检索结果-内蒙古大学图书馆

A Novel Evaluation Strategy to Artificial Neural Network Model Based on Bionics

Journal of Bionic engineering 2022年第1期19卷 224-239页

作者： Sen Tian Jin Zhang Xuanyu Shu Lingyu Chen Xin Niu You Wang School of Mathematics and Statistics Hunan Normal UniversityChangsha410081China College of Information Science and Engineering Hunan Normal UniversityChangsha410081China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China Key Laboratory of Industrial Control Technology Zhejiang UniversityHangzhou310058China Science and Technology on Parallel and Distributed Laboratory College of ComputerNational University of Defense TechnologyChangsha410199China Key Laboratory of Industrial Control Technology Institute of Cyber Systems and ControlZhejiang UniversityHangzhou310027China

With the continuous deepening of Artificial Neural Network(ANN)research,ANN model structure and function are improving towards diversification and ***,the model is more evaluated from the pros and cons of the problem-solving results and the lack of evaluation from the biomimetic aspect of imitating neural networks is not inclusive ***,a new ANN models evaluation strategy is proposed from the perspective of bionics in response to this problem in the ***,four classical neural network models are illustrated:Back Propagation(BP)network,Deep Belief Network(DBN),LeNet5 network,and olfactory bionic model(KIII model),and the neuron transmission mode and equation,network structure,and weight updating principle of the models are analyzed *** analysis results show that the KIII model comes closer to the actual biological nervous system compared with other models,and the LeNet5 network simulates the nervous system in ***,evaluation indexes of ANN are constructed from the perspective of bionics in this paper:small-world,synchronous,and chaotic ***,the network model is quantitatively analyzed by evaluation indexes from the perspective of *** experimental results show that the DBN network,LeNet5 network,and BP network have synchronous *** the DBN network and LeNet5 network have certain chaotic characteristics,but there is still a certain distance between the three classical neural networks and actual biological neural *** KIII model has certain small-world characteristics in structure,and its network also exhibits synchronization characteristics and chaotic *** with the DBN network,LeNet5 network,and the BP network,the KIII model is closer to the real biological neural network.

关键词： Artificial neural network(ANN) Back Propagation(BP)network Deep Belief Network(DBN) LeNet5 network Olfactory bionic model(KIII model) Small world Chaos Synchronous

来源：评论

学校读者我要写书评

暂无评论

An improvement in the observation model for Monte Carlo localization 11

An improvement in the observation model for Monte Carlo loca...

引用

11th International Conference on Informatics in control, Automation and Robotics, ICINCO 2014

作者： Alhashimi, Anas W. Hostettler, Roland Gustafsson, Thomas Automatic Control Group Computer Science Electrical and Space Engineering Luleå University of Technology Luleå Sweden

ISBN: (纸本)9789897580406

Accurate and robust mobile robot localization is very important in many robot applications. Monte Carlo localization (MCL) is one of the robust probabilistic solutions to robot localization problems. The sensor model used in MCL directly influence the accuracy and robustness of the pose estimation process. The classical beam models assumes independent noise in each individual measurement beam at the same scan. In practice, the noise in adjacent beams maybe largely correlated. This will result in peaks in the likelihood measurement function. These peaks leads to incorrect particles distribution in the MCL. In this research, an adaptive sub-sampling of the measurements is proposed to reduce the peaks in the likelihood function. The sampling is based on the complete scan analysis. The specified measurement is accepted or not based on the relative distance to other points in the 2D point cloud. The proposed technique has been implemented in ROS and stage simulator. The result shows that selecting suitable value of distance between accepted scans can improve the localization error and reduce the required computations effectively.

关键词： Robot applications

来源：评论

学校读者我要写书评

暂无评论

Mean-field Theory for Some Bus Transport Networks with Random Overlapping Clique Structure

引用

Communications in Theoretical Physics 2010年第4期53卷 688-692页

作者：杨旭华孙豹王波孙优贤 College of Information Engineering Zhejiang University of Technology State Key Laboratory of Industrial Control Technology Zhejiang University Department of Computer Science and Engineering Yiwu Industrial and Commercial College

Transport networks, such as railway networks and airport networks, are a kind of random network with complex topology. Recently, more and more scholars paid attention to various kinds of transport networks and try to explore their inherent characteristics. Here we study the exponential properties of a recently introduced Bus Transport Networks （BTNs） evolution model with random overlapping clique structure, which gives a possible explanation for the observed exponential distribution of the connectivities of some BTNs of three major cities in China. Applying mean-field theory, we analyze the BTNs model and prove that this model has the character of exponential distribution of the connectivities, and develop a method to predict the growth dynamics of the individual vertices, and use this to calculate analytically the connectivity distribution and the exponents. By comparing mean-field based theoretic results with the statistical data of real BTNs, we observe that, as a whole, both of their data show similar character of exponential distribution of the connectivities, and their exponents have same order of magnitude, which show the availability of the analytical result of this paper.

关键词： mean-field theory bus transport network evolution model exponential distribution

来源：评论

学校读者我要写书评

暂无评论

Integrated Inspection of QoM, QoP, and QoS for AOI Industries in Metaverses

引用

IEEE/CAA Journal of automatica Sinica 2022年第12期9卷 2071-2078页

作者： Yutong Wang Yonglin Tian Jiangong Wang Yansong Cao Shixing Li Bin Tian IEEE The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China Department of Engineering Science Faculty of Innovation EngineeringMacao University of Science and TechnologyMacao 999078China North Automatic Control Technology Institute in Taiyuan ShanxiChina Qingdao Academy of Intelligent Industries Shandong 266109China

With the rapid development of information technologies such as digital twin, extended reality, and blockchain,the hype around "metaverse" is increasing at astronomical speed. However, much attention has been paid to its entertainment and social functions. Considering the openness and interoperability of metaverses, the market of quality inspection promises explosive growth. In this paper, taking advantage of metaverses, we first propose the concept of Automated Quality Inspection(Auto QI), which performs integrated inspection covering the entire manufacturing process, including Quality of Materials, Quality of Manufacturing(Qo M), Quality of Products, Quality of Processes(Qo P), Quality of Systems, and Quality of Services(Qo S). Based on the scenarios engineering theory, we discuss how to perform interactions between metaverses and the physical world for virtual design instruction and physical validation feedback. Then we introduce a bottomup inspection device development workflow with productivity tools offered by metaverses, making development more effective and efficient than ever. As the core of quality inspection,we propose Quality Transformers to complete detection task,while federated learning is integrated to regulate data *** summary, we point out the development directions of quality inspection under metaverse tide.

关键词： Automated Optical Inspection Metaverses Quality Inspection Transformers

来源：评论

学校读者我要写书评

暂无评论

Towards green for relay in InterPlaNetary Internet based on differential game model

引用

science China(Information sciences) 2014年第4期57卷 65-73页

作者： LIN FuHong LIU Qian ZHOU XianWei XIONG Ke School of Computer and Communication Engineering University of Science and Technology Beijing School of Computer and Information Technology Beijing Jiaotong University State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University

InterPlaNetary Internet(IPN)plays a very important role in the exploitation of ***,the relays in IPN are suffered from high symbol error,limited storage space,and limited available *** analyze the performance of the relay in IPN,in this article,we build a differential game model,where the controller is transmitting rate,and the goal is to maximize the payoff according to the symbol error rate,the storage space and the available energy in the *** such a design,the green relays can be achieved for IPNs,which could prolong the live of the *** the model is not easy to discuss,we analyze it using the Bellman theorem and then get some formulas on the trace of the optimal transmitting ***,extensive simulation results are presented to demonstrate the performance of our proposed model,which shows that by using our derived optimal transmitting rate trace,the relay’s payoff can be maximized.

关键词： IPN differential game symbol error limited storage space energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Character recognition competition for street view shop signs

引用

National science Review 2023年第6期10卷 27-31页

作者： Jingqun Tang Weidong Du Bin Wang Wenyang Zhou Shuqi Mei Tao Xue Xing Xu Hai Zhang Shanghai Byte Dance Technology Co. Ltd School of Control Science and Engineering Zhejiang University School of Computer Science and Technology University of Science and Technology of China School of Computer Science and Technology Tsinghua Univeristy Shenzhen Tencent Technology Co. Ltd School of Computer Science and Engineering University of Electronic Science and Technology of China Pazhou Laboratory (Huangpu) School of Mathematics Northwest University

INTRODUCTION Store signboards provide important information in street view images,andcharacter recognition in natural scenes is an important research direction in computer *** view store signboard character recognitio...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Domain Adaptation via Variational Inference for Evolving Concept Drift

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Wang, Chuang Wang, Zidong Sheng, Weiguo Liu, Qingqiang Dong, Hongli Northeast Petroleum University Artificial Intelligence Energy Research Institute Daqing163318 China Northeast Petroleum University Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Daqing163318 China Northeast Petroleum University Sanya Offshore Oil & Gas Research Institute Sanya572025 China Brunel University London Department of Computer Science Middlesex UxbridgeUB8 3PH United Kingdom Hangzhou Normal University School of Information Science and Technology Hangzhou311121 China Northeast Petroleum University School of Electrical & Information Engineering Daqing163318 China

The concept of fuzzy domain adaptation (FDA) isfocused on transferring a model trained in a source domainto a target domain, where intrinsic distribution discrepanciesexist in non-stationary and non-deterministic environments. Inthis paper, a novel drift decoupling-based variational adaptationnetwork (DD-VAN) is proposed for FDA, allowing for the learningof intra-domain evolutionary patterns and inter-domain uncer-tainties. The DD-VAN algorithm is implemented in three mainsteps: (1) an intra-domain evolutionary trend modeling module isfirst employed to capture unknown temporal variations throughan autoencoder architecture with variational inference;(2) aprototype-assisted fuzzy clustering module is used to estimate themembership degree of the target data, characterizing the inherentuncertainty and imprecision present in real-world distributions;and (3) a membership-aware domain fuzzy matching module isutilized to learn the gradual transitions between category-relateddata pairs in the source and target domains by introducing un-certainties. Furthermore, it is theoretically demonstrated that theinferred posterior distributions of latent codes can be optimizedto align with the corresponding prior distributions by minimizingthe Kullback-Leibler divergence. Extensive experiments are con-ducted on cross-domain tasks involving both synthetic and real-world datasets, and the experimental results suggest that the DD-VAN algorithm outperforms existing state-of-the-art methods. © 1993-2012 IEEE.

关键词： Variational techniques

来源：评论

学校读者我要写书评

暂无评论

EMO: Edge Model Overlays to Scale Model Size in Federated Learning

arXiv

引用

arXiv 2025年

作者： Wu, Di He, Weibo Feng, Wanglei Wen, Zhenyu Qian, Bin Varghese, Blesson School of Computer Science University of St Andrews United Kingdom Institute of Cyberspace Security College of Information Engineering Zhejiang University of Technology China University of Science and Technology of China China State Key Laboratory of Industrial Control Technology Zhejiang University China

Federated Learning (FL) trains machine learning models on edge devices with distributed data. However, the computational and memory limitations of these devices restrict the training of large models using FL. Split Federated Learning (SFL) addresses this challenge by distributing the model across the device and server, but it introduces a tightly coupled data flow, leading to computational bottlenecks and high communication costs. We propose EMO as a solution to enable the training of large models in FL while mitigating the challenges of SFL. EMO introduces Edge Model Overlay(s) between the device and server, enabling the creation of a larger ensemble model without modifying the FL workflow. The key innovation in EMO is Augmented Federated Learning (AFL), which builds an ensemble model by connecting the original (smaller) FL model with model(s) trained in the overlay(s) to facilitate horizontal or vertical scaling. This is accomplished through three key modules: a hierarchical activation replay cache to decouple AFL from FL, a convergence-aware communication controller to optimize communication overhead, and an ensemble inference module. Evaluations on a real-world prototype show that EMO improves accuracy by up to 17.77% compared to FL, and reduces communication costs by up to 7.17× and decreases training time by up to 6.9× compared to SFL. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Degree of Spiking Neural P Systems Without Delay

引用

电子学报(英文版) 2012年第3期21卷 419-424页

作者： JIANG Keqin SHI Xiaolong Key Laboratory of Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan 430074 China School of Computer and Intormation Anqing Teachers College Anqing 246133 China

Spiking neural P systems are a class of dis- tributed parallel computing models inspired from the way neurons communicate with each other by means of electri- cal impulses (called "spikes"). In this paper, we continue the research of normal forms for spiking neural P systems. Specifically, we prove that the degree of spiking neural P systems without delay can be decreased to two without losing the computational completeness (both in the gener- ating and accepting modes).

关键词：电脉冲神经元膜系统并行计算模型延时分布式

来源：评论

学校读者我要写书评

暂无评论

Optimal control of quantum systems with SU(1,1)dynamical symmetry

引用

control Theory and technology 2015年第3期13卷 211-220页

作者： Wenbin DONG Rebing WU Jianwu WU Chunwen LI Tzyh-Jong TARN Department of Automation Tsinghua University Center for Quantum Information Science and Technology Tsinghua National Laboratory for Information Science and Technology(TNlist) Beijing Aerospace Automatic Control Institute Electrical and Systems Engineering Department Washington University in St.Louis

SU（1,1） dynamical symmetry is of fundamental importance in analyzing unbounded quantum systems in theoretical and applied physics. In this paper, we study the control of generalized coherent states associated with quantum systems with SU（1,1） dynamical symmetry. Based on a pseudo Riemannian metric on the SU（1,1） group, we obtain necessary conditions for minimizing the field fluence of controls that steer the system to the desired final state. Further analyses show that the candidate optimal control solutions can be classified into normal and abnormal extremals. The abnormal extremals can only be constant functions when the control Hamiltonian is non-parabolic, while the normal extremals can be expressed by Weierstrass elliptic functions according to the parabolicity of the control Hamiltonian. As a special case, the optimal control solution that maximally squeezes a generalized coherent state is a sinusoidal field, which is consistent with what is used in the laboratory.

关键词： Quantum control optimal control dynamical symmetry

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：