检索结果-内蒙古大学图书馆

第33届中国控制与决策会议

作者： Tong Bie Xiaoqing Zhu Xiaoli Li Xiaogang Ruan Faulty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

ISBN: (纸本)9781665431293

The problem of path planning in the field of robot navigation is now a major re search hot *** the premise of ensuring that the robot can successfully navigate to the target point,the safety of the path also needs to be *** order to find a safer path,a safe pathfinding path planning method is proposed,which introduces two safety parameters that affect the path selection:hazard coefficient and movement *** defining two security parameters,design an appropriate reward function and use A2 C algorithm and PPO algorithm to guide the robot to conduct reinforcement *** experiment will be conducted on a two-dimensional grid map containing various *** conducting comparative experiments,it is verified that the safety pathfinding method proposed in this paper is feasible and reasonable,and can enable the robot to choose a safer road instead of a faster road when planning the path.

关键词： Robot Navigation Deep Reinforcement Learning Path Planning Method Proximal Policy Optimization Grid Map Safe Pathfinding Guidance

来源：评论

学校读者我要写书评

暂无评论

Magnetic Hard Disk Serial Number Recognition Method Based on Machine Vision 33

Magnetic Hard Disk Serial Number Recognition Method Based on...

引用

第33届中国控制与决策会议

作者： Zhe Xu Xiaoge Liu Jian Tang Pengsheng Li Ziying Zhang Beijing University of Technology Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

ISBN: (纸本)9781665431293

Degaussing used magnetic hard drives is a common means of destroying magnetic *** degaussing for different magnetic hard drives can improve the efficiency of magnetic information *** this scenario,it is necessary to quickly identify the used magnetic hard disk *** at the above problem,this paper proposes to apply machine vision to the identification of magnetic hard disk serial *** first,the magnetic hard disk serial number image is ***,the serial number is segmented and its HOG features are ***,a support vector machine(SVM) algorithm is used to construct a recognition *** effectiveness of the proposed method is verified by the magnetic hard disk serial number image.

关键词： Serial number of magnetic hard disk Image preprocessing Histogram of oriented gradient(HOG) feature extraction Support vector machines(SVM)

来源：评论

学校读者我要写书评

暂无评论

A Novel Dissolve Oxygen Control Method Based on Fuzzy Neural Network 36

A Novel Dissolve Oxygen Control Method Based on Fuzzy Neural...

引用

第36届中国控制会议

作者： Jinchao Xu Cuili Yang Junfei Qiao Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory Computational Intelligence and Intelligent System

ISBN: (纸本)9781538629185

In the wastewater treatment processes（WWTPs）,the oxygen transfer is a nonlinear and large time-delay process,which makes the dissolved oxygen（DO） concentration difficult to *** this paper,a novel kind of control method based on fuzzy neural network（FNN） is proposed for controlling DO *** parameters of the neural network were adjusted online through the gradient descent algorithm to get the minimum ***,the simulation results in Benchmark Simulation Model No.1（BSM1） show that the proposed fuzzy neural network controller has better adaptability than some other existing methods.

关键词： Fuzzy Neural Network Dissolved Oxygen Control Wastewater Treatment Processes

来源：评论

学校读者我要写书评

暂无评论

The Prediction of Daily Water Demand based on Fuzzy Neural Network with an Improved Levenberg-Marquardt Algorithm 36

The Prediction of Daily Water Demand based on Fuzzy Neural N...

引用

第36届中国控制会议

作者： Li Zhang Wen Jing Li Jun Fei Qiao Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

ISBN: (纸本)9781538629185

Short-term prediction of water demand provides basic guarantee of water supply system operation and *** this study,an effective model for daily water demand forecasting is ***,principle component analysis(PCA) is utilized to simplify the complexity and reduce the correlation between influence variables,and the score values of selected principle components(PCs) turn into the irrelevant input data of fuzzy neural network(FNN),which models the prediction of water ***,an improved Levenberg-Marquardt(ILM) algorithm is employed to optimize the parameters of FNN ***-Hessian and gradient matrices could be calculated directly without the storage and multiplication of whole Jaccobian matrix,therefore the problems of heavy computing burden and limited memory space could be *** last,contrast experiments are implemented to demonstrate the fuzzy neural network with Levenberg-Marquardt algorithm(ILM-FNN)has better prediction performance and capability to handle practical issues.

关键词： PCA fuzzy neural network improved LM algorithm water demand forecasting

来源：评论

学校读者我要写书评

暂无评论

A Recurrent RBF Neural Network Based on Adaptive Optimum Steepest Descent Learning Algorithm 36

A Recurrent RBF Neural Network Based on Adaptive Optimum Ste...

引用

第36届中国控制会议

作者： Shijie Ma Cuili Yang Junfei Qiao Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

ISBN: (纸本)9781538629185

In order to overcome the defects of gradient descent（GD） algorithm which lead to slow convergence and easy to fall into local minima,this paper proposes an adaptive optimum steepest descent（AOSD） learning algorithm which is used for the recurrent radial basis function（RRBF） neural *** with traditional GD algorithm,the adaptive learning rate is integrated into the AOSD learning algorithm in order to accelerate the convergence speed of training algorithm and improve the network performance of nonlinear system *** comparisons show that the proposed RRBF has faster convergence speed and better prediction performance.

关键词： Nonlinear system modeling recurrent RBF neural network AOSD learning algorithm fast convergence

来源：评论

学校读者我要写书评

暂无评论

Used Mobile Phone Recognition Method Based on Differential Evolution-Deep Forest 33

Used Mobile Phone Recognition Method Based on Differential E...

引用

第33届中国控制与决策会议

作者： Zixuan Wang Jian Tang Chengyu Cui Honggui Han Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

ISBN: (纸本)9781665431293

With the continuous development of the mobile phone industry,used mobile phone(UMP) recycling has become a hot *** present,few experts research UMP recognization(UMPR) methods based on UMP recycling *** forest(DF) identification model of UMPs for intelligent recycling equipment has been proposed,which has many parameters to be manually *** at the above problems,this paper combines differential evolution(DE) algorithm and DF model to propose a method for identifying ***,the candidate multi-scale feature parameters and DF parameters are given ***,we use DE to find the optimal parameters with DF accuracy as the evaluation ***,we feed the obtained optimal parameters into the DF model to construct the final UMPR *** results based on mobile phone pictures of the Ministry of Industry and Information Technology prove the effectiveness of the method.

关键词： Used mobile phones(UMPs) Used mobile phone recognization(UMPR) Deep forest(DF) Differential evolution(DE) UMP recycling equipment Image identification

来源：评论

学校读者我要写书评

暂无评论

A Novel RBF Neural Network Design Based On Immune Algorithm system 36

A Novel RBF Neural Network Design Based On Immune Algorithm ...

引用

第36届中国控制会议

作者： Fei Li Cuili Yang Junfei Qiao Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

ISBN: (纸本)9781538629185

To solve the problem of gradient descent(GD) method which has low accuracy and easily falling into local optimum,the radial basis function(RBF) based on immune algorithm system(IAS-RBF) is *** this method,each antibody is a RBF neural network and the optimal affinity is calculated by immune algorithm system(IAS) to get the best antibody,then the optimal parameter of RBF neural network(i.e.,the RBF centers,the widths,and the output weights) are *** simulation results show that IAS-RBF overcomes the problem of premature convergence,and has a better accuracy than other RBF neural networks.

关键词： Radial basis function neural networks immune algorithm system nonlinear approximation ability

来源：评论

学校读者我要写书评

暂无评论

An echo state network based on Levenberg-Marquardt algorithm 36

An echo state network based on Levenberg-Marquardt algorithm

引用

第36届中国控制会议

作者： Lei Wang Cuili Yang Junfei Qiao Gongming Wang Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

ISBN: (纸本)9781538629185

An abnormal solution might occur during the learning process of echo state network if the least singular value of reservoir state matrix is very close *** solve this problem,an echo state network based on Levenberg-Marquardt(LM-ESN)algorithm replacing linear regression for output weights is proposed and a new damping term is *** the proposed method,it is demonstrated that the output weights sequence has quadratical convergence if the norm of error vector provides a local error *** show that the new method could deal with abnormal solution problems effectively,also it has better performance and robustness for time series prediction than some existing methods.

关键词： echo state network Levenberg-Marquardt algorithm time series prediction

来源：评论

学校读者我要写书评

暂无评论

Adaptive candidate estimation-assisted multi-objective particle swarm optimization

引用

Science China(Technological Sciences) 2022年第8期65卷 1685-1699页

作者： HAN HongGui ZHANG LinLin HOU Ying QIAO JunFei Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing 100124China Engineering Research Center of Digital Community Ministry of EducationBeijing 100124China

The selection of global best(Gbest) exerts a high influence on the searching performance of multi-objective particle swarm optimization algorithm(MOPSO). The candidates of MOPSO in external archive are always estimated to select Gbest. However,in most estimation methods, the candidates are considered as the Gbest in a fixed way, which is difficult to adapt to varying evolutionary requirements for balance between convergence and diversity of MOPSO. To deal with this problem, an adaptive candidate estimation-assisted MOPSO(ACE-MOPSO) is proposed in this paper. First, the evolutionary state information,including both the global dominance information and global distribution information of non-dominated solutions, is introduced to describe the evolutionary states to extract the evolutionary requirements. Second, an adaptive candidate estimation method,based on two evaluation distances, is developed to select the excellent leader for balancing convergence and diversity during the dynamic evolutionary process. Third, a leader mutation strategy, using the elite local search(ELS), is devised to select Gbest to improve the searching ability of ACE-MOPSO. Fourth, the convergence analysis is given to prove the theoretical validity of ACE-MOPSO. Finally, this proposed algorithm is compared with popular algorithms on twenty-four benchmark functions. The results demonstrate that ACE-MOPSO has advanced performance in both convergence and diversity.

关键词： multi-objective particle swarm optimization evolutionary state information adaptive candidate estimation convergence and diversity convergence analysis

来源：评论

学校读者我要写书评

暂无评论

Univariate imputation method for recovering missing data in wastewater treatment process

引用

Chinese Journal of Chemical Engineering 2023年第1期53卷 201-210页

作者： Honggui Han Meiting Sun Huayun Han Xiaolong Wu Junfei Qiao Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing 100124China Engineering Research Center of Digital Community Ministry of EducationBeijing 100124China

High-quality data play a paramount role in monitoring,control,and prediction of wastewater treatment process(WWTP)and can effectively ensure the efficient and stable operation of *** values seriously degrade the accuracy,reliability and completeness of the data quality due to network collapses,connection errors and data transformation *** these cases,it is infeasible to recover missing data depending on the correlation with other *** tackle this issue,a univariate imputation method(UIM)is proposed for WWTP integrating decomposition method and imputation ***,the seasonal-trend decomposition based on loess method is utilized to decompose the original time series into the seasonal,trend and remainder components to deal with the nonstationary characteristics of WWTP ***,the support vector regression is used to approximate the nonlinearity of the trend and remainder components respectively to provide estimates of its missing values.A self-similarity decomposition is conducted to fill the seasonal component based on its periodic ***,all the imputed results are merged to obtain the imputation ***,six time series of WWTP are used to evaluate the imputation performance of the proposed UIM by comparing with existing seven methods based on two *** experimental results illustrate that the proposed UIM is effective for WWTP time series under different missing ***,the proposed UIM is a promising method to impute WWTP time series.

关键词： Univariate Self-similarity Waste water Algorithm Integration

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：