检索结果-南通市图书馆

Detection of a temporal salient object benefits from visual stimulus-specific adaptation in avian midbrain inhibitory nucleus

引用

Integrative Zoology 2024年第2期19卷 288-306页

作者： Jiangtao WANG Xiaoping RAO Shuman HUANG Zhizhong WANG Xiaoke NIU Minjie ZHU Songwei WANG Li SHI department of {1. Zhengzhou University School of Electrical EngineeringZhengzhouChina State Key Laboratory of Magnetic Resonance and Atomic and Molecular Physics National Center for Magnetic Resonance in WuhanKey Laboratory of Magnetic Resonance in Biological SystemsInnovation Academy for Precision Measurement Science and TechnologyChinese Academy of SciencesWuhanChina department of {1. Tsinghua UniversityBeijingChina

Food and predators are the most noteworthy objects for the basic survival of wild animals,and both are often deviant in both spatial and temporal domains and quickly attract an animal’s *** stimulus-specific adaptation(SSA)is considered a potential neural basis of salient sound detection in the temporal domain,related research on visual SSA is limited and its relationship with temporal saliency is *** avian nucleus isthmi pars magnocellularis(Imc),which is central to midbrain selective attention network,is an ideal site to investigate the neural correlate of visual SSA and detection of a salient object in the time ***,the constant order paradigm was applied to explore the visual SSA in the Imc of *** results showed that the firing rates of Imc neurons gradually decrease with repetitions of motion in the same direction,but recover when a motion in a deviant direction is presented,implying visual SSA to the direction of a moving ***,enhanced response for an object moving in other directions that were not presented ever in the paradigm is also *** verify the neural mechanism underlying these phenomena,we introduced a neural computation model involving a recoverable synaptic change with a“center-surround”pattern to reproduce the visual SSA and temporal saliency for the moving *** results suggest that the Imc produces visual SSA to motion direction,allowing temporal salient object detection,which may facilitate the detection of the sudden appearance of a predator.

关键词： adaptation attention model pigeon saliency

来源：

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

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

引用

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 {1. 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

来源：

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

Reinforcement Learning-Based Dynamic Order Recommendation for On-Demand Food Delivery

引用

Tsinghua Science and Technology 2024年第2期29卷 356-367页

作者： Xing Wang Ling Wang Chenxin Dong Hao Ren Ke Xing department of {1. Tsinghua UniversityBeijing 100080China School of Mechanical and Automotive Engineering Qingdao Hengxing University of Science and TechnologyQingdao 266100China Meituan Beijing 100015China

On-demand food delivery(OFD)is gaining more and more popularity in modern *** a kernel order assignment manner in OFD scenario,order recommendation directly influences the delivery efficiency of the platform and the delivery experience of *** paper addresses the dynamism of the order recommendation problem and proposes a reinforcement learning solution *** actor-critic network based on long short term memory(LSTM)unit is designed to deal with the order-grabbing conflict between different ***,three rider sequencing rules are accordingly proposed to match different time steps of the LSTM unit with different *** test the performance of the proposed method,extensive experiments are conducted based on real data from Meituan delivery *** results demonstrate that the proposed reinforcement learning based order recommendation method can significantly increase the number of grabbed orders and reduce the number of order-grabbing conflicts,resulting in better delivery efficiency and experience for the platform and riders.

关键词： on-demand food delivery order recommendation reinforcement learning actor-critic network long short term memory

来源：

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

Evaluation of E-sail parameters on central spacecraft attitude stability using a high-fidelity rigid–flexible coupling model

引用

Astrodynamics 2024年第2期8卷 271-284页

作者： Chonggang Du Zheng H.Zhu Changqing Wang Aijun Li Tuanjie Li School of Electro-Mechanical Engineering Xidian UniversityXi’an 710071China department of Mechanical Engineering York University4700 Keele StreetTorontoOntario M3J 1P3Canada School of automation Northwestern Polytechnical UniversityXi’an 710129China

This study examines the impact of electric solar wind sail(E-sail)parameters on the attitude stability of E-sail’s central spacecraft by using a comprehensive rigid–flexible coupling dynamic *** this model,the nodal position finite element method is used to model the elastic deformation of the tethers through interconnected two-node tensile *** attitude dynamics of the central spacecraft is described using a natural coordinate *** rigid–flexible coupling between the central spacecraft and its flexible tethers is established using Lagrange *** research reveals the significant influences of parameters such as tether numbers,tether’s electric potential,and solar wind velocity on attitude ***,solar wind fluctuations and the distribution of electric potential on the main tethers considerably affect the attitude stability of the *** consistent management,the angular velocities of the spacecraft must remain at target ***,the attitude stability of a spacecraft has a pronounced dependence on the geometrical configuration of the E-sail,with axisymmetric E-sails proving to be more stable.

关键词： electric solar wind sail(E-sail) space tether nodal position finite element method(NPFEM) natural coordinate formulation (NCF) attitude stability

来源：

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

Lift system optimization for hover-capable flapping wing micro air vehicle

引用

Frontiers of Mechanical Engineering 2024年第3期19卷 61-75页

作者： Shengjie XIAO Yongqi SHI Zemin WANG Zhe NI Yuhang ZHENG Huichao DENG Xilun DING department of Mechanical Engineering and {1. Beihang UniversityBeijing 100191China department of Mechanical Engineering Tsinghua UniversityBeijing 100084China Shenzhen International Graduate School Tsinghua UniversityShenzhen 518055China

A key challenge is using bionic mechanisms to enhance aerodynamic performance of hover-capable flapping wing micro air vehicle(FWMAV).This paper presented a new lift system with high lift and aerodynamic efficiency,which use a hummingbird as a bionic *** new lift system is able to effectively utilize the high lift mechanism of hummingbirds,and this study innovatively utilizes elastic energy storage elements and installs them at the wing root to help improve aerodynamic performance.A flapping angle of 1.4°is achieved through the optimization of the flapping mechanism *** optimized wing shape and parameters are obtained through experimental studies on the ***,the max net lift generated is 1..6%of the flapping wing vehicle’s ***,energy is stored and released periodically during the flapping cycle,by imitating the musculoskeletal system at the wing roots of hummingbirds,thereby improving the energy utilization rate of the FWMAV and reducing power consumption by 4.5%under the same ***,strength verification and modal analyses are conducted on the flapping mechanism,and the weight of the flapping mechanism is reduced through the analysis and testing of different *** results show that the lift system can generate a stable lift of 31.98 g with a wingspan of 1.5 mm,while the lift system weighs only 1..5 g,providing aerodynamic conditions suitable for high maneuverability flight of FWMAVs.

关键词： lift optimization flapping wing elastic energy hovering flapping mechanism

来源：

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

PAL-BERT:An Improved Question Answering Model

引用

Computer Modeling in Engineering & Sciences 2024年第6期139卷 2729-2745页

作者： Wenfeng Zheng Siyu Lu Zhuohang Cai Ruiyang Wang Lei Wang Lirong Yin School of automation University of Electronic Science and Technology of ChinaChengdu610054China department of Geography and Anthropology Louisiana State UniversityBaton RougeLA70803USA

In the field of natural language processing(NLP),there have been various pre-training language models in recent years,with question answering systems gaining significant ***,as algorithms,data,and computing power advance,the issue of increasingly larger models and a growing number of parameters has ***,model training has become more costly and less *** enhance the efficiency and accuracy of the training process while reducing themodel volume,this paper proposes a first-order pruningmodel PAL-BERT based on the ALBERT model according to the characteristics of question-answering(QA)system and language ***,a first-order network pruning method based on the ALBERT model is designed,and the PAL-BERT model is ***,the parameter optimization strategy of the PAL-BERT model is formulated,and the Mish function was used as an activation function instead of ReLU to improve the ***,after comparison experiments with traditional deep learning models TextCNN and BiLSTM,it is confirmed that PALBERT is a pruning model compression method that can significantly reduce training time and optimize training *** with traditional models,PAL-BERT significantly improves the NLP task’s performance.

关键词： PAL-BERT question answering model pretraining language models ALBERT pruning model network pruning TextCNN BiLSTM

来源：

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

A Study on Enhancing Chip Detection Efficiency Using the Lightweight Van-YOLOv8 Network

引用

Computers, Materials & Continua 2024年第4期79卷 531-547页

作者： Meng Huang Honglei Wei Xianyi Zhai School of Mechanical Engineering and automation Dalian Polytechnic UniversityDalian116034China

In pursuit of cost-effective manufacturing,enterprises are increasingly adopting the practice of utilizing recycled semiconductor *** ensure consistent chip orientation during packaging,a circular marker on the front side is employed for pin alignment following successful functional ***,recycled chips often exhibit substantial surface wear,and the identification of the relatively small marker proves ***,the complexity of generic target detection algorithms hampers seamless *** these issues,this paper introduces a lightweight YOLOv8s-based network tailored for detecting markings on recycled chips,termed ***,to alleviate the influence of diminutive,low-resolution markings on the precision of deep learning models,we utilize an upscaling approach for enhanced *** technique relies on the Super-Resolution Generative Adversarial Network with Extended Training(SRGANext)network,facilitating the reconstruction of high-fidelity images that align with input ***,we replace the original YOLOv8smodel’s backbone feature extraction network with the lightweight VanillaNetwork(VanillaNet),simplifying the branch structure to reduce network ***,a Hybrid Attention Mechanism(HAM)is implemented to capture essential details from input images,improving feature representation while concurrently expediting model inference *** results demonstrate that the Van-YOLOv8 network outperforms the original YOLOv8s on a recycled chip dataset in various ***,it demonstrates superiority in parameter count,computational intricacy,precision in identifying targets,and speed when compared to certain prevalent algorithms in the current *** proposed approach proves promising for real-time detection of recycled chips in practical factory settings.

关键词： Lightweight neural networks attention mechanisms image super-resolution enhancement feature extraction small object detection

来源：

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

Cognitive Navigation for Intelligent Mobile Robots:A Learning-Based Approach With Topological Memory Configuration

引用

IEEE/CAA Journal of Automatica Sinica 2024年第9期11卷 1933-1943页

作者： Qiming Liu Xinru Cui Zhe Liu Hesheng Wang department of {1. Shanghai Jiao Tong UniversityShanghai 200240China MoE Key Laboratory of Artificial Intelligence AI InstituteShanghai Jiao Tong UniversityShanghai 200240China department of {1. Key Laboratory of System Control and Information Processing of Ministry of EducationKey Laboratory of Marine Intelligent Equipment and System of Ministry of EducationShanghai Engineering Research Center of Intelligent Control and ManagementShanghai Jiao Tong UniversityShanghai 200240China

Autonomous navigation for intelligent mobile robots has gained significant attention,with a focus on enabling robots to generate reliable policies based on maintenance of spatial *** this paper,we propose a learning-based visual navigation pipeline that uses topological maps as memory *** introduce a unique online topology construction approach that fuses odometry pose estimation and perceptual similarity *** tackles the issues of topological node redundancy and incorrect edge connections,which stem from the distribution gap between the spatial and perceptual ***,we propose a differentiable graph extraction structure,the topology multi-factor transformer(TMFT).This structure utilizes graph neural networks to integrate global memory and incorporates a multi-factor attention mechanism to underscore elements closely related to relevant target cues for policy *** from photorealistic simulations on image-goal navigation tasks highlight the superior navigation performance of our proposed pipeline compared to existing memory *** validation through behavior visualization,interpretability tests,and real-world deployment further underscore the adapt-ability and efficacy of our method.

关键词： Graph neural networks(GNNs) spatial memory topological map visual navigation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Physics-informed deep Koopman operator for Lagrangian dynamic systems

引用

Science China(Information Sciences) 2024年第9期67卷 146-163页

作者： Xuefeng WANG Yang CAO Shaofeng CHEN Yu KANG department of {1. University of Science and Technology of China State Key Laboratory of Fire Science University of Science and Technology of China Institute of Advanced Technology University of Science and Technology of China

Accurate mechanical system models are crucial for safe and stable control. Unlike linear systems,Lagrangian systems are highly nonlinear and difficult to optimize because of their unknown system *** research thus used deep neural networks to generate linear models of original systems by mapping nonlinear dynamic systems into a linear space with a Koopman observable function encoder. The controller then relies on the Koopman linear model. However, without physical information constraints, ensuring control consistency between the original nonlinear system and the Koopman system is tough, as the learning process of the Koopman observation function is unsupervised. This paper thus proposes a two-stage learning algorithm that uses structural subnetworks to build a physics-informed network topology to simultaneously learn the Koopman observable functions and the system energy representation. In the Koopman matrix learning session, a quadratic-constrained optimization problem is solved to ensure that the Koopman representation satisfies the energy difference matching hard constraint. The proposed energy-preserving deep Lagrangian Koopman(EPDLK) framework effectively represents the dynamics of the Lagrangian system while ensuring control consistency. The effectiveness of EPDLK is compared with those of various Koopman observable function construction methods in multistep prediction and trajectory tracking tasks. EPDLK achieves better control consistency by guaranteeing energy difference matching, which facilitates the application of the control law generated on the Koopman system directly to the original nonlinear Lagrangian system.

关键词： Koopman operator Lagrangian physics-informed nonlinear model predictive control (MPC)

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Immunomodulatory activity of polycaprolactone nanoparticles with calcium phosphate salts against Leishmania infantum infection

引用

Asian Pacific Journal of Tropical Biomedicine 2024年第8期14卷 359-368页

作者： Kübra Kelleci Adil Allahverdiyev Melahat Bağırova Murat Ihlamur EmrahŞefik Abamor department of Bioengineering Yildiz Technical UniversityIstanbulTurkey V.Akhundov National Scientific Research Medical Prophylactic Institute BakuAzerbaijan department of Electronics and {1. Biruni UniversityIstanbulTurkey

Objective:To prepare and characterize polycaprolactone(PCL)nanoparticles loaded with sonicator fragmented(SLA)and freeze-thaw Leishmania antigens(FTLA)and to investigate the in vitro immunogenicity of antigen-encapsulated nanoparticles with calcium phosphate ***:The water/oil/water binary emulsion solvent evaporation method was used to synthesize antigen-loaded PCL *** were characterized by scanning electron microscopy and zeta potential *** cytotoxicity in J774 macrophages in vitro was determined by MTT *** addition,the amount of nitric oxide and the level of cytokines produced by macrophages were determined by Griess reaction and ELISA method,*** protective effect of the developed formulations was evaluated by determining the infection index percentage in macrophages infected with Leishmania ***:Compared to the control group,SLA PCL and FTLA PCL nanoparticles with calcium phosphate adjuvant induced a 6-and 7-fold increase in nitric oxide,***,the vaccine formulations promoted the production of IFN-γand *** PCL and FTLA PCL nanoparticles combined with calcium phosphate adjuvant caused an approximately 1.-and 1.-fold reduction in infection index,respectively,compared to the control ***:The encapsulation of antigens obtained by both sonication and freeze-thawing into PCL nanoparticles and the formulations with calcium phosphate adjuvant show strong in vitro immune stimulating ***,PCL-based antigen delivery systems and calcium phosphate adjuvant are recommended as a potential vaccine candidate against leishmaniasis.

关键词： Leishmaniasis Calcium phosphate Polycaprolactone Nanoparticle Antigen delivery system Adjuvant Vaccine design

来源：

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

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：