检索结果-内蒙古大学图书馆

Effects of supervised Self Organising Maps parameters on classification performance

ANALYTICA CHIMICA ACTA 2013年 765卷 45-53页

作者： Ballabio, Davide Vasighi, Mandi Filzmoser, Peter Univ Milano Bicocca Dept Environm Sci Milano Chemometr & QSAR Res Grp I-20126 Milan Italy IASBS Dept Comp Sci & Informat Technol Zanjan Iran Vienna Univ Technol Dept Stat & Probabil Theory A-1040 Vienna Austria

Self Organising Maps (SOMs) are one of the most powerful learning strategies among neural networks algorithms. SOMs have several adaptable parameters and the selection of appropriate network architectures is required in order to make accurate predictions. The major disadvantage of SOMs is probably due to the network optimisation, since this procedure can be often time-expensive. Effects of network size, training epochs and learning rate on the classification performance of SOMs are known, whereas the effect of other parameters (type of SOMs, weights initialisation, training algorithm, topology and boundary conditions) are not so obvious. This study was addressed to analyse the effect of SOMs parameters on the network classification performance, as well as on their computational times, taking into consideration a significant number of real datasets, in order to achieve A comprehensive statistical comparison. Parameters were contemporaneously evaluated by means of an approach based on the design of experiments, which enabled the investigation of their interaction effects. Results highlighted the most important parameters which influence the classification performance and enabled the identification of the optimal settings, as well as the optimal architectures to reduce the computational time of SOMs. (C) 2012 Elsevier B.V. All rights reserved.

关键词： Self Organising Maps Kohonen maps Classification training algorithm SOMs parameters

来源：评论

学校读者我要写书评

暂无评论

Degenerated simplex search method to optimize neural network error function

引用

KYBERNETES 2013年第1-2期42卷 106-124页

作者： Ahmed, Shamsuddin Univ S Pacific Grad Sch Business Suva Fiji

Purpose - The purpose of this paper is to present a degenerated simplex search method to optimize neural network error function. By repeatedly reflecting and expanding a simplex, the centroid property of the simplex changes the location of the simplex vertices. The proposed algorithm selects the location of the centroid of a simplex as the possible minimum point of an artificial neural network (ANN) error function. The algorithm continually changes the shape of the simplex to move multiple directions in error function space. Each movement of the simplex in search space generates local minimum. Simulating the simplex geometry, the algorithm generates random vertices to train ANN error function. It is easy to solve problems in lower dimension. The algorithm is reliable and locates minimum function value at the early stage of training. It is appropriate for classification, forecasting and optimization problems. Design/methodology/approach - Adding more neurons in ANN structure, the terrain of the error function becomes complex and the Hessian matrix of the error function tends to be positive semi-definite. As a result, derivative based training method faces convergence difficulty. If the error function contains several local minimum or if the error surface is almost flat, then the algorithm faces convergence difficulty. The proposed algorithm is an alternate method in such case. This paper presents a non-degenerate simplex training algorithm. It improves convergence by maintaining irregular shape of the simplex geometry during degenerated stage. A randomized simplex geometry is introduced to maintain irregular contour of a degenerated simplex during training. Findings - Simulation results show that the new search is efficient and improves the function convergence. Classification and statistical time series problems in higher dimensions are solved. Experimental results show that the new algorithm (degenerated simplex algorithm, DSA) works better than the random simplex

关键词： Programming and algorithm theory Neural nets Searching Simplex search Derivative free Artificial neural networks training algorithm Robust Benchmark solution

来源：评论

学校读者我要写书评

暂无评论

Optimization of Prediction Error in CO2 Laser Cutting process by Taguchi Artificial Neural Network Hybrid with Genetic algorithm

引用

APPLIED MATHEMATICS & INFORMATION SCIENCES 2013年第1期7卷 363-370页

作者： Nukman, Y. Hassan, M. A. Harizam, M. Z. Univ Malaya Fac Engn Dept Engn Design & Mfg Kuala Lumpur 50603 Malaysia Assiut Univ Fac Engn Dept Mech Engn Assiut 71516 Egypt

Simulation and prediction of CO2 laser cutting of Perspex glass has been done by feed forward back propagation Artificial Neural Network (ANN). Experimental data of Taguchi orthogonal array L9 was used to train the ANN model. The simulation results were evaluated and verified with the experiment. In some cases, the prediction errors of Taguchi ANN model was larger than 10% even with Levenberg Marquardt training algorithm. To overcome such problem, a hybrid genetic algorithm-based Taguchi ANN (GA-Taguchi ANN) has been developed. The potential of genetic algorithm in optimization was utilized in the proposed hybrid model to minimize the error prediction for regions of cutting conditions away from the Taguchi based factor level points. The hybrid model was constructed in such a way to realize mutual input output between ANN and GA. The simulation results showed that the developed GA-Taguchi ANN model could reduce the maximum prediction error below 10%. The model has significant benefits in application to fabrication processes.

关键词： Artificial Neural Network training algorithm Genetic algorithm Laser cutting kerf width Perspex Sheet

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Neural Network Backpropagation algorithms for Electricity Load Forecasting

A Comparison of Neural Network Backpropagation Algorithms fo...

引用

IEEE International Workshop on Intelligent Energy Systems (IWIES)

作者： Pan, Xinxing Lee, Brian Zhang, Chunrong Athlone Inst Technol Software Res Inst Athlone Ireland

ISBN: (纸本)9781479911356

Load forecasting plays a significant role in planning and operation of electrical power networks. Artificial neural networks have been extensively employed for load forecasting over the last 20 years, owing to their powerful non-linear mapping capability. A range of neural network training algorithms have been developed to solve different kinds of problems. Due to different goals of prediction and variation in size of datasets for load forecasting, the choice of algorithm to train the neural network can greatly influence the forecasting result. In this paper we consider different backpropagation training algorithms for medium term load forecasting and analyze each of the characteristics such as parameter setting complexity, training speed, convergence, prediction accuracy and result stability. From our case study, we conclude Bayesian Regulation Backpropagation to be the best overall choice for medium term load prediction. For cases where processing capability is limited, Resilient Backpropagation and Conjugate Gradient Backpropagation may be suitable alternative choices.

关键词： artificial neural networks training algorithm load forecasting smart grid

来源：评论

学校读者我要写书评

暂无评论

Local Directional Pattern (LDP) Based Fingerprint Matching Using SLFNN

Local Directional Pattern (LDP) Based Fingerprint Matching U...

引用

IEEE 2nd International Conference on Image Information Processing (ICIIP)

作者： Kumar, Ravinder Chandra, Pravin Hanmandlu, Madasu GGSIP Univ Uni Sch Informat & Commun Tech Sect 16C Dwarka Delhi India IIT Dept Elect Engn New Delhi India

ISBN: (纸本)9781467360999;9781467361002

Recently a number of biometric indicators are in use for human identification, but the fingerprint based individual identification is still the dominating biometric indicator. In this paper, we present a fingerprint matching system by exploiting local directional pattern (LDP) based features, which are originally proposed for face recognition and facial expression detection. Fingerprint image texture is encoded by computing the response value of edges in different directions from the extracted region of interest (ROI) images. Single hidden layer feed forward neural network (SLFNN) is trained using three training algorithms namely gradient decent with momentum (GDM), resilient propagation (RP), and scaled conjugate gradient (SCG) to detect the match between test and trainee images. The experimental results show that the RP algorithm converges faster and perform well in terms of matching accuracy as compared to the other two algorithms.

关键词： SLFNN training algorithm Local Directional Pattern Fingerprint Matching Region of Interest (ROI)

来源：评论

学校读者我要写书评

暂无评论

Designing Stepped Impedance Microstrip Low-Pass Filters Using Artificial Neural Network at 1.8 GHz

Designing Stepped Impedance Microstrip Low-Pass Filters Usin...

引用

3rd International Conference on Communication Systems and Network Technologies (CSNT)

作者： Kushwah, Vivek Singh Tomar, Geetam S. Bhadauria, Sarita Singh Amity Sch Engn & Technol Dept Elect Gwalior India

ISBN: (纸本)9780769549583;9781467356039

In this paper a design technique for a Stepped impedance Microstrip Low-pass filters is presented by using the artificial neural network (ANN) modeling method. Required dimensions of the microstrip filter layout are used to get the input-output relationships in the ANN model. This paper presents the design and analysis of Stepped impedance Microstrip Low-pass filters at cut-off frequency 1.8 GHz which gives insertion loss (S-21) of -3 dB at cut-off point. Subsequently an artificial neural network model is developed to find out the Magnitude variation of scattering parameters (S-parameters) of Microstrip Low-pass filters at 1.8 GHz for different dimensions. After developing the ANN model of microstrip low-pass filter, it is computationally more efficient in the design and it has been displayed to be as accurate as an Electromagnetic simulator. The simulation is performed using the commercial software IE3D 14.1 and MATLAB programming language GUI Tools are used for ANN training.

关键词： Microstrip Low Pass Filters Lumped elements ANN model MATLAB IE3D EM Simulation S-parameters training algorithm

来源：评论

学校读者我要写书评

暂无评论

An Intuitionistic Fuzzy Neural Network with Triangular Membership Function

An Intuitionistic Fuzzy Neural Network with Triangular Membe...

引用

Chinese Intelligent Automation Conference (CIAC)

作者： Zhou, Xiaoguang Zhao, Renhou Zhang, Lili Flight Simulat & Training CenterNavy Aviat Acad Hu Ludao 125001 Liaoning Peoples R China Changchun Univ Sci & Technol Coll Optoelect Engn Changchun 130022 Jilin Peoples R China

ISBN: (纸本)9783642385247;9783642385230

In this paper, an intuitionistic fuzzy neural network model with a triangular membership and 1 minus triangular form non-membership functions is proposed. The network structure has six layers, and adopts Mandani's fuzzy reasoning. A new fuzzy inference system is applied in the model, which contains hesitation margin as a part. The two steps dynamic optimal training algorithms for the IFNN is development, the first step is membership function parameters training, the second step is membership function parameters training, which can promise the summing of the trained membership and non-membership functions on finite universal set less then 1. An example is given to demonstrate the intuitionistic fuzzy neural network has a higher degree of accuracy and higher learning efficiency than fuzzy neural network.

关键词： Intuitionistic fuzzy neural networks Fuzzy inference system training algorithm

来源：评论

学校读者我要写书评

暂无评论

Fingerprint matching using rotational invariant image based descriptor and machine learning techniques

Fingerprint matching using rotational invariant image based ...

引用

6th International Conference on Emerging Trends in Engineering and Technology (ICETET)

作者： Kumar, Ravinder Chandra, Pravin Hanmandlu, Madasu GGSIP Univ Univ Sch Informat & Comm Technol Sect 16C Delhi India Indian Inst Technol Dept Elect Engn New Delhi 110016 India

ISBN: (纸本)9781479925605

The reliability of fingerprint matching system is highly depends on the perfect alignment algorithm and a suitable matching techniques, which assign a label to the input fingerprint image. In this paper, we propose a rotation invariant fingerprint descriptor and a improved generalization performance classifier. The proposed new descriptor is represented by a histogram of local directional pattern (LDP) computed from extracted region of interest (ROI) of fingerprint images. For fingerprint matching, we propose a single hidden layer neural network (SLFN), which combines a powerful extreme learning machine (ELM) and a well generalized resilient propagation (RPROP) algorithm. The proposed fingerprint matching system comprises the following steps: fingerprint pre-processing / enhancement, ROI extraction, invariant LDP feature extraction, and matching using proposed hybrid classifier. The experimental result shows that the matching accuracy of the proposed system is improved as compare to ELM for lower values of hidden nodes, and other distance based matching approaches proposed in the literature.

关键词： SLFN training algorithm local directional pattern fingerprint matching region of interest (ROI) ELM hybrid RP ELM

来源：评论

学校读者我要写书评

暂无评论

The Improved training algorithm of Back Propagation Neural Network with Self-adaptive Learning Rate

The Improved Training Algorithm of Back Propagation Neural N...

引用

2009 International Conference on Computational Intelligence and Natural Computing(CINC 2009)

作者： Yong Li, Yang Fu, Hui Li and Si-Wen Zhang School of Energy Resources and Mechanical Engineering Northeast Dianli University Jilin City, China

This paper addresses the questions of improving convergence performance for back propagation (BP) neural network. For traditional BP neural network algorithm, the learning rate selection is depended on experience and trial. In this paper, based on Taylor formula the function relationship between the total quadratic training error change and connection weights and biases changes is obtained, and combined with weights and biases changes in batch BP learning algorithm, the formula for self-adaptive learning rate is given. Unlike existing algorithm, the self-adaptive learning rate depends on only neural network topology, training samples, average quadratic error and error curve surface gradient but not artificial selection. Simulation results show iteration times is significant less than that of traditional batch BP learning algorithm with constant learning rate.

关键词： artificial neural network back propagation neural network training algorithm learning rate self-adaptive

来源：评论

学校读者我要写书评

暂无评论

Random Sampler M-Estimator algorithm With Sequential Probability Ratio Test for Robust Function Approximation via Feed-Forward Neural Networks

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2013年第7期24卷 1074-1085页

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

This paper addresses the problem of fitting a functional model to data corrupted with outliers using a multilayered feed-forward neural network. Although it is of high importance in practical applications, this problem has not received careful attention from the neural network research community. One recent approach to solving this problem is to use a neural network training algorithm based on the random sample consensus (RANSAC) framework. This paper proposes a new algorithm that offers two enhancements over the original RANSAC algorithm. The first one improves the algorithm accuracy and robustness by employing an M-estimator cost function to decide on the best estimated model from the randomly selected samples. The other one improves the time performance of the algorithm by utilizing a statistical pretest based on Wald's sequential probability ratio test. The proposed algorithm is successfully evaluated on synthetic and real data, contaminated with varying degrees of outliers, and compared with existing neural network training algorithms.

关键词： Function approximation Multilayered feed-forward neural networks (MFNNs) robust statistics training 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：