This study comprises developing a more appropriate hybrid wavelet-modified GMDH model for forecas... more This study comprises developing a more appropriate hybrid wavelet-modified GMDH model for forecasting the monthly crude palm oil (CPO) price of Malaysia. In the proposed hybrid model, the complex data of monthly CPO price is decomposed into different sub series using discrete wavelet transform (DWT) and then it has been linked with modified GMDH model. Sigmoid, radial basis, tangent and polynomial functions are selected as transfer functions in modified GMDH for the best fit and correct model compared to conventional GMDH. The monthly CPO data were taken from Malaysian Palm Oil Board (MPOB) spanning the period January 1983 to November 2019. The capabilities of modified GMDH and hybrid wavelet-modified GMDH in modelling and forecasting the monthly CPO price are determined by MAE, RMSE, MAPE, R and R2. The MAPE of the proposed hybrid wavelet-modified GMDH model for the monthly CPO price of Malaysia is less than 4 % and coefficient of correlation (R) is 0.99, which show an excellent fi...
Palm oil has known as the important source of vegetables oils in the global market. Malaysia is t... more Palm oil has known as the important source of vegetables oils in the global market. Malaysia is the one of the major producer and exporters of palm oil. An accurate forecasting on crude palm oil (CPO) prices is considered significant to the oil palm business. This study was conducted to identify suitable model between Multiple Linear Regression (MLR) model and Artificial Neural Network (ANN) model on predicting Malaysia crude palm oil (CPO) prices. The Malaysia crude palm oil was predicted by three other Malaysia primary commodity prices which are natural rubber (NR) prices, black pepper (BP) prices and cocoa beans (CB) prices. The analysis use weekly data on the prices from Jan 2004 until Dec 2013. The methods are compared to obtain the best model for predicting crude palm oil price. It was found that, the value of in ANN model is higher than MLR model by 20.61%. The value of mean squared error (MSE) in ANN model also lower compared to MLR model. Therefore, ANN model is preferred t...
This paper aims at introducing the notion of intuitionistic N-fuzzy set (INFS) and its applicatio... more This paper aims at introducing the notion of intuitionistic N-fuzzy set (INFS) and its application along with its examples. As the application of this set, its idea has been applied to a newly defined algebraic structure "BiΓ-Ternary Semigroup". The notions of intuitionistic N-fuzzy biΓ-ternary subsemigroup and intuitionistic N-fuzzy biΓ-left (right, lateral and bi) ideals have been defined and related properties have been investigated here. The characterization of biΓ-ternary semigroup under these ideals has been established.
Forecasting crude palm oil price is important, particularly when the investors encounter with the... more Forecasting crude palm oil price is important, particularly when the investors encounter with the increasing risks and uncertainties in the future. Therefore, the aim of this study is to forecast the price of palm oil in Malaysia for the next years based on price for the period of 31 years. The objective of the research is to propose an appropriate model to forecast the CPO price. Thus, this study proposes three types of models, which are namely: Autoregressive Integrated Moving Average (ARIMA), Autoregressive Conditional Heteroskedasticity (ARCH) and Generalized Autoregressive Conditional Heteroskedasticity (GARCH). Akaike Information Criterion (AIC) and Hannan-Quinn Criterion (H-Q) statistic were used to obtain the best model. It was found that ARIMA (2, 1, 5) performed better compared to ARCH and GARCH models. It is concluded that ARIMA (2, 1, 5) can be used as an alternative model to forecast the CPO price.
This study explored the use of survival analysis to investigate the Bachelor's degree students' p... more This study explored the use of survival analysis to investigate the Bachelor's degree students' performance based on GPA, entrance qualification, faculty, and course. The study considered the application of semi-parametric and parametric Accelerated Failure Time (AFT) models. The main objectives of the study are to identify the covariates that dominate students' performance via the Cox model, to investigate the performance of the Cox model based on the Proportional Hazard (PH) assumption, and to compare the performance of parametric AFT models using Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), and Corrected Akaike Information Criterion (AICc). Results revealed that the Cox model suggested the covariates of GPA, faculty, entrance qualification, and the course had affected student performance. PH assumption in the Cox model was violated. This analysis concluded that the Cox model provided a less accurate estimate of student performance and further study should be conducted with parametric AFT models. In parametric AFT models, the Log-normal AFT was chosen as the best model and can be used as an alternative model for estimating student performance at universities and other similar higher educational institutions.
Background: The issue of abandoned construction projects is something common that has been widely... more Background: The issue of abandoned construction projects is something common that has been widely discussed globally, including Malaysia. This issue has brought a lot of loss to the construction industry and to the economy of the country as well. Identifying factors contributing towards the restoration of the abandoned projects are important to have a successful completed project. This paper is subjected to a study conducted in the purpose of identifying those factors and analyzing it further on to know the significance of it in abandoned project restoration. The study focuses on residential projects and a survey was conducted by distributing questionnaires to targeted groups, and 244 completed questionnaires were collected at the end of the survey. The collected questionnaires was tested on its’ reliability and the factor analysis was also conducted using the SPSS software. The data from it was further on used to construct the latent and measured variables, and lastly a model with ...
International Journal for Research in Applied Science and Engineering Technology, 2020
Gold price is volatile since their currency changes rapidly over time. Kijang Emas is famous with... more Gold price is volatile since their currency changes rapidly over time. Kijang Emas is famous with an official Malaysian gold bullion coin. In this research, selling price of Kijang Emas is used to forecast. The price is in Ringgit Malaysia units of 1 ounce Kijang Emas is used. The aim of this research is to evaluate two different methods in forecasting Kijang Emas price and to propose the appropriate model in the end of this research. The methods of forecasting are Holt-Trend exponential smoothing and ARIMA are used in this research. Their comparative study is conducted by using error measurements that commonly used in forecasting research. They are mean absolute percentage error (MAPE), mean absolute error (MAE) and root mean squared error (RMSE). The finding of this research is Holt-Trend exponential smoothing model is proposed as an appropriate model for forecasting Kijang Emas price.
Bitcoin is the most popular cryptocurrency with the highest market value. It was said to have pot... more Bitcoin is the most popular cryptocurrency with the highest market value. It was said to have potential in changing the way of trading in future. However, Bitcoin price prediction is a hard task and difficult for investors to make decision. This is caused by nonlinearity property of the Bitcoin price. Hence, a better forecasting method are essential to minimize the risk from inaccuracy decision. The aim of this paper is to compare two different training algorithms which are Levenberg-Marquardt (LM) backpropagation algorithm and Scaled Conjugate Gradient (SCG) backpropagation algorithm using Feedforward Neural Network (FNN) to forecast the Bitcoin price. After obtaining the forecasting result, forecast accuracy measurement will be carried out to identify the best model to forecast Bitcoin price. The result showed that the performance of Bitcoin price forecasting increased after the application of FNN – LM model. It is proven that Levenberg-Marquardt backpropagation algorithm is bette...
International Journal of Scientific & Technology Research, 2014
This study was conducted to compare the performance between Multiple Linear Regression (MLR) mode... more This study was conducted to compare the performance between Multiple Linear Regression (MLR) model and Neural Network model on estimate house prices in New York. A sample of 1047 houses is randomly selected and retrieved from the Math10 website. The factors in prediction house prices including living area, number of bedrooms, number of bathrooms, lot size and age of house. The methods used in this study are MLR and Artificial Neural Network. It was found that, the value of R 2 in Neural Network model is higher than MLR model by 26.475%. The value of Mean Squared Error (MSE) in Neural Network model also lower compared to MLR model. Therefore, Neural Network model is prefered to be used as alternative model in estimating house price compared to MLR model.
The objective of this study is to identify the factor that effect the student loyalty towards res... more The objective of this study is to identify the factor that effect the student loyalty towards residential college. Students who live in residential colleges at UTHM are the subject of this study. Students are stratified according to their residential college and then random sample was chosen. The dependent variable is student loyalty towards residential college, while the independent variables are facilities, management and staff performance. The causal relationships were established by structural equation modelling (SEM) method using SPSS and AMOS statistical software. It is shows that facilities, management and staff performance have significant and direct effect toward student loyalty.
This research aims to spot the factors that influence job satisfaction among Royal Malaysian Cust... more This research aims to spot the factors that influence job satisfaction among Royal Malaysian Customs Department employees. Primary data was used in this research and it was collected from the employees who work in five different departments at Royal Malaysian Customs Department Tower Johor. Those departments were customs department, Internal Taxes, Technical Services, Management and Prevention. The research used stratified random sampling to collect the sample and Structural Equation Modelling (SEM) to measure the relationship between variables using AMOS software. About 127 employees are selected as the respondents from five departments to represent the sample. The result showed that 'Organizational Commitment' (p-value = 0.001) has significant and direct effect toward job satisfaction compared to the 'Stress Condition' (p-value = 0.819) and 'Motivation' factor (pvalue = 0.978). It was also concluded that 'Organizational Commitment' was the most influential factor toward job satisfaction among Royal Malaysian Customs Department employees at Tower Custom Johor, Johor Bahru.
Multi-stage biological treatment of petroleum refinery wastewater using different biological cond... more Multi-stage biological treatment of petroleum refinery wastewater using different biological conditions (anaerobic-anoxic-aerobic) has many advantages over other biological methods. It can result in maximum treatment for type of complex wastewater. In this study, raw data obtained from two multi-stage biological reactors (MSBR) used for treatment of different loads of petroleum refinery wastewater was used for developing mathematical model that could predict the process trend. The data consists of 160 entries and were gathered over approximately 180 days from two MSBR reactors that were continuously operated in parallel. A Matlab code was written with two configurations of artificial neural network. The configurations were compared and different number of neurons at the hidden layer were tested for optimum model that represent the process behavior under different loads. The tangent sigmoid transfer function (Tansig) at hidden layer and a linear transfer function (Purelin) at output layer with 6 neurons were selected as the optimum best model. The model was then used for prediction; highest removal efficiency observed was 98% which was repeatedly recorded for various loads. Effluent concentration below 100 mg/L as chemical oxygen demand (COD) was recorded for influent concentration ranged between 900 and 3600 mg COD/L.
This study provided the basic needs of parameters estimation for nonlinear growth model such as p... more This study provided the basic needs of parameters estimation for nonlinear growth model such as partial derivatives of each model, determination of initial values for each parameter and statistical tests of industrial usage. Twelve nonlinear growth models and its partial derivatives for oil palm yield growth are presented in this study. The parameters are estimated using the Marquardt iterative method of nonlinear regression relating oil palm yield growth data. The best model was selected based on the model performance and it can be used to estimate the oil palm yield at any age of oil palm. This study found that the Gompertz, logistic, log-logistic, Morgan-Mercer-Flodin and Chapman-Richard growth models have the ability for quantifying a growth phenomenon that exhibit a sigmoid pattern over time. Based on the statistical testing and goodness of fit, the best model is the Logistic model and followed by the Gompertz model, Morgan-Mercer-Flodin, Chapman-Richard (with initial stage) and Log-logistic growth models.
A current optimal control problem has the numerical properties that do not fall into the standard... more A current optimal control problem has the numerical properties that do not fall into the standard optimal control problem detailing. In our concern, the state incentive at the final time, y(T ) = z, is free and obscure, and furthermore, the integrand is a piecewise consistent capacity of the obscure esteem y(T ). This is not a standard optimal control problem and cannot be settled utilizing Pontryagin’s minimum principle with the standard limit conditions at the final time. In the standard issue, a free final state y(T ) yields an important limit condition p(T ) = 0, where p(t) is the costate. Since the integrand is a component of y(T ), the new fundamental condition is that y(T ) yields to be equivalent to a necessary consistent capacity of z. We tackle a case utilizing a C++ shooting method with Newton emphasis for tackling the two point boundary value problem (TPBVP). The limiting free y(T ) value is computed in an external circle emphasis through the golden section method. Compa...
Hybridization of existing competitive modeling methodologiesis now an active area of research.The... more Hybridization of existing competitive modeling methodologiesis now an active area of research.The GMDH algorithm is a heuristic and computer oriented method which provides the foundation for the construction of high order regression models of complex system.The research for improving the effectiveness of forecasting models has never been stopped. Currently it was reported that a hybrid system in prediction and classification achieved a higher performance level against the traditional system. The selection of the forcasting model is the important criteria that will influence to the forcasting accuracy. So the enhancement of conventional GMDH model through hybridization will improve the prediction accuracy of the traditional GMDH for time series forcasting.This paper presents a short overview of Group Method of Data Handling (GMDH),itsmodification and hybridization for time series forecasting.The overviewwill aim to provide further investigation on the hybrid Group Method of Data Hand...
This study comprises developing a more appropriate hybrid wavelet-modified GMDH model for forecas... more This study comprises developing a more appropriate hybrid wavelet-modified GMDH model for forecasting the monthly crude palm oil (CPO) price of Malaysia. In the proposed hybrid model, the complex data of monthly CPO price is decomposed into different sub series using discrete wavelet transform (DWT) and then it has been linked with modified GMDH model. Sigmoid, radial basis, tangent and polynomial functions are selected as transfer functions in modified GMDH for the best fit and correct model compared to conventional GMDH. The monthly CPO data were taken from Malaysian Palm Oil Board (MPOB) spanning the period January 1983 to November 2019. The capabilities of modified GMDH and hybrid wavelet-modified GMDH in modelling and forecasting the monthly CPO price are determined by MAE, RMSE, MAPE, R and R2. The MAPE of the proposed hybrid wavelet-modified GMDH model for the monthly CPO price of Malaysia is less than 4 % and coefficient of correlation (R) is 0.99, which show an excellent fi...
Palm oil has known as the important source of vegetables oils in the global market. Malaysia is t... more Palm oil has known as the important source of vegetables oils in the global market. Malaysia is the one of the major producer and exporters of palm oil. An accurate forecasting on crude palm oil (CPO) prices is considered significant to the oil palm business. This study was conducted to identify suitable model between Multiple Linear Regression (MLR) model and Artificial Neural Network (ANN) model on predicting Malaysia crude palm oil (CPO) prices. The Malaysia crude palm oil was predicted by three other Malaysia primary commodity prices which are natural rubber (NR) prices, black pepper (BP) prices and cocoa beans (CB) prices. The analysis use weekly data on the prices from Jan 2004 until Dec 2013. The methods are compared to obtain the best model for predicting crude palm oil price. It was found that, the value of in ANN model is higher than MLR model by 20.61%. The value of mean squared error (MSE) in ANN model also lower compared to MLR model. Therefore, ANN model is preferred t...
This paper aims at introducing the notion of intuitionistic N-fuzzy set (INFS) and its applicatio... more This paper aims at introducing the notion of intuitionistic N-fuzzy set (INFS) and its application along with its examples. As the application of this set, its idea has been applied to a newly defined algebraic structure "BiΓ-Ternary Semigroup". The notions of intuitionistic N-fuzzy biΓ-ternary subsemigroup and intuitionistic N-fuzzy biΓ-left (right, lateral and bi) ideals have been defined and related properties have been investigated here. The characterization of biΓ-ternary semigroup under these ideals has been established.
Forecasting crude palm oil price is important, particularly when the investors encounter with the... more Forecasting crude palm oil price is important, particularly when the investors encounter with the increasing risks and uncertainties in the future. Therefore, the aim of this study is to forecast the price of palm oil in Malaysia for the next years based on price for the period of 31 years. The objective of the research is to propose an appropriate model to forecast the CPO price. Thus, this study proposes three types of models, which are namely: Autoregressive Integrated Moving Average (ARIMA), Autoregressive Conditional Heteroskedasticity (ARCH) and Generalized Autoregressive Conditional Heteroskedasticity (GARCH). Akaike Information Criterion (AIC) and Hannan-Quinn Criterion (H-Q) statistic were used to obtain the best model. It was found that ARIMA (2, 1, 5) performed better compared to ARCH and GARCH models. It is concluded that ARIMA (2, 1, 5) can be used as an alternative model to forecast the CPO price.
This study explored the use of survival analysis to investigate the Bachelor's degree students' p... more This study explored the use of survival analysis to investigate the Bachelor's degree students' performance based on GPA, entrance qualification, faculty, and course. The study considered the application of semi-parametric and parametric Accelerated Failure Time (AFT) models. The main objectives of the study are to identify the covariates that dominate students' performance via the Cox model, to investigate the performance of the Cox model based on the Proportional Hazard (PH) assumption, and to compare the performance of parametric AFT models using Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), and Corrected Akaike Information Criterion (AICc). Results revealed that the Cox model suggested the covariates of GPA, faculty, entrance qualification, and the course had affected student performance. PH assumption in the Cox model was violated. This analysis concluded that the Cox model provided a less accurate estimate of student performance and further study should be conducted with parametric AFT models. In parametric AFT models, the Log-normal AFT was chosen as the best model and can be used as an alternative model for estimating student performance at universities and other similar higher educational institutions.
Background: The issue of abandoned construction projects is something common that has been widely... more Background: The issue of abandoned construction projects is something common that has been widely discussed globally, including Malaysia. This issue has brought a lot of loss to the construction industry and to the economy of the country as well. Identifying factors contributing towards the restoration of the abandoned projects are important to have a successful completed project. This paper is subjected to a study conducted in the purpose of identifying those factors and analyzing it further on to know the significance of it in abandoned project restoration. The study focuses on residential projects and a survey was conducted by distributing questionnaires to targeted groups, and 244 completed questionnaires were collected at the end of the survey. The collected questionnaires was tested on its’ reliability and the factor analysis was also conducted using the SPSS software. The data from it was further on used to construct the latent and measured variables, and lastly a model with ...
International Journal for Research in Applied Science and Engineering Technology, 2020
Gold price is volatile since their currency changes rapidly over time. Kijang Emas is famous with... more Gold price is volatile since their currency changes rapidly over time. Kijang Emas is famous with an official Malaysian gold bullion coin. In this research, selling price of Kijang Emas is used to forecast. The price is in Ringgit Malaysia units of 1 ounce Kijang Emas is used. The aim of this research is to evaluate two different methods in forecasting Kijang Emas price and to propose the appropriate model in the end of this research. The methods of forecasting are Holt-Trend exponential smoothing and ARIMA are used in this research. Their comparative study is conducted by using error measurements that commonly used in forecasting research. They are mean absolute percentage error (MAPE), mean absolute error (MAE) and root mean squared error (RMSE). The finding of this research is Holt-Trend exponential smoothing model is proposed as an appropriate model for forecasting Kijang Emas price.
Bitcoin is the most popular cryptocurrency with the highest market value. It was said to have pot... more Bitcoin is the most popular cryptocurrency with the highest market value. It was said to have potential in changing the way of trading in future. However, Bitcoin price prediction is a hard task and difficult for investors to make decision. This is caused by nonlinearity property of the Bitcoin price. Hence, a better forecasting method are essential to minimize the risk from inaccuracy decision. The aim of this paper is to compare two different training algorithms which are Levenberg-Marquardt (LM) backpropagation algorithm and Scaled Conjugate Gradient (SCG) backpropagation algorithm using Feedforward Neural Network (FNN) to forecast the Bitcoin price. After obtaining the forecasting result, forecast accuracy measurement will be carried out to identify the best model to forecast Bitcoin price. The result showed that the performance of Bitcoin price forecasting increased after the application of FNN – LM model. It is proven that Levenberg-Marquardt backpropagation algorithm is bette...
International Journal of Scientific & Technology Research, 2014
This study was conducted to compare the performance between Multiple Linear Regression (MLR) mode... more This study was conducted to compare the performance between Multiple Linear Regression (MLR) model and Neural Network model on estimate house prices in New York. A sample of 1047 houses is randomly selected and retrieved from the Math10 website. The factors in prediction house prices including living area, number of bedrooms, number of bathrooms, lot size and age of house. The methods used in this study are MLR and Artificial Neural Network. It was found that, the value of R 2 in Neural Network model is higher than MLR model by 26.475%. The value of Mean Squared Error (MSE) in Neural Network model also lower compared to MLR model. Therefore, Neural Network model is prefered to be used as alternative model in estimating house price compared to MLR model.
The objective of this study is to identify the factor that effect the student loyalty towards res... more The objective of this study is to identify the factor that effect the student loyalty towards residential college. Students who live in residential colleges at UTHM are the subject of this study. Students are stratified according to their residential college and then random sample was chosen. The dependent variable is student loyalty towards residential college, while the independent variables are facilities, management and staff performance. The causal relationships were established by structural equation modelling (SEM) method using SPSS and AMOS statistical software. It is shows that facilities, management and staff performance have significant and direct effect toward student loyalty.
This research aims to spot the factors that influence job satisfaction among Royal Malaysian Cust... more This research aims to spot the factors that influence job satisfaction among Royal Malaysian Customs Department employees. Primary data was used in this research and it was collected from the employees who work in five different departments at Royal Malaysian Customs Department Tower Johor. Those departments were customs department, Internal Taxes, Technical Services, Management and Prevention. The research used stratified random sampling to collect the sample and Structural Equation Modelling (SEM) to measure the relationship between variables using AMOS software. About 127 employees are selected as the respondents from five departments to represent the sample. The result showed that 'Organizational Commitment' (p-value = 0.001) has significant and direct effect toward job satisfaction compared to the 'Stress Condition' (p-value = 0.819) and 'Motivation' factor (pvalue = 0.978). It was also concluded that 'Organizational Commitment' was the most influential factor toward job satisfaction among Royal Malaysian Customs Department employees at Tower Custom Johor, Johor Bahru.
Multi-stage biological treatment of petroleum refinery wastewater using different biological cond... more Multi-stage biological treatment of petroleum refinery wastewater using different biological conditions (anaerobic-anoxic-aerobic) has many advantages over other biological methods. It can result in maximum treatment for type of complex wastewater. In this study, raw data obtained from two multi-stage biological reactors (MSBR) used for treatment of different loads of petroleum refinery wastewater was used for developing mathematical model that could predict the process trend. The data consists of 160 entries and were gathered over approximately 180 days from two MSBR reactors that were continuously operated in parallel. A Matlab code was written with two configurations of artificial neural network. The configurations were compared and different number of neurons at the hidden layer were tested for optimum model that represent the process behavior under different loads. The tangent sigmoid transfer function (Tansig) at hidden layer and a linear transfer function (Purelin) at output layer with 6 neurons were selected as the optimum best model. The model was then used for prediction; highest removal efficiency observed was 98% which was repeatedly recorded for various loads. Effluent concentration below 100 mg/L as chemical oxygen demand (COD) was recorded for influent concentration ranged between 900 and 3600 mg COD/L.
This study provided the basic needs of parameters estimation for nonlinear growth model such as p... more This study provided the basic needs of parameters estimation for nonlinear growth model such as partial derivatives of each model, determination of initial values for each parameter and statistical tests of industrial usage. Twelve nonlinear growth models and its partial derivatives for oil palm yield growth are presented in this study. The parameters are estimated using the Marquardt iterative method of nonlinear regression relating oil palm yield growth data. The best model was selected based on the model performance and it can be used to estimate the oil palm yield at any age of oil palm. This study found that the Gompertz, logistic, log-logistic, Morgan-Mercer-Flodin and Chapman-Richard growth models have the ability for quantifying a growth phenomenon that exhibit a sigmoid pattern over time. Based on the statistical testing and goodness of fit, the best model is the Logistic model and followed by the Gompertz model, Morgan-Mercer-Flodin, Chapman-Richard (with initial stage) and Log-logistic growth models.
A current optimal control problem has the numerical properties that do not fall into the standard... more A current optimal control problem has the numerical properties that do not fall into the standard optimal control problem detailing. In our concern, the state incentive at the final time, y(T ) = z, is free and obscure, and furthermore, the integrand is a piecewise consistent capacity of the obscure esteem y(T ). This is not a standard optimal control problem and cannot be settled utilizing Pontryagin’s minimum principle with the standard limit conditions at the final time. In the standard issue, a free final state y(T ) yields an important limit condition p(T ) = 0, where p(t) is the costate. Since the integrand is a component of y(T ), the new fundamental condition is that y(T ) yields to be equivalent to a necessary consistent capacity of z. We tackle a case utilizing a C++ shooting method with Newton emphasis for tackling the two point boundary value problem (TPBVP). The limiting free y(T ) value is computed in an external circle emphasis through the golden section method. Compa...
Hybridization of existing competitive modeling methodologiesis now an active area of research.The... more Hybridization of existing competitive modeling methodologiesis now an active area of research.The GMDH algorithm is a heuristic and computer oriented method which provides the foundation for the construction of high order regression models of complex system.The research for improving the effectiveness of forecasting models has never been stopped. Currently it was reported that a hybrid system in prediction and classification achieved a higher performance level against the traditional system. The selection of the forcasting model is the important criteria that will influence to the forcasting accuracy. So the enhancement of conventional GMDH model through hybridization will improve the prediction accuracy of the traditional GMDH for time series forcasting.This paper presents a short overview of Group Method of Data Handling (GMDH),itsmodification and hybridization for time series forecasting.The overviewwill aim to provide further investigation on the hybrid Group Method of Data Hand...
Uploads
Papers by azme khamis