检索结果-南通市图书馆

Traffic safety helmet wear detection based on improved YOLOv5 network

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

Optoelectronics Letters 2024年

作者： GUI Dongdong SUN Bo College of Software Southeast University Quanzhou Equipment Research Centre Haixi institute Chinese Academy of Sciences

Aiming at the problem that the current traffic safety helmet detection model can’t balance the accuracy of detection with the size of the model and the poor generalization of the model， a method based on improving YOLOv5 is proposed. By incorporating the lightweight GhostNet module into the YOLOv5 backbone network， we effectively reduce the model size. The addition of the Receptive Fields Block (RFB) module enhances feature extraction and improves the feature acquisition capability of the lightweight model. Subsequently， the high-performance lightweight convolution， GSConv， is integrated into the neck structure for further model size compression. Moreover， the baseline model’s loss function is substituted with EIoU， accelerating network convergence and enhancing detection precision. Experimental results corroborate the effectiveness of this improved algorithm in real-world traffic scenarios.

关键词：

Cartan-Fubini type extension of holomorphic maps respecting varieties of minimal rational tangents

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 Mathematics 2015年第3期58卷 513-518页

作者： HWANG JunMuk Korea institute for advanced Study

A fundamental result in the theory of minimal rational curves on projective manifolds is CartanFubini extension theorem proved by Hwang and Mok,which describes the extensibility of biholomorphisms between connected open subsets of two Fano manifolds of Picard number 1 which preserve varieties of minimal rational tangents(VMRT),under a mild geometric assumption on the second fundamental forms of VMRT’*** and Mok have developed Cartan-Fubini extension for non-equidimensional holomorphic immersions from a connected open subset of a Fano manifold of Picard number 1 into a uniruled projective manifold,under the assumptions that the map sends VMRT’s onto linear sections of VMRT’s and it satisfies a mild geometric condition formulated in terms of second fundamental forms on VMRT’*** the current paper,we give a generalization of Hong and Mok’s result,under the same condition on second fundamental forms,assuming only that the holomorphic immersions send VMRT’s to VMRT’*** argument is different from Hong and Mok’s and is based on the study of natural foliations on the total family of VMRT’*** gives a substantially simpler proof than Hong and Mok’s argument.

关键词：全纯映射卡尔切线品种第二基本形式类型几何条件有理曲线

Jamming Recognition Based on Feature Fusion and Convolutional Neural Network

在线全文

学校读者我要写书评

暂无评论

Journal of Beijing institute of technology 2022年第2期31卷 169-177页

作者： Sitian Liu Chunli Zhu School of Information and Electronics Beijing Institute of TechnologyBeijing 100081China.

The complicated electromagnetic environment of the BeiDou satellites introduces vari-ous types of external jamming to communication links,in which recognition of jamming signals with uncertainties is *** this work,the jamming recognition framework proposed consists of fea-ture fusion and a convolutional neural network(CNN).Firstly,the recognition inputs are obtained by prepossessing procedure,in which the 1-D power spectrum and 2-D time-frequency image are ac-cessed through the Welch algorithm and short-time Fourier transform(STFT),***,the 1D-CNN and residual neural network(ResNet)are introduced to extract the deep features of the two prepossessing inputs,***,the two deep features are concatenated for the following three fully connected layers and output the jamming signal classification results through the softmax *** show the proposed method could reduce the impacts of potential feature loss,therefore improving the generalization ability on dealing with uncertainties.

关键词： time-frequency image feature power spectrum feature convolutional neural network feature fusion jamming recognition

Single-pixel imaging using physics enhanced deep learning

在线全文

学校读者我要写书评

暂无评论

Photonics Research 2022年第1期10卷 104-110页

作者： FEI WANG CHENGLONG WANG CHENJIN DENG SHENSHENG HAN GUOHAI SITU Shanghai institute of Optics and Fine Mechanics Chinese Academy of SciencesShanghai 201800China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of SciencesBeijing 100049China Hangzhou institute for advanced Study University of Chinese Academy of SciencesHangzhou 310024China

Single-pixel imaging(SPI) is a typical computational imaging modality that allows two-and three-dimensional image reconstruction from a one-dimensional bucket signal acquired under structured *** is in particular of interest for imaging under low light conditions and in spectral regions where good cameras are ***,the resolution of the reconstructed image in SPI is strongly dependent on the number of measurements in the temporal ***-driven deep learning has been proposed for high-quality image reconstruction from a undersampled bucket *** the generalization issue prohibits its practical *** we propose a physics-enhanced deep learning approach for *** blending a physics-informed layer and a model-driven fine-tuning process,we show that the proposed approach is generalizable for image *** implement the proposed method in an in-house SPI system and an outdoor single-pixel LiDAR system,and demonstrate that it outperforms some other widespread SPI algorithms in terms of both robustness and *** proposed method establishes a bridge between data-driven and model-driven algorithms,allowing one to impose both data and physics priors for inverse problem solvers in computational imaging,ranging from remote sensing to microscopy.

关键词： SPI image illumination

Highly robust spatiotemporal wavefront prediction with a mixed graph neural network in adaptive optics

在线全文

学校读者我要写书评

暂无评论

Photonics Research 2023年第11期11卷 1802-1813页

作者： JU TANG JI WU JIAWEI ZHANG MENGMENG ZHANG ZHENBO REN JIANGLEI DI LIUSEN HU GUODONG LIU JIANLIN ZHAO Key Laboratory of Light Field Manipulation and Information Acquisition Ministry of Industry and Information Technologyand Shaanxi Key Laboratory of Optical Information TechnologySchool of Physical Science and TechnologyNorthwestern Polytechnical UniversityXi’an 710129China Research&Development institute of Northwestern Polytechnical University in Shenzhen Shenzhen 518063China Key Laboratory of Photonic technology for Integrated Sensing and Communication Ministry of Educationand Guangdong Provincial Key Laboratory of Information Photonics TechnologyGuangdong University of TechnologyGuangzhou 510006China institute of Fluid Physics China Academy of Engineering PhysicsMianyang 621900China

The time-delay problem,which is introduced by the response time of hardware for correction,is a critical and nonignorable problem of adaptive optics(AO)*** will result in significant wavefront correction errors while turbulence changes severely or system responses *** AO is proposed to alleviate the time-delay problem for more accurate and stable corrections in the real time-varying ***,the existing prediction approaches either lack the ability to extract non-linear temporal features,or overlook the authenticity of spatial features during prediction,leading to poor robustness in ***,we propose a mixed graph neural network(MGNN)for spatiotemporal wavefront *** MGNN introduces the Zernike polynomial and takes its inherent covariance matrix as physical *** takes advantage of conventional convolutional layers and graph convolutional layers for temporal feature catch and spatial feature analysis,*** particular,the graph constraints from the covariance matrix and the weight learning of the transformation matrix promote the establishment of a realistic internal spatial pattern from limited ***,its prediction accuracy and robustness to varying unknown turbulences,including the generalization from simulation to experiment,are all discussed and *** experimental verification,the MGNN trained with simulated data can achieve an approximate effect of that trained with real *** comparing it with two conventional methods,the demonstrated performance of the proposed method is superior to the conventional AO in terms of root mean square error(RMS).With the prediction of the MGNN,the mean and standard deviation of RMS in the conventional AO are reduced by 54.2%and 58.6%at most,*** stable prediction performance makes it suitable for wavefront predictive correction in astronomical observation,laser communication,and microscopic imaging.

关键词： correction optics generalization

Hierarchical Hypergames and Bayesian Games:A generalization of the Theoretical Comparison of Hypergames and Bayesian Games Considering Hierarchy of Perceptions

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2016年第1期29卷 187-201页

作者： SASAKI Yasuo KIJIMA Kyoichi School of Knowledge Science Japan Advanced Institute of Science and Technology 1-1AsahidaiNomiIshikawaJapan Department of Value and Decision Science Tokyo Institute of Technology 2-12-1OokayamaMeguro-kuTokyoJapan

This paper discusses the relationship of two independently developed models of games with incomplete information,hierarchical hypergames and Bayesian *** can be considered as a generalization of the previous study on the theoretical comparison of simple hypergames and Bayesian games(Sasaki and Kijima,2012) by taking into account hierarchy of perceptions,i.e.,an agent's perception about the other agents' perceptions,and so *** authors first introduce the general way of transformation of any hierarchical hypergames into corresponding Bayesian games,which was called as the Bayesian representation of hierarchical *** authors then show that some equilibrium concepts for hierarchical hypergames can be associated with those for Bayesian games and discuss implications of the results.

关键词：系统科学系统学系统工程理论

Large language models and brain-inspired general intelligence

在线全文

学校读者我要写书评

暂无评论

National Science Review 2023年第10期10卷 6-7页

作者： Bo Xu Mu-ming Poo institute of Automation Chinese Academy of Sciences CAS Center for Excellence for Brain Science and Intelligence technology

The emergence of large language models(LLMs) such as ChatGPT/GPT-4 and their stunning performance in generative tasks heralds the beginning of a new era of artificial general intelligence(AGI).The LLMs have shown amazing generalization ability in natural language processing,computer vision and other generative tasks [1].These models point to a feasible approach for developing *** a large extent,they have passed the classical Turing test and their capability is still growing without an upper bound identified.

关键词：

A Second-Order Semi-Implicit Method for the Inertial Landau-Lifshitz-Gilbert Equation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Numerical Mathematics(Theory,Methods and Applications) 2023年第1期16卷 182-203页

作者： Panchi Li Lei Yang Jin Lan Rui Du Jingrun Chen School of Mathematical Sciences Soochow UniversitySuzhou 215006China School of Computer Science and Engineering Macao University of Science and TechnologyMacao SARChina Center for Joint Quantum Studies and Department of Physics School of ScienceTianjin University92 Weijin RoadTianjin 300072China Mathematical Center for Interdisciplinary Research Soochow UniversitySuzhou 215006China Suzhou institute for advanced Research University of Science and Technology of ChinaSuzhouJiangsu 215123China School of Mathematical Sciences University of Science and Technology of ChinaHefeiAnhui 230026China

Electron spins in magnetic materials have preferred orientations collectively and generate the macroscopic *** dynamics spans over a wide range of timescales from femtosecond to picosecond,and then to *** Landau-Lifshitz-Gilbert(LLG)equation has been widely used in micromagnetics simulations over *** theoretical and experimental advances have shown that the inertia of magnetization emerges at sub-picosecond timescales and contributes significantly to the ultrafast magnetization dynamics,which cannot be captured intrinsically by the LLG ***,as a generalization,the inertial LLG(iLLG)equation is proposed to model the ultrafast magnetization ***,the LLG equation is a nonlinear system of parabolic type with(possible)***,the iLLG equation is a nonlinear system of mixed hyperbolic-parabolic type with degeneracy,and exhibits more complicated *** behaves as a hyperbolic system at sub-picosecond timescales,while behaves as a parabolic system at larger timescales spanning from picosecond to *** hybrid behaviors impose additional difficulties on designing efficient numerical methods for the iLLG *** this work,we propose a second-order semiimplicit scheme to solve the iLLG *** second-order temporal derivative of magnetization is approximated by the standard centered difference scheme,and the first-order temporal derivative is approximated by the midpoint scheme involving three time *** nonlinear terms are treated semi-implicitly using one-sided interpolation with second-order *** each time step,the unconditionally unique solvability of the unsymmetric linear system is proved with detailed discussions on the condition ***,the second-order accuracy of the proposed method in both time and space is *** sub-picosecond timescales,the inertial effect of ferromagnetics is observed in micromagnetics simulations,in consistency wi

关键词： Inertial Landau-Lifshitz-Gilbert equation semi-implicit scheme second-order accuracy micromagnetics simulations

Novel integration of extreme learning machine and improved Harris hawks optimization with particle swarm optimization-based mutation for predicting soil consolidation parameter

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 Rock Mechanics and Geotechnical Engineering 2022年第5期14卷 1588-1608页

作者： Abidhan Bardhan Navid Kardani Abdel Kareem Alzo'ubi Bishwajit Roy Pijush Samui Amir HGandomi Department of Civil Engineering National Institute of Technology PatnaPatna800005India Discipline of Civil and Infrastructure Engineering School of EngineeringRoyal Melbourne Institute of Technology(RMIT)MelbourneVIC3001Australia Department of Civil Engineering Abu Dhabi UniversityAbu DhabiUnited Arab Emirates School of Computer Science Engineering and technology Bennett UniversityGreater NoidaIndia Faculty of Engineering and Information technology University of Technology SydneySydneyNSW2007Australia

The study proposes an improved Harris hawks optimization(IHHO) algorithm by integrating the standard Harris hawks optimization(HHO) algorithm and mutation-based search mechanism for developing a high-performance machine learning solution for predicting soil compression index. HHO is a newly introduced meta-heuristic optimization algorithm(MOA) used to solve continuous search *** to the original HHO, the proposed IHHO can evade trapping in local optima, which in turn raises the search capabilities and enhances the search mechanism relying on mutation. Subsequently, a novel meta-heuristic-based soft computing technique called ELM-IHHO was established by integrating IHHO and extreme learning machine(ELM) to estimate soil compression index. A sum of 688 consolidation test data was collected for this purpose from an ongoing dedicated freight corridor railway project. To evaluate the generalization capability of the proposed ELM-IHHO model, a detailed comparison between ELM-IHHO and other well-established MOAs, such as particle swarm optimization,genetic algorithm, and biogeography-based optimization integrated with ELM, was performed. Based on the outcomes, the ELM-IHHO model exhibits superior performance over the other MOAs in predicting soil compression index.

关键词： Compression index Artificial intelligence Swarm intelligence Meta-heuristic optimization Dedicated freight corridor