检索结果-内蒙古大学图书馆

Self-Organised Sequential Multi-Agent Reinforcement Learning for Closely Cooperation Tasks

IEEE Robotics and Automation Letters 2025年第6期10卷 5967-5974页

作者： Fu, Hao You, Mingyu Zhou, Hongjun He, Bin Tongji University College of Electronic and Information Engineering Shanghai200070 China Frontiers Science Center for Intelligent Autonomous Systems Ministry of Educatio National Key Laboratory of Autonomous Intelligent Unmanned Systems Shanghai201804 China

Cooperative tasks are common in multi-agent systems, with closely cooperative tasks being a special case of this, where a change in the state of the environment requires multiple agents to perform a specific operation at the same time. Take a box-pushing task as an example, the box is heavy and requires multiple agents to push it simultaneously. Optimal actions in a closely cooperation task are correlated with the actions of other agents, which makes the individual optimal action potentially inconsistent with the group optimal action, which leads to more non-globally optimal Nash equilibrium policies in the problem. This makes it easier for the policy learned by reinforcement learning to fall into these locally optimal policies. In this letter, we propose a self-organised sequential multi-agent reinforcement learning algorithm (SOS-MARL). We propose sequential decision-making to change the optimization objective of the agent's policy so that the learned policy tends to group optimal policies. And propose an automatic grouping mechanism to make the policy smoother for training and reasoning in large-scale agent environments. We decompose the joint action value factorization outside the group into a combination of each group action value, thus guiding the agents to improve their group policies in a fine-grained manner. We deployed scenarios in both simulated and real environments and compared SOS-MARL with various classical MARL algorithms on box-pushing tasks, demonstrating the state-of-the-art of our method. © 2016 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Deliberate design of MOF-based pre-catalyst rationalizing the structural reconstruction toward efficient oxygen evolution reaction

引用

science China Chemistry 2025年第6期68卷 2388-2398页

作者： Yunhui Chen Meng Tian Zhongqi Zhang Guangzhao Wang Yan Guo Jing Wu Dawei Qi Zhenhua Yan Xiangyu Liu Xi Liu State Key Laboratory of High-efficiency Coal Utilization and Green Chemical Engineering College of Chemistry and Chemical EngineeringNingxia University Key Laboratory of Extraordinary Bond Engineering and Advanced Materials Technology of Chongqing School of Electronic Information Engineering Yangtze Normal University Frontiers Science Center for New Organic Matter Key Laboratory of Advanced Energy Materials Chemistry (Ministry of Education) State Key Laboratory of Advanced Chemical Power Sources College of Chemistry Nankai University School of Chemistry and Chemical Engineering In-situ Center for Physical Sciences Frontiers Science Center for Transformative MoleculesShanghai Jiao Tong University

Metal-organic frameworks（MOFs）, that have emerged as promising electrocatalysts in oxygen evolution reaction（OER）,usually undergo structural reconstruction to form metal hydroxides as active sites. However, it remains a great challenge to design and synthesize ideal MOF-based pre-catalysts for properly cognizing and utilizing the reconstruction process toward efficient OER activity. Herein, the well-defined MOF-808 is post-modified by 2-hydroxyphosphonoacetic acid（HPAA） to form a micro-adsorber that enables to capture of metal ions effectively. Fe3+and Ni2+ions are synergistically anchored into the microadsorber, developing a Fe/Ni-containing pre-catalyst that can be dynamically electrooxidized to be an active and stable dual-site electrocatalyst denoted by R-MOF-HPAA@Fe Ni with abundant metal sites. As a result, R-MOF-HPAA@Fe Ni exhibits an excellent OER performance with a low overpotential of 272 m V and Tafel slope of 35.9 m V dec-1, as well as long-term stability over 300 h at 10 m A cm-2. Experiments and theoretical calculations suggest the resulting catalyst mainly follows a lattice oxygen mechanism（LOM） of dual-metal-site mechanism（DMSM）. Owing to the chelating role of HPAA, the post-synthesized MOFHPAA behaves as a trap to uniformly and firmly adhere Fe3+and Ni2+ions, leading to a functionalized MOF-based pre-catalyst which can be structurally evolved into atomic level-distributed OER electrocatalysts.

关键词： metal-organic frameworks functionalization electrochemical reconstruction electrocatalyst oxygen evolution reaction

来源：评论

学校读者我要写书评

暂无评论

A merged machine learning model for seasonal climate prediction in China

引用

science China Earth sciences 2025年第5期68卷 1469-1484页

作者： Danwei QIAN Yanyan HUANG Huijun WANG State Key Laboratory of Climate System Prediction and Risk Management/Key Laboratory of Meteorological Disaster Ministry of Education/Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters Nanjing University of Information Science and Technology Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai) Nansen-Zhu International Research Centre Institute of Atmospheric Physics Chinese Academy of Sciences

Improving the current level of skill in seasonal climate prediction is urgent for achieving sustainable socioeconomic development, and this is especially true in China where meteorological disasters are experienced frequently. In this study, based upon big climate data and traditional statistical prediction experiences, a merged machine learning model(Y-model) was developed to address this, as well as to further explore unknown potential predictors. In Y-model, empirical orthogonal function analysis was firstly applied to reduce the data dimensionality of the target predictand(temperature and precipitation in the four seasons over China). Image recognition techniques were used to automatically identify possible predictors from the big climate data. These predictors, associated with significant circulation anomalies, were recombined into a large ensemble according to different threshold settings for five factors determining the statistical forecast skill. Facebook Prophet was chosen to conduct the independent hindcasts for each season's climate at a lead time of two months. During 2011–2022, the seasonal climate in China was skillfully predicted by Y-model, with an averaged pattern correlation coefficient skill of 0.60 for temperature and 0.24 for precipitation, outperforming CFSv2. Potential predictor analysis for recent extreme events suggested that prior signals from the Indian Ocean and the stratosphere were important for determining the super Mei-yu in 2020, while the prior sea surface temperature over the western Pacific and the soil temperature over West Asia may have contributed to the extreme high temperatures in 2022. Our study provides new insights for seasonal climate prediction in China.

关键词： Machine learning Seasonal climate prediction China’s climate Image recognition techniques Large ensemble

来源：评论

学校读者我要写书评

暂无评论

Ce-UiO-66 nanozymes with charge-regulated uricase-like activity for enzyme/reagent-free detection of uric acid

引用

Nano Research 2025年第2期18卷 675-686页

作者： Zhixiong Guo Da Chen Wei Gao Yongquan Qu Zhimin Tian Key Laboratory of Special Functional and Smart Polymer Materials of Ministry of Industry and Information Technology School of Chemistry and Chemical EngineeringNorthwestern Polytechnical UniversityXi’an 710054China State Key Laboratory of Solidification Processing Center for Nano Energy MaterialsSchool of Materials Science and EngineeringNorthwestern Polytechnical UniversityXi’an 710072China

Designing highly performed uricase-like nanozymes through enzymatic-like colorimetric analysis system is of vital significance for the quantitative detection of uric acid(UA).Herein,series of Ce-UiO-66 nanozymes with different surface charges through the ligand engineering strategy were rationally designed and synthesized as efficient uricase mimics with tailorable uricase-like activities to catalytically convert UA into allantoin and ***,by tuning the functional groups of 1,4-benzoic acid ligands,we explored the relationships between the surface charges of Ce-UiO-66-X(X=H,NO_(2),Br,CH_(3),and OH)nanozymes and their uricase-like *** them,Ce UiO-66-CH_(3) with the moderate surface charge exhibited optimal substrate adsorption and product desorption,displaying the highest uricase-like ***,H2O2,as the product of UA oxidation,enabled Ce-UiO-66-CH_(3) itself as a dose-dependent chromogenic substrate of H_(2)O_(2),giving a white-to-orange color evolution due to the Ce-UiO-66-CH_(3)-to-CeO_(2) phase ***,a smartphone-assisted all-in-one enzyme/reagent-free biosensor based on Ce-UiO-66-CH_(3) was established for the precise visual detection of UA analysis,which was featured by a wide detection range(31–4000µM),a high sensitivity(limit of detection:8.9µM),a rapid response(-3 min),a high structural stability,and a high anti-interference ability.

关键词： Ce-UiO-66 uricase-like nanozyme colorimetric uric acid analysis enzyme/reagent-free detection smartphone

来源：评论

学校读者我要写书评

暂无评论

Giant spatial Goos-Hänchen shift achieved in superconducting hyperbolic metamaterials with graphene

引用

Optics Express 2025年第9期33卷 19359-19370页

作者： Yang, Junfu Xie, Zhijiang Ni, Hao Chen, Xiaoling Qin, Zhongli Zhao, Dong Zhao, Miaomiao State Key Laboratory of Mechanical Transmission for Advanced Equipment Chongqing University Chongqing400044 China College of Mechanical and Vehicle Engineering Chongqing University Chongqing400044 China School of Electronic and Information Engineering Hubei University of Science and Technology Xianning437100 China Hubei Provincial Key Laboratory of Optoelectronic Information and Intelligent Control Hubei University of Science and Technology Xianning437100 China

We have theoretically analyzed the enhancement and regulation of the Goos-Hänchen (GH) shift within hyperbolic metamaterials in the near-infrared band under low-temperature conditions. Given a fixed incident wavelength, photonic crystals constructed from graphene and superconductor present hyperbolic dispersion characteristics in the dispersion space by modulating the Fermi energy of graphene. Near the critical phase transition point from elliptic dispersion to hyperbolic dispersion, the phase of the reflection coefficient undergoes an abrupt alteration. Consequently, a remarkably large GH shift occurs precisely at the resonant state. A substantial GH shift can be effectively realized by regulating the layers of graphene, the thickness of the superconductor, and the temperature. The largest positive GH shift reaches up to 4000λ at T = 200 K. This research is anticipated to provide theoretical guidance for devising high-sensitivity temperature sensors based on the GH shift effect in hyperbolic materials within a low-temperature environment. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Metamaterials

来源：评论

学校读者我要写书评

暂无评论

Si/Si3N4/Ag hybrid nanocavity: a platform for enhancing light-matter interaction

引用

Photonics Research 2025年第3期13卷 709-720页

作者： TIANQI PENG ZHUO WANG SHULEI LI LIDAN ZHOU SHIMEI LIU YUHENG MAO MINGCHENG PANMAI WEICHEN HE SHENG LAN Guangdong Provincial Key Laboratory of Nanophotonic Functional Materials and Devices School of Optoelectronic Science and EngineeringSouth China Normal University School of Optoelectronic Engineering Guangdong Polytechnic Normal University State Key Laboratory of Optoelectronic Materials and Technologies School of Electronics and Information TechnologySun Yat-sen University School of Electrical and Electronic Engineering Nanyang Technological University GBA Branch of Aerospace Information Research Institute Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Terahertz Quantum Electromagnetics

High-index dielectric nanoparticles supporting strong Mie resonances, such as silicon （Si） nanoparticles, provide a platform for manipulating optical fields at the subwavelength scale. However, in general, the quality factors of Mie resonances supported by an isolated nanoparticle are not sufficient for realizing strong light-matter interaction. Here, we propose the use of dielectric-metal hybrid nanocavities composed of Si nanoparticles and silicon nitride/silver （Si3N4∕Ag） heterostructures to improve light-matter interaction. First, we demonstrate that the nonlinear optical absorption of the Si nanoparticle in a Si∕Si3N4∕Ag hybrid nanocavity can be greatly enhanced at the magnetic dipole resonance. The Si∕Si3N4∕Ag nanocavity exhibits luminescence burst at substantially lower excitation energy （～20.5 pJ） compared to a Si nanoparticle placed on a silica substrate （～51.3 pJ）. The luminescence intensity is also enhanced by an order of magnitude. Second, we show that strong exciton-photon coupling can be realized when a tungsten disulfide （WS2） monolayer is inserted into a Si∕Si3N4∕Ag *** such a system is excited by using s-polarized light, the optical resonance supported by the nanocavity can be continuously tuned to sweep across the two exciton resonances of the WS2monolayer by simply varying the incident angle. As a result, Rabi splitting energies as large as ～146.4 meV and ～110 meV are observed at the A-and B-exciton resonances of the WS2monolayer, satisfying the criterion for strong exciton-photon *** proposed nanocavities provide, to our knowledge, a new platform for enhancing light-matter interaction in multiple scenarios and imply potential applications in constructing nanoscale photonic devices.

关键词： Light matter interactions Nonlinear absorption Optical absorption Optical fields Photonic devices Q factor

来源：评论

学校读者我要写书评

暂无评论

Adaptive Closed-Loop Functional Electrical Stimulation System With Visual Feedback for Enhanced Grasping in Neurological Impairments

IEEE Transactions on Medical Robotics and Bionics

引用

IEEE Transactions on Medical Robotics and Bionics 2025年第2期7卷 678-686页

作者： Lin, Chengyu Cheng, Kong Hoi Pan, Wei Sun, Jinxin Gou, Guotao Fu, Junyun Leng, Yuquan Fu, Chenglong Southern University of Science and Technology Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Guangdong Provincial Key Laboratory of Human-Augmentation Rehabilitation Robotics in Universities Department of Mechanical and Energy Engineering Shenzhen518055 China Guilin University of Electronic Technology Guangxi Human Physiological Information Non Invasive Detection Engineering Technology Research Center School of Life and Environmental Sciences Guilin541004 China

Grasping is a critical motor skill essential for daily activities, but it is often compromised in individuals with neural impairments. Functional Electrical Stimulation (FES) has emerged as a promising intervention, utilizing electrical pulses to stimulate muscles and thereby restore impaired motor functions. However, existing closed-loop FES systems depend on pre-calibrated angles or forces specific to individual objects, which limits their practicality in dynamic, real-world environments with varying object properties. This paper presents a novel closed-loop FES (CLFES) system with visual feedback, designed to dynamically adjust stimulation parameters based on real-time interaction states without requiring object-specific calibration. The system employs a finite state machine to manage sequential grasp-release tasks and integrates a visual perception module for slip detection and intent recognition. The system was tested with two individuals with disabilities on five common household objects. Experimental results demonstrate significant improvements, including a 42.6% increase in success rate and a 45.9% reduction in task completion time compared to tasks performed without the system. These results underscore the system's potential to improve daily task performance for individuals with neural impairments. © 2018 IEEE.

关键词： Visual servoing

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Secure Data Aggregation for Smart Grids with Privacy Preservation

引用

Computers, Materials & Continua 2025年第1期82卷 799-816页

作者： Congcong Wang Chen Wang Wenying Zheng Wei Gu School of Software Nanjing University of Information Science and TechnologyNanjing210044China School of Information Science and Engineering Zhejiang Sci-Tech UniversityHangzhou310018China State Key Laboratory of Public Big Data Guizhou UniversityGuiyang550025China School of Computer Science and Technology(School of Artificial Intelligence) Zhejiang Sci-Tech UniversityHangzhou310018China School of Computer Science(School of Cyber Science and Engineering) Nanjing University of Information Science and TechnologyNanjing210044China

As smart grid technology rapidly advances,the vast amount of user data collected by smart meter presents significant challenges in data security and privacy *** research emphasizes data security and user privacy concerns within smart ***,existing methods struggle with efficiency and security when processing large-scale *** efficient data processing with stringent privacy protection during data aggregation in smart grids remains an urgent *** paper proposes an AI-based multi-type data aggregation method designed to enhance aggregation efficiency and security by standardizing and normalizing various data *** approach optimizes data preprocessing,integrates Long Short-Term Memory(LSTM)networks for handling time-series data,and employs homomorphic encryption to safeguard user *** also explores the application of Boneh Lynn Shacham(BLS)signatures for user *** proposed scheme’s efficiency,security,and privacy protection capabilities are validated through rigorous security proofs and experimental analysis.

关键词： Smart grid data security privacy protection artificial intelligence data aggregation

来源：评论

学校读者我要写书评

暂无评论

Chirp-pulse pair φOTDR

引用

Optics Letters 2025年第9期50卷 2844-2847页

作者： Xu, Pengbai Lian, Jinhui Ye, Zhigeng Yu, Xinfeng Zheng, Hua Yu, Zhangjun Wen, Kunhua Yan, Han Yang, Jun Wang, Yuncai Qin, Yuwen Institute of Advanced Photonics Technology School of Information Engineering Guangdong University of Technology Guangzhou510006 China Key Laboratory of Photonic Technology for Integrated Sensing and Communication Ministry of Education of China Guangdong University of Technology Guangzhou510006 China Guangdong Provincial Key Laboratory of Information Photonics Technology Guangdong University of Technology Guangzhou510006 China CSSC Systems Engineering Research Institute Beijing100000 China

We proposed a novel, to the best of our knowledge, chirp-pulse pair phase-sensitive optical time-domain reflectometry (CPP-φOTDR) technique, enhanced by an adaptive filtering algorithm. This technique utilizes a pair of chirp pulses: one with a low chirp rate and another with a high chirp rate, with their Rayleigh backscattering (RBS) processed through a low-pass (LP) electrical filter. The adaptive filtering algorithm effectively preserves the extensive measurement range afforded by the high chirp rate pulse while enhancing the sensitivity provided by the low chirp rate pulse. Consequently, the CPP-φOTDR enables vibration measurements over a wide dynamic range and broad frequency bandwidth without incurring additional acquisition costs. In the experiments, we employed a chirp-pulse pair featuring bandwidths of 500 MHz and 8 GHz, utilizing only the receiver’s 500 MHz bandwidth to retrieve the vibrational signal. The dynamic range of the CPP-φOTDR was enhanced by 25.1 dB, with the assistance of adaptive filtering of the acoustic waveform demodulated with RBS of the chirp-pulse pair. The proposed method could be utilized for monitoring the ocean in marine science and for analyzing seismic waves in geophysics. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

Programmable array antenna based on nematic liquid crystals for the Ka-band

引用

Journal of Southeast University (English Edition) 2025年第1期41卷 78-83页

作者： Wang, Qiang Ke, Junchen Bai, Lin Guangxi Key Laboratory of Optoelectronic Information Processing Guilin University of Electronic Technology Guilin541004 China School of Optoelectronic Engineering Guilin University of Electronic Technology Guilin541004 China School of Information Science and Engineering Southeast University Nanjing211189 China

A programmable low-profile array antenna based on nematic liquid crystals(NLCs) is proposed. Each antenna unit comprises a square patch radiating structure and a tunable NLC-based phase shifter capable of achieving a phase shift exceeding 360° with high linearity. First, the above 64 antenna units are periodically arranged into an 8 × 8 NLC-based antenna array, and the bias voltage of the NLC-based phase shifter loaded on the antenna unit is adjusted through the control of the field-programmable gate array(FPGA)programming sequences. This configuration enables precise phase changes for all 64 channels. Numerical simulation, sample processing, and experimental measurements of the antenna array are conducted to validate the performance of the antenna. The numerical and experimental results demonstrate that the proposed antenna performs well within the frequency range of 19. 5-20. 5 GHz, with a 3 dB relative bandwidth of 10% and a maximum main lobe gain of 14. 1 dBi. A maximum scanning angle of ±34° is achieved through the adjustment of the FPGA programming sequence. This NLC-based programmable array antenna shows promising potential for applications in satellite communication. © 2025 Southeast University. All rights reserved.

关键词： Nematic liquid crystals

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：