检索结果-南通市图书馆

Reconstruction algorithm for cross-waveband optical computing imaging

在线全文

学校读者我要写书评

暂无评论

chinese Physics B 2024年第10期33卷 233-239页

作者： Jin-Tao Xie Shu-Hang Bie Ming-Fei Li Yuan-Jin Yu Yi-Fei Li Jin-Guang Wang Bao-Gang Quan Ling-An Wu institute of Physics Chinese Academy of SciencesBeijing 100190China School of Physical sciences University of Chinese Academy of SciencesBeijing 100049China School of automation Beijing Institute of TechnologyBeijing 100081China

In a single-pixel fast imaging setup,the data collected by the single-pixel detector needs to be processed by a computer,but the speed of the latter will affect the image reconstruction *** we propose two kinds of setups which are able to transform non-visible into visible light imaging,wherein their computing process is replaced by a camera integration *** image captured by the camera has a low contrast,so here we present an algorithm that can realize a high quality image in near-infrared to visible cross-waveband *** scheme is verified both by simulation and in actual *** setups demonstrate the great potential for single-pixel imaging and high-speed cross-waveband imaging for future practical applications.

关键词： optical computing imaging single-pixel imaging

Fixed-Time Antidisturbance Consensus Tracking for Nonlinear Multiagent Systems With Matching and Mismatching Disturbances

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第6期11卷 1410-1423页

作者： Xiangmin Tan Chunyan Hu Guanzhen Cao Qinglai Wei Wei Li Bo Han institute of Engineering Thermophysics Chinese Academy of SciencesBeijing 100190 School of Aeronautics and Astronautics University of Chinese Academy of SciencesBeijing 100049China institute of automation Chinese Academy of SciencesBeijing 100190 School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China IEEE

In this paper,fixed-time consensus tracking for mul-tiagent systems(MASs)with dynamics in the form of strict feed-back affine nonlinearity is addressed.A fixed-time antidistur-bance consensus tracking protocol is proposed,which consists of a distributed fixed-time observer,a fixed-time disturbance observer,a nonsmooth antidisturbance backstepping controller,and the fixed-time stability analysis is conducted by using the Lyapunov theory *** paper includes three main ***,a distributed fixed-time observer is developed for each follower to obtain an estimate of the leader’s output by utilizing the topology of the communication ***,a fixed-time disturbance observer is given to estimate the lumped disturbances for feedforward ***,a nonsmooth antidisturbance backstepping tracking controller with feedforward compensation for lumped disturbances is *** order to mitigate the“explosion of complexity”in the tradi-tional backstepping approach,we have implemented a modified nonsmooth command filter to enhance the performance of the closed-loop *** simulation results show that the pro-posed method is effective.

关键词： Antidisturbance backstepping consensus tracking fixed-time stability multiagent system(MASs) strict feedback affine nonlinear systems.

A Knowledge-enhanced Two-stage Generative Framework for Medical Dialogue Information Extraction

在线全文

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第1期21卷 153-168页

作者： Zefa Hu Ziyi Ni Jing Shi Shuang Xu Bo Xu School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China institute of automation Chinese Academy of SciencesBeijing 100190China

This paper focuses on term-status pair extraction from medical dialogues(MD-TSPE),which is essential in diagnosis dia-logue systems and the automatic scribe of electronic medical records(EMRs).In the past few years,works on MD-TSPE have attracted increasing research attention,especially after the remarkable progress made by generative ***,these generative methods output a whole sequence consisting of term-status pairs in one stage and ignore integrating prior knowledge,which demands a deeper un-derstanding to model the relationship between terms and infer the status of each *** paper presents a knowledge-enhanced two-stage generative framework(KTGF)to address the above *** task-specific prompts,we employ a single model to com-plete the MD-TSPE through two phases in a unified generative form:We generate all terms the first and then generate the status of each generated *** this way,the relationship between terms can be learned more effectively from the sequence containing only terms in the first phase,and our designed knowledge-enhanced prompt in the second phase can leverage the category and status candidates of the generated term for status ***,our proposed special status"not mentioned"makes more terms available and en-riches the training data in the second phase,which is critical in the low-resource *** experiments on the Chunyu and CMDD datasets show that the proposed method achieves superior results compared to the state-of-the-art models in the full training and low-re-sourcesettings.

关键词： Medical dialogue understanding information extraction text generation knowledge-enhanced prompt low-resource setting dataaugmentation

Learning Top-K Subtask Planning Tree Based on Discriminative Representation Pretraining for Decision-making

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第4期21卷 782-800页

作者： Jingqing Ruan Kaishen Wang Qingyang Zhang Dengpeng Xing Bo Xu institute of automation Chinese Academy of SciencesBeijing 100190China School of Future Technology University of Chinese Academy of SciencesBeijing 100049China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China

Decomposing complex real-world tasks into simpler subtasks and devising a subtask execution plan is critical for humans to achieve effective ***,replicating this process remains challenging for AI agents and naturally raises two questions:(1)How to extract discriminative knowledge representation from priors?(2)How to develop a rational plan to decompose complex problems?To address these issues,we introduce a groundbreaking framework that incorporates two main ***,our multiple-encoder and individual-predictor regime goes beyond traditional architectures to extract nuanced task-specific dynamics from datasets,enriching the feature space for ***,we innovate in planning by introducing a top-K subtask planning tree generated through an attention mechanism,which allows for dynamic adaptability and forward-looking *** framework is empirically validated against challenging benchmarks BabyAI including multiple combinatorially rich synthetic tasks(e.g.,GoToSeq,SynthSeq,BossLevel),where it not only outperforms competitive baselines but also demonstrates superior adaptability and effectiveness incomplex task decomposition.

关键词： Reinforcement learning representation learning subtask planning task decomposition pretraining.

Enhancing Multi-agent Coordination via Dual-channel Consensus

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第2期21卷 349-368页

作者： Qingyang Zhang Kaishen Wang Jingqing Ruan Yiming Yang Dengpeng Xing Bo Xu institute of automation Chinese Academy of SciencesBeijing 100190China School of Future Technology University of Chinese Academy of SciencesBeijing 100049China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China

Successful coordination in multi-agent systems requires agents to achieve *** works propose methods through information sharing,such as explicit information sharing via communication protocols or exchanging information implicitly via behavior ***,these methods may fail in the absence of communication channels or due to biased *** this work,we propose to develop dual-channel consensus(DuCC)via contrastive representation learning for fully cooperative multi-agent systems,which does not need explicit communication and avoids biased *** comprises two types of consensus:temporally extended consensus within each agent(inner-agent consensus)and mutual consensus across agents(inter-agent consensus).To achieve DuCC,we design two objectives to learn representations of slow environmental features for inner-agent consensus and to realize cognitive consistency as inter-agent *** DuCC is highly general and can be flexibly combined with various MARL *** extensive experiments on StarCraft multi-agent challenge and Google research football demonstrate that our method efficiently reaches consensus and performs superiorly to state-of-the-art MARL algorithms.

关键词： Multi-agent reinforcement learning contrastive representation learning consensus multi-agent cooperation cognitive consistency

A survey on facial image deblurring

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2024年第1期10卷 3-25页

作者： Bingnan Wang Fanjiang Xu Quan Zheng institute of Software Chinese Academy of SciencesBeijing100190China University of chinese academy of sciences Beijing100049China

When a facial image is blurred,it significantly affects high-level vision tasks such as face *** purpose of facial image deblurring is to recover a clear image from a blurry input image,which can improve the recognition accuracy,***,general deblurring methods do not perform well on facial ***,some face deblurring methods have been proposed to improve performance by adding semantic or structural information as specific priors according to the characteristics of the facial *** this paper,we survey and summarize recently published methods for facial image deblurring,most of which are based on deep ***,we provide a brief introduction to the modeling of image ***,we summarize face deblurring methods into two categories:model-based methods and deep learning-based ***,we summarize the datasets,loss functions,and performance evaluation metrics commonly used in the neural network training *** show the performance of classical methods on these datasets and metrics and provide a brief discussion on the differences between model-based and learning-based ***,we discuss the current challenges and possible future research directions.

关键词： facial image deblurring model-based deep learning-based semantic or structural prior

Distributed Deep Reinforcement Learning:A Survey and a Multi-player Multi-agent Learning Toolbox

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第3期21卷 411-430页

作者： Qiyue Yin Tongtong Yu Shengqi Shen Jun Yang Meijing Zhao Wancheng Ni Kaiqi Huang Bin Liang Liang Wang institute of automation Chinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Department of automation Tsinghua UniversityBeijing 100084China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of SciencesBeijing 100190China

With the breakthrough of AlphaGo,deep reinforcement learning has become a recognized technique for solving sequential decision-making *** its reputation,data inefficiency caused by its trial and error learning mechanism makes deep reinforcement learning difficult to apply in a wide range of *** methods have been developed for sample efficient deep reinforcement learning,such as environment modelling,experience transfer,and distributed modifications,among which distributed deep reinforcement learning has shown its potential in various applications,such as human-computer gaming and intelligent *** this paper,we conclude the state of this exciting field,by comparing the classical distributed deep reinforcement learning methods and studying important components to achieve efficient distributed learning,covering single player single agent distributed deep reinforcement learning to the most complex multiple players multiple agents distributed deep reinforcement ***,we review recently released toolboxes that help to realize distributed deep reinforcement learning without many modifications of their non-distributed *** analysing their strengths and weaknesses,a multi-player multi-agent distributed deep reinforcement learning toolbox is developed and released,which is further validated on Wargame,a complex environment,showing the usability of the proposed toolbox for multiple players and multiple agents distributed deep reinforcement learning under complex ***,we try to point out challenges and future trends,hoping that this brief review can provide a guide or a spark for researchers who are interested in distributed deep reinforcement learning.

关键词： Deep reinforcement learning distributed machine learning self-play population-play toolbox

Numerical simulation of the dynamic migration mechanism and prediction of saturation of tight sandstone oil

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 Earth sciences 2024年第1期67卷 179-195页

作者： Gaohui CAO Mian LIN Likuan ZHANG Lili JI Wenbin JIANG institute of Mechanics Chinese Academy of SciencesBeijing 100190China School of Engineering Science University of Chinese Academy of SciencesBeijing 100049China institute of Geology and Geophysics Chinese Academy of SciencesBeijing 100029China

Quantitative characterization of tight sandstone oil migration and accumulation is an emerging research frontier in the field of oil and gas *** this study,a conceptual model containing multiple basic geological elements is developed,and a nonlinear seepage numerical model for tight sandstone oil migration and accumulation is *** effects of the slip effect,overpressure driving force,buoyancy,and capillary force on the migration and accumulation of tight oil are *** results showed that(1)the differences in oil migration and accumulation between tight and conventional reservoirs are reflected in the growth mode of oil saturation,distribution characteristics of oil and water,and extent of the effect of the formation dip angle;(2)the slip effect has a significant impact when the average pore throat radius is less than 150 nm and the overpressure driving force and capillary force are the main mechanical mechanisms controlling oil migration and accumulation in tight sandstone,while the coupling effect of buoyancy,capillary force,and overpressure driving force controls the upper and lower limits of oil ***,a dimensional and dimensionless identification chart for rapidly predicting the oil saturation of tight sandstone is proposed and verified using the measured *** study provides a basis for analyzing the migration and accumulation mechanisms of tight sandstone oil and a new approach for predicting oil ***,we developed digital and visual analysis methods for the migration results,enriching the expression of the dynamics of hydrocarbon accumulation.

关键词： Tight sandstone Migration and accumulation Dynamics Oil saturation Numerical simulation

Flame Synthesis of Zr/ZSM-5 Catalysts with Tunable Acidity for the Oxidative Dehydrogenation of Propane to Propene

在线全文

学校读者我要写书评

暂无评论

Journal of Thermal Science 2024年第1期33卷 268-283页

作者： DANIEL Samuel FONZEU MONGUEN Cedric Karel WU Lingnan TIAN Zhenyu institute of Engineering Thermophysics Chinese Academy of SciencesBeijing 100190China University of chinese academy of sciences Beijing 100049China

Tuning the surface acidity of ZSM-5 catalyst is essential to achieve desired propene selectivity and *** several ratios of Zr were utilized to modify ZSM-5 via flame spray pyrolysis technique coupled with a pulse spray evaporation *** interaction between Zr and ZSM-5 in the flame influenced the physicochemical and acidity properties of the Zr/*** increasing Zr ratio in ZSM-5 shows coated layers of irregular nano-sized Zr with an increase in crystallite sizes due to the synergetic effect between Zr and *** surface chemical analysis revealed increased lattice oxygen on the Zr modified ZSM-5(1:4) sample compared to other *** acidity analysis revealed the Lewis and Br?nsted acid distribution in the weak and medium acid sites on the catalyst ***,the increase in Zr loading decreased the concentration of Br?nsted acid sites and tuned the catalyst surface to more Lewis acidity,promoting propene selectivity and hindering the over-oxidation of *** modified ZSM-5 catalysts were examined in a fixed bed reactor within 300℃-700℃ at a gas hourly space velocity(GHSV) of 6000 mL·g(catalysts)^(-1)·h^(-1) for the oxidative dehydrogenation of propane(ODHP) to *** the catalysts,Zr/ZSM-5(1:4) exhibited the best propene yield, with 57.19% propane conversion and 75.54% selectivity to propene and the highest *** work provides a promising strategy for tuning the surface acidity of ZSM-5 with Zr for ODHP applications.

关键词： flame synthesis Zr modified ZSM-5 catalyst ODHP surface acidity lattice oxygen