检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Fares Fourati Mohamed-Slim Alouini Vaneet Aggarwal Computer Electrical and Mathematical Science and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal KSA School of Industrial Engineering Purdue University West Lafayette IN

This paper introduces a federated learning framework tailored for online combinatorial optimization with bandit feedback. In this setting, agents select subsets of arms, observe noisy rewards for these subsets without accessing individual arm information, and can cooperate and share information at specific intervals. Our framework transforms any offline resilient single-agent (α - ε)-approximation algorithm--having a complexity of Õ(ψ/εβ), where the logarithm is omitted, for some function ψ and constant β--into an online multi-agent algorithm with m communicating agents and an a-regret of no more than Õ(m-1/3+β ψ1/3+βT2+β/3+β). Our approach not only eliminates the ε approximation error but also ensures sublinear growth with respect to the time horizon T and demonstrates a linear speedup with an increasing number of communicating agents. Additionally, the algorithm is notably communication-efficient, requiring only a sublinear number of communication rounds, quantified as Õ(ψTβ/β+1). Furthermore, the framework has been successfully applied to online stochastic submodular maximization using various offline algorithms, yielding the first results for both singleagent and multi-agent settings and recovering specialized single-agent theoretical guarantees. We empirically validate our approach to a stochastic data summarization problem, illustrating the effectiveness of the proposed framework, even in single-agent scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive PID Gain Scheduling Control for Hydropower Turbine Using Neural CDE and Stochastic Distribution Shaping

引用

IEEE Access 2025年 13卷 102032-102043页

作者： Hong Wang Zhun Yin Zhong-Ping Jiang Energy and Transportation Science Division Oak Ridge National Laboratory Oak Ridge TN USA Department of Electrical and Computer Engineering New York University Brooklyn NY USA

This paper introduces a gain-scheduling PID controller design strategy for hydroturbine frequency control mode. This scheme first uses real data to learn the nonlinear dynamics of the hydroturbine using neural controlled differential equations and then perturbs the obtained nonlinear system at different equilibrium points, based on which a static output feedback adaptive dynamic programming algorithm is then used to optimize the PID gains for each equilibrium point. Moreover, a continuous-time version of stochastic distribution control is proposed to further fine-tune the optimized PID gains. Finally, the controller is obtained by implementing linear interpolation between the optimized PID control gains. The simulation results show that the proposed gain-scheduling PID controller can control a larger range of operation points compared with the given fixed PID controller and the baseline method. Compared with the given fixed PID controller, the proposed gain-scheduling PID controller can regulate hydroturbine frequency against disturbances induced by power-load variation with over 50% less overshoot for some operation points.

关键词： Stochastic processes Frequency control Output feedback Hydraulic turbines Shafts Hydroelectric power generation Neural networks Mathematical models Dynamic programming Differential equations

来源：评论

学校读者我要写书评

暂无评论

Joint Estimation of Vessel Parameter-Motion and Sea State 26

Joint Estimation of Vessel Parameter-Motion and Sea State

引用

26th International Conference on Information Fusion, FUSION 2023

作者： Nguyen, Hoa Van Luong, Hao Sgarioto, Daniel Skvortsov, Alex Arulampalam, Sanjeev Duffy, Jonathan Ranasinghe, Damith C. Curtin University School of Electrical Engineering BentleyWA Australia The University of Adelaide School of Computer Science AdelaideSA Australia Defence Science and Technology Maritime Division Australia University of Tasmania Australian Maritime College HobartTAS Australia

ISBN: (纸本)9798890344854

We consider the problem of real-time estimation of sea state and wave-induced motions on a moving vessel using onboard inertial sensors without knowing vessel's dynamic parameters (i.e., draught and breadth). This is crucial for vessel operational planning and performance, preventing structure failure, emissions reduction and fuel economy. This work proposes a new estimation approach by reformulating the conventional problem of sea state and vessel motion estimation (unknown input into a known dynamic system) as an input-state-parameter estimation problem of mass-spring-damper systems. We exploit the strong correlations between a vessel's vertical displacement and its rotation to develop a new estimation algorithm-Parameter-Sharing Extended-Augmented Kalman Filter (PS-EAKF)-for the problem to estimate the unidentified vessel parameters together with vessel motion (heave and pitch) and sea state. Experimental data from a scale-model vessel in regular head seas demonstrate the effectiveness and robustness of the proposed approach. © 2023 International Society of Information Fusion.

关键词： Condition monitoring

来源：评论

学校读者我要写书评

暂无评论

Stochastic Q-learning for large discrete action spaces 24

Stochastic Q-learning for large discrete action spaces

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Fares Fourati Vaneet Aggarwal Mohamed-Slim Alouini Computer Electrical and Mathematical Science and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal KSA School of Industrial Engineering Purdue University West Lafayette IN

In complex environments with large discrete action spaces, effective decision-making is critical in reinforcement learning (RL). Despite the widespread use of value-based RL approaches like Q-learning, they come with a computational burden, necessitating the maximization of a value function over all actions in each iteration. This burden becomes particularly challenging when addressing large-scale problems and using deep neural networks as function approximators. In this paper, we present stochastic value-based RL approaches which, in each iteration, as opposed to optimizing over the entire set of n actions, only consider a variable stochastic set of a sublinear number of actions, possibly as small as O(log(n)). The presented stochastic value-based RL methods include, among others, Stochastic Q-learning, StochDQN, and StochDDQN, all of which integrate this stochastic approach for both value-function updates and action selection. The theoretical convergence of Stochastic Q-learning is established, while an analysis of stochastic maximization is provided. Moreover, through empirical validation, we illustrate that the various proposed approaches outperform the baseline methods across diverse environments, including different control problems, achieving near-optimal average returns in significantly reduced time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Positioning and Computation Offloading in Multi-UAV MEC Networks for Low Latency Applications

Joint Optimization of Positioning and Computation Offloading...

引用

IEEE Conference on Wireless Communications and Networking

作者： Yuhui Wang Junaid Farooq Hakim Ghazzai Gianluca Setti Department of Electrical and Computer Engineering University of Michigan-Dearborn Dearborn MI USA Computer Electrical and Mathematical Sciences Division King Abdullah University of Science & Technology Saudi Arabia

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

The advent of multi-unmanned aerial vehicle (multi-UAV) networks in mobile edge computing (MEC) introduces dynamic computational topologies where UAVs, acting as mobile edge servers, are tasked with processing data from ground-based user equipment (UE). This paper addresses the dual challenges of optimizing both UAV deployment and task offloading within such networks to minimize communication latency and efficiently utilize UAV resources, which are limited by battery life and processing capabilities. We propose a bi-level optimization framework that simultaneously tackles the placement of UAVs and the distribution of computational tasks among them. At the higher level, UAV deployment is optimized to ensure minimal distance to the UEs, thereby reducing latency and energy consumption during data transmission. At the lower level, task offloading is optimized to balance the computational load across the UAV network, considering each UAV's capacity and battery constraints. We demonstrate through extensive simulations the significant improvements in system efficiency, latency, and resilience. This approach not only enhances the performance of UAV-assisted MEC networks but also provides scalable solutions adaptable to various operational scenarios.

关键词： Multi-access edge computing Simulation Autonomous aerial vehicles Batteries Topology Servers Time factors Vehicle dynamics Optimization Resilience

来源：评论

学校读者我要写书评

暂无评论

Information Compression in Dynamic Games

arXiv

引用

arXiv 2024年

作者： Tang, Dengwang Subramanian, Vijay Teneketzis, Demosthenis Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los AngelesCA90089-2560 United States Electrical and Computer Engineering Division Electrical Engineering and Computer Science Department University of Michigan Ann ArborMI48109 United States

MSC Codes 90C40, 91A10, 91A15, 91A25, 91A50One of the reasons why stochastic dynamic games with an underlying dynamic system are challenging is because strategic players have access to enormous amount of information which leads to the use of extremely complex strategies at equilibrium. One approach to resolve this challenge is to simplify players’ strategies by identifying appropriate compression of information maps so that the players can make decisions solely based on the compressed version of information, called the information state. Such maps allow players to implement their strategies efficiently. For finite dynamic games with asymmetric information, inspired by the notion of information state for single-agent control problems, we propose two notions of information states, namely mutually sufficient information (MSI) and unilaterally sufficient information (USI). Both these information states are obtained by applying information compression maps that are independent of the strategy profile. We show that Bayes-Nash Equilibria (BNE) and Sequential Equilibria (SE) exist when all players use MSI-based strategies. We prove that when all players employ USI-based strategies the resulting sets of BNE and SE payoff profiles are the same as the sets of BNE and SE payoff profiles resulting when all players use full information-based strategies. We prove that when all players use USI-based strategies the resulting set of weak Perfect Bayesian Equilibrium (wPBE) payoff profiles can be a proper subset of all wPBE payoff profiles. We identify MSI and USI in specific models of dynamic games in the literature. We end by presenting an open problem: Do there exist strategy-dependent information compression maps that guarantee the existence of at least one equilibrium or maintain all equilibria that exist under perfect recall? We show, by a counterexample, that a well-known strategy-dependent information compression map used in the literature does not possess any of the propertie

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Multi-UAV Placement for Integrated Access and Backhauling Using LLM-Driven Optimization

Multi-UAV Placement for Integrated Access and Backhauling Us...

引用

IEEE Conference on Wireless Communications and Networking

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Unmanned aerial vehicles (UAVs) can enhance wireless access by dynamically positioning themselves closer to users while maintaining a backhaul connection to cellular base stations. In scenarios where users are geographically dispersed, multiple UAVs can be orchestrated to establish multi-hop integrated access and backhaul (IAB) connections. Traditionally, finding optimal UAV placement has required computationally demanding methods, such as combinatorial optimization or reinforcement learning, which are often impractical for real-time applications due to their complexity and training requirements. Additionally, UAV operators may lack the capability to solve complex optimization problems during live operations. This paper presents a novel framework that leverages large language models (LLMs) for optimizing the placement of multiple UAVs through iterative structured prompting. The proposed method achieves near-optimal solutions in significantly fewer iterations compared to traditional methods, making it suitable for real-time deployment without extensive mathematical modeling. Simulation result demonstrate that the proposed method achieves scores over 82% of the theoretical optimal solution while reducing computational time from hours to minutes compared to the baseline deep Q network approach, ensuring robust network connectivity and service quality. The LLM-driven framework simplifies problem-solving for UAV network operators, paving the way for its application in more complex real-world scenarios.

关键词： Wireless communication Simulation Large language models Computational modeling Autonomous aerial vehicles Real-time systems Internet of Things Vehicle dynamics Optimization Backhaul networks

来源：评论

学校读者我要写书评

暂无评论

K-means Clustering Powered Context Aware Food Recommender System

K-means Clustering Powered Context Aware Food Recommender Sy...

引用

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Panwar, Minakshi Sharma, Ashish Mahela, Om Prakash Khan, Baseem Maulana Azad University Jodhpur Department of Computer Science Rajasthan India Rajasthan Rajya Vidyut Prasaran Nigam Ltd Power System Planning Division Jaipur India Hawassa University Department of Electrical Engineering Ethiopia

ISBN: (纸本)9798350315455

This paper designed a K-means clustering powered context aware food recommender system (CAFRS). The CAFRS is based on dividing the food data sets into clusters to minimize the error between the user input and available data by computing the distance between the cluster centroid and available food data in the data set of CAFRS. Recommended food has the minimum distance from the K-means clustering (KMC) centroid. Root mean square error (RMSE) and mean absolute error (MAE) are computed to evaluate requirement of the repeat orders to meet energy demand of the user. Proposed CAFRS is effective to recommend a suitable recipe for the user and RMSE and MAE are effective to estimate the requirement of repeat order. Performance of the proposed CAFRS is superior compared to a rule based food recommender system (RBFRS). This study is performed in MATLAB environment. © 2023 IEEE.

关键词： Context aware food recommender system Food preference K-means clustering Mean absolute error Root mean square error

来源：评论

学校读者我要写书评

暂无评论

End-to-End Learning of Beam Probing and RSSI-Based Multi-User Hybrid Precoding Design

End-to-End Learning of Beam Probing and RSSI-Based Multi-Use...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Asmaa Abdallah Abdulkadir Celik Ahmed Alkhateeb Ahmed M. Eltawil Computer Electrical and Mathematical Sciences and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal KSA Department of Electrical Computer and Energy Engineering Arizona State University Tempe USA

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

This paper presents an end-to-end (E2E) autoencoder learning framework that relies on unsupervised deep learning for the joint design of millimeter wave (mmWave) probing beams and hybrid precoding matrices in multi-user communication systems. Our model utilizes prior channel observations to achieve two main objectives: designing a compact set of probing beams and predicting off-grid radio frequency (RF) beamforming vectors. The E2E learning framework optimizes probing beams in an unsupervised manner, concentrating sensing power on promising spatial directions based on the environment. To this aim, we develop a neural network architecture respecting RF chain constraints and model received signal strength (RSS) using complex-valued convolutional layers. The autoencoder is trained to directly produce RF beamforming vectors for hybrid architectures based on projected RSS indicators (RSSIs). Once RF beamforming vectors for multi-users are predicted, baseband digital precoders are designed by accounting for multi-user interference. The autoencoder neural network is trained E2E in an unsupervised manner with a customized loss function aimed at maximizing RSS. In a system with 64 antennas, 4 RF chains, and 4 users, our approach requires only 8 probing beams to design RF beamforming vectors, compared to the conventional predefined codebooks with 64 or 128 beams.

关键词： Radio frequency Array signal processing Precoding Autoencoders Neural networks Millimeter wave technology Interference Predictive models Vectors Millimeter wave communication

来源：评论

学校读者我要写书评

暂无评论

Ultra-flexible semitransparent organic photovoltaics

引用

npj Flexible Electronics 2023年第1期7卷 274-282页

作者： Hanbee Lee Soyeong Jeong Jae-Hyun Kim Yong-Ryun Jo Hyeong Ju Eun Byoungwook Park Sung Cheol Yoon Jong H.Kim Seung-Hoon Lee Sungjun Park Department of Electrical and Computer Engineering Ajou UniversitySuwon 16499Republic of Korea Department of Chemistry and Centre for Processable Electronics Imperial College LondonWhite City W120BZUK Department of Intelligence Semiconductor Engineering Ajou UniversitySuwon 16499Republic of Korea Advanced Photonics Research Institute(APRI) Gwangju Institute of Science and Technology(GIST)Gwangju 61005Republic of Korea Division of Molecular Science and Technology Ajou UniversitySuwon 16499Republic of Korea Division of Advanced Materials Korea Research Institute of Chemical Technology(KRICT)Daejeon 34114Republic of Korea Division of Advanced materials Engineering Kongju National University1223-24 Cheonan-daeroSeobuk-guCheonan-siChungcheongnam-doRepublic of Korea

Ultra-flexible organic photovoltaics(OPVs)are promising candidates for next-generation power sources owing to their low weight,transparency,and ***,obtaining ultra-flexibility under extreme repetitive mechanical stress while maintaining optical transparency remains challenging because of the intrinsic brittleness of transparent ***,we introduce straindurable ultra-flexible semitransparent OPVs with a thickness below 2μ*** conformal surface coverage of nanoscale thin metal electrodes(<10 nm)is achieved,resulting in extremely low flexural rigidity and high strain ***-depth optical and electrical analyses on ultrathin metal electrodes showed that the devices maintain over 73%of their initial efficiency after 1000 cycles of repetitive compression and release at 66%compressive strain,and the average visible light transmittances remain higher than 30%.To our knowledge,this is the first systematical study on mechanical behaviors of strain-durable ultra-flexible ST-OPVs through precise adjustment of each ultrathin electrode thickness toward the emergence of next-generation flexible power sources.

关键词： transparency durability rigidity

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：