检索结果-内蒙古大学图书馆

Hamiltonian Learning using Machine Learning Models Trained with Continuous Measurements

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tucker, Kris Rege, Amit Kiran Smith, Conor Monteleoni, Claire Albash, Tameem Department of Applied Math University of Colorado Boulder United States Department of Computer Science University of Colorado Boulder United States Center for Quantum Information and Control University of New Mexico University of New Mexico AlbuquerqueNM United States Department of Electrical and Computer Engineering University of New Mexico AlbuquerqueNM United States INRIA Centre de Recherche de Paris France Center for Computing Research Sandia National Laboratories AlbuquerqueNM87185 United States

We build upon recent work on using Machine Learning models to estimate Hamiltonian parameters using continuous weak measurement of qubits as input. We consider two settings for the training of our model: (1) supervised learning where the weak measurement training record can be labeled with known Hamiltonian parameters, and (2) unsupervised learning where no labels are available. The first has the advantage of not requiring an explicit representation of the quantum state, thus potentially scaling very favorably to a larger number of qubits. The second requires the implementation of a physical model to map the Hamiltonian parameters to a measurement record, which we implement using an integrator of the physical model with a recurrent neural network to provide a model-free correction at every time step to account for small effects not captured by the physical model. We test our construction on a system of two qubits and demonstrate accurate prediction of multiple physical parameters in both the supervised and unsupervised contexts. We demonstrate that the model benefits from larger training sets establishing that it is in fact "learning," and we show robustness to errors in the assumed physical model by achieving accurate parameter estimation in the presence of unanticipated single particle relaxation. © 2024, CC BY.

关键词： Qubits

Learning from Heterogeneity: A Dynamic Learning Framework for Hypergraphs

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Tiehua Liu, Yuze Shen, Zhishu Ma, Xingjun Qi, Peng Ding, Zhijun Jin, Jiong The School of Computer Science and Technology Tongji University Shanghai China Ant Group Shanghai China The School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China The School of Computer Science Fudan University Shanghai China The Department of Control Science and Engineering Tongji University Shanghai China The School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne Australia

Graph neural network (GNN) has gained increasing popularity in recent years owing to its capability and flexibility in modeling complex graph structure data. Among all graph learning methods, hypergraph learning is a technique for exploring the implicit higher-order correlations when training the embedding space of the graph. In this paper, we propose a hypergraph learning framework named Learning from Heterogeneity (LFH) that is capable of dynamic hyperedge construction and attentive embedding update utilizing the heterogeneity attributes of the graph. Specifically, in our framework, the high-quality features are first generated by the pairwise fusion strategy that utilizes explicit graph structure information when generating initial node embedding. Afterwards, a hypergraph is constructed through the dynamic grouping of implicit hyperedges, followed by the type-specific hypergraph learning process. To evaluate the effectiveness of our proposed framework, we conduct comprehensive experiments on several popular datasets with twelve state-of-the-art models on both node classification and link prediction tasks, which fall into categories of homogeneous pairwise graph learning, heterogeneous pairwise graph learning, and hypergraph learning. The experiment results demonstrate a significant performance gain (an average of 12.9% in node classification and 12.8% in link prediction) compared with recent state-of-the-art methods. © 2023, CC BY.

关键词： Contrastive Learning

Foreign Material Detection and Localization in Stored Grain with Passive RFID Tag Arrays

学校读者我要写书评

暂无评论

Foreign Material Detection and Localization in Stored Grain ...

IEEE International Conference on RFID-Technology and Applications (RFID-TA)

作者： Erbo Shen Weidong Yang Xuyu Wang Shiwen Mao Henan Key Laboratory of Grain Photoelectric Detection & Control Henan University of Technology Zhengzhou China Kaifeng University Kaifeng China College of Information Science & Engineering Henan University of Technology Zhengzhou China Knight Foundation School of Computing & Information Sciences Florida International University Miami FL USA Department of Electrical and Computer Engineering Auburn University Auburn AL USA

In the early stage of harvesting, transportation, and storage, the grain could be mingled with clods from the field, metal pieces from aging machines, and other objects of foreign material, which will greatly influence the grain quality and food security. In this paper, we propose a novel radio frequency (RF) sensing system termed TagSee, which leverages passive RFID tag arrays. The goal is to simultaneously sense the presence of foreign materials and locate their locations in the 3D space, to automatically monitor the stored grain. Specifically, we use RFID received signal strength (RSS) and phase as features for foreign material detection. To design the TagSee system, we first introduce a sensing space division method. Then, an Euclidean Distance Ratio (EDR) algorithm and a heuristic method are proposed to achieve high localization accuracy. Experimental results show that TagSee can effectively detect foreign materials in stored grain and achieve a centimeter-level localization accuracy.

关键词：

Federated Reinforcement Learning for Electric Vehicles Charging control on Distribution Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qian, Junkai Jiang, Yuning Liu, Xin Wang, Qiong Wang, Ting Shi, Yuanming Chen, Wei The MoE Engineering Research Center of Software/Hardware Co-design Technology and Application The Shanghai Key Lab. of Trustworthy Computing East China Normal University China The Automatic Control Laboratory EPFL Switzerland The School of Information Science and Technology ShanghaiTech University China The State Grid Beijing Electric Power Company China The Department of Electronic Engineering Tsinghua University China

With the growing popularity of electric vehicles (EVs), maintaining power grid stability has become a significant challenge. To address this issue, EV charging control strategies have been developed to manage the switch between vehicle-to-grid (V2G) and grid-to-vehicle (G2V) modes for EVs. In this context, multi-agent deep reinforcement learning (MADRL) has proven its effectiveness in EV charging control. However, existing MADRL-based approaches fail to consider the natural power flow of EV charging/discharging in the distribution network and ignore driver privacy. To deal with these problems, this paper proposes a novel approach that combines multi-EV charging/discharging with a radial distribution network (RDN) operating under optimal power flow (OPF) to distribute power flow in real time. A mathematical model is developed to describe the RDN load. The EV charging control problem is formulated as a Markov Decision Process (MDP) to find an optimal charging control strategy that balances V2G profits, RDN load, and driver anxiety. To effectively learn the optimal EV charging control strategy, a federated deep reinforcement learning algorithm named FedSAC is further proposed. Comprehensive simulation results demonstrate the effectiveness and superiority of our proposed algorithm in terms of the diversity of the charging control strategy, the power fluctuations on RDN, the convergence efficiency, and the generalization ability. © 2023, CC BY-NC-SA.

关键词： Reinforcement learning

Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Qiong Li, Jiahan Dai, Pingyang Ye, Qixiang Cao, Liujuan Wu, Yongjian Ji, Rongrong Institute of Artificial Intelligence The Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Xiamen University Xiamen361005 China School of Information and Control Engineering China University of Mining and Technology Xuzhou221000 China The Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Xiamen University Xiamen361005 China The Peng Cheng Laboratory Shenzhen518066 China The School of Electronics Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China The Media Analytics and Computing Lab Department of Computer Science School of Informatics Xiamen University Xiamen361005 China The Youtu Laboratory Tencent Shanghai200233 China The Fujian Engineering Research Center of Trusted Artificial Intelligence Analysis and Application Institute of Artificial Intelligence Xiamen University Xiamen361005 China

Unsupervised domain adaptation person re-identification (Re-ID) aims to identify pedestrian images within an unlabeled target domain with an auxiliary labeled source-domain dataset. Many existing works attempt to recover reliable identity information by considering multiple homogeneous networks. And take these generated labels to train the model in the target domain. However, these homogeneous networks identify people in approximate subspaces and equally exchange their knowledge with others or their mean net to improve their ability, inevitably limiting the scope of available knowledge and putting them into the same mistake. This paper proposes a Dual-level Asymmetric Mutual Learning method (DAML) to learn discriminative representations from a broader knowledge scope with diverse embedding spaces. Specifically, two heterogeneous networks mutually learn knowledge from asymmetric subspaces through the pseudo label generation in a hard distillation manner. The knowledge transfer between two networks is based on an asymmetric mutual learning manner. The teacher network learns to identify both the target and source domain while adapting to the target domain distribution based on the knowledge of the student. Meanwhile, the student network is trained on the target dataset and employs the ground-truth label through the knowledge of the teacher. Extensive experiments in Market-1501, CUHK-SYSU, and MSMT17 public datasets verified the superiority of DAML over state-of-the-arts. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

Frustration Elimination and Excited State Search in Coherent Ising Machines

学校读者我要写书评

暂无评论

Physical Review Letters 2025年第9期134卷 090401-090401页

作者： Zheng-Yang Zhou Clemens Gneiting J. Q. You Franco Nori Zhejiang Key Laboratory of Quantum State Control and Optical Field Manipulation Department of Physics Zhejiang Sci-Tech University 310018 Hangzhou China Theoretical Quantum Physics Laboratory Cluster for Pioneering Research RIKEN Wakoshi Saitama 351-0198 Japan Center for Quantum Computing RIKEN Wakoshi Saitama 351-0198 Japan Zhejiang Key Laboratory of Micro-Nano Quantum Chips and Quantum Control School of Physics and State Key Laboratory for Extreme Photonics and Instrumentation Zhejiang University Hangzhou 310027 China College of Optical Science and Engineering Zhejiang University Hangzhou 310027 China Physics Department The University of Michigan Ann Arbor Michigan 48109-1040 USA

Frustration, that is, the impossibility of satisfying the energetic preferences between all spin pairs simultaneously, underlies the complexity of many fundamental properties in spin systems, including the computational difficulty in determining their ground states. Coherent Ising machines (CIMs) have been proposed as a promising analog computational approach to efficiently find different degenerate ground states of large and complex Ising models. However, CIMs also face challenges in solving frustrated Ising models: frustration not only reduces the probability of finding good solutions, but it also prohibits the leveraging of quantum effects in doing so. To circumvent these detrimental effects of frustration, we show how frustrated Ising models can be mapped to frustration-free CIM configurations by including ancillary modes and modifying the coupling protocol used in current CIM designs. Such frustration elimination may empower current CIMs to benefit from quantum effects in dealing with frustrated Ising models. In addition, these ancillary modes can also enable error detection and searching for excited states.

关键词： Ising model

Full life-cycle cost model for practical application of solar energy system

学校读者我要写书评

暂无评论

Energy Informatics 2025年第1期8卷

作者： Sha, Ang Xiong, Zhen Zang, Xiaolin Zhao, Wei Ge, Ruibang Yao, Wanxiang Aiello, Marco Innovation Institute for Sustainable Maritime Architecture Research and Technology Qingdao University of Technology Qingdao266033 China School of Architecture and Urban Planning Qingdao University of Technology Qingdao266033 China School of Information and Control Engineering Qingdao University of Technology Qingdao266520 China School of Continuing Education Qingdao University of Technology Qingdao266033 China Service Computing Department Institute of Architecture of Application Systems University of Stuttgart Universitätsstraße 38 Stuttgart70569 Germany

In pursuit of carbon neutrality, a swift transformation is underway in the global energy structure, marked by a consistent rise in the installed capacity of solar energy systems. Meanwhile, the substantial reduction of government subsidies in the solar industry intensifies focus on the economic viability of solar energy installations. In this study, we propose a full life-cycle cost model, named the F-LCC model, for calculating the cost of the solar energy system on the long term, e.g., 20–30 years. This model integrates replacement costs, residual value calculation, interest rate, and inflation impacts while supporting market price estimation for individual components, thereby aiding feasibility analysis in the early project phase. We design an investment cost recovery algorithm based on the F-LCC model to calculate the break-even electricity price for solar energy system. Moreover, we analyze component cost distributions, Net Present Value (NPV), and Discounted Payback Period (DPP) for grid-connected and off-grid solar energy systems with capacities of 10 kWp and 100 kWp in the Chinese market. The results show that the proposed model, compared to other models, captures the fact that payback times are longer. In a solar energy system without storage, solar panels have the highest component cost share at 28.8%. With battery storage, batteries dominate the total cost, reaching up to 74.6%. And the the grid-connected systems DPP ranging from a minimum of 5.5 to a maximum of 7.0 years by grid-connected electricity price, while off-grid systems require at least 19.9 years. The 10 kWp off-grid fixed mounting system’s break-even price being 137.1% higher than its grid-connected counterpart. In addition, tracking-mount systems offer greater cost-reduction potential than fixed installations, with the payback period reduced by 20% for 100 kWp grid-connected systems and 15% for off-grid systems. Finally, we develop a plugin based on the F-LCC model. These findings deepen unde

关键词： Commerce

Towards Dynamic Reconfiguration of Composite Services Via Failure Estimation of General and Domain Quality of Services

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Liu, Zhizhong Zheng, Hedan Sheng, Qaun Z. Chu, Dianhui Yu, Jian Xu, Xiaofei School of Computer and Control Engineering Yantai University Yantai264005 China Weihai264209 China School of Computing Macquarie University SydneyNSW2109 Australia Department of Computer Science Auckland University of Technology Auckland1142 New Zealand

Composite services (CSs) are large-grained services composed of simple ones to satisfy users’ complex requirements. A major issue concerning a CS is that the general quality of service (GQoS) and the domain quality of service (DQoS) of its component services often fail for environment changes. To tackle this problem, we propose an approach for dynamic reconfiguration of CSs by considering both GQoS and DQoS failures. Our approach includes three stages: at the first stage, we estimate the failure judgement basis of GQoS and DQoS for each component services based on global GQoS decomposition and statistical method. At the second stage, during the execution of a CS, we proactively estimate whether the component services to be executed will encounter GQoS or DQoS failure based on GQoS and DQoS joint *** the third stage, when the component service to be executed encounters GQoS or DQoS failure, we reconfigure the CS by replacing the failed component service with a best-matched similar service, while the predicted GQoS and DQoS of the matched service can satisfy the local GQoS and DQoS constraints of the failed component services. Extensive experiments have been carried out to demonstrate the effectiveness and performance superiority of our approach. © 2022, The Authors. All rights reserved.

关键词： Quality of service

Synthesis of the Decision Support System for controlling the Process of Combined Destruction of Butyl Rubber Vulcanizates 3

学校读者我要写书评

暂无评论

Synthesis of the Decision Support System for Controlling the...

3rd International Conference on control Systems, Mathematical Modeling, Automation and Energy Efficiency, SUMMA 2021

作者： Tikhomirov, German Karmanov, Andrey Zhatova, Victoria Popov, Alexey Obraztsov, Nikolay Podvalny, Evgeniy Voronezh State University Department of System Analysis and Management Voronezh Russia Voronezh State Technical University Department of Automated and Computing Systems Voronezh Russia Voronezh State University Department of Geoecology of Environmental Monitoring Voronezh Russia Voronezh State University of Engineering Technologies Department of Information and Control Systems Voronezh Russia Russian Presidental Academy of National Economy and Public Administration Department of Mathematics and Information Technologies in Management Moscow Russia

ISBN: (纸本)9781665439817

the article is devoted to solving the problems of synthesis of algorithmic support of the decision support system for the controlled destruction of resin vulcanizates of butyl rubber. As an object of research, the destruction processes have been selected, which are carried out by combining external destructive factors: ionization irradiation and subsequent thermomechanical treatment. Based on the results of the system analysis of the destruction process stages as control objects, the main and cross system connections between the input, internal parameters of the process and the physical properties of the final product have been revealed. The most preferred channels for controlling the rate of physical and chemical processes occurring during destruction have been selected. Using a combination of control actions, a method and an algorithm for controlling the stages of destruction has been proposed, which allows for programmed control of the operating parameters of the process to obtain reclaimed butyl rubber with target quality indicators. The structural synthesis of the mathematical support of the decision support system, which calculates the optimal values of the process parameters in accordance with the formed search criteria, has been carried out. An algorithm for controlling the destruction process has been developed, which calculates the optimal parameters of the process using the mathematical tools, which includes the Choquet integral, the Sugeno fuzzy measure, and a genetic algorithm for solving optimization problems. © 2021 IEEE.

关键词： Irradiation