检索结果-内蒙古大学图书馆

2nd International Conference on Current Trends In Engineering and Technology (ICCTET)

作者： Joseph, Sheeba Sowmiya, R. Thomas, Roshni Ann Sofia, X. Maharaja Engn Coll Dept Comp Sci Engn Coimbatore Tamil Nadu India

ISBN: (纸本)9781479979868

The aim of this paper is to implement an effective system to locate upright frontal faces on monochromatic images with use of a neural network-based classifier. In this paper, a new approach to reduce the computation time taken by fast neural nets for the searching process is presented. The principle of divide and conquer strategy is applied through image decomposition. Each image is divided into small size sub-images and then each one is tested separately using a fast neural network. Compared to conventional and fast neural networks, experimental results show that a speed up ratio is achieved when applying this technique to locate human faces in automatically in clustered scenes. Furthermore, faster face detection is obtained by using parallel processing techniques to test the resulted sub-images at the same time using the same number of fast neural networks. Moreover, the problem of sub-image centering and normalization in the Fourier space is solved.

关键词： Sobel masks feed forward network sliding window training set back propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Performance Study of Combined Artificial Neural Network algorithms for Image Steganalysis 1

引用

1st International Conference on Internet Computing and Information Communications (ICICIC)

作者： Sujatha, P. Purushothaman, S. Rajeswari, R. VELS Univ Dept Comp Sci Madras 600117 Tamil Nadu India PET Engn Coll Tirunelveli 627117 Tamil Nadu India Mother Teresa Womens Univ Kodaikanal India

ISBN: (纸本)9788132212980;9788132212997

Steganalaysis is a technique for detecting the presence of hidden information. Artificial neural network (ANN) is a widespread method for steganalysis. back propagation algorithm (BPA), radial basis function (RBF), and functional update back propagation algorithm (FUBPA) are some of the popular ANN algorithms for detecting hidden information. Training and testing performance is improved when two algorithms are combined instead of using them separately. This paper analyzes the performance of combined algorithms of BPARBF and FUBPARBF. Among the two combinations FUBPARBF provides promising results than BPARBF since FUBPA uses less number of iterations for the network to converge. But still organizing the retrieved information is a challenging task.

关键词： back propagation algorithm Functional update back propagation algorithm Radial basis function Carrier image Information image

来源：评论

学校读者我要写书评

暂无评论

A Stable Nonlinear in Parameter Neural Network Controller for a Class of Saturated Nonlinear Systems

引用

IFAC Proceedings Volumes 2014年第3期47卷 2533-2538页

作者： K. Esfandiari F. Abdollahi H.A. Talebi The Center of Excellence on Control and Robotics Department of Electrical Engineering Amirkabir University of Technology Tehran Iran Department of Electrical and Computer Engineering Concordia University Montreal QC Canada

This paper deals with the tracking problem for a class of uncertain nonlinear systems subjected to actuator saturation constraint. Despite most of proposed control schemes for saturated systems which employed linear in parameter neural networks (LPNNs), in the present work nonlinear in parameter neural network (NLPNN) is introduced to support global approximation property. To compensate the effect of the input saturation constraint an auxiliary system is introduced and the error dynamics are modified based on the auxiliary states. Then, learning rules are achieved based on the back propagation (BP) algorithm and by adding two robustifying terms to the standard BP learning rules the stability of the overall system is ensured via Lyapunov direct method. Finally simulations performed on a “generalized pendulum” nonlinear system to illustrate the effectiveness of the proposed tracking control scheme.

关键词： Adaptive tracking control back propagation algorithm Input saturation Neural networks Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

A type-2 diabetes early warning system using particle swarm optimized artificial neural networks: a case of trans Nzoia county of Kenya

A type-2 diabetes early warning system using particle swarm ...

引用

作者： Mbirika, Douglas H University of Nairobi

This research aimed at developing an early warning system for pre-diabetic and diabetics by analyzing simple and easily determinable signs and symptoms of diabetes among the people living in Trans Nzoia County of Kenya using Particle Swarm Optimized Artificial Neural Networks. With the skyrocketing prevalence of type 2 diabetes in Kenya the system can be used to encourage affected people to seek further medical attention to prevent the onset of diabetes or start managing it early enough to avoid the associated complications. The study sought to find out the best predictive variables of Type 2 Diabetes Mellitus, developed a system to diagnose diabetes from the variables using Artificial Neural Networks and tested the system on accuracy to find out the effectiveness of the system as an early warning system for the disease. Data was collected from diabetes clinics in hospitals within Trans Nzoia County of Kenya. The collected data was first preprocessed by R software to select the best generalizing attributes which were thereafter used to model an Artificial Neural Network. Particle Swarm Optimization algorithm was used to explore the global minima of the solution curve which was later exploited using the back propagation algorithm. The network attained a 70% and 66.23% accuracy on training and test data respectively. The network also attained a sensitivity of 70.23% and a specificity of 64.24%. This clearly shows that the system can be used as an early warning system for type 2 diabetes mellitus.

关键词： Artificial Neural Networks Particle Swarm Optimization back propagation algorithm Type 2 Diabetes Thesis

来源：评论

学校读者我要写书评

暂无评论

Handwriting Thai Signature Recognition System based on Multilayer Perceptron and Radial Basis Network

Handwriting Thai Signature Recognition System based on Multi...

引用

Int’l Conference on Advanced Computational Technologies & Creative Media (ICACTCM’2014, Pattaya)

作者： Naruemol Chumuang Mahasak Ketcham the Department of Information Technology Faculty of Information Technology King Mongkut’s University of Technology North Bangkok Bangkok Department of Information Technology Management Faculty of Information TechnologyKing Mongkut’s University of Technology North Bangkok Bangkok

In this paper,we proposed to develop Handwriting Thai Signature Recognition System（HTSRS） based on multilayer perceptron and radial basis *** order to achieve this objective,a combination of back-propagation and generalized regression neural networks is *** first stage is implemented by using two parallel back propagation and generalized regression neural network in order to reduce training time and make a system *** second stage is implemented by using the generalized regression neural network for final *** system is composed of two principal phases:signature feature extraction and *** the extraction step,global and grid features of all signature images are first *** this features are feed into the first and second stage neural network classifier for *** second group is for testing and unknown *** experimental results show that the accuracy of the proposed system performs rate is 90.00%.

关键词： Signature Recognition Neural Network Multilayer Perceptron back propagation algorithm Generalized Regression Network

来源：评论

学校读者我要写书评

暂无评论

Pre-processed back propagation Neural Networks for CDMA Interference Cancellation

Pre-processed Back propagation Neural Networks for CDMA Inte...

引用

IEEE International Conference on Emerging Trends in Computing, Communication and Nanotechnology (ICECCN)

作者： Geevarghese, Biju Thomas, Jibu Anil, Muth Francis, Anish Ambedkar Univ Hyderabad Bihar India Toc H Inst Sci & Technol Dept ECE Arakkunnam India Amal Jyothi Coll Engn Dept ECE Kottayam Kerala India Kerala State Elect Board Trichur Kerala India

ISBN: (纸本)9781467350372;9781467350365;9781467350358

This paper attempts to show the effects of pre-processing in bit error rate of neural network interference cancellation in spread spectrum receivers. Multiple access interference (MAI) which is one of the primary issues in CDMA multiuser detection is combated by interference cancellers. Feed-Forward Neural Networks with back propagation is used for interference cancellers. The works shows that pre-processing can bring adequate improvement in bit error rate as well as complexity.

关键词： Code Division Multiple Access Neural network Bit Error Rate Pre-processing back propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Determining quality of caviar from Caspian Sea based on Raman spectroscopy and using artificial neural networks

引用

TALANTA 2013年 111卷 98-104页

作者： Monavar, H. Mohamadi Afseth, N. K. Lozano, J. Alimardani, R. Omid, M. Wold, J. P. Univ Tehran Fac Agr Engn & Technol Karaj *** Iran Norwegian Food Res Inst Nofima Mat N-1430 As Norway Univ Extremadura Escuela Ingn Ind Dept Ingn Elect Elect & Automat E-06071 Badajoz Spain

The purpose of this study was to evaluate the feasibility of Raman spectroscopy for predicting purity of caviars. The 93 wild caviar samples of three different types, namely;Beluga, Asetra and Sevruga were analysed by Raman spectroscopy in the range 1995 cm(-1) to 545 cm(-1). Also, 60 samples from combinations of every two types were examined. The chemical origin of the samples was identified by reference measurements on pure samples. Linear chemometric methods like Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) were used for data visualisation and classification which permitted clear distinction between different caviars. Non-linear methods like Artificial Neural Networks (ANN) were used to classify caviar samples. Two different networks were tested in the classification: Probabilistic Neural Network with Radial-Basis Function (PNN) and Multilayer Feed Forward Networks with back propagation (BP-NN). In both cases, scores of principal components (PCs) were chosen as input nodes for the input layer in PC-ANN models in order to reduce the redundancy of data and time of training. Leave One Out (LOO) cross validation was applied in order to check the performance of the networks. Results of PCA indicated that, features like type and purity can be used to discriminate different caviar samples. These findings were also supported by LDA with efficiency between 83.77% and 100%. These results were confirmed with the results obtained by developed PC-ANN models, able to classify pure caviar samples with 93.55% and 71.00% accuracy in BP network and PNN, respectively. In comparison, LDA, PNN and BP-NN models for predicting caviar types have 90.3%, 73.1% and 91.4% accuracy. Partial least squares regression (PLSR) models were built under cross validation and tested with different independent data sets, yielding determination coefficients (R-2) of 0.86, 0.83, 0.92 and 0.91 with root mean square error (RMSE) of validation of 0.32, 0.11, 0.03 and 0.09 for fa

关键词： Caviar Raman spectroscopy Principal component analysis Linear discriminant analysis Radial-basis function back propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

A Review on Neural Network Models for Wind Speed Prediction

引用

WIND ENGINEERING 2013年第2期37卷 111-123页

作者： Sheela, K. Gnana Deepa, S. N. Anna Univ Reg Ctr Coimbatore Tamil Nadu India

This paper presents review of neural network models for wind speed prediction during the past 15 years. Wind energy is one of renewable energy system with lowest cost of electricity production. The prediction of wind speed is recognized as a major contribution of wind farm. Wind speed prediction has many applications in Military, Air traffic control and Ship navigation etc. The prediction of wind speed depends on meteorological variables such as pressure, temperature, humidity and rainfall etc. The aim is to identify the importance, advantages and comparison of different neural network models of wind speed prediction. This review is to be useful for researchers working in this field and identify performance of neural network models. It is very helpful to the wind farm owners to understand the current wind prediction model capabilities and give an idea which model will be suitable for predicting the wind speed at their wind farms.

关键词： Wind speed prediction Neural Network Models back propagation algorithm Radial Basis Function Recurrent network

来源：评论

学校读者我要写书评

暂无评论

Estimation of seasonal variation of ground resistance using Artificial Neural Networks

引用

ELECTRIC POWER SYSTEMS RESEARCH 2013年第Jan.期94卷 113-121页

作者： Asimakopoulou, Fani E. Tsekouras, George J. Gonos, Ioannis F. Stathopulos, Ioannis A. Natl Tech Univ Athens Sch Elect & Comp Engn GR-15780 Athens Greece Hellen Naval Acad Dept Elect Engn & Comp Sci GR-18539 Athens Greece

Objective of this paper is the development of a methodological approach for estimating the ground resistance by using Artificial Neural Network. The value of the ground resistance greatly depends on the grounding system and the properties of the soil, where the system is embedded. Given that the value of soil resistivity fluctuates during the year. the ground resistance does not have one single value. The approach proposed in this paper, takes advantage of the capability of Artificial Neural Networks (ANNs) to recognize linear and non-linear relationships between various parameters. By taking into account measurements of resistivity and rainfall data accrued for previous clays, the ground resistance is estimated. On that purpose ANNs have been trained and validated by using experimental data in order to examine their ability to predict the ground resistance. The results prove the effectiveness of the proposed methodology. (C) 2012 Elsevier B.V. All rights reserved.

关键词： Soil resistivity measurements Ground resistance Artificial Neural Networks back propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

A Learning System for Detecting Transformer Internal Faults

A Learning System for Detecting Transformer Internal Faults

引用

International Conference on Informatics, Electronics and Vision (ICIEV)

作者： Saleh, Abdullah Md. Hossain, Md. Zakir Rabin, Md. Jubayer Alam Kabir, A. N. M. Enamul Khan, Md. Fazle Elahi Shahjahan, Md. Khulna Univ Engn & Technol Khulna 9203 Bangladesh

ISBN: (纸本)9781479904006;9781479903979

Miniature transformer is one of the most important components of electronic devices. A serious failure of such kind of transformer may cause loss of time and money. This paper presents a learning system to recognize internal fault of such kind of transformer. The different kinds of faults are made to occur intentionally and data are collected at various conditions. The faults include turn to turn, winding to ground, and dielectric faults. The data are then processed and entered in the learning algorithms to recognize the type of fault. We devise a learning system to recognize the various types of faults. Several versions of learning algorithms such as standard back propagation, Levenberg-Marquardt, Bayesian regulation, Resilient back propagation, Gradient descent, One-step secant, Elman recurrent network are used. The result of Levenberg-Marquardt algorithm was found to be faster than that of other algorithms. Therefore it is suitable for real time fault detection.

关键词： Miniature transformer internal fault neural network (NN) back propagation algorithm fault detection

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：