检索结果-内蒙古大学图书馆

International Conference of Soft Computing and Pattern Recognition

作者： Mohamed, Azlinah Bandi, Ahmad Fuad Mohamed Tamrin, Abdul Razif Jaafar, Md Daud Hasan, Suriah Jusof, Faeizah Univ Teknol MARA Fac Math & Comp Sci Shah Alam Selangor Malaysia TM Innovat Ctr Telekom Res & Dev Sdn Bhd Cyberjaya Malaysia

ISBN: (纸本)9781424453306

Telecommunication fraud prediction in this paper is an interpolation problem that uses the daily telecommunication network services information to analyze and predict the alarm information generated from a detection engine by minimizing false cases. This paper proposed the use of backpropagation neural network (BPNN) to perform telecommunication interpolation based on local telecommunication network services. The backpropagation algorithm is adjusted accordingly to control the speed of obtaining solution. The validation of this method is carried out following a series of experiments to establish the suitable BPNN parameters value for this interpolation problem. 20,000 cases were used and divided suitably into training and testing samples in analyzing the performance of the BPNN network. It is observed that the performance of BPNN in predicting fraud was merely 100% if the threshold value was set to 0.64 and above the predicted value. Consequently, the network model created could be used to analyze fraud risk classification and subsequently, provide contribution to the domain of fraud detection system.

关键词： Fraud detection system Telecommunication fraud backpropagation algorithm Call data records fraud risk clasification

来源：评论

学校读者我要写书评

暂无评论

Stochastic modeling applications for the prediction of COD removal efficiency of UASB reactors treating diluted real cotton textile wastewater

引用

STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT 2009年第1期23卷 13-26页

作者： Yetilmezsoy, Kaan Sapci-Zengin, Zehra Yildiz Tech Univ Fac Civil Engn Dept Environm Engn TR-34349 Istanbul Turkey

A three-layer Artificial Neural Network (ANN) model (9:12:1) for the prediction of Chemical Oxygen Demand Removal Efficiency (CODRE) of Upflow Anaerobic Sludge Blanket (UASB) reactors treating real cotton textile wastewater diluted with domestic wastewater was presented. To validate the proposed method, an experimental study was carried out in three lab-scale UASB reactors to investigate the treatment efficiency on total COD reduction. The reactors were operated for 80 days at mesophilic conditions (36-37.5C) in a temperature-controlled water bath with two hydraulic retention times (HRT) of 4.5 and 9.0 days and with organic loading rates (OLR) between 0.072 and 0.602 kg COD/m3p/day. Five different dilution ratios of 15, 30, 40, 45 and 60% with domestic wastewater were employed to represent seasonal fluctuations, respectively. The study was undertaken in a pH range of 6.20-8.06 and an alkalinity range of 1,350-1,855 mg/l CaCO3. The concentrations of volatile fatty acids (VFA) and total suspended solids (TSS) were observed between 420 and 720 mg/l CH3COOH and 68-338 mg/l, respectively. In the study, a wide range of influent COD concentrations (CODi) between 651 and 4,044 mg/l in feeding was carried out. CODRE of UASB reactors being output parameter of the conducted anaerobic treatment was estimated by nine input parameters such as HRT, pH, CODi concentration, operating temperature, alkalinity, VFA concentration, dilution ratio (DR), OLR, and TSS concentration. After backpropagation (BP) training combined with principal component analysis (PCA), the ANN model predicted CODRE values based on experimental data and all the predictions were proven to be satisfactory with a correlation coefficient of about 0.8245. In the ANN study, the Levenberg-Marquardt algorithm (LMA) was found as the best of 11 BP algorithms. In addition to determination of the optimal ANN structure, a linear-nonlinear study was also employed to investigate the effects of input variables on CODRE values

关键词： Textile wastewater Anaerobic treatment COD removal efficiency Neural network backpropagation algorithm Modeling

来源：评论

学校读者我要写书评

暂无评论

ARTIFICIAL NEURAL NETWORKS LEARNING IN ROC SPACE

ARTIFICIAL NEURAL NETWORKS LEARNING IN ROC SPACE

引用

1st International Joint Conference on Computational Intelligence

作者： Castro, Cristiano Leite Braga, Antonio Padua Univ Fed Lavras Dept Comp Sci Campus UnivCaixa Postal 3037 BR-37200000 Lavras Brazil Univ Fed Minas Gerais Dept Elect Engn BR-30161970 Belo Horizonte MG Brazil

ISBN: (纸本)9789896740146

In order to control the trade-off between sensitivity and specificity of MLP binary classifiers, we extended the backpropagation algorithm, in batch mode, to incorporate different misclassification costs via separation of the global mean squared error between positive and negative classes. By achieving different solutions in ROC space, our algorithm improved the MLP classifier performance on imbalanced training sets. In our experiments, standard MLP and SVM algorithms were compared to our solution using real world imbalanced applications. The results demonstrated the efficiency of our approach to increase the number of correct positive classifications and improve the balance between sensitivity and specificity.

关键词： Multi-Layer Perceptron (MLP) backpropagation algorithm ROC analysis Imbalanced data sets Cost-sensitive learning

来源：评论

学校读者我要写书评

暂无评论

Using Particle Swarm Optimization in Training Neural Network for Indoor Field Strength Prediction

Using Particle Swarm Optimization in Training Neural Network...

引用

51st International Symposium ELMAR

作者： Vilovic, Ivan Burum, Niksa Milic, Dorde Univ Dubrovnik Dubrovnik Croatia

ISBN: (纸本)9789537044107

This paper presents a comparison of results obtained from neural network training by backpropagation and particle swarm optimization (PSO) algorithms. The neural network model has been developed for field strength prediction in indoor environments. It has been already shown for neural networks as powerful tool in RF propagation prediction. It is very important to choose proper algorithm for training a neural network, so we compared BP training algorithms: gradient descent method and Levenberg- Marquardt algorithm with PSO algorithm. PSO algorithm has been shown as powerful method for global optimization in several applications. A floor of university building in Dubrovnik has been used as case for simulation and measurement of signal strength. The results show that the neural network weights converge faster with PSO than with standard BP algorithms.

关键词： Neural network Multilayer Perceptron Training algorithm backpropagation algorithm Gradient descent algorithm Levenberg-Marquardt algorithm Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Testing Artificial Metaplasticity in MLP Applications

Testing Artificial Metaplasticity in MLP Applications

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Andina, Diego Marcano-Cedeno, Alexis Torres, Joaquin Alarcon, Martin J. Tech Univ Madrid UPM Grp Automat Signals & Commun Madrid Spain

ISBN: (纸本)9781424427932

In this work we tested and compared Artificial Metaplasticity (AMP) results for Multilayer Perceptrons (MLPs). AMP is a novel Artificial Neural Network (ANN) training algorithm inspired on the biological metaplasticity property of neurons and Shannon's information theory. During training phase, AMP training algorithm gives more relevance to less frequent patterns and subtracts relevance to the frequent ones, claiming to achieve a much more efficient training, while at least maintaining the MLP performance. AMP is specially recommended when few patterns are available to train the network. We implement an Artificial Metaplasticity MLP (AMMLP) on standard and well-used databases for Machine Learning. Experimental results show the superiority of AMMLPs when compared with recent results on the same databases.

关键词： Neural Network MLPs backpropagation algorithm Pattern Recognition Metaplasticity

来源：评论

学校读者我要写书评

暂无评论

Neural Network Approach to the Prediction of Percentage Data Packet Loss for Wireless Sensor Networks

Neural Network Approach to the Prediction of Percentage Data...

引用

41st Southeastern Symposium on System Theory

作者： Barve, Yogesh D. Tennessee Technol Univ Dept Elect & Comp Engn Cookeville TN 38505 USA

ISBN: (纸本)9781424433247

Wireless sensor networks are used in the field of communications and have gained enormous popularity in recent times. Depending upon the environment in which the wireless sensor network operates, the amount of noise level would differ and hence the data packet loss in wireless communication would vary. This paper presents a solution to the prediction of percentage data packet loss in the wireless sensor network in indoor and outdoor environment. It uses the Artificial Neural Network (ANN) to predict the data packet loss and the Erasure Coding technique to find the actual percentage data packet lost in wireless sensor network. The results obtained from the ANN are compared to the respective ones yielded by the Erasure Coding technique and are found to exhibit satisfactory accuracy.

关键词： backpropagation algorithm Neural network Wireless sensor network

来源：评论

学校读者我要写书评

暂无评论

Prediction of stress in fillet portion of spur gears using artificial neural networks

引用

AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGN ANALYSIS AND MANUFACTURING 2008年第1期22卷 41-51页

作者： Shunmugam, M. S. Prasad, N. Siva Indian Inst Technol Dept Mech Engn Madras 600036 Tamil Nadu India

A fillet curve is provided at the root of the spur gear tooth, as stresses are high in this portion. The fillet curve may be a trochoid or an arc of suitable size as specified by designer. The fillet stress is influenced by the fillet geometry as well as the number of teeth, modules, and the pressure angle of the gear. Because the relationship is nonlinear and complex, an artificial neural network and a backpropagation algorithm are used in the present work to predict the fillet stresses. Training data are obtained from finite element simulations that are greatly reduced using Taguchi's design of experiments. Each simulation takes around 30 min. The 4-5-1 network and a sigmoid activation function are chosen. TRAINLM function is used for training the network with a learning rate parameter of 0.01 and a momentum constant of 0.8. The neural network is able to predict the fillet stresses in 0.03 s with reasonable accuracy for spur gears having 25-125 teeth, a 1-5 mm module, a 0.05-0.45 mm fillet radius, and a 15 degrees-25 degrees pressure angle.

关键词： artificial neural network backpropagation algorithm fillet geometry finite element method spur gear Taguchi method

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Takagi-Sugeno type fuzzy system for diabetes mellitus forecasting

Hierarchical Takagi-Sugeno type fuzzy system for diabetes me...

引用

7th International Conference on Machine Learning and Cybernetics

作者： Sharifi, Arash Vosolipour, Asiyeh Sh, Mahdi Aliyari Teshnehlab, Mohammad Islamic Azad Univ Sci & Res Branch Dept Comp Tehran Iran KN Toosi Univ Technol Elect Engn Dept Tehran Iran

ISBN: (纸本)9781424420957

In this study, a new group method of data handling (GMDH) method, based on adaptive neurofuzzy inference system (ANFIS) structure, called ANFIS-GMDH and its application for diabetes mellitus forecasting is presented. Conventional neurofuzzy GMDH (NF-GMDH) uses radial basis network (RBF) as the partial descriptions. In this study the RBF partial descriptions are replaced with two input ANFIS structures and backpropagation algorithm is chosen for learning this network structure. The Prima Indians diabetes data set is used as training and testing sets which consist of 768 data whereby 268 of them are diagnosed with diabetes. The result of this study will provide solutions to the medical staff in determining whether someone is (he diabetes sufferer or not which is much easier rather than currently doing a blood test. The results show that the proposed method performs better than the other models such as multi layer perceptron (MLP), RBF and ANFIS structure.

关键词： hierarchical Takagi-Sugeno fuzzy system ANFIS structure backpropagation algorithm diabetic mellitus

来源：评论

学校读者我要写书评

暂无评论

Nonlinear system identification using discrete-time neural networks with stable learning algorithm

Nonlinear system identification using discrete-time neural n...

引用

5th International Conference on Informatics in Control, Automation and Robotics

作者： Korkobi, Talel Djemel, Mohamed Chtourou, Mohamed XYZ Univ Inst Problem Solving Natl Engn Sch Sfax ENIS BP W Sfax 3038 Tunisia ENIS Natl Engn Sch Sfax Design & Optimizat Complex Syst Sfax 3038 Tunisia

ISBN: (纸本)9789898111302

This paper presents a stable neural sytem identification for nonlinear systems. An input output discrete time representation is considered. No a priori knowledge about the nonlinearities of the system is assumed. The proposed learning rule is the backpropagation algorithm under the condition that the learning rate belongs to a specified range defining the stability domain. Satisfying such condition, unstable phenomenon during the learning process is a-voided. A Lyapunov analysis is made in order to extract the new updating formulation which contain a set of inequality constraints. In the constrained learning rate algorithm, the learning rate is updated at each iteration by an equation derived using the stability conditions. As a case study, identification of two discrete time systems is considered to demonstrate the effectiveness of the proposed algorithm. Simulation results concerning the considered systems are presented.

关键词： stability neural networks identification backpropagation algorithm constrained learning rate Lyapunov approach

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis of Neural Networks-Based System Identification

引用

MODELLING AND SIMULATION IN ENGINEERING 2008年第unknown期2008卷

作者： Korkobi, Talel Djemel, Mohamed Chtourou, Andmohamed Univ Sfax Natl Engn Sch Sfax ENIS Res Unit Intelligent Control Design & Optimizat Complex Syst ICOS BP W Sfax 3038 Tunisia

This paper treats some problems related to nonlinear systems identification. A stability analysis neural network model for identifying nonlinear dynamic systems is presented. A constrained adaptive stable backpropagation updating law is presented and used in the proposed identification approach. The proposed backpropagation training algorithm is modified to obtain an adaptive learning rate guarantying convergence stability. The proposed learning rule is the backpropagation algorithm under the condition that the learning rate belongs to a specified range defining the stability domain. Satisfying such condition, unstable phenomena during the learning process are avoided. A Lyapunov analysis leads to the computation of the expression of a convenient adaptive learning rate verifying the convergence stability criteria. Finally, the elaborated training algorithm is applied in several simulations. The results confirm the effectiveness of the CSBP algorithm. Copyright (C) 2008 Talel Korkobi et al.

关键词： .Lyapunov neural network learning process System identification ectiveness learning rate convergence stability backpropagation algorithm CSBP

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：