检索结果-南通市图书馆

Depth-Guided Vision Transformer With Normalizing Flows for Monocular 3D Object Detection

IEEE/CAA Journal of Automatica Sinica 2024年第3期11卷 673-689页

作者： Cong pan Junran Peng Zhaoxiang Zhang the Center for research on Intelligent Perception and Computing(CrIPAC) National Laboratory of Pattern Recognition(NLPR)Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190 the School of Future Technology University of Chinese Academy of Sciences(UCAS)Beijing 100049China the huawei Inc. Beijing 100085China IEEE the Institute of Automation Chinese Academy of Sciences(CASIA)Beijing 100190 the University of Chinese Academy of Sciences(UCAS) Beijing 100049 the Centre for Artificial Intelligence and robotics hong Kong Institute of Science&Innovation Chinese Academy of Sciences(HKISI CAS)Hong Kong 999077China

Monocular 3D object detection is challenging due to the lack of accurate depth *** methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input to augment the rGB ***-based methods attempt to convert estimated depth maps to pseudo-LiDAr and then use LiDAr-based object detectors or focus on the perspective of image and depth fusion ***,they demonstrate limited performance and efficiency as a result of depth inaccuracy and complex fusion mode with *** from these approaches,our proposed depth-guided vision transformer with a normalizing flows(NF-DVT)network uses normalizing flows to build priors in depth maps to achieve more accurate depth *** we develop a novel Swin-Transformer-based backbone with a fusion module to process rGB image patches and depth map patches with two separate branches and fuse them using cross-attention to exchange information with each ***,with the help of pixel-wise relative depth values in depth maps,we develop new relative position embeddings in the cross-attention mechanism to capture more accurate sequence ordering of input *** method is the first Swin-Transformer-based backbone architecture for monocular 3D object *** experimental results on the KITTI and the challenging Waymo Open datasets show the effectiveness of our proposed method and superior performance over previous counterparts.

关键词： Monocular 3D object detection normalizing flows Swin Transformer

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

An Encoding-Decoding Framework Based on CNN for circ rNA-rBP Binding Sites Prediction

引用

Chinese Journal of Electronics 2024年第1期33卷 256-263页

作者： Yajing GUO Xiujuan LEI Yi pan School of Computer Science Shaanxi Normal University Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of Sciences Department of Computer Science Georgia State University

Predicting rNA binding protein(rBP) binding sites on circular rNAs(circ rNAs) is a fundamental step to understand their interaction mechanism. Numerous computational methods are developed to solve this problem, but they cannot fully learn the features. Therefore, we propose circ-CNNED, a convolutional neural network(CNN)-based encoding and decoding framework. We first adopt two encoding methods to obtain two original matrices. We preprocess them using CNN before fusion. To capture the feature dependencies, we utilize temporal convolutional network(TCN) and CNN to construct encoding and decoding blocks, respectively. Then we introduce global expectation pooling to learn latent information and enhance the robustness of circ-CNNED. We perform circ-CNNED across 37 datasets to evaluate its effect. The comparison and ablation experiments demonstrate that our method is superior. In addition, motif enrichment analysis on four datasets helps us to explore the reason for performance improvement of circ-CNNED.

关键词： Proteins rNA Neural networks Encoding robustness Decoding Convolutional neural networks

来源：

同方期刊数据库

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

Multi-agent reinforcement learning behavioral control for nonlinear second-order systems

引用

Frontiers of Information Technology & Electronic Engineering 2024年第6期25卷 869-886页

作者： Zhenyi ZhANG Jie hUANG Congjie pan College of Electrical Engineering and Automation Fuzhou UniversityFuzhou 350108China G+Industrial Internet Institute Fuzhou UniversityFuzhou 350108China

reinforcement learning behavioral control(rLBC)is limited to an individual agent without any swarm mission,because it models the behavior priority learning as a Markov decision *** this paper,a novel multi-agent reinforcement learning behavioral control(MArLBC)method is proposed to overcome such limitations by implementing joint ***,a multi-agent reinforcement learning mission supervisor(MArLMS)is designed for a group of nonlinear second-order systems to assign the behavior priorities at the decision *** modeling behavior priority switching as a cooperative Markov game,the MArLMS learns an optimal joint behavior priority to reduce dependence on human intelligence and high-performance computing *** the control layer,a group of second-order reinforcement learning controllers are designed to learn the optimal control policies to track position and velocity signals *** particular,input saturation constraints are strictly implemented via designing a group of adaptive *** simulation results show that the proposed MArLBC has a lower switching frequency and control cost than finite-time and fixed-time behavioral control and rLBC methods.

关键词： reinforcement learning Behavioral control Second-order systems Mission supervisor

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

Shape optimisation of basin insulator for DC gas insulated switchgear/gas insulated transmission lines based on artificial bee colony algorithm

引用

high Voltage 2024年第2期9卷 275-286页

作者： Yi Luo Shiyi Mao Ju Tang Zijun pan Cheng pan State Key Laboratory of Power Grid Environmental Protection School of Electrical Engineering and AutomationWuhan UniversityWuhanChina

The surface charge accumulation on the basin insulator is a particular problem in high-voltage direct current(hVDC)gas insulated switchgears(GIS)and gas insulated trans-mission lines(GIL),which restricts the development and application of extra/ultra high-voltage(EhV/UhV)*** surface charge distribution and anti-flashover performance are closely related to the insulator *** obtain the optimal basin insulator,a shape optimisation model based on artificial bee colony algorithm was established,and the minimisation objective functions based on capacitive(initial)electric field distribution and resistive(steady-state)electric field distribution were respectively *** optimisation results of the two objective functions were calculated,and the electric field and charge distribution on the surface of the insulator before and after optimisation were evaluated and compared using the simulation *** results indicated that the optimisation based on the capacitive electric field can significantly inhibit the surface charge accumulation,and the optimised insulator can significantly reduce the surface normal electric field and make the distribution of the tangential electric field more uniform,and the maximum tangential electric field can be reduced by 10%;the optimisation based on resistive electric field can achieve similar results,but requires more computational *** on the results,the‘anti-charge’basin insulator structure suitable for the DC field was given.

关键词： insulator artificial charge

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

2-local unstable homotopy groups of indecomposable A32-complexes

引用

Science China Mathematics 2024年第3期67卷 607-626页

作者： Zhongjian Zhu Jianzhong pan College of Mathematics and Physics Wenzhou University hua Loo-Keng Key Laboratory of Mathematics Institute of MathematicsAcademy of Mathematics and Systems ScienceChinese Academy of Sciences School of Mathematical Sciences University of Chinese Academy of Sciences

In this paper,we calculate the 2-local unstable homotopy groups of indecomposable *** main technique used is analysing the homotopy property of J(A,X),defined by Gray(1973) for a CW-pair(X,A),which is homotopy equival... 详细信息

关键词： homotopy groups A 2 n -complexes fibration sequence relative James construction 55P15

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

A blockchain-based data auditing scheme with key-exposure resistance for IIoT

引用

Science China(Information Sciences) 2024年第2期67卷 327-328页

作者： pan YANG Jingli rEN henan Academy of Big Data Zhengzhou University

The Industrial Internet of Things(IIoT) enables enterprises to collect data from end devices and outsource the data to cloud servers for flexible data sharing. Public auditing plays an important role in ensuring the integrity of the *** are blockchain-based public auditing schemes that utilize smart contracts to achieve decentralized verification(such as [1]),

关键词：

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

rethinking the Encoder-decoder Structure in Medical Image Segmentation from releasing Decoder Structure

引用

Journal of Bionic Engineering 2024年第3期21卷 1511-1521页

作者： Jiajia Ni Wei Mu An pan Zhengming Chen School of Artificial Intelligence Anhui Polytechnic UniversityWuhu241000China School of Information Science and Engineering HoHai UniversityChangzhou213000China

Medical image segmentation has witnessed rapid advancements with the emergence of encoder-decoder based *** the encoder-decoder structure,the primary goal of the decoding phase is not only to restore feature map resolution,but also to mitigate the loss of feature information incurred during the encoding ***,this approach gives rise to a challenge:multiple up-sampling operations in the decoder segment result in the loss of feature *** address this challenge,we propose a novel network that removes the decoding structure to reduce feature information loss(CBL-Net).In particular,we introduce a Parallel Pooling Module(PPM)to counteract the feature information loss stemming from conventional and pooling operations during the encoding ***,we incorporate a Multiplexed Dilation Convolution(MDC)module to expand the network's receptive ***,although we have removed the decoding stage,we still need to recover the feature map ***,we introduced the Global Feature recovery(GFr)*** uses attention mechanism for the image feature map resolution recovery,which can effectively reduce the loss of feature *** conduct extensive experimental evaluations on three publicly available medical image segmentation datasets:DrIVE,ChASEDB and MoNuSeg *** results show that our proposed network outperforms state-of-the-art methods in medical image *** addition,it achieves higher efficiency than the current network of coding and decoding structures by eliminating the decoding component.

关键词： Medical image segmentation Encoder-decoder architecture Attention mechanisms releasing decoder architecture Neural network

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

Semi-Varying Coefficient panel Data Model with Technical Indicators Predicts Stock returns in Financial Market

引用

Journal of Systems Science & Complexity 2024年第4期37卷 1638-1652页

作者： hU Xuemei pan Ying LI Xiang School of Mathematics and Statistics Chongqing Technology and Business UniversityChongqing 400067China Chongqing Key Laboratory of Social Economy and Applied Statistics Chongqing 400067China research Center for Economy of Upper reaches of the Yangtse river Chongqing Technology and Business UniversityChongqing 400067China

Accurately predicting stock returns is a conundrum in financial *** this conundrum can bring huge economic benefits for investors and also attract the attention of all circles of *** this paper the authors combine semi-varying coefficient model with technical analysis and statistical learning,and propose semi-varying coefficient panel data model with individual effects to explore the dynamic relations between the stock returns from five companies:CVX,DFS,EMN,LYB,and MET and five technical indicators:CCI,EMV,MOM,ln ATr,ln rSI as well as closing price(ln CP),combine semi-parametric fixed effects estimator,semi-parametric random effects estimator with the testing procedure to distinguish fixed effects(FE) from random effects(rE),and finally apply the estimated dynamic relations and the testing set to predict stock returns in December 2020 for the five *** proposed method can accommodate the varying relationship and the interactive relationship between the different technical indicators,and further enhance the prediction accuracy to stock returns.

关键词： Fixed effects random effects semi-varying coefficient panel data model stock returns technical indicators

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

Channel Estimation for reconfigurable Intelligent Surface Aided Multiuser Millimeter-Wave/Thz Systems

引用

China Communications 2024年第3期21卷 91-103页

作者： Chu hongyun pan Xue Li Baijiang School of Communications and Information Engineering Xi’an University of Posts and TelecommunicationsXi’an 710121China

It is assumed that reconfigurable intelligent surface(rIS)is a key technology to enable the potential of mmWave *** passivity of the rIS makes channel estimation difficult because the channel can only be measured at the transceiver and not at the *** this paper,we propose a novel separate channel estimator via exploiting the cascaded sparsity in the continuously valued angular domain of the cascaded channel for the rIS-enabled millimeter-wave/Tera-hz systems,i.e.,the two-stage estimation method where the cascaded channel is separated into the base station(BS)-rIS and the rIS-user(UE)***,we first reveal the cascaded sparsity,i.e.,the sparsity exists in the hybrid angular domains of BS-rIS and the rIS-UEs separated channels,to construct the specific sparsity structure for rIS enabled multi-user ***,we formulate the channel estimation problem using atomic norm minimization(ANM)to enhance the proposed sparsity structure in the continuous angular domains,where a low-complexity channel estimator via Alternating Direction Method of Multipliers(ADMM)is *** findings demonstrate that the proposed channel estimator outperforms the current state-of-the-arts in terms of performance.

关键词： atomic norm minimization cascaded channel estimation convex optimization mmWave/Thz reconfigurable intelligent surface(rIS) sparsity

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

A Generalized MSST Algorithm for Counting Points of Elliptic Curves over F_(p)^(n)

引用

Journal of Systems Science & Complexity 2024年第4期37卷 1738-1754页

作者： LI Xiao LV Chang pan Zhizhong Key Laboratory of Cyberspace Security Defense Institute of Information EngineeringChinese Academy of SciencesBeijing 100085China School of Cyber Security University of Chinese Academy of SciencesBeijing 100085China huawei Technologies Co. Ltd.Shenzhen 518129China

Elliptic curve cryptography is an important part of nowaday's public key *** points of elliptic curves over finite fields is of great significance to the selection of safety *** present,there are many p-adic algorithms,such as SST algorithm,generalized AGM algorithm,Kedlaya algorithm,etc.,which can deal with the situation of finite fields of small *** this paper,the authors generalize the MSST algorithm of characteristic 2 to general fields of odd characteristic,and propose the generalized MSST *** generalized MSST algorithm is achieved by combining the advantages of the SST algorithm and the generalized AGM *** the time complexity of the multiplication of two n-bit numbers is denoted as O((n)^(μ)),then the time complexity of the generalized MSST algorithm is O(n^(2μ+1/1+μ)),which is the same as the improved SST *** practical experiments,the running time of the generalized MSST algorithm is less than that of the improved SST algorithm.

关键词： Elliptic curve generalized AGM algorithm generalized MSST algorithm SST algorithm

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

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：