检索结果-南通市图书馆

Self‑supervised zero‑shot dehazing network based on dark channel prior

在线全文

学校读者我要写书评

暂无评论

Frontiers of Optoelectronics 2023年第1期16卷 95-108页

作者： Xinjie Xiao Yuanhong Ren Zhiwei Li Nannan Zhang wuneng zhou School of Electronic and Electrical Engineering Shanghai University of Engineering ScienceShanghai 201620China College of Information Science and Technology Donghua UniversityShanghai 201620China

Most learning-based methods previously used in image dehazing employ a supervised learning strategy,which is timeconsuming and requires a large-scale ***,large-scale datasets are difcult to ***,we propose a selfsupervised zero-shot dehazing network(SZDNet)based on dark channel prior,which uses a hazy image generated from the output dehazed image as a pseudo-label to supervise the optimization process of the ***,we use a novel multichannel quad-tree algorithm to estimate atmospheric light values,which is more accurate than previous ***,the sum of the cosine distance and the mean squared error between the pseudo-label and the input image is applied as a loss function to enhance the quality of the dehazed *** most signifcant advantage of the SZDNet is that it does not require a large dataset for training before performing the dehazing *** testing shows promising performances of the proposed method in both qualitative and quantitative evaluations when compared with state-of-the-art methods.

关键词： Image dehazing Quad-tree algorithm Self-supervised Zero-shot

Adaptive constrained population extremal optimisation-based robust proportional-integral-derivation frequency control method for an islanded microgrid

在线全文

学校读者我要写书评

暂无评论

IET Cyber-Systems and Robotics 2021年第3期3卷 210-227页

作者： Kang-Di Lu Guo-Qiang Zeng wuneng zhou College of Information Sciences and Technology Donghua UniversityShanghaiChina College of Cyber Security and the National-Local Joint Engineering Research Center of Network Security Detection and Protection Technology Jinan UniversityGuangzhouChina National-Local Joint Engineering Laboratory of Digitalise Electrical Design Technology Wenzhou UniversityWenzhouChina

The expected penetration of renewable sources is driving the islanded microgrid towards uncertainties,which have highly influence the reliability and complexities of frequency *** alleviate the influence caused by load fluctuations and inherent variability of renewable sources,this article proposes an optimised robust proportional-integralderivation(PID)frequency control method by taking full advantage of a robust control strategy while simultaneously maintaining the basic characteristics of a PID *** the process of iterated optimisation,a weighted objective function is used to balance the tracking error performance,robust stability and disturbance attenuation ***,the robust PID frequency(RPIDF)controller is determined by an adaptive constrained population extremal optimisation algorithm based on self-adaptive penalty constraint-handling *** proposed control method is examined on a typical islanded microgrid,and the control performance is evaluated under various disturbances and parametric ***,the simulation results indicate that the fitness value of the proposed method is 1.7872,which is lower than 2.9585 and 3.0887 obtained by two other evolutionary algorithms-based RPIDF ***,the comprehensive simulation results fully demonstrate that the proposed method is superior to other comparison methods in terms of four performance indices on the most considered scenarios.

关键词： constrained evolutionary algorithm frequency control islanded microgrid population extremal optimisation robust PID controller

Video Based Fire Detection Systems on Forest and Wildland Using Convolutional Neural 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

Journal of Donghua University(English Edition) 2019年第2期36卷 149-157页

作者： HICINTUKA Jean Philippe zhou wuneng College of Information Science and Technology Donghua University

The devastating effects of wildland fire are an unsolved problem,resulting in human losses and the destruction of natural and economic *** neural network(CNN)is shown to perform very well in the area of object *** network has the ability to perform feature extraction and classification within the same *** this paper,we propose a CNN for identifying fire in videos.A deep domain based method for video fire detection is proposed to extract a powerful feature representation of *** on real video sequences,the proposed approach achieves better classification performance as some of relevant conventional video based fire detection methods and indicates that using CNN to detect fire in videos is *** balance the efficiency and accuracy,the model is fine-tuned considering the nature of the target problem and fire *** results on benchmark fire datasets reveal the effectiveness of the proposed framework and validate its suitability for fire detection in closed-circuit television surveillance systems compared to state-of-the-art methods.

关键词： fire detection wildland fires convolutional neural network(CNN) video sequences video analysis object analysis

Cross Function Projective Synchronization of Liu System and the New Lorenz System with Known and Unknown Parameters

在线全文

学校读者我要写书评

暂无评论

Cross Function Projective Synchronization of Liu System and ...

2013年中国智能自动化学术会议

作者： Yuqing Sun wuneng zhou Yuan Du College of Information Science and Technology Donghua University

In this paper,we focuses on a new way of the function projective synchronization(FPS) of the hyperchaotic Liu system and the hyperchaotic New Lorenz *** call this new method the cross function projective synchronization (CFPS).Within the two systems,we achieved the CFPS at the first place through a proper control ***,by designing the parameter update law,the time of reaching projective synchronization could be ***, several numerical simulations are presented to verify the feasibility and effectiveness of the method.

关键词： Cross function projective synchronization Adaptive control Hyperchaotic system Lyapunov stability theorem

The Decomposition and the Gradated Structure of Clousure,Interior and Derived Sets of LF Sets in Induced Spaces

在线全文

cnki会议

学校读者我要写书评

暂无评论

The Decomposition and the Gradated Structure of Clousure,Int...

98年中国模糊数学与模糊系统委员会第九届年会

作者： wuneng zhou Jingzhou Normal College, Jingzhou, 434104

In this paper, a kinds of decomposition formulas of closure, interior and N-derived set of LF sets are given and the gradated structure of theirs are discussed in induced spaces.

关键词： LF topological spaces induced spaces closure interior N-derived set

Exponential synchronization of stochastic complex dynamical networks with impulsive perturbations and Markovian switching

在线全文

cnki会议

学校读者我要写书评

暂无评论

Exponential synchronization of stochastic complex dynamical ...

第26届中国控制与决策会议

作者： Anding Dai wuneng zhou Yichao Zheng Shengchao Su College of Information Science and Technology Donghua University Laboratory of Robotics and Intelligent Control Shanghai University of Engineering Science

ISBN: (纸本)9781479937097

This paper investigates the exponential synchronization problem of stochastic complex dynamical networks with impulsive perturbations and Markovian switching. The complex dynamical networks consists of ? modes and the networks switch from one mode to another according to a Markovian chain with known transition probability. Basing on the Lyapunov functional method and stochastic analysis, by employing ?-matrix approach, some sufficiency conditions are presented to ensure the exponential synchronization of stochastic complex dynamical networks with impulsive perturbations and Markovian switching, and the upper bound of impulsive gain is evaluated. At the end of this paper, a numerical examples are included to show the effectiveness of our results.

关键词： Exponential synchronization Complex dynamical network Markovian switching Impulsive perturbation

New Strategy of Delay-Dependent H∞ Stability and Stabilization for Uncertain Neutral Systems with Mixed Time-Varying Delays

在线全文

cnki会议

学校读者我要写书评

暂无评论

New Strategy of Delay-Dependent H∞ Stability and Stabilizat...

2009中国控制与决策会议

作者： Zhongqi Ma,wuneng zhou,Lin Pan College of Information Science and Technology,Donghua University,Shanghai 201620

A novel approach was employed to design state feedback H

关键词： Neutral Systems H∞ Stability Mixed Time-Varying Delays Augmented Lyapunov Functional Linear Matrix Inequality(LMI)

在线全文

cnki会议

学校读者我要写书评

暂无评论

基于粒子群算法优化PCNN的织物疵点分割

棉纺织技术 2017年第10期45卷 5-8页

作者：钱炜周武能东华大学上海201620

探讨基于粒子群算法优化PCNN参数的织物疵点分割。将PCNN中3个参数当作粒子群中粒子,根据经PCNN分割后图像的熵作为PSO的适应度函数,寻找PCNN模型中参数的最优值。分割对比实验从主观和客观两方面验证了该方法的可行性和有效性,并与传统... 详细信息

探讨基于粒子群算法优化PCNN参数的织物疵点分割。将PCNN中3个参数当作粒子群中粒子,根据经PCNN分割后图像的熵作为PSO的适应度函数,寻找PCNN模型中参数的最优值。分割对比实验从主观和客观两方面验证了该方法的可行性和有效性,并与传统PCNN和OTSU分割方法进行比较。认为:此种方法的分割效果良好,可以有效提高模型的自动化程度。

关键词：粒子群算法脉冲耦合神经网络疵点分割迭代适应度

一类动态系统可靠D-稳定性条件-LMI方法

在线全文

学校读者我要写书评

暂无评论

数学物理学报（A辑） 2008年第1期28卷 144-154页

作者：周武能苏宏业褚健工业控制国家重点实验室浙江大学先进控制研究所杭州310027 东华大学信息科学与技术学院自动化系上海201620

考虑一类具有执行器和传感器故障的动力系统可靠鲁棒控制综合问题.提出了一个系统D-稳定的充分必要条件.基于这一充分必要条件,得到了可靠H_∞控制器存在的条件.接着用线性矩阵不等式(LMI)方法设计控制器,使闭环系统当部分控制器件出现... 详细信息

考虑一类具有执行器和传感器故障的动力系统可靠鲁棒控制综合问题.提出了一个系统D-稳定的充分必要条件.基于这一充分必要条件,得到了可靠H_∞控制器存在的条件.接着用线性矩阵不等式(LMI)方法设计控制器,使闭环系统当部分控制器件出现故障时鲁棒D -稳定且具有H_∞性能.最后通过一个仿真实例说明该文给出的方法及其有效性.

关键词：动力系统 D-稳定性可靠控制线性矩阵不等式(LMI)