检索结果-内蒙古大学图书馆

Analysis of international debt problem using artificial neural networks and statistical methods

NEURAL COMPUTING & APPLICATIONS 2010年第8期19卷 1207-1216页

作者： Yazici, Berna Memmedli, Memmedaga Aslanargun, Atilla Asma, Senay Anadolu Univ Dept Stat TR-26470 Eskisehir Turkey

It is known from the scientific researches that artificial neural networks are alternatives of statistical methods such as regression analysis and classification in recent years. Since multi-layer backpropagation neural network models are nonlinear, it is expected that the neural network models should make better classifications and predictions. The studies on this subject support that idea. In this study, a macro-economic problem on rescheduling or non-rescheduling of the countries' international debts is taken into account. Among the statistical methods, logistic and probit regression, and the different neural network backpropagation algorithms are applied and comparisons are made. Evaluations and suggestions are made depending on the results and different neural network architecture.

关键词： Artificial neural network backpropagation algorithm Conjugate gradient method Quasi-Newton method Logistic and probit regression Rescheduling and non-rescheduling of the international debts

来源：评论

学校读者我要写书评

暂无评论

A neural network based model for prognosis of early breast cancer

引用

APPLIED INTELLIGENCE 2004年第3期20卷 231-238页

作者： Gómez-Ruiz, JA Jerez-Aragonés, JM Muñoz-Pérez, J Alba-Conejo, E Univ Malaga Dept Lenguajes & Ciencias Computac E-29071 Malaga Spain Hosp Clin Univ Malaga Oncol Serv E-29071 Malaga Spain

The prediction of clinical outcome of patients after breast cancer surgery plays an important role in medical tasks such as diagnosis and treatment planning. Survival estimations are currently performed by clinicians using non-numerical techniques. Artificial neural networks are shown to be a powerful tool for analyzing data sets where there are complicated nonlinear interactions between the input data and the information to be predicted. In this paper, a new estimation to set the maximum bound on prediction accuracy is presented, based on the approximation of the a posteriori probability of Bayes by feed-forward three-layer neural networks. This result is applied to different patients' follow-up time intervals, in order to obtain the best prediction accuracy for the correct classification probability of patient relapse after breast cancer surgery using clinical-pathological data (tumor size, patient age, menarchy age, etc.), which were obtained from the Medical Oncology Service of the Hospital Clinico Universitario of Malaga, Spain. Different network topologies and learning parameters are investigated to obtain the best prediction accuracy. The actual results show as, after training process, the final model is appropriate to make predictions about the relapse probability at different times of follow-up.

关键词： backpropagation algorithm Bayes error breast cancer multi-layer feed-forward neural networks medical prognosis

来源：评论

学校读者我要写书评

暂无评论

AUTOMATIC RANKING OF FUZZY NUMBERS WITH THE CRITERION OF A DECISION-MAKER LEARNT BY AN ARTIFICIAL NEURAL-NETWORK

引用

FUZZY SETS AND SYSTEMS 1994年第1期64卷 1-19页

作者： REQUENA, I DELGADO, M VERDEGAY, JL Departamento de Ciencias de la Computacion e I.A. Facultad de Ciencias Universidad de Granada 18071-Granada Spain

In a previous work, we indicated that Artificial Neural Networks (ANN) would be able to learn to compare fuzzy numbers as a real decision maker does. In this paper, we describe in detail the experiment that we have developed to that goal, and in which we have obtained good results. We apply this trained ANN to some decision problems with fuzzy environment, by means of the automatic ranking of the decision problem utilities, performed as trapezoidal fuzzy numbers. So, we use the trained ANN as a personal method to compare fuzzy numbers. We have trained a multilayer feedforward ANN with the criterions (to compare fuzzy numbers) of three people, each with different characteristic, using the backpropagation algorithm and different structures. Then we use this trained ANN to rank a set of fuzzy numbers which can be considered as utilities of decision problems with fuzzy environment, hence enabling us to make the best choice. Several examples are shown also.

关键词： FUZZY NUMBERS COMPARISON backpropagation algorithm DECISION MAKING FUZZY ENVIRONMENT DECISIONS

来源：评论

学校读者我要写书评

暂无评论

Generation of artificial neural networks models in anticancer study

引用

NEURAL COMPUTING & APPLICATIONS 2013年第3-4期23卷 577-582页

作者： Sousa, Ines J. Padron, Jose M. Fernandes, Miguel X. Univ Madeira Ctr Quim Madeira Ctr Competencia Ciencias Exatas & Engn P-9000390 Funchal Portugal Univ La Laguna BioLab Inst Univ Bioorgan Antonio Gonzalez San Cristobal la Laguna 38206 Spain

Artificial neural networks (ANNs) have several applications;one of them is the prediction of biological activity. Here, ANNs were applied to a set of 32 compounds with anticancer activity assayed experimentally against two cancer cell lines (A2780 and T-47D). Using training and test sets, the obtained correlation coefficients between experimental and calculated values of activity, for A2780, were 0.804 and 0.829, respectively, and for T-47D, we got 0.820 for the training set and 0.927 for the test set. Comparing multiple linear regression and ANN models, the latter were better suited in establishing relationships between compounds' structure and their anticancer activity.

关键词： backpropagation algorithm Correlation coefficients Heuristics Learning algorithms Machine learning Neural network models Nonlinear models Prediction methods Radial base function network

来源：评论

学校读者我要写书评

暂无评论

Exit wave reconstruction of a focal series of images with structural changes in high-resolution transmission electron microscopy

引用

JOURNAL OF MICROSCOPY 2024年第1期296卷 24-33页

作者： Zhang, Xiaohan Chen, Shaowen Wang, Shuya Huang, Ying Jin, Chuanhong Lin, Fang South China Agr Univ Coll Elect Engn Dept Appl Phys Guangzhou Guangdong Peoples R China Jihua Lab Foshan Guangdong Peoples R China Zhuhai Multiplier Informat Technol Co Ltd Dept Res & Dev Zhuhai Guangdong Peoples R China Zhejiang Univ Sch Mat Sci & Engn State Key Lab Silicon & Adv Semicond Mat Hangzhou Peoples R China South China Agr Univ Coll Elect Engn Guangzhou 510642 Guangdong Peoples R China

High-resolution transmission electron microscopy (HRTEM) images can capture the atomic-resolution details of the dynamically changing structure of nanomaterials. Here, we propose a new scheme and an improved reconstruction algorithm to reconstruct the exit wave function for each image in a focal series of HRTEM images to reveal structural changes. In this scheme, the wave reconstructed from the focal series of images is treated as the initial wave in the reconstruction process for each HRTEM image. Additionally, to suppress noise at the frequencies where the signal is weak due to the modulation of the lens transfer function, a weight factor is introduced in the improved reconstruction algorithm. The advantages of the new scheme and algorithms are validated by using the HRTEM images of a natural specimen and a single-layer molybdenum disulphide. This algorithm enables image resolution enhancement and lens aberration removal, while potentially allowing the visualisation of the structural evolution of nanostructures.

关键词： backpropagation algorithm exit wave function reconstruction high-resolution transmission electron microscopy steepest descent algorithm

来源：评论

学校读者我要写书评

暂无评论

A hybrid algorithm for artificial neural network training

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2013年第1期26卷 293-301页

作者： Yaghini, Masoud Khoshraftar, Mohammad M. Fallahi, Mehdi Iran Univ Sci & Technol Sch Railway Engn Rail Transportat Dept Tehran Iran

Artificial neural network (ANN) training is one of the major challenges in using a prediction model based on ANN. Gradient based algorithms are the most frequent training algorithms with several drawbacks. The aim of this paper is to present a method for training ANN. The ability of metaheuristics and greedy gradient based algorithms are combined to obtain a hybrid improved opposition based particle swarm optimization and a back propagation algorithm with the momentum term. Opposition based learning and random perturbation help population diversification during the iteration. Use of time-varying parameter improves the search ability of standard PSO, and constriction factor guarantees particles convergence. Since several contingent local minima conditions may happen in the weight space, a new cross validation method is proposed to prevent overfitting. Effectiveness and efficiency of the proposed method are compared with several other famous ANN training algorithms on the various benchmark problems. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Artificial Neural Networks Hybrid training algorithm Particle swarm optimization backpropagation algorithm Cross validation Time-varying parameter

来源：评论

学校读者我要写书评

暂无评论

Improving performance in pulse radar detection using Bayesian regularization for neural network training

引用

DIGITAL SIGNAL PROCESSING 2004年第5期14卷 438-448页

作者： Kumar, P Merchant, SN Desai, UB Indian Inst Technol Dept Elect Engn Bombay 400076 Maharashtra India Indian Inst Technol Dept Elect & Commun Engn Gauhati 781039 India

A better approach for training a multi-layered feedforward network for pulse compression is presented. The Bayesian regularization technique used for training the network for pulse radar detection results in superior performance in terms of signal-to-sidelobe ratio compared to the backpropagation algorithm. The presented method also has better range resolution performance in terms of resistance to lower input code magnitude ratios. 13-bit Barker code, 31-bit m-sequence and 63-bit m-sequence are used as the signal codes. (C) 2004 Elsevier Inc. All rights reserved.

关键词： backpropagation algorithm Bayesian regularization multi-layered feedforward neural network pulse compression

来源：评论

学校读者我要写书评

暂无评论

Precise GPS orbit determination and prediction using H_∞ neural network

引用

JOURNAL OF THE CHINESE INSTITUTE OF ENGINEERS 2006年第2期29卷 211-219页

作者： Wang, HS Natl Taiwan Ocean Univ Dept Commun & Guidance Engn Chilung 202 Taiwan

In this paper, I present a method to determine and predict precisely the GPS satellite orbit by using a neural network. The neural network used in this paper is based on the BP (backpropagation) learning algorithm. The BP algorithm is particularly attractive because it is H-infinity optimal. It is a robust algorithm in the sense that small disturbances and modeling errors lead to small estimation errors (For a non-robust algorithm, such as the classical maximum likelihood and least square methods, it is possible that small disturbances and modeling errors may result in large estimation errors). This is certainly the case for the estimation of the GPS satellite orbit because the satellite orbital model usually contains small disturbances and perturbations that are difficult to model. Currently, the simulation result shows that we can use the well-trained network to predict about six days' data and the orbital will can be within a meter. The result is compared with the classical polynomial interpolation method. It is believed that, if we extend the training time, the prediction period can be much longer.

关键词： global positioning systemm H-infinity optimality backpropagation algorithm indoor GPS

来源：评论

学校读者我要写书评

暂无评论

Classification of Venezuelan spirituous beverages by means of discriminant analysis and artificial neural networks based on their Zn, Cu and Fe concentrations

引用

TALANTA 2003年第6期60卷 1259-1267页

作者： Hernández-Caraballo, EA Avila-Gómez, RM Capote, T Rivas, F Pérez, AG Univ Los Andes Fac Ciencias IVAIQUIM Lab Espectroscopia Mol Merida 5101 Venezuela Univ Ctr Occidental Lisandro Alvarado Dept Quim & Suelos Unidad Anal Instrumental Barquisimeto 3001 Venezuela Univ Los Andes Fac Ingn Escuela Ingn Sistemas Lab Sistemas Inteligentes Merida 5101 Venezuela Univ Los Andes Fac Ciencias Econ & Sociales Inst Estadist Aplicada & Computac Merida 5101 Venezuela

Copper, zinc and iron concentrations were determined in "aguardiente de Cocuy de Penca" (Cocuy de Penca Firewater), a spirituous beverage very popular in the North-Western region of Venezuela, by flame atomic absorption spectrometry (FAAS). These elements were selected for their presence can be traced to the (illegal) manufacturing process of the aforementioned beverages. Linear and quadratic discriminant analysis (QDA), and artificial neural networks (ANNs) trained with the backpropagation algorithm were employed for estimating if such beverages can be distinguished based on the concentrations of these elements in the final product, and whether it is possible to assess the geographic location of the manufacturers (Lara or Falcon states) and the presence or absence of sugar in the end product. A linear discriminant analysis (LDA) performed poorly, overall estimation and prediction rates being 51.7% and 50.0%, respectively. A QDA showed a slightly better overall performance, yet unsatisfactory (estimation: 79.2% prediction: 72.5%). Various ANNs, comprising a linear function (L) in the input layer, a sigmoid function (S) in the hidden layer(s) and a hyperbolic tangent function (T) in the output layer, were evaluated. Of the networks studied, the (3L:5S:7S:4T) gave the highest estimation (overall: 96.5%) and prediction rates (overall: 97.0%), demonstrating the superb performance of ANNs for classification purposes. (C) 2003 Elsevier B.V. All rights reserved.

关键词： iron copper zinc classification Cocuy spirituous beverages linear discriminant analysis (LDA) quadratic discriminant analysis (QDA) artificial neural networks (ANNs) backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Modelling combined open channel flow by artificial neural networks

引用

HYDROLOGICAL PROCESSES 2005年第18期19卷 3747-3762页

作者： Yang, HC Chang, FJ Natl Taiwan Univ Dept Bioenvironm Syst Engn Taipei 10764 Taiwan

Combined open channel flow is encountered in many hydraulic engineering structures and processes, such as irrigation ditches and wastewater treatment facilities. Extensive experimental studies have conducted to investigate combined flow characteristics. Nevertheless, there is no simple relationship that can fully describe the velocity profiles in a turbulent flow. The artificial neural network (ANN) has great computational capability for solving various complex problems, such as function approximation. The main objective of this study is to evaluate the applicability of the ANN for simulating velocity profiles, velocity contours and estimating the discharges accordingly. The velocity profiles measured by an acoustic doppler velocimeter in the open channel of the Chihtan purification plant, Taipei, with different discharges at fixed measuring section and different depths are presented. The total number of data sets is 640 and the data sets are split into two subsets, i.e. training and validation sets. The backpropagation algorithm is used to construct the neural network. The results demonstrate that the velocity profiles can be modelled by the ANN, and the ANN constructed can nicely fit the velocity profiles and can precisely predict the discharges for the conditions investigated. Copyright (c) 2005 John Wiley & Sons, Ltd.

关键词： velocity profile acoustic Doppler velocimeter (ADV) artificial neural network (ANN) backpropagation 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：