Fatemeh haghighat; Fariborz Golai
Abstract
In order to predict the values of passengers movement indexes which enjoy seasonal changes, this research uses Holt Winters Markov chain model, which is a combination of Markov chain and Holt Winters models. In this regard, Data on the number of moved passengers and the number of made trips indexes are ...
Read More
In order to predict the values of passengers movement indexes which enjoy seasonal changes, this research uses Holt Winters Markov chain model, which is a combination of Markov chain and Holt Winters models. In this regard, Data on the number of moved passengers and the number of made trips indexes are analyzed in Bushehr Province during the seasons of 1387 to 1391. First, Data on the each indexes of the studied intervals divided into two parts, then the second part data were predicted using Holt Winters model. In the next step, by calculating and classifying the errors of the actual and predicted values, Holt Winters Markov chain model is used in order to predict the Index values based on probabilities of errors mode and also improve the performance of Holt Winters model in prediction. The results obtained from the Comparison of two models of Holt Winters and Markov chain Holt Winters shows that Holt Winters Markov chain model is more accurate at predicting
Payam Hanafizadeh; Abolfazl Jafari
Volume 8, Issue 19 , December 2010, , Pages 165-187
Abstract
In this paper, a hybrid model of artificial neural networks is designed and used to evaluate the prediction ability of this hybrid model with individual Back Propagation feed forward. This study employs hybrid artificial neural networks consisting of Back Propagation and Kohonen Self Organizing Map (SOM) ...
Read More
In this paper, a hybrid model of artificial neural networks is designed and used to evaluate the prediction ability of this hybrid model with individual Back Propagation feed forward. This study employs hybrid artificial neural networks consisting of Back Propagation and Kohonen Self Organizing Map (SOM) for better stock price prediction. Computational experience in predicting stock prices obtained from Tehran Stock Exchange reveals that the combination of Self Organizing Map and Back Propagation leads to better performance in comparison with the most popular individual Back Propagation feed forward networks.
JEL Classification: E37, C45, C51, C52, C53
Mahmood Alborzi; Seyed Amir Reza Abtahi
Volume 4, Issue 13 , June 2006, , Pages 41-66
Abstract
This paper uses neural network to predict corrosion rate. Corrosion can not modeled easily, because of wide range of causes either known or unknown. In mechanistic approach, physical, chemical and electrochemical reactions and processes are considered to model and predict. ...
Read More
This paper uses neural network to predict corrosion rate. Corrosion can not modeled easily, because of wide range of causes either known or unknown. In mechanistic approach, physical, chemical and electrochemical reactions and processes are considered to model and predict. But as stated before this models are not practically successful in prediction because of unknown parameters.
This paper uses genetic optimized neural network to predict corrosion rate. Among different neural networks, multi layer neural network with gradient descent learning algorithm has been selected. After developing the network, learning process has been done, using an oil refinery'S data. Then evaluation and test have been performed. After preparing the network Garson's algorithm and sensitivity analysis have been used for knowledge extraction.
According to results, neural network approach can predict corrosion rate with acceptable correlation coefficient (R) and mean squared error (MSE). Sensitivity analysis depicts the strength of each oil parameter influence on corrosion rate. Among these results, salt and sulphur are the most affecting parameters in corrosion rate.