检索结果-内蒙古大学图书馆

作者： Yonghua Huo Chunxiao Song Sheng Gao Haodong Yang Yu Yan Yang Yang The 54th Research Institute of CETC State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications

With the continuous development of computer networks in recent years, the scale and types of services carried by the network are *** traffic prediction results provide the main support and reference basis for network operation and maintenance functions such as network attack detection. Since network traffic has certain dynamics, continuity, and long correlation and self-similar characteristics, the artificial intelligence method is generally used for network traffic prediction. Among them, the recurrent neural network has a short-term memory performance and has a good prediction effect for time series data such as network traffic. However, when the time series span is relatively long, the problem of gradient disappearance or gradient explosion may occur, so further optimization is required. In this paper, we propose a network traffic prediction method based on parameter pre-training of clockwork neural network. This method is first based on CW-RNN, and then introduces the differential evolution algorithm to pre-train the clock parameters. At the same time, the differential evolution algorithm is further improved by changing its crossover factor and mutation factor to improve the accuracy of its *** computer simulation, the flow prediction method proposed in this paper can obtain accurate prediction results.

关键词： Internet traffic prediction differential evolution algorithm Recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

A Novel Friction Compensation Method Based on a Hybrid Model for Vision-Based Optoelectronic Platform

A Novel Friction Compensation Method Based on a Hybrid Model...

引用

Artificial Intelligence and Electromechanical Automation (AIEA), International Conference on

作者： Huimin Cui Xuebing Zhang Yuning Wang Jijun Ma Beijing Research Institute of Telemetry Beijing China

ISBN: (数字)9781728182889

ISBN: (纸本)9781728182896

With the development of technology, the demand for detection distance and stable tracking accuracy of vision-based stable tracking platforms is getting much higher. However, the line of sight often shakes due to friction, which ultimately causes a decline in imaging quality and a reduction in stable tracking accuracy. Inspired by Lurge friction model and neural network, a hybrid friction model has been proposed in the paper to improve the performance of the photoelectric platform. First of all, a Lurge friction model is established for the static friction part and its parameter is identified by means of differential evolution algorithm. Second, a recurrent single multiplication neuron is built for the system's dynamic friction part and the differential evolution algorithm is also introduced to obtain the model's parameters based on the speed change data collected during free deceleration movement. Finally, the experimental results show that the proposed hybrid friction model can effectively approximate the realistic friction and eliminate the "flat top" and "dead zone" phenomena of speed response. The maximum speed tracking accuracy is reduced to ±0.05 °/s after compensation, which greatly improves the system's speed tracking accuracy and stability accuracy.

关键词： friction compensation optoelectronic platform stability accuracy neural network differential evolution algorithm differential evolution algorithms friction compensation friction force model Hybrid modes tracking accuracy Neural network model parameters

来源：评论

学校读者我要写书评

暂无评论

Advanced Electromyogram Signal Processing with an Emphasis on Simplified, Near-Optimal Whitening

Advanced Electromyogram Signal Processing with an Emphasis o...

引用

作者： He Wang Worcester Polytechnic Institute

学位级别：硕士

Estimates of the time-varying standard deviation of the surface EMG signal (EMGσ) are extensively used in the field of EMG-torque estimation. The use of a whitening filter can substantially improve the accuracy of EMGσ estimation by removing the signal correlation and increasing the statistical bandwidth. However, a subject-specific whitening filter which is calibrated to each subject, is quite complex and inconvenient. To solve this problem, we first calibrated a 60th-order "Universal" FIR whitening filter by using the ensemble mean of the inverse of the square root of the power spectral density (PSD) of the noise-free EMG signal. Pre-existing data from elbow contraction of 64 subjects, providing 512 recording trials were used. The test error on an EMG-torque task based on the "Universal" FIR whitening filter had a mean error of 4.80% maximum voluntary contraction (MVC) with a standard deviation of 2.03% MVC. Meanwhile the subject-specific whitening filter had performance of 4.84±1.98% MVC (both have a whitening band limit at 600 Hz). These two methods had no statistical difference. Furthermore, a 2nd-order IIR whitening filter was designed based on the magnitude response of the "Universal" FIR whitening filter, via the differential evolution algorithm. The performance of this IIR whitening filter was very similar to the FIR filter, with a performance of 4.81±2.12% MVC. A statistical test showed that these two methods had no significant difference either. Additionally, a complete theory of EMG in additive measured noise contraction modeling is described. Results show that subtracting the variance of whitened noise by computing the root difference of the square (RDS) is the correct way to remove noise from the EMG signal.

关键词： Electromyogram Whitening differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of Ideal Bode Transfer Function Tuning Fractional Order PID in Pressure Difference of Vertical Mill

Application of Ideal Bode Transfer Function Tuning Fractiona...

引用

第32届中国控制与决策会议

作者： Lei Zhang Qiang Zhang Wei Wang School of Electrical Engineering University of Jinan Department of Electrical Tancheng branch of linyi zhonglian cement co.LTD

Summing the grinding process of cement vertical mill,this paper analyzes the technology of this process,points out the key controlled variable in the process-the vertical mill pressure difference,and establishes the *** this paper,the vertical mill pressure difference is controlled by fractional order PID controller,which is based on the parameter optimization method with ideal bode transfer function as the reference model,because of its insensitivity to gain *** the integral order λ and differential μ are also adjustable,parameter optimization is more complex,a modified differential evolution algorithm is adopted to speed up the *** simulation results show that the control performance of fractional order PID controller is better than that of integer order controller,and the optimization speed of modified differential evolution algorithm is also improved.

关键词： vertical roller mill Bodes ideal transfer function fractional order PID differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Chaotic differential evolution algorithm Based on Simplex Method for Large-scale Industrial Processes of Fuzzy Model

Chaotic Differential Evolution Algorithm Based on Simplex Me...

引用

The 24th Chinese Control and Decision Conference (第24届中国控制与决策学术年会 2012 CCDC)

作者： Dakuo He Lifeng Wang Shuo Li Bingyu Yang School of Information Science and Engineering Northeastern University Shenyang China

In the large-scale industrial processes, there are more slow perturbations. So the mathematical model of an actual system is difficult to be accurate. When optimizing large-scale industrial processes, the mathematical model and the actual system does not match, that is model-reality difference. In order to deal with this problem, the structure of decomposition and coordination is used in this paper. The whole large-scale industrial processes can be decomposed into several sub processes that are interactive, and the simplex method including open-loop simplex method and the simplex method with global feedback is the coordinate strategy. The main idea of the differential evolution algorithm with simple method is that find out the best individual in every generation with the standard differential evolution algorithm method ,then around the best individual do local search for some times and compared the former best one with the ones from the local search, if the latter is better, substitute the best one with the latter .A classical example of large-scale industrial processes is applied and the simulation results show the validity of the method.

关键词： fuzzy nonlinear programming fuzzy model large-scale industrial processes simplex method differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on MapReduce Parallel Optimization Method Based on Improved K-means Clustering algorithm

Research on MapReduce Parallel Optimization Method Based on ...

引用

作者： Ye Xiong Qingyu Peng Zhenhang Zhang School of Automation & Electrical Engineering Lanzhou Jiaotong University Construction Second Division CMCU Engineering Co. Ltd. School of Electrical Engineering Chongqing University

The traditional K-means clustering algorithm occupies a large quantity of memory resources and computing costs when dealing with massive data. It is easy to be restricted by something such as the initial center point as well abnormal data, and usually can not achieve effective clustering of large-scale data. In order to effectively solve the limitations of the algorithm, we propose a MapReduce parallel optimization method based on improved K-means clustering algorithm. Firstly, differential evolution theory is introduced to determine the optimal initial clustering center, after that, on the basis of the influence of samples on clustering results, the corresponding weighted Euclidean distance is designed to achieve effective data differentiation, so as to effectively reduce the impact of samples on clustering *** negative effect of abnormal data on clustering analysis can improve the accuracy of clustering. Finally, MapReduce programming model is used to realize parallel clustering. We use UCI datasets to verify the parallel optimization method. From the experimental results we can clearly know that the method we proposed has relatively stable parallel clustering results, faster operation speed, and effectively saves the operation time.

关键词： K-means clustering algorithm MapReduce programming model differential evolution algorithm UCI dataset Initial clustering center Weighted Euclidean distance

来源：评论

学校读者我要写书评

暂无评论

Research on Crowd-Sourcing Distribution Path Considering Real-Time Customer Demand

Research on Crowd-Sourcing Distribution Path Considering Rea...

引用

2020年第五届经济与企业管理国际学术会议

作者： Jing Wang Zhuzhi Shen School of Management Wuhan University of Science and Technology

With the rapid development of crowd-sourcing distribution,most of the existing researches focus on the path optimization of single distribution,and few consider the dynamic customer *** on this,under certain assumptions,fuzzy time window is introduced to express customer satisfaction,which is constrained by achieving the expected customer satisfaction of the *** the basis of static model,considering the characteristics of real-time order generation,the dynamic model is built by delay *** the example analysis,the dynamic model uses the way of delay processing and inserting orders to carry out the order integration distribution,solves some problems in the distribution network under the crowd-sourcing mode,effectively reduces the number of crowd-sourcing distributors,and reduces the overall distribution *** validity of the model is verified.

关键词： Crowd-sourcing distribution path optimization real-time customer demand differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

differential evolution based meta heuristic algorithm for dynamic continuous berth allocation problem

引用

APPLIED MATHEMATICAL MODELLING 2016年第23-24期40卷 10679-10688页

作者： Sahin, Cenk Kuvvetli, Yusuf Cukurova Univ Dept Ind Engn TR-01330 Adana Turkey

In this study, a new solution method based on differential evolution algorithm is proposed for solving Dynamic Berth Allocation Problem (DBAP). Continuous type of this problem which deals with continuous wharf space is considered. differential evolution algorithm, a meta-heuristic approach, is a type of evolutionary algorithm that is powerful on continuous space problems. In determining the optimal values for this meta-heuristic approach, a statistical analysis is conducted. The test problems generated randomly are used to evaluate the algorithm and the schedules generated by the algorithm are compared with that obtained by other meta-heuristics initials from literature, and analyzed. The results show that the proposed method solves test problems and achieves optimal solutions. (C) 2016 Elsevier Inc. All rights reserved.

关键词： Dynamic berth allocation problem Continuous wharf differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

A hybrid differential evolution and estimation of distribution algorithm based on neighbourhood search for job shop scheduling problems

引用

INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH 2016年第4期54卷 1039-1060页

作者： Zhao, Fuqing Shao, Zhongshi Wang, Junbiao Zhang, Chuck Lanzhou Univ Technol Sch Comp & Commun Technol Lanzhou Peoples R China Northwestern Polytech Univ Key Lab Contemporary Design & Integrated Mfg Tech Minist Educ Xian 710072 Peoples R China Georgia Inst Technol H Milton Stewart Sch Ind & Syst Engn Atlanta GA 30332 USA

Job shop scheduling problem (JSSP) is a typical NP-hard problem. In order to improve the solving efficiency for JSSP, a hybrid differential evolution and estimation of distribution algorithm based on neighbourhood search is proposed in this paper, which combines the merits of Estimation of distribution algorithm and differential evolution (DE). Meanwhile, to strengthen the searching ability of the proposed algorithm, a chaotic strategy is introduced to update the parameters of DE. Two mutation operators are adopted. A neighbourhood search (NS) algorithm based on blocks on critical path is used to further improve the solution quality. Finally, the parametric sensitivity of the proposed algorithm has been analysed based on the Taguchi method of design of experiment. The proposed algorithm was tested through a set of typical benchmark problems of JSSP. The results demonstrated the effectiveness of the proposed algorithm for solving JSSP.

关键词： estimation of distribution algorithm differential evolution algorithm neighbourhood search hybrid optimisation job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

Environmental assesment of surface waters based on monitoring data and neuro-evolutive modelling

引用

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION 2018年 120卷 136-145页

作者： Dragoi, E. N. Kovacs, Zs. Juzsakova, T. Curteanu, S. Cretescu, I. Gheorghe Asachi Tech Univ Iasi Fac Chem Engn & Environm Protect 73 Blvd D Mangeron Iasi 700050 Romania Univ Pannonia Inst Environm Engn Egyet St 10 HU-8200 Veszprem Hungary

The surface water quality highly depends on the natural conditions and on the industrial, agricultural and other anthropogenic activities in the river catchment areas. The quality of the surface water is the key factor in the water quality management. The monitoring of the water quality indicators is requested to follow up (in time and space) the changes in the water quality, providing healthy water for the people. The water quality indicators (physical-chemical specific parameters such as: pH, electrical conductivity, dissolved oxygen, turbidity etc.) provide information about the pollution degree of different waters (stemming from wastewater treatment plants, precipitation, sewer lines, tributaries, etc.). The main aim of the research was to demonstrate the efficiency of artificial intelligence techniques for the water quality prediction. Consequently, the considered system was modelled using a neuro-evolutive technique, combining artificial neural networks (ANN) with differential evolution (DE) algorithm. The neural network acts as a system model, while the differential evolution algorithm is the optimizer with the function to determine the optimal parameters of the model. The simulation results pointed out that the approach is suitable to set up adequate models for the three parameters, pH, electrical conductivity, dissolved oxygen, respectively. For the fourth parameter (turbidity), an average absolute error of 30% was obtained, which indicates a more complex relation in rapport to the other parameters of the system. The DE-ANN approach can, thus, be further used in decision making solutions for water quality management. (C) 2018 Published by Elsevier B.V. on behalf of Institution of Chemical Engineers.

关键词： Water framework directive Surface water monitoring Water quality assessment Artificial neural networks differential evolution algorithm

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：