Thammano, Arit

Loading...
Thumbnail Image
Preferred name
Thammano, Arit
Alternative Name
Thammano, A.
Thummano, Arit
Main Affiliation
Email
arit.th@kmitl.ac.th

Filters

1998 - 19994

Settings

Now showing 1 - 4 of 4
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    An artificial neural network model in economic forecasting: A study in Thailand's natural rubber industry
    (1998-12-01)
    Thammano, Arit
    ;
    Raviwongse, Rawin
    ;
    Tanatammatid, Monticha
    In the past forty years, the world demand for rubber, both natural and synthetic, as raw material has increased drastically. However, the use of natural rubber in industry has been declining due to several reasons such as unreliable quality, delayed delivery time, and fluctuating prices. Since Thailand is among the top three natural rubber producers in the world, in addition to the need to promote the use of natural rubber, the country must also improve its competitive edge in exporting them over other exporters. As such, one way to support the improvement is to develop a reliable model to forecast the demand and supply of natural rubber in the world market. In this study, an artificial neural network technique is applied to (i) study and forecast the world demand of natural rubber by region and (ii) estimate the appropriate export quantity for Thailand's natural rubber industry. The output from the neural network model can be directly applied to the economic planning for Thailand's natural rubber industry.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    New forecasting approach with neuro-fuzzy architecture
    (1999-12-01)
    Thammano, Arit
    Planning is an integral part of any work processes. However, it is difficult to plan effectively if uncertainties cloud the planning horizon. Forecasts can help organizations by reducing some of the uncertainty, thereby enabling them to develop a more practical plan. Currently, there are many different kinds of forecasting techniques available, but no single technique works best in every situation. Therefore, the objective of this paper is to propose a new intelligent forecasting technique which employs the concepts of neural network and fuzzy system. The neural network determines the output of the system based on the current state of the input parameters. The fuzzy-inference network evaluates the performance of the model by assessing the error and the derivative error of the system. If the error is high, the corrective action will be sent to the neural network to improve the system performance. To test the performance of the proposed model, it is used to approximate the nonlinear function in comparison to the most commonly used backpropagation neural network. The testing results demonstrate a very reliable performance of the proposed model.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Equipment modeling for plasma etch process using artificial neural network
    (1998-12-01)
    Thammano, Arit
    The artificial neural network, with the help from genetic algorithm, is introduced as an alternative simulation technique. This technique is easy and inexpensive yet very effective. The proposed technique enables process engineers to easily create the equipment modeling by themselves using the data collected in the past.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Neuro-fuzzy model for stock market prediction
    (1999-12-01)
    Thammano, Arit
    Stock value prediction is a widely concerned issue. In the stock market, every investor certainly would like to be able to precisely forecast stock prices in order to maximize their profit and reduce potential risks. The tools used by stock market analysts, such as moving average and trend techniques, can only give investors an alarm or a sign of possible increase or decrease in prices. These traditional mathematical approaches are not very effective in forecasting the future stock value because they are not susceptible to a change in circumstances, especially for Thai stock market which is very small in volume and easily disturbed by the outside environments, e.g. political issues and tumors. In this study, the new neuro-fuzzy architecture is proposed. The proposed system is employed to build the model to predict the future values of the Krung Thai Bank PLC, Thailand's largest government-owned bank. The results demonstrate a very reliable performance of the proposed model.