检索结果-南通市图书馆

Learning to represent 2D human face with mathematical model

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第1期9卷 54-68页

作者： Liping Zhang Weijun Li Linjun Sun Lina Yu Xin Ning Xiaoli Dong AnnLab Institute of SemiconductorsChinese Academy of SciencesBeijingChina Center of Materials Science and optoelectronics Engineering School of Integrated CircuitsUniversity of Chinese Academy of SciencesBeijingChina Beijing Key Laboratory of Semiconductor Neural Network intelligent Sensing and Computing Technology BeijingChina

How to represent a human face pattern?While it is presented in a continuous way in human visual system,computers often store and process it in a discrete manner with 2D arrays of *** authors attempt to learn a continuous surface representation for face image with explicit ***,an explicit model(EmFace)for human face representation is pro-posed in the form of a finite sum of mathematical terms,where each term is an analytic function ***,to estimate the unknown parameters of EmFace,a novel neural network,EmNet,is designed with an encoder-decoder structure and trained from massive face images,where the encoder is defined by a deep convolutional neural network and the decoder is an explicit mathematical expression of *** authors demonstrate that our EmFace represents face image more accurate than the comparison method,with an average mean square error of 0.000888,0.000936,0.000953 on LFW,IARPA Janus Benchmark-B,and IJB-C *** results show that,EmFace has a higher representation performance on faces with various expressions,postures,and other ***,EmFace achieves reasonable performance on several face image processing tasks,including face image restoration,denoising,and transformation.

关键词： artificial neural networks face analysis image processing mathematics computing

A vectorial model for the nonlinear gradient force exerted on metallic Rayleigh nanoparticles

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Optics Letters 2024年第2期22卷 207-213页

作者：朱政张聿全闵长俊 Aurèle J.LAdam H.Paul Urbach 袁小聪 Research Center for Humanoid Sensing Research Institute of Intelligent SensingZhejiang LabHangzhou 311100China Nanophotonics Research Center Institute of Microscale Optoelectronics&State Key Laboratory of Radio Frequency Heterogeneous IntegrationShenzhen UniversityShenzhen 518060China Optics Research Group ImPhys DepartmentFaculty of Applied SciencesDelft University of TechnologyDelft 2628 CJThe Netherlands

Optical tweezers have proved to be a powerful tool with a wide range of *** gradient force plays a vital role in the stable optical trapping of *** scalar method is convenient and effective for analyzing the gradient force in traditional optical ***,when the third-order nonlinear effect of the nano-object is stimulated,the scalar method cannot adequately present the optical response of the metal nanoparticle to the external optical ***,we propose a theoretical model to interpret the nonlinear gradient force using the vector *** combining the optical Kerr effect,the polarizability vector of the metallic nanoparticle is derived.A quantitative analysis is obtained for the gradient force as well as for the optical potential *** vector method yields better agreement with reported experimental *** suggest that this method could lead to a deeper understanding of the physics relevant to nonlinear optical trapping and binding phenomena.

关键词： gradient forces nonlinear effect metallic nanoparticles

Learning Scalable Task Assignment with Imperative-Priori Conflict Resolution in Multi-UAV Adversarial Swarm Defense Problem

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第1期37卷 369-388页

作者： ZHAO Zhixin CHEN Jie XIN Bin LI Li JIAO Keming ZHENG Yifan School of Electronics and Information Engineering Tongji UniversityShanghai 201804China Shanghai institute of intelligent Science and Technology Tongji UniversityShanghai 201804China School of Automation Beijing Institute of TechnologyBeijing 100081China National Key Laboratory of Autonomous intelligent Unmanned Systems Beijing 100081China Shanghai institute of intelligent Science and Technology Tongji UniversityShanghai 201804China.

The multi-UAV adversary swarm defense(MUASD)problem is to defend a static base against an adversary UAV swarm by a defensive UAV *** the problem into task assignment and low-level interception strategies is a widely used ***-based approaches for task assignment are a promising *** studies on learning-based methods generally assume decentralized decision-making architecture,which is not beneficial for conflict *** contrast,centralized decision-making architecture is beneficial for conflict resolution while it is often detrimental to *** achieve scalability and conflict resolution simultaneously,inspired by a self-attention-based task assignment method for sensor target coverage problem,a scalable centralized assignment method based on self-attention mechanism together with a defender-attacker pairwise observation preprocessing(DAP-SelfAtt)is ***,an imperative-priori conflict resolution(IPCR)mechanism is proposed to achieve conflict-free ***,the IPCR mechanism is parallelized to enable efficient *** validate the algorithm,a variant of proximal policy optimization algorithm(PPO)is employed for training in scenarios of various *** experimental results show that the proposed algorithm not only achieves conflict-free task assignment but also maintains scalability,and significantly improve the success rate of defense.

关键词： Conflict resolution reinforcement learning scalability task assignment.

具有三明治结构的MXene/聚酰亚胺复合泡沫用于多尺度微波吸收

在线全文

学校读者我要写书评

暂无评论

Science China Materials 2024年第1期67卷 272-278页

作者：张亚君韩美康胡荣祥张培根潘龙孙正明 Key Laboratory of Advanced Metallic Materials of Jiangsu Province School of Materials Science and EngineeringSoutheast UniversityNanjing 211189China institute of optoelectronics and Shanghai Frontiers Science Research Base of intelligent optoelectronics and Perception Fudan UniversityShanghai 200433China

三维多孔结构可促进电磁波在材料内部的多重反射,是提升微波吸收性能的有效方法.然而,传统的三维多孔结构中,多重反射仅发生在孔内.扩大多重反射的范围应能进一步提升材料的吸收性能.因此,本文开发了一种孔壁为三明治结构的三维多孔复... 详细信息

三维多孔结构可促进电磁波在材料内部的多重反射,是提升微波吸收性能的有效方法.然而,传统的三维多孔结构中,多重反射仅发生在孔内.扩大多重反射的范围应能进一步提升材料的吸收性能.因此,本文开发了一种孔壁为三明治结构的三维多孔复合泡沫,在亚毫米尺度孔和亚微米尺度孔壁中同时发生多重反射,实现多尺度微波吸收.本研究采用聚多巴胺修饰的聚酰亚胺泡沫(PDA@PIF)作为三维多孔骨架,在其孔壁表面负载Ti_(3)C_(2)T_(x).所得的Ti_(3)C_(2)T_(x)@PDA@PIF能够在整个X波段吸收超过90%的入射波.这得益于多尺度多重反射、电导损耗和界面极化.同时,该复合泡沫具有优异的柔性和低密度(~30 mg cm^(-3)).该工作为实现轻质、柔性、宽频的吸波材料提供了一种可行的方法,丰富了电磁防护的有效结构.

关键词：三明治结构聚酰亚胺泡沫多重反射微米尺度微波吸收复合泡沫电磁防护吸收性能

All laser direct writing process for temperature sensor based on graphene and silver

在线全文

学校读者我要写书评

暂无评论

Frontiers of optoelectronics 2024年第1期17卷 45-55页

作者： Qi Li Ruijie Bai Lianbo Guo Yang Gao Shanghai Key Laboratory of intelligent Sensing and Detection Technology School of Mechanical and Power EngineeringEast China University of Science and TechnologyShanghai 200237China North Automatic Control Technology institute Taiyuan 030006China Wuhan National Laboratory for optoelectronics Huazhong University of Science&TechnologyWuhan 430074China

A highly sensitive temperature sensing array is prepared by all laser direct writing(LDW)method,using laser induced silver(LIS)as electrodes and laser induced graphene(LIG)as temperature sensing layer.A finite element analysis(FEA)photothermal model incorporating a phase transition mechanism is developed to investigate the relationship between laser parameters and LIG properties,providing guidance for laser processing parameters selection with laser power of 1–5 W and laser scanning speed(greater than 50 mm/s).The deviation of simulation and experimental data for widths and thickness of LIG are less than 5%and 9%,*** electrical properties and temperature responsiveness of LIG are also *** changing the laser process parameters,the thickness of the LIG ablation grooves can be in the range of 30–120μm and the resistivity of LIG can be regulated within the range of 0.031–67.2Ω・*** percentage temperature coefficient of resistance(TCR)is calculated as−0.58%/°***,the FEA photothermal model is studied through experiments and simulations data regarding LIS,and the average deviation between experiment and simulation is less than 5%.The LIS sensing samples have a thickness of about 14μm,an electrical resistivity of 0.0001–100Ω・m is insensitive to temperature and pressure ***,for a LIS-LIG based temperature sensing array,a correction factor is introduced to compensate for the LIG temperature sensing being disturbed by pressure stimuli,the temperature measurement difference is decreased from 11.2 to 2.6°C,indicating good accuracy for temperature measurement.

关键词： Laser direct writing Temperature sensor Finite element analysis Laser induced graphene Laser induced silver

Continuous advantage learning for minimum-time trajectory planning of autonomous vehicles

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第7期67卷 285-294页

作者： Zhuo LI Weiran WU Jialin WANG Gang WANG Jian SUN School of Automation Beijing Institute of Technology Beijing institute of Technology Chongqing Innovation Center China Academy of Launch Vehicle Technology Intelligent Game and Decision Laboratory

This paper investigates the minimum-time trajectory planning problem of an autonomous vehicle. To deal with unknown and uncertain dynamics of the vehicle, the trajectory planning problem is modeled as a Markov decision process with a continuous action space. To solve it, we propose a continuous advantage learning(CAL) algorithm based on the advantage-value equation, and adopt a stochastic policy in the form of multivariate Gaussian distribution to encourage exploration. A shared actor-critic architecture is designed to simultaneously approximate the stochastic policy and the value function, which greatly reduces the computation burden compared to general actor-critic methods. Moreover, the shared actor-critic is updated with a loss function built as mean square consistency error of the advantage-value equation, and the update step is performed several times at each time step to improve data efficiency. Simulations validate the effectiveness of the proposed CAL algorithm and its better performance than the soft actor-critic algorithm.

关键词： trajectory planning continuous advantage learning stochastic policy shared actor-critic

Simulating the GRF of Humanoid Robot Vertical Jumping Using a Simplified Model with a Foot Structure for Foot Design

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2024年第1期21卷 112-125页

作者： Chuanku Yi Xuechao Chen Yu Zhang Zhangguo Yu Haoxiang Qi Yaliang Liu Qiang Huang School of Mechatronical Engineering Beijing Institute of TechnologyZizhuyaunHaidianBeijing 100081China Beijing Advanced Innovation Center for intelligent Robots and Systems Beijing Institute of Tec

There are many theories and tools for human or robot motion simulation,but most of them require complex *** LNZN model(a simplified model named by the proposers)simplifies the human model and facilitates simulation of the Ground Reaction Force(GRF)of body landing by spring damping model and ignoring joint rotation movements,which can reduce the amount of computation *** this paper,the LNZN model of human running is selected as the basis and is modified to obtain the LNZN model of a robot,which expands the application of the LNZN *** to the structure of the human foot,a foot structure is then added to the simplified model to reduce the *** also applied driving forces to the new model to simulate the whole high jump motion of the robot to expand the functions of the LNZN *** obtained GRF data were anastomotic to the actual experimental *** addition,the effects of variables,such as the mass,hardness,and damping,of the foot on the GRF at the moment of landing were also ***,based on the guidelines obtained for the design of the robot’s foot structure,we fabricated new robot’s feet and installed them on the actual robot and achieved a better cushioning effect than the original foot in experiments.

关键词： LNZN model-GRF simulation Humanoid foot structure Foot parameters

Distributed collaborative complete coverage path planning based on hybrid strategy

维普期刊数据库评论

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 Systems Engineering and Electronics 2024年第2期35卷 463-472页

作者： ZHANG Jia DU Xin DONG Qichen XIN Bin School of Automation Beijing Institute of TechnologyBeijing 100081China National Key Laboratory of Autonomous intelligent Unmanned Systems Beijing Institute of TechnologyBeijing 100081China

Collaborative coverage path planning(CCPP) refers to obtaining the shortest paths passing over all places except obstacles in a certain area or space. A multi-unmanned aerial vehicle(UAV) collaborative CCPP algorithm is proposed for the urban rescue search or military search in outdoor *** to flexible control of small UAVs, it can be considered that all UAVs fly at the same altitude, that is, they perform search tasks on a two-dimensional plane. Based on the agents’ motion characteristics and environmental information, a mathematical model of CCPP problem is established. The minimum time for UAVs to complete the CCPP is the objective function, and complete coverage constraint, no-fly constraint, collision avoidance constraint, and communication constraint are considered. Four motion strategies and two communication strategies are designed. Then a distributed CCPP algorithm is designed based on hybrid strategies. Simulation results compared with patternbased genetic algorithm(PBGA) and random search method show that the proposed method has stronger real-time performance and better scalability and can complete the complete CCPP task more efficiently and stably.

关键词： multi-agent cooperation unmanned aerial vehicles(UAV) distributed algorithm complete coverage path planning(CCPP)

Adaptive interaction driven by the learning effect in the spatial prisoner's dilemma

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第3期33卷 160-169页

作者：李佳奇张建磊刘群 institute of intelligent Information Hexi UniversityGansu 734000China College of Artificial Intelligence Nankai UniversityTianjin 300350China

We propose a computing model in which individuals can automatically adjust their interaction intensity with their mentor according to the learning *** model is designed to investigate the cooperative dynamics of the spatial prisoner's *** specifically,when the cumulative payoff of a learner is more than his reference earning,he will strengthen his interaction with his mentor;otherwise,he will reduce *** experimental results indicate that this mechanism can improve the emergence of cooperation in a networked population and that the driving coefficient of interaction intensity plays an important role in promoting ***,under a certain social dilemma condition,there exists a minimal driving coefficient that leads to optimal *** occurs due to a positive feedback effect between the individual's satisfaction frequency and the number of effective ***,we find that the experimental results are in accord with theoretical predictions obtained from an extension of the classical pair-approximation *** conclusions obtained by considering relationships with mentors can provide a new perspective for future investigations into the dynamics of evolutionary games within structured populations.

关键词： self-adapting interaction evolutionary game mentor spatial prisoner's dilemma