The primary contribution of this paper is the suggestion of a brand-new, minimally difficult Maximization optimization Data rate based power allocation (MODRFPA) in downlink CR-NOMA. The combined effects of SNR per subcarrier and typically combined channel gains have been thoroughly analyzed and investigated. Users' feedback on NOMA's performance in terms of user fairness and capacity is demonstrated. The outcomes of the simulation demonstrate that the suggested MODRPA can enhance the fairness and data rate of current UP techniques. Additionally, simulation findings demonstrate that the proposed coefficient power performs schemes more effectively and offers performance that is close to ideal. © 2023 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A-ReSEUnet: Achieve no-label binary segmentation of nuclei in histology images

引用

Knowledge-Based Systems 2024年 301卷

作者： Chang, Jui-Hung Wu, Pei-Hsuan Wang, Ti-Hao Chung, Pau-Choo Computer and Network Center and Department of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan Department of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan Department of Radiation Oncology China Medical University Hospital Taichung Taiwan Department of Medicine China Medical University Taichung Taiwan Department of Electrical Engineering National Cheng Kung University Tainan Taiwan

Histopathological images reveal a lot of information about tissue health. The task of nucleus segmentation can be applied to more diverse studies. The potential of deep learning has been demonstrated for the task of nuclei segmentation. However, the cost and time required for labeling data, as well as the lack of annotators, makes it difficult to keep up with the continuous generation of new pathological images. This paper proposes a method that combines attention mechanisms and self-supervised learning to train a model for nuclei segmentation on unlabeled data. The method is mainly divided into two stages. After the initial preprocessing of the image, the enhanced image of the nucleus area can be obtained in the first stage. Subsequently, the original image and the augmented image needed for self-supervised learning undergo feature extraction in the second stage. The results of this study show that the proposed method can achieve dice scores exceeding 0.7 in the nucleus binary segmentation task without labels. Fine-tuning the model for downstream tasks can also achieve the effect of F1 score 0.7 multi-category segmentation. Using the same experimental setting, the method proposed in this study achieves a dice score of 0.779 on the MoNuSeg dataset, which is only 0.03 lower than the highest dice score of 0.809 achieved by the compared supervised learning methods. In comparison to other unsupervised models, this method demonstrates superior segmentation performance. Moreover, this study applies the training weights to other histopathology image datasets, enabling the generation of the same binary segmentation effect. © 2017 Elsevier Inc. All rights reserved. © 2024

关键词： Image segmentation

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：