检索结果-内蒙古大学图书馆

Computation and Privacy Protection for Satellite-Ground Digital Twin Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gong, Yongkang Yao, Haipeng Liu, Xiaonan Bennis, Mehdi Nallanathan, Arumugam Han, Zhu The School of Information and Communication Engineering BUPT Beijing100876 China The Communication Systems Research group in Queen Mary University of London QMUL LondonE1 4NS United Kingdom The Center for Wireless Communications University of Oulu Oulu90014 Finland The School of Electrical and Computer Engineering University of Houston HoustonTX77004 United States

Satellite-ground integrated digital twin networks (SGIDTNs) are regarded as innovative network architectures for reducing network congestion, enabling nearly-instant data mapping from the physical world to digital systems, and offering ubiquitous intelligence services to terrestrial users. However, the challenges, such as the pricing policy, the stochastic task arrivals, the time-varying satellite locations, mutual channel interference, and resource scheduling mechanisms between the users and cloud servers, are critical for improving quality of service in SGIDTNs. Hence, we establish a blockchain-aided Stackelberg game model for maximizing the pricing profits and network throughput in terms of minimizing overhead of privacy protection, thus performing computation offloading, decreasing channel interference, and improving privacy protection. Next, we propose a Lyapunov stability theory-based model-agnostic meta-learning aided multi-agent deep federated reinforcement learning (MAML-MADFRL) framework for optimizing the CPU cycle frequency, channel selection, task-offloading decision, block size, and cloud server price, which facilitate the integration of communication, computation, and block resources. Subsequently, the extensive performance analyses show that the proposed MAML-MADFRL algorithm can strengthen the privacy protection via the transaction verification mechanism, approach the optimal time average penalty, and fulfill the long-term average queue size via lower computational complexity. Finally, our simulation results indicate that the proposed MAML-MADFRL learning framework is superior to the existing baseline methods in terms of network throughput, channel interference, cloud server profits, and privacy overhead. © 2023, CC BY.

关键词： Reinforcement learning

AI-Powered Anomaly Detection to Strengthen Internet of Things Security and Forestall Cyber Attacks in Networked Device Environments

学校读者我要写书评

暂无评论

AI-Powered Anomaly Detection to Strengthen Internet of Thing...

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： S. Varalakshmi Suresh Kottur R Sasikumar K Saravanan Tanaya Kanungo Balamurugan Annamalai Department of ECE Bharath Institute of Higher Education and Research Chennai Tamil Nadu India IT Infrastructure Architect/IT Systems V-Soft Consulting Group Inc Louisville KY United States of America Department of Computer Science & Engineering R.M.D Engineering College Kavaraipettai Tamil Nadu India Department of Information Technology R.M.K Engineering College Kavaraipettai Tamil Nadu India Department of ECE St. Peter's College of Engineering and Technology Avadi Tamil Nadu India Department of EEE Shree Sathyam College of Engineering and Technology Sangagiri Tamil Nadu India

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

As millions of devices are linked, the IoT has revolutionized numerous businesses by automating and data-driven decision-making. Due to the proliferation of linked devices, cybercriminals target IoT environments for security breaches. This research examines AI-powered anomaly detection systems for real-time threat discovery and mitigation in IoT security. Advanced machine learning and deep learning models based on artificial intelligence can detect suspicious activity in networked environments and early security breaches. Artificial intelligence systems learn from network traffic and device behaviors to respond to emerging cyber threats, unlike rule-based security solutions. The study found that AI-driven anomaly detection can prevent data breaches, malware outbreaks, and DDoS attacks. This study compares artificial intelligence algorithms for real-time anomaly detection across IoT frameworks. Supervised, unsupervised, and hybrid learning models are used. It also discusses the challenges of large-scale AI system deployment, including the need for high-quality labelled datasets for training and computational resource constraints. The results suggest that AI-enabled anomaly detection could become a crucial part of IoT security, adapting to the growing number of connected devices.

关键词： Accuracy Computational modeling Biological system modeling Real-time systems Malware Internet of Things Security Hybrid learning Artificial intelligence Anomaly detection

Evaluating the Experience of LGBTQ+ People Using Large Language Model Based Chatbots for Mental Health Support

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Zilin Mei, Yiyang Long, Yinru Su, Zhaoyuan Gajos, Krzysztof Z. Intelligent Interactive Systems Group Harvard School of Engineering and Applied Sciences AllstonMA United States Law School Emory University AtlantaGA United States Psychology and Human Development Peabody College Vanderbilt University NashvilleTN United States Donald Bren School of Information and Computer Sciences University of California Irvine IrvineCA United States

LGBTQ+ individuals are increasingly turning to chatbots powered by large language models (LLMs) to meet their mental health needs. However, little research has explored whether these chatbots can adequately and safely provide tailored support for this demographic. We interviewed 18 LGBTQ+ and 13 non-LGBTQ+ participants about their experiences with LLM-based chatbots for mental health needs. LGBTQ+ participants relied on these chatbots for mental health support, likely due to an absence of support in real life. Notably, while LLMs offer prompt support, they frequently fall short in grasping the nuances of LGBTQ-specific challenges. Although fine-tuning LLMs to address LGBTQ+ needs can be a step in the right direction, it isn’t the panacea. The deeper issue is entrenched in societal discrimination. Consequently, we call on future researchers and designers to look beyond mere technical refinements and advocate for holistic strategies that confront and counteract the societal biases burdening the LGBTQ+ community. © 2024, CC BY.

关键词： Computational linguistics

Robust Optimization of RIS in Terahertz under Extreme Molecular Re-radiation Manifestations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Pradhan, Anish Abd-Elmagid, Mohamed A. Dhillon, Harpreet S. Molisch, Andreas F. Wireless@VT Department of ECE Virginia Tech BlacksburgVA United States The Wireless Devices and Systems Group Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los AngelesCA United States

Terahertz (THz) communication signals are susceptible to severe degradation because of the molecular interaction with the atmosphere in the form of subsequent absorption and re-radiation. Recently, reconfigurable intelligent surface (RIS) has emerged as a potential technology to assist in THz communications by boosting signal power or providing virtual line-of-sight (LOS) paths. However, the re-radiated energy has either been modeled as a non-line-of-sight (NLOS) scattering component or as additive Gaussian noise in the literature. Since the precise characterization is still a work in progress, this paper presents the first comparative investigation of the performance of an RIS-aided THz system under these two extreme re-radiation models. In particular, we first develop a novel parametric channel model that encompasses both models of the re-radiation through a simple parameter change, and then utilize that to design a robust block-coordinate descent (BCD) algorithmic framework which maximizes a lower bound on channel capacity while accounting for imperfect channel state information (CSI). In this framework, the original problem is split into two sub-problems: a) receive beamformer optimization, and b) RIS phase-shift optimization. As the latter sub-problem (unlike the former) has no analytical solution, we propose three approaches for it: a) semi-definite relaxation (SDR) (high complexity), b) signal alignment (SA) (low complexity), and c) gradient descent (GD) (low complexity). The time complexities associated with the proposed approaches are explicitly derived. We analytically demonstrate the limited interference suppression capability of a passive RIS by deriving the stationary points of signal-to-interference and noise ratio (SINR) of a one-element RIS system with one interferer. Our numerical results also demonstrate that slightly better throughput is achieved when the re-radiation manifests as scattering. Copyright © 2022, The Authors. All rights reserved.

关键词： Optimization

Fault Analysis of Microgrids with Inverter Interfaced Resources in Grid-Connected and Islanded Modes

学校读者我要写书评

暂无评论

Fault Analysis of Microgrids with Inverter Interfaced Resour...

On-Line Conference (ONCON), Industrial Electronics Society Annual

作者： Jigyesh Sharma Kushan Tharuka Lulbadda Anindita Golder Tarlochan Sidhu Sheldon S. Williamson Department of Electrical and Computer Engineering Advanced Storage Systems and Electric Transportation (ASSET) Laboratory Ontario Tech-Automotive Center of Excellence (ACE) Faculty of Engineering and Applied Science Smart Transportation Electrification and Energy Research (STEER) Group Ontario Tech University Oshawa ON Canada

The increasing penetration of inverter-based generation such as solar, wind and battery energy storage systems (BESS) has an impact on the fault currents in a microgrid. Also, if the microgrid is grid-connected or islanded affects the fault current. As such, it is important to conduct fault analysis of microgrids in grid-connected and islanded modes with different penetration levels of inverter-based generation sources to understand the impact of increasing levels of renewable energy on the fault currents. Different types of faults in a microgrid with inverter-based resources are simulated and the results are discussed and analyzed in this paper.

关键词： Wind energy generation Industrial electronics Renewable energy sources Wind energy Microgrids Inverters Batteries

Developing Action Policies with Q-Learning and Shallow Neural Networks on Reconfigurable Embedded Devices

学校读者我要写书评

暂无评论

ACM Transactions on Autonomous and Adaptive systems 2021年第4期15卷

作者： Burger, Alwyn Schiele, Gregor King, David W. Embedded Systems Group University of Duisburg-Essen Duisburg47057 Germany Dept of Electrical and Computer Engineering Air Force Institute of Technology DaytonOH United States

The size of sensor networks supporting smart cities is ever increasing. Sensor network resiliency becomes vital for critical networks such as emergency response and waste water treatment. One approach is to engineer "self-aware"sensors that can proactively change their component composition in response to changes in work load when critical devices fail. By extension, these devices could anticipate their own termination, such as battery depletion, and offload current tasks onto connected devices. These neighboring devices can then reconfigure themselves to process these tasks, thus avoiding catastrophic network failure. In this article, we compare and contrast two types of self-aware sensors. One set uses Q-learning to develop a policy that guides device reaction to various environmental stimuli, whereas the others use a set of shallow neural networks to select an appropriate reaction. The novelty lies in the use of field programmable gate arrays embedded on the sensors that take into account internal system state, configuration, and learned state-action pairs, which guide device decisions to meet system demands. Experiments show that even relatively simple reward functions develop both Q-learning policies and shallow neural networks that yield positive device behaviors in dynamic environments. © 2021 Copyright held by the owner/author(s).

关键词： Field programmable gate arrays (FPGA)

A Letter on Progress Made on Husky Carbon: A Legged-Aerial, Multi-modal Platform

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Salagame, Adarsh Manjikian, Shoghair Wang, Chenghao Krishnamurthy, Kaushik Venkatesh Pitroda, Shreyansh Gupta, Bibek Jacob, Tobias Mottis, Benjamin Sihite, Eric Ramezani, Milad Ramezani, Alireza The Department of Electrical and Computer Engineering Northeastern University SiliconSynapse Laboratory BostonMA United States The Department of Aerospace Engineering California Institute of Technology PasadenaCA United States The Robotics and Autonomous Systems Group Data61 CSIRO BrisbaneQLD Australia

Animals, such as birds, widely use multi-modal locomotion by combining legged and aerial mobility with dominant inertial effects. The robotic biomimicry of this multi-modal locomotion feat can yield ultra-flexible systems in terms of their ability to negotiate their task spaces. The main objective of this paper is to discuss the challenges in achieving multi-modal locomotion, and to report our progress in developing our quadrupedal robot capable of multi-modal locomotion (legged and aerial locomotion), the Husky Carbon. We report the mechanical and electrical components utilized in our robot, in addition to the simulation and experimentation done to achieve our goal in developing a versatile multi-modal robotic platform. Copyright © 2022, The Authors. All rights reserved.

关键词： Antennas

Wheel Slip Balance Based Anti-Slip Regulation on Dissymmetric Road Grip

学校读者我要写书评

暂无评论

Wheel Slip Balance Based Anti-Slip Regulation on Dissymmetri...

Control Conference (ICC), 2019 Sixth Indian

作者： Gaël G. Atheupe R. Sreekanth S. Arrvind K. Bordignon B. Monsuez A. Tapus RENAULT Group and the Computer science & systems engineering Lab (U2IS) of ENSTA Paris Institute Polytechnique de Paris (IP Paris) Palaiseau FRANCE RNTBCI Chennai Chengalpattu Tamil Nadu INDIA Embry-Riddle Aeronautical University Prescott AZ USA Computer science & systems engineering Lab (U2IS) of ENSTA Paris Institute Polytechnique de Paris (IP Paris) Palaiseau FRANCE

Anti-Slip regulation system (ASR) as the name suggests, prevents excessive wheel spin by limiting wheel slip on the spinning wheel using brake torque or engine torque intervention when starting off and accelerating, particularly on a slippery road surface. These kinds of circumstances can overtax the driver not only causing them to react inappropriately but also causing the vehicle to become unstable. (ASR) tackles these problems, providing the vehicle remains within the physical limits. This paper presents an inter-axle anti-slip regulation logic for vehicle stability in the midst of dissymmetric road grip conditions. It employs the inter-axle wheel slip balance control strategy, to increase driving stability and improve traction with respect to the driver's torque request. The proposed method is assessed and validated by simulation in AMESim. Results demonstrate the effectiveness of the proposed method in terms of vehicle stability and steer ability through the regulation of drive torque at each driven wheel based on the inter- axle slip balance target. In addition to this safety relevant-task of ensuring stability and steering ability of the vehicle in the acceleration phase, ASR improves traction by helping find levels of wheel slip not easily accessible.

关键词： Torque Limiting Roads Wheels Stability analysis Regulation Safety

T-Graph: Enhancing Sparse-view Camera Pose Estimation by Pairwise Translation Graph

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xian, Qingyu Jiao, Weiqin Cheng, Hao van der Zwaag, Berend Jan Huang, Yanqiu Pervasive Systems Research Group Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede Netherlands University of Twente Enschede Netherlands

Sparse-view camera pose estimation, which aims to estimate the 6-Degree-of-Freedom (6-DoF) poses from a limited number of images captured from different viewpoints, is a fundamental yet challenging problem in remote sensing applications. Existing methods often overlook the translation information between each pair of viewpoints, leading to suboptimal performance in sparse-view scenarios. To address this limitation, we introduce T-Graph, a lightweight, plug-and-play module to enhance camera pose estimation in sparse-view settings. T-graph takes paired image features as input and maps them through a Multilayer Perceptron (MLP). It then constructs a fully connected translation graph, where nodes represent cameras and edges encode their translation relationships. It can be seamlessly integrated into existing models as an additional branch in parallel with the original prediction, maintaining efficiency and ease of use. Furthermore, we introduce two pairwise translation representations, relative-t and pair-t, formulated under different local coordinate systems. While relative-t captures intuitive spatial relationships, pair-t offers a rotation-disentangled alternative. The two representations contribute to enhanced adaptability across diverse application scenarios, further improving our module’s robustness. Extensive experiments on two state-of-the-art methods (RelPose++ and Forge) using public datasets (C03D and IMC PhotoTourism) validate both the effectiveness and generalizability of T-Graph. The results demonstrate consistent improvements across various metrics, notably camera center accuracy, which improves by 1% to 6% from 2 to 8 viewpoints. © 2025, CC BY-NC-ND.

关键词： Photointerpretation