检索结果-内蒙古大学图书馆

Robust optimization of ANFIS based on a new modified GA

NEUROCOMPUTING 2015年 166卷 357-366页

作者： Sarkheyli, Arezoo Zain, Azlan Mohd Sharif, Safian Univ Teknol Malaysia Fac Comp Soft Comp Res Grp Skudai 81310 Johor Malaysia Univ Teknol Malaysia Fac Mech Engn Dept Mfg & Ind Engn Skudai 81310 Johor Malaysia

Adaptive Network-based Fuzzy Inference Systems (ANFIS) is one of the most well-known predictions modeling technique utilized to find the superlative relationship between input and output parameters in different processes. training the adaptive modeling parameters in ANFIS is still a challengeable problem which has been recently considered by researchers. Hybridizing of a robust optimization algorithm with ANFIS as its training algorithm provides a scope to improve the effectiveness of membership functions and fuzzy rules in the model. In this paper, a new Modified Genetic algorithm (MGA) by using a new type of population is proposed to optimize the modeling parameters for membership functions and fuzzy rules in ANFIS. As well, a case study on a machining process is considered to illustrate the robustness of the proposed training technique in prediction of machining performances. The prediction results have demonstrated the superiority of the presented hybrid ANFIS-MGA in term of prediction accuracy (with 97.74%) over the other techniques such as hybridization of ANFIS with Genetic algorithm (GA), Taguchi-GA, Hybrid Learning algorithm (HL), Leave-One-Out Cross-Validation (LOO-CV), Particle Swarm Optimization (PSO) and Grid Partition method (GP), as well as RBFN and basic Grid Partition Method (GPM). In addition, an attempt is done to specify the effectiveness of different improvement rates on the prediction result and measuring the number of function evaluations required. The comparison result reveals that MGA with improvement rate 0.8 raises the convergence speed and accuracy of the prediction results compared to GA. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Adaptive network-based fuzzy inference systems (ANFIS) Modified genetic algorithm (MGA) training algorithm Population Prediction model Prediction accuracy Improvement rate

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of MLPFF Neural Network Back propagation training algorithms for Time Series Data

Performance Analysis of MLPFF Neural Network Back propagatio...

引用

World Congress on Computing and Communication Technologies (WCCCT)

作者： Kumar, Ashok Murugan, S. Govt Arts Coll Dept Comp Sci Tiruchirappalli Tamil Nadu India Alagappa Govt Arts Coll Dept Comp Sci Karaikkudi Tamil Nadu India

ISBN: (纸本)9781479928767

This paper investigates the various training algorithm with Multi-Layer Perceptron Feed Forward Neural Network (MLPFFNN) and identify the best training algorithm for Indian Stock Exchange Market especially for BSE100 and NIFTY MIDCAP50. The forecasting accuracy is analyzed and measured with reference to an Indian stock market index such as Bombay Stock Exchange (BSE) and NIFTY MIDCAP50 in this study and it is found that the best training algorithm is Levenberg-Marquardt. All training algorithms uses the 1-5-1 MLPFFNN architecture and its various parameter such as epochs, learning rate, etc are studied and the results are tabulated for the data division ratio 60%, 20% and 20% which represents training, validating and testing for all training algorithm.

关键词： Time serie Neural Network forecasting training algorithm stock market

来源：评论

学校读者我要写书评

暂无评论

Repetitive neurocontroller with disturbance dual feedforward - choosing the right dynamic optimization algorithm 17

Repetitive neurocontroller with disturbance dual feedforward...

引用

17th European Conference on Power Electronics and Applications (EPE ECCE-Europe)

作者： Ufnalski, Bartlomiej Grzesiak, Lech M. Warsaw Univ Technol Inst Control & Ind Elect 75 Koszykowa St PL-00662 Warsaw Poland

ISBN: (纸本)9789075815238

The paper presents a recently developed repetitive neurocontroller (RNC) that does not require additional filtering and/or forgetting to robustify it, i.e. to circumvent the long horizon stability issue present in the classic iterative learning control (ILC) scheme. Initially, the Levenberg-Marquardt (L-M) error backpropagation (BP) algorithm was used as a DOP(dynamic optimization problem)-capable search mechanism. At that time the choice of the training algorithm was made based on the frequently reported effectiveness of the L-M method in static optimization problems. However, there is an abundance of neural network training methods characterized, e.g., by different convergence rates, computational burden, noise sensitivity, etc. The performance of a particular optimization method is always problem specific. The case study of a constant-amplitude constant-frequency (CACF) voltage-source inverter (VSI) with an LC output filter is analysed here and some recommendations regarding the trade-off between convergence rate and computational complexity are made. The robustness to a measurement noise is also tested. The comparison is based on the results of numerical experiments. A couple of algorithms is then suggested for real-time implementation.

关键词： repetitive control iterative learning control neurocontroller sine wave converter repetitive disturbance rejection dynamic optimization problem disturbance dual feedforward training algorithm non-local update rule global update rule

来源：评论

学校读者我要写书评

暂无评论

A speech recognition system using fast learning algorithm and beta wavelet network 15

A speech recognition system using fast learning algorithm an...

引用

15th International Conference on Intelligent Systems Design and Applications (ISDA)

作者： Ejbali, Ridha Jemai, Olfa Zaied, Mourad Ben Amar, Chokri Natl Sch Engineers Sfax REs Grp Intelligent Machines BP W 3038 Sfax Tunisia

ISBN: (纸本)9781467387095

Speech recognition is a specialized pattern recognition task with several applications such as vocal command system, dictating machines, and understanding systems. In recent years, research on pattern recognition has increased by developing various methods and algorithms for different applications. In this paper, we proposed a novel training algorithm based on the fast Beta wavelet transform for speech recognition. This approach has many advantages compared to other algorithms. The majority of the old approaches need to inverse matrix, which can be computationally intensive. However, the new algorithm is computed by the iterative application of fast wavelet transform to compute connection weights. To highlight our approach, we compared its experimental results to those of the old ones.

关键词： speech recognition pattern recognition fast Beta wavelet network acoustical environment training algorithm

来源：评论

学校读者我要写书评

暂无评论

A Fuzzy Hypermatrix-based Skin Color Filtering Method 19

A Fuzzy Hypermatrix-based Skin Color Filtering Method

引用

19th IEEE International Conference on Intelligent Engineering Systems (INES)

作者： Varkonyi-Koczy, A. R. Tusor, B. Toth, J. T. Obuda Univ Integrated Intelligent Syst Japanese Hungarian La Budapest Hungary Obuda Univ Inst Mechatron & Vehicle Engn Budapest Hungary Doctoral Sch Appl Informat Budapest Hungary J Selye Univ Dept Math & Informat Komarno Slovakia

ISBN: (纸本)9781467379397

In this paper, a classification method is proposed. The idea behind the classifier is the pre-calculation of fuzzy membership function values that are stored in fuzzy multidimensional arrays (so-called fuzzy hypermatrices) so their data can be accessed quickly run-time using the parameter values of the input data. This paper focuses on the 3 dimensional 2-class case in order to achieve rapid skin area identification based on pixel color using the images of a camera. A training algorithm is presented and the performance is illustrated by an image processing problem.

关键词： cameras fuzzy set theory image classification image colour analysis image filtering learning (artificial intelligence) matrix algebra 3-dimensional 2-class case camera classification method fuzzy hypermatrix-based skin color filtering method fuzzy membership function value precalculation fuzzy multidimensional arrays image processing problem pixel color rapid skin area identification training algorithm Decision trees Filtering Image color analysis Skin training training data image colour analysis Cameras Classification Methods image filtering Filtration training data matrix algebra Decision Trees Image classification Fuzzy Set Theory skin Functional training skin color

来源：评论

学校读者我要写书评

暂无评论

Numerical and Neural Network Modeling of Motors of a Robot 3

Numerical and Neural Network Modeling of Motors of a Robot

引用

3rd RSI/ISM International Conference on Robotics and Mechatronics (ICROM)

作者： Tourajizadeh, H. Manteghi, S. Nekoo, S. R. Kharazmi Univ Fac Engn Dept Mech Engn Tehran Iran Islamic Azad Univ Coll Comp & Mechatron Engn Branch Sci & Res Tehran Iran Iran Univ Sci & Technol Sch Mech Engn Tehran Iran

ISBN: (纸本)9781467372343

In this paper, parametric and numerical model of the motors of a robot are extracted. A method is proposed here to control the torque and velocity of the motor simultaneously using the extracted dynamics of the motor and consequently control the robot motion more accurately. Parametric model of the motors are derived by conducting standard tests like locked rotor test and step and sine wave input test. In order to derive the neural network and numerical models, a set of sinusoidal, triangular, and random steps signal, are applied as the input to the motor and its speed is recorded as the output. Neural network model of the motors is extracted by using these dataset and considering the MLP neural network structure with Levenberg _Marquardt training method. Results of the numerical model and parametric models are compared and validated by experimental tests.

关键词： Robot Modeling of DC motor Torque-speed control training algorithm Levenberg-Marquardt

来源：评论

学校读者我要写书评

暂无评论

Error assessment of laser cutting predictions by semi-supervised learning

引用

Journal of Central South University 2014年第10期21卷 3736-3745页

作者： Mustafa Zaidi Imran Amin Ahmad Hussain Nukman Yusoff Department of Computing Shaheed Zulfikar Ali Bhutto Institute of Science & Technology (SZABIST) Department of Nuclear Engineering King Abdulaziz University Manufacturing Systems Integration Department of Mechanical Engineering University of Malaya

Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification of orthogonal array based model prediction. It shows improvement in modelling of edge quality and kerf width by applying semi-supervised learning algorithm, based on novel error assessment on simulations. The results are expected to depict better prediction on average by utilizing the systematic randomized techniques to initialize the neural network weights and increase the number of initialization. Missing values handling is difficult with statistical tools and supervised learning techniques; on the other hand, semi-supervised learning generates better results with the smallest datasets even with missing values.

关键词： semi-supervised learning training algorithm kerf width edge quality laser cutting process artificial neural network（ANN）

来源：评论

学校读者我要写书评

暂无评论

Model-wise and point-wise random sample consensus for robust regression and outlier detection

引用

NEURAL NETWORKS 2014年 59卷 23-35页

作者： El-Melegy, Moumen T. Assiut Univ Dept Elect Engn Assiut 71516 Egypt

Popular regression techniques often suffer at the presence of data outliers. Most previous efforts to solve this problem have focused on using an estimation algorithm that minimizes a robust M-estimator based error criterion instead of the usual non-robust mean squared error. However the robustness gained from M-estimators is still low. This paper addresses robust regression and outlier detection in a random sample consensus (RANSAC) framework. It studies the classical RANSAC framework and highlights its model-wise nature for processing the data. Furthermore, it introduces for the first time a point-wise strategy of RANSAC. New estimation algorithms are developed following both the model-wise and point-wise RANSAC concepts. The proposed algorithms' theoretical robustness and breakdown points are investigated in a novel probabilistic setting. While the proposed concepts and algorithms are generic and general enough to adopt many regression machineries, the paper focuses on multilayered feed-forward neural networks in solving regression problems. The algorithms are evaluated on synthetic and real data, contaminated with high degrees of outliers, and compared to existing neural network training algorithms. Furthermore, to improve the time performance, parallel implementations of the two algorithms are developed and assessed to utilize the multiple CPU cores available on nowadays computers. (C) 2014 Elsevier Ltd. All rights reserved.

关键词： Multi-layered feed-forward neural networks training algorithm Robust statistics Regression Outliers

来源：评论

学校读者我要写书评

暂无评论

A Global Convergence PSO training algorithm of Neural Networks

A Global Convergence PSO Training Algorithm of Neural Networ...

引用

8th World Congress on Intelligent Control and Automation (WCICA)

作者： Li, Ming Li, Wei Yang, Cheng-wu Southwest Forestry Univ Coll Commun Machinery & Civil Engn Kunming Yunnan Peoples R China Nanjing Univ Sci & Technol Coll Power Engn Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781424467129

Traditional gradient-based training algorithms have been known to suffer from local minima and have heavy computation load for obtaining the derivative information. The particle swarm optimization (PSO) method was used as a training algorithm of neural networks to improve the convergence rate. However, as the network architecture grows, the size of swarm increases exponentially, which increase the computational complexity evidently. Moreover, such algorithms had the problem of premature convergence. An improved PSO training algorithm was proposed in this paper. The swarm was only composed of two particles in the new algorithm. The algorithm was guaranteed to converge to the global optimization solution with probability one. Simulation results show the new algorithm has fast convergence rate and high accuracy. Moreover, the convergence of the algorithm didn't depend on the initial value of weights of neural networks.

关键词： neural network training algorithm PSO algorithm global convergence

来源：评论

学校读者我要写书评

暂无评论

Active Control of 3-D Irregular Building by using Energy Based Neuro-Controller

引用

ADVANCES IN STRUCTURAL ENGINEERING 2014年第6期17卷 837-849页

作者： Bigdeli, Y. Kim, D. Kunsan Natl Univ Dept Civil Engn Jeonbuk South Korea

In this paper, a methodology of active control of structures based on modal energy is extended to control the response of irregular structures. The nonlinearities of material and geometry are taken into account in the training algorithm. A three-dimensional (3-D) multi-story irregular building is employed to scrutinize the performance of the improved control strategy. The torsional and lateral responses of the structure and the dynamic behavior of actuators have been incorporated in the control model simultaneously. Thus, the lateral-torsional coupling as well as the structure-actuator interaction is considered. The incident angle of ground motion and the time delay of actuators are also included in the model. El-Centro 1940 earthquake is used to train the algorithm, and then five different earthquake records have been used to evaluate the trained control system. The results of controlled structural responses in each case proved that the proposed control algorithm may be promising in vibration control of 3-D irregular structures.

关键词： active control training algorithm actuator dynamic irregular building Neuro-controller

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：