检索结果-内蒙古大学图书馆

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan The Beijing Key Laboratory of Network System Architecture and Convergence The Beijing Advanced Information Network Laboratory Beijing University of Posts and Telecommunications Beijing China Singapore The Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The Department of Industrial and Systems Engineering University of Miami Coral GablesFL33146 United States The College of Information Science and Electronic Engineering Zhejiang University Zhejiang Hangzhou310027 China The Department of Computer Science North Carolina State University RaleighNC27695 United States The Beijing Key Laboratory of Network System Architecture and Convergence China The Beijing Advanced Information Network Laboratory Beijing University of Posts and Telecommunications Beijing100876 China

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods. © 2025, CC BY-NC-SA.

关键词： Markov processes

Crossing Roads of Federated Learning and Smart Grids: Overview, Challenges, and Perspectives

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bousbiat, Hafsa Bousselidj, Roumaysa Himeur, Yassine Amira, Abbes Bensaali, Faycal Fadli, Fodil Mansoor, Wathiq Elmenreich, Wilfried University of Applied Sciences Institut für Informatic Wiener Neustadt2700 Austria University of Skikda Department of Computer Science Mezghich Skikda21000 Algeria University of Dubai College of Engineering and Information Technology Dubai United Arab Emirates University of Sharjah College of Computing and Informatics Sharjah United Arab Emirates De Montfort University Leicester Institute of Artificial Intelligence United Kingdom Qatar University Department of Electrical Engineering Doha2713 Qatar Qatar University College of Engineering Department of Architecture and Urban Planning Doha2713 Qatar University of Klagenfurt Smart Grids Research Group Klagenfurt9020 Austria

Consumer’s privacy is a main concern in Smart Grids (SGs) due to the sensitivity of energy data, particularly when used to train machine learning models for different services. These data-driven models often require huge amounts of data to achieve acceptable performance leading in most cases to risks of privacy leakage. By pushing the training to the edge, Federated Learning (FL) offers a good compromise between privacy preservation and the predictive performance of these models. The current paper presents an overview of FL applications in SGs while discussing their advantages and drawbacks, mainly in load forecasting, electric vehicles, fault diagnoses, load disaggregation and renewable energies. In addition, an analysis of main design trends and possible taxonomies is provided considering data partitioning, the communication topology, and security mechanisms. Towards the end, an overview of main challenges facing this technology and potential future directions is presented. © 2023, CC BY-NC-SA.

关键词： Internet of Energy

Adaptive Electric Vehicle Charge Controllers Using Deep Reinforcement Learning for Real-Time Optimization

学校读者我要写书评

暂无评论

Adaptive Electric Vehicle Charge Controllers Using Deep Rein...

Advances in Computer Science, Electrical, Electronics, and Communication Technologies (CE2CT), International Conference on

作者： N. Kavitha Mohammad Bdair P. Chandrasekar Veerakumar S M. Hema Kumar Vinay Kumar Department of EEE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India School of Architecture Computing & Engineering University of East London London Uk Department of EEE Bannari Amman Institute of Technology Erode Tamil Nadu India Department of ECE Sona College of Technology Salem Tamil Nadu India Department of Artificial Intelligence and Machine Learning B N M Institute of Technology Bengaluru India

ISBN: (数字)9798331518578

ISBN: (纸本)9798331518585

The increasing adoption of electric vehicles necessitates intelligent charging systems to address challenges such as grid overload, renewable energy integration, and user prioritization. This paper presents a new framework in optimizing the efficiency of electric car charging: Hierarchical Multi-Agent Deep Reinforcement Learning. In this architecture, a global coordinator relies on Proximal Policy Optimization to coordinate across stations, and the local agents follow Deep Q-Networks to manage their resources at the station level. Test results: A comparison of the test results with regular methods shows an average waiting time reduced by 30%, a 15% increase in the usage of renewable energy, and a reduction of 22% in the system latency. For grid loads, consistent results from the operation of this architecture ensure that minimal unserved energy demand leads to the balanced serving of loads. This method, therefore, aligns well with sustainable energy goals through simultaneous improvement in effectiveness of charging infrastructure and on the flexible scale of solution.

关键词： Renewable energy sources Vehicle-to-grid Deep reinforcement learning Electric vehicle charging Real-time systems Automobiles Resource management Optimization Standards Testing

URL Spam Detection Using Machine Learning Classifiers

学校读者我要写书评

暂无评论

URL Spam Detection Using Machine Learning Classifiers

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Omar Almomani Adeeb Alsaaidah Mosleh M. Abualhaj Mohammed Amin Almaiah Ammar Almomani Shahzad Memon Department of Networks and Cybersecurity Al-Ahliyya Amman University Amman Jordan Department of Computer Science King Abdullah the II IT School The University of Jordan Amman Jordan Department of Information Technology Al-Huson University College Al-Balqa Applied University Irbid Jordan Department of Computer Information Science Higher Colleges of Technology Sharjah United Arab Emirates Department of Computer Science and Digital Technologies Faculty of Architecture Computing and Engineering University of East London UK

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Cybersecurity has emerged as one of the most prevalent and significant challenges in recent years due to the advancement of technology. Among the most frequent and hazardous cybersecurity threats are spam URLs (Uniform Resource Locators), which are also one of the most popular methods for user fraud. Users are the victims of this attack, which also steals their data and infects their devices with harmful software. The detection of spam URLs has become very important in protecting the user. Therefore, this study aims to investigate the efficiency of machine learning classifiers in detecting spam URLs. The following machine learning classifiers were chosen: Random Forest, Decision Tree, and SVM. The evaluation was based on the ISCXURL2016 dataset, which is divided into three groups: All Features, BestFirst Features, and Infogain Features and evaluation matrices were the Accuracy, Precision, Sensitivity, and F-measure. The results obtained showed that Random Forest with All Features is superior to others with an accuracy of 99.75%, Precision of 99.74%, and Sensitivity of 99. 79%, and F-measure 99.76 %.

关键词： Uniform resource locators Support vector machines Sensitivity Accuracy Phishing Metaheuristics Feature extraction Malware Decision trees Random forests

Corrigendum to “Proposing thematic mapping for integrated risk communication: A study of British & Japanese perspectives in flood-prone communities” [Int. J. Disaster Risk Reduc., 107 (2024) 104472]

学校读者我要写书评

暂无评论

International Journal of Disaster Risk Reduction 2024年 109卷

作者： Maciej Pawlik Kaori Kitagawa Hideyuki Shiroshita Ravindra Jayaratne Soma Nomoto Yoshihiro Okumura Kazuhiro Kono University of East London School of Architecture Computing and Engineering UK University College London Institute of Education UK Kansai University Graduate School of Societal Safety Sciences Japan

Crosslinker energy landscape effects on dynamic mechanical properties of ideal polymer hydrogels

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Khare, Eesha Alcantara, Amadeus Lee, Nic Skaf, Munir S. Buehler, Markus Massachusetts Institute of Technology 77 Massachusetts Avenue CambridgeMA United States Department of Materials Science and Engineering Massachusetts Institute of Technology 77 Massachusetts Avenue CambridgeMA United States Department of Computational Mechanics School of Mechanical Engineering University of Campinas - UNICAMP Campinas Sao Paulo Brazil Center for Computing in Engineering & Sciences CCES University of Campinas - UNICAMP Campinas Sao Paulo Brazil School of Architecture and Planning Media Lab Massachusetts Institute of Technology 75 Amherst Street CambridgeMA United States Institute of Chemistry School of Mechanical Engineering University of Campinas - UNICAMP Campinas Sao Paulo Brazil Center for Computational Science and Engineering Schwarzman College of Computing Massachusetts Institute of Technology 77 Massachusetts Avenue CambridgeMA United States

Reversible crosslinkers can enable several desirable mechanical properties, such as improved toughness and self-healing, when incorporated in polymer networks for bioengineering and structural applications. In this work, we performed coarse-grained molecular dynamics to investigate the effect of the energy landscape of reversible crosslinkers on the dynamic mechanical properties of crosslinked polymer network hydrogels. We report that, for an ideal network, the energy potential of the crosslinker interaction drives the viscosity of the network, where a stronger potential results in a higher viscosity. Additional topographical analyses reveal a mechanistic understanding of the structural rearrangement of the network as it deforms and indicate that as the number of defects increases in the network, the viscosity of the network increases. As an important validation for the relationship between the energy landscape of a crosslinker chemistry and the resulting dynamic mechanical properties of a crosslinked ideal network hydrogel, this work enhances our understanding of deformation mechanisms in polymer networks that cannot easily be revealed by experiment and reveals design ideas that can lead to better performance of the polymer network at the macroscale. © 2023, CC BY-NC-SA.

关键词： Hydrogels

Deep Learning-Based Object Pose Estimation: A Comprehensive Survey

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Jian Sun, Wei Yang, Hui Zeng, Zhiwen Liu, Chongpei Zheng, Jin Liu, Xingyu Rahmani, Hossein Sebe, Nicu Mian, Ajmal The National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering the State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China The School of Architecture and Art Central South University Changsha410082 China The Department of Automation Tsinghua University Beijing100084 China The School of Computing and Communications Lancaster University LA1 4YW United Kingdom The Department of Information Engineering and Computer Science University of Trento Trento38123 Italy The Department of Computer Science The University of Western Australia WA6009 Australia

Object pose estimation is a fundamental computer vision problem with broad applications in augmented reality and robotics. Over the past decade, deep learning models, due to their superior accuracy and robustness, have increasingly supplanted conventional algorithms reliant on engineered point pair features. Nevertheless, several challenges persist in contemporary methods, including their dependency on labeled training data, model compactness, robustness under challenging conditions, and their ability to generalize to novel unseen objects. A recent survey discussing the progress made on different aspects of this area, outstanding challenges, and promising future directions, is missing. To fill this gap, we discuss the recent advances in deep learning-based object pose estimation, covering all three formulations of the problem, i.e., instance-level, category-level, and unseen object pose estimation. Our survey also covers multiple input data modalities, degrees-of-freedom of output poses, object properties, and downstream tasks, providing the readers with a holistic understanding of this field. Additionally, it discusses training paradigms of different domains, inference modes, application areas, evaluation metrics, and benchmark datasets, as well as reports the performance of current state-of-the-art methods on these benchmarks, thereby facilitating the readers in selecting the most suitable method for their application. Finally, the survey identifies key challenges, reviews the prevailing trends along with their pros and cons, and identifies promising directions for future research. We also keep tracing the latest works at Awesome-Object-Pose-Estimation. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

Removal of cadmium and zinc from water using sewage sludge-derived biochar

学校读者我要写书评

暂无评论

Sustainable Chemistry for the Environment

Sustainable Chemistry for the Environment 2024年 6卷

作者： Shah, Ahsan Zakharova, Julia Batool, Maryam Coley, Matthew P. Arjunan, Arun Hawkins, Alisha J. Bolarinwa, Timothy Devi, Shreah Thumma, Anusha Williams, Craig School of Engineering Computing and Mathematical Sciences University of Wolverhampton WV1 1LY United Kingdom School of Architecture and Built Environment University of Wolverhampton WV1 1LY United Kingdom Department of Chemistry University of Sahiwal Sahiwal Pakistan Faculty of Science and Engineering University of Wolverhampton WV1 1LY United Kingdom Department of Pharmaceutical Sciences College of Pharmacy Nova Southeastern University FL United States

This research reveals the adsorption of cadmium (Cd2+) and zinc (Zn+2) from water using sewage sludge-derived biochar pyrolysed at 700 °C (SSB). The morphology and particle characteristics of SSB were characteris... 详细信息

This research reveals the adsorption of cadmium (Cd²⁺) and zinc (Zn⁺²) from water using sewage sludge-derived biochar pyrolysed at 700 °C (SSB). The morphology and particle characteristics of SSB were characterised through scanning electron microscopy (SEM), particle size distribution (PSD), fourier transform infrared (FTIR), X-ray diffraction (XRD), and X-ray fluorescence (XRF). The adsorption study showed that the optimum contact times for removing Zn²⁺ and Cd²⁺ were 80 and 140 minutes, respectively. 95.51% Zn²⁺ and 97.54% Cd²⁺ could be removed from spiked solutions featuring 50 mg/L of Zn²⁺ and 50 mg/L Cd²⁺, each treated with 25 g/L biochar. The optimum pH of the solutions was 8–9 at a temperature of 40°C, indicating some precipitation of the metal ions at an alkaline pH. The highest adsorption capacity of SSB for Cd²⁺ and Zn²⁺ was found to be 3.02 and 2.51 mg/g, respectively, which compares favourably with other adsorbents. The isotherm studies confirmed experimental data to closely follow the Langmuir isotherm model at an R² value of 0.9846 and 0.9816 for Cd²⁺ and Zn²⁺, respectively. The kinetic study confirmed the physical interaction between the adsorbents and the adsorbate. The spontaneous and exothermic nature of the process was confirmed by negative values of change in Gibbs free energy (ΔG) and enthalpy (ΔH). SSB could be regenerated for 6 cycles. Overall, this study explores sustainability, recycling, and waste management by offering SSB as a potentially cost-effective and environment-friendly solution to remove Cd²⁺ and Zn²⁺ from water. © 2024 The Authors

关键词： Adsorption Biochar Cadmium Isotherms and kinetics Regeneration Thermodynamics Zinc

PRF: a process-RAM-feedback performance model to reveal bottlenecks and propose optimizations

学校读者我要写书评

暂无评论

High Technology Letters 2020年第3期26卷 285-298页

作者： Xie Zhen Tan Guangming Liu Weifeng Sun Ninghui Key Laboratory of Computer Architecture Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190P.R.China University of Chinese Academy of Sciences Beijing 100190P.R.China College of Information Science and Engineering China University of PetroleumBeijing 102249P.R.China

Performance models provide insightful perspectives to predict performance and to propose optimization *** there has been much researches,pinpointing bottlenecks of various memory access patterns and reaching high accurate prediction of both regular and irregular programs on various hardware configurations are still not *** work proposes a novel model called process-RAM-feedback(PRF)to quantify the overhead of computation and data transmission time on general-purpose multi-core *** PRF model predicts the cost of instruction for singlecore by a directed acyclic graph(DAG)and the transmission time of memory access between each memory hierarchy through a newly designed cache *** using performance modeling and feedback optimization method,this paper uses PRF model to analyze and optimize convolution,sparse matrix-vector multiplication and sn-sweep as case study for covering with typical regular kernel to irregular and data *** the PRF model,it obtains optimization guidance with various sparsity structures,algorithm designs,and instruction sets support on different data sizes.

关键词： performance model feedback optimization convolution sparse matrix-vector multiplication sn-sweep