检索结果-南通市图书馆

Online Pareto optimal control of mean-field stochastic multi-player systems using policy iteration

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第4期67卷 21-37页

作者： Xiushan jiang Yanshuang WANG Dongya ZHAO Ling SHI College of New Energy China University of Petroleum(East China) Department of Electronic and Computer Engineering Hong Kong University of Science and Technology

In this study, the Pareto optimal strategy problem was investigated for multi-player mean-field stochastic systems governed by It? differential equations using the reinforcement learning(RL) method.A partially model-free solution for Pareto-optimal control was derived. First, by applying the convexity of cost functions, the Pareto optimal control problem was solved using a weighted-sum optimal control problem. Subsequently, using on-policy RL, we present a novel policy iteration(PI) algorithm based on the Hrepresentation technique. In particular, by alternating between the policy evaluation and policy update steps,the Pareto optimal control policy is obtained when no further improvement occurs in system performance,which eliminates directly solving complicated cross-coupled generalized algebraic Riccati equations(GAREs).Practical numerical examples are presented to demonstrate the effectiveness of the proposed algorithm.

关键词： mean-field stochastic systems Pareto optimal control policy iteration scheme $\mathcal{H}$-representation

STDNet: A Spatio-Temporal Decomposition Neural Network for Multivariate Time Series Forecasting

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第4期29卷 1232-1247页

作者： Zhuolun jiang Zefei Ning Hao Miao Li Wang College of Computer Science and Technology(College of Data Science) Taiyuan University of TechnologyJinzhong 030600China

Long-term multivariate time series forecasting is an important task in engineering applications. It helps grasp the future development trend of data in real-time, which is of great significance for a wide variety of fields. Due to the non-linear and unstable characteristics of multivariate time series, the existing methods encounter difficulties in analyzing complex high-dimensional data and capturing latent relationships between multivariates in time series, thus affecting the performance of long-term prediction. In this paper, we propose a novel time series forecasting model based on multilayer perceptron that combines spatio-temporal decomposition and doubly residual stacking, namely Spatio-Temporal Decomposition Neural Network (STDNet). We decompose the originally complex and unstable time series into two parts, temporal term and spatial term. We design temporal module based on auto-correlation mechanism to discover temporal dependencies at the sub-series level, and spatial module based on convolutional neural network and self-attention mechanism to integrate multivariate information from two dimensions, global and local, respectively. Then we integrate the results obtained from the different modules to get the final forecast. Extensive experiments on four real-world datasets show that STDNet significantly outperforms other state-of-the-art methods, which provides an effective solution for long-term time series forecasting.

关键词： time series forecasting multivariate time series spatio-temporal decomposition

Metal reflector-enhanced thermoacoustic imaging as a guidance for puncture biopsy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Innovative Optical Health Sciences 2024年第6期17卷 83-96页

作者： Shuang Du Tao Qiang Zihui Chi Huabei jiang School of Optoelectronic Engineering Chongqing University of Posts and TelecommunicationsChongqing 400065P.R.China Department of Medical Engineering University of South FloridaTampaFL 33620USA

Puncture biopsy is an important clinical technique to obtain diseased tissue for pathological diagnosis,where imaging guidance is *** this paper,we describe a metal reflector-enhanced microwave-induced thermoacoustic imaging(TAI)approach capable of guiding puncture biopsy for detection of breast cancer and joint *** experimentations simulating puncture guidance in breast cancer and knee gout models werefirst conducted using(CST STUDIO SUITE)(CST)software,and then ex-vivo experiments were performed followed by qualitative observations and semi-quantitative *** results of both the simulations and ex-vivo experiments showed that our reflector-enhanced TAI could image the puncture needle in high resolution with a large depth of>12 cm.

关键词： Microwave-induced thermoacoustic imaging puncture guidance reflector

FNNWV: farthest-nearest neighbor-based weighted voting for class-imbalanced crowdsourcing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第10期67卷 172-188页

作者： Wenjun ZHANG Liangxiao jiang Ziqi CHEN Chaoqun LI School of Computer Science China University of Geosciences Key Laboratory of Artificial Intelligence Ministry of Education School of Mathematics and Physics China University of Geosciences

In crowdsourcing scenarios, we can hire crowd workers to label crowdsourced tasks and then use label integration algorithms to infer the integrated label for each instance in the tasks. As more and more label integration algorithms are proposed, the performance of inference based only on the information of the inferred instance gradually converges. Recent algorithms attempt to exploit the information of the inferred instance's nearest neighbors to infer and achieve good performance. However, when crowdsourced tasks are class-imbalanced, negative instances are more easily to occur in the nearest neighbors because negative instances are the majority, and thus recent algorithms are more easily biased toward the negative class. To this end, in this paper, we propose a novel label integration algorithm called farthest-nearest neighbor-based weighted voting(FNNWV) for class-imbalanced crowdsourcing. Specifically, FNNWV considers the nearest neighbors to be more similar to the inferred instance and thus uses them to vote ayes in weighted voting. Yet at the same time, FNNWV considers the farthest neighbors to be more different from the inferred instance and thus uses them to vote nays in weighted voting. Since negative instances are easier to occur in both the nearest neighbors and the farthest neighbors, FNNWV weakens the effect of negative instances by voting ayes and nays. The experimental results on 22 simulated and one real-world crowdsourced datasets show that FNNWV significantly outperforms all the other state-of-the-art competitors.

关键词： crowdsourcing label integration nearest neighbor farthest neighbor weighted voting

Robust boundary-induced bulk propagations in elastic waveguides with nonplanar surfaces

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2024年第4期67卷 88-96页

作者： Baizhan Xia Jielong Zhang Zihan jiang Jianting Liu State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan UniversityChangsha 410082China College of Mechanical and Vehicle Engineering Hunan UniversityChangsha 410082China

Trivial elastic waveguides induced by line defects and nontrivial elastic waveguides protected by topological edge states have been extensively examined in planar waveguide *** these investigations,little is known about topologically protected bulk states and their resulting robust transmission properties,especially in nonplanar elastic waveguides with folded,curved,and twisted *** Dirac waveguides with robust boundary-induced bulk states are *** states arise from the truncated boundaries of bulks with linear Dirac conical dispersions,differing from topologically protected edge states ensured by the bulk-edge *** proof is provided,in which boundary-induced bulk states show robustly high-throughput transmissions along the waveguides,even with folded,curved,and twisted *** results not only open up new avenues for examining novel topological phenomena about bulk but also offer new platforms for developing topological devices with nonplanar surfaces.

关键词： elastic waveguides boundary-induced bulk propagations Dirac conical dispersions nonplanar surfaces

New black-to-white hole solutions with improved geometry and energy conditions

在线全文

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2024年第7期67卷 30-43页

作者： Zhongwen Feng Yi Ling Xiaoning Wu Qingquan jiang School of Physics and Astronomy China West Normal UniversityNanchong 637009China Institute of High Energy Physics Chinese Academy of SciencesBeijing 100049China School of Physics University of Chinese Academy of SciencesBeijing 100049China Institute of Mathematics Academy of Mathematics and System Science and Hua Loo-Keng Key Laboratory of MathematicsChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100190China

We construct new black-to-white hole solutions which connect the geometry of spacetime at some gluing surface inside the *** continuity of the metric can be guaranteed up to the arbitrary order which is controlled by the power factor *** sort of black-to-white holes is characterized by the sub-Planckian scalar curvature,independent of the mass of black-to-white *** importantly,we show that the energy condition is only violated within a small region near the gluing *** geodesics of particles within the region from black hole to white hole is also *** turns out that the matter falling into the black hole may pass through the center without singularity and come out from the white *** scenario provides novel ideas for understanding the information loss paradox in traditional black hole physics.

关键词： regular black hole energy condition singularity quantum gravity

Information manifold and fault detection of multi-agent systems

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第10期37卷 410-423页

作者： Ruotong QU Bin jiang Yuehua CHENG Xiaodong HAN College of Automation Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China China Academy of Space Technology Beijing 100098China

With the increase of the number of agents in multi-agent systems and the rapid increase of the complexity of the overall structure of the system,the fault detection and diagnosis work has brought great *** have carried out considerable research work on fault detection and diagnosis of multi-agent systems,but there is no research on fault state estimation and diagnosis based on the information and state of the whole multi-agent *** on the global perspective of information geometry theory,this paper presents two new physical quantities of the information manifold of multi-agent systems,as Lagrangian and energy–momentum tensor,to express the state of the overall information of multi-agent systems,and to characterize the energy state and development trend of *** this paper,two new physical parameters are introduced into the research of multi-agent fault detection and diagnosis,and the fault state and trend of multi-agent system are evaluated from the global perspective,which provides more comprehensive theoretical support for designing more scientific and reasonable fault diagnosis and fault recovery *** of the application example confirms the competitive performance of the proposed method.

关键词： Multi-Agent Systems(MASs) Fault information manifold Lagrangian Fault detection Energy-momentum Tensor

Physical neural networks with self-learning capabilities

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2024年第8期67卷 23-42页

作者： Weichao Yu Hangwen Guo jiang Xiao Jian Shen State Key Laboratory of Surface Physics and Institute for Nanoelectronic Devices and Quantum Computing Fudan UniversityShanghai 200433China Zhangjiang Fudan International Innovation Center Fudan UniversityShanghai 201210China Department of Physics Fudan UniversityShanghai 200433China Shanghai Research Center for Quantum Sciences Shanghai 201315China Collaborative Innovation Center of Advanced Microstructures Nanjing 210093China

Physical neural networks are artificial neural networks that mimic synapses and neurons using physical systems or *** networks harness the distinctive characteristics of physical systems to carry out computations effectively,potentially surpassing the constraints of conventional digital neural networks.A recent advancement known as“physical self-learning”aims to achieve learning through intrinsic physical processes rather than relying on external *** article offers a comprehensive review of the progress made in implementing physical self-learning across various physical *** learning strategies that contribute to the realization of physical self-learning are *** challenges in understanding the fundamental mechanism of learning,this work highlights the progress towards constructing intelligent hardware from the ground up,incorporating embedded self-organizing and self-adaptive dynamics in physical systems.

关键词： self-learning physical neural networks neuromorphic computing physical learning

Piezoelectric sensing method for segmental joint contact stress during shield tunnel construction

在线全文

学校读者我要写书评

暂无评论

Underground Space 2024年第4期17卷 82-99页

作者： Guodong jiang Minghao Dai Guozhu Zhang Limin Gao Institute of Geotechnical Engineering Southeast UniversityNanjing 211189China Nanjing Metro Group Co.Ltd Nanjing 210000China No.4 Construction Company of China Petroleum Pipeline Engineering Co.Ltd Langfang 065000China

The emergence of curved shield tunnels poses a significant construction *** the quality of the segment assembly is not guaranteed,many segment cracks and damage will result from the stress *** the contact stresses between segmental joints is necessary to improve the quality of segments assembled for shield tunnel *** difluoride(PVDF)piezoelectric material was chosen for the sensor because it can convert contact stresses into electrical signals,allowing the state of the segmental joints to be effectively *** matches the working environment between the segmental joints of the shield tunnel,where flexible structures such as rubber gaskets and force transfer pads are *** study proposes a piezoelectric sensing method for segmental joints in shield tunnels and conducts laboratory tests,numerical analyses,and field tests to validate the feasibility of the *** results indicate that the PVDF film sensor can effectively sense the entire compression process of the gasket with different amounts of *** piezoelectric cable sensor can effectively sense the joint offset direction of the *** differently shaped sections,the variation in the force sensed by the piezoelectric cable sensors was different,as verified by numerical *** the field test,it was found that the average contact stress between the segmental joints was in the range of 1.2–1.8 MPa during construction of the curved shield *** location of the segmental joints and the type of segment affect the contact stress *** field monitoring results show that piezoelectric sensing technology can be successfully applied during assembly of the segments for effective sensing of the contact stress.

关键词： Shield tunnel Segmental joint Contact stress Piezoelectric sensor