Publish in OALib Journal

ISSN: 2333-9721

APC: Only $99


Any time

2019 ( 4 )

2018 ( 29 )

2017 ( 14 )

2016 ( 33 )

Custom range...

Search Results: 1 - 10 of 3255 matches for " Zuhaimy Hj Ismail "
All listed articles are free for downloading (OA Articles)
Page 1 /3255
Display every page Item
SARIMA Model for Forecasting Malaysian Electricity Generated
Zuhaimy Hj. Ismail,Khairil Asmani Mahpol
Matematika , 2005,
Abstract: Time-series extrapolation which is also known as univariate time series forecasting relies on quantitative methods to analyse data for the variable of interest. Pure extrapolation is based only on values of variable being forecast. We are interested in forecasting the electricity generated for Malaysia. The Tenaga Nasioanl Berhad (TNB) operates an electricity network with the largest capacity of over 7100MW that accounts for over 62% of the total power generation of Peninsular Malaysia. The rest of the power is generated by other Independent Power Producer (IPP). A forecasting model has been developed which identifies seasonal factors in the time-series. Seasonality often accounts for the major part of time series data. In this paper we examine the forecasting perforamnce of Box-Jenkins methodology for SARIMA models and ARIMA models to forecast future electricity generated for Malaysia. We employ the data on the electricity generated at Power Plant to forecast future electricity demand. The error statistics of forecast between the models for a month ahead are presented and behaviour of data is also observed.
Pemodelan Harga Minyak Sayuran Menggunakan Analisis Regresi Linear Berganda
Azme Khamis,Zuhaimy Hj Ismail,Ani Shabri
Matematika , 2003,
Abstract: This study focused on application of multiple regression in modeling vegetable oil prices. Five vegetable oil prices, namely CPO, SBO, CNO, PKO, and RSO have been analysed using monthly oil price data from year 2000. We found that multiple linear regression gave the R2 value of 0.887, meaning 88.7% of variance in CPO price could be explained by RSO, PKO, and CNO. The t-test showed that the parameter estimates is significant at one percent level. This study concluded that multicollinearity and autocorrelation were detected inmuliple linear regression and are needed to be considered in further research.
A decision support system for improving forecast using genetic algorithm and tabu search
Zuhaimy Ismail
Journal of Engineering and Applied Sciences , 2008,
Abstract: The intrinsic uncertainties associated with demand forecasting become more acute when it is required to provide invaluable dimensions for the decision-making process. The concept of decision support system (DSS) is very broad and it can take many different forms. In general, we can say that a DSS is a computerized system for assisting decision making. Forecasting models has been recognized as one of the tools used in DSS. The need and relevance of forecasting tools has become a much-discussed issue and this has led to the development of various new tools and methods for forecasting in the last two decades. One traditional tool for forecasting time series data is the Winter’s method with three parameters that determine the accuracy of the model. The search for the best parameter value of a, b and g and their combinations using trial and error method is time consuming. Hence, a good optimization technique is required to select the best parameter value to minimize the fitness function. We employ the unique search of Genetic Algorithm (GA) to generate and search for the best value and due to the nature of GA that is based on random search; the near optimum solution could be improved by the introduction of a more systematic search known as Tabu Search (TS). Our study shows that combining both GA and TS search methods generate a more accurate forecast.
Comparative Study on Nonlinear Growth Model to Tobacco Leaf Growth Data
Azme Khamis,Zuhaimy Ismail
Journal of Agronomy , 2004,
Abstract: The present study presents to compare the fitting performance of the nonlinear growth models to the tobacco leaf data. Fourteen models are tests to fit the tobacco leaf growth. Fitting performance is measured by sum squares error and root mean squares error. This study found that Weibull, Richards, Inverse Power Transformation Logistics and Simple Logistic models are shown to significantly outperform compare to the other growth models.
A Backpropagation Method for Forecasting Electricity Load Demand
Zuhaimy Ismail,Faridatul Azna Jamaluddin
Journal of Applied Sciences , 2008,
Abstract: This study presents the implementation of back propagation neural network method to improve forecasting of electricity load demand where the demand is highly dependent on various independent variables such as the weather, temperature, holidays, days of the week or even strikes. The implementation of this method requires mathematical software, data preparation and the calculation of degree of freedom, which is necessary for the neural networks architecture. We also consider the use of various combinations of activation functions in input layer to hidden layer and hidden layer to output layer and using analysis of variance and multiple comparison using Duncan`s tests to analyze the neural network`s performance. Two modifications to the backpropagation methods were developed to improve error with selected activation functions and a new improved error using mean square error. The data used are the daily electricity load demand for Malaysian from 2006 to 2007. The forecast accuracy based on the error statistics of forecast between the models for a month ahead is presented and behaviour of data is also observed.
Fitting Nonlinear Gompertz Curve to Tobacco Growth Data
Zuhaimy Ismail,Azme Khamis,Md. Yunus Jaafar
Journal of Agronomy , 2003,
Abstract: This study is to discuss the application of nonlinear Gompertz curve to measure the growth data. Data used are the growth of leaves, stem and roots of tobacco. The sample are divided into two and measured in kilograms. By using specific starting values, it is found that the nonlinear Gompertz curve is suitable to match the growth of leaves, stem and roots of tobacco plant. It is found that both samples have the sum squares error, which is low and the variance analysis conducted showing that this model is statistically significant. Furthermore, it is supported by the as asymptotic correlation matrix value among the parameter estimated much lower.
The use of response surface analysis in obtaining maximum profit in oil palm industry
Azme Khamis,Zuhaimy Ismail,Khalid Haron,Ahmad Tarmizi Mohammed
Songklanakarin Journal of Science and Technology , 2006,
Abstract: This study was conducted to show how to use Response Surface Analysis in obtaining the optimum level of fertilizer needs by oil palm. The ridge analysis was proposed to overcome the saddle point problem. Data from Malaysian Palm Oil Board database was analyzed. The fertilizers considered are N, P, K and Mg. The results from ridge analysis provided several alternatives of the fertilizer combination. Profit analysis was then applied to determine the best combination of fertilizers needed by the oil palm in order to generate maximum profit. It is found that N and K fertilizers were the important fertilizers required by the oil palm. It is also found that the N and K nutrient concentrations of the foliar nutrient composition were higher compared to other nutrients. Three different stations were considered and it was found that the fertilizersneeded by the oil palm and foliar nutrient composition were different at the different type of soil series.
Neural Network Model for Oil Palm Yield Modeling
Azme Khamis,Zuhaimy Ismail,Khalid Haron,Ahmad Tarmizi Mohammed
Journal of Applied Sciences , 2006,
Abstract: This research presents a study on the development of a model for oil palm yield using neural network approach. The structure of this neural network requires the identification of the input variables and the output. We identified that the percentages of nitrogen, phosphorus, potassium, calcium and magnesium in leave were used as input variables and fresh fruit bunch was used as the target variable. An investigation of the combinations of activation function in the input layer to the hidden layer and the hidden layer to the output layer found that each combination also affects the neural network performance. The effect of the learning rate, momentum term, number of runs and number of hidden nodes was also investigated. The number of hidden nodes was found to significantly affect the neural network performance. However, the learning rate, momentum term and number of runs were found to have an insignificant effect on the neural network performance. Using R2 values the suitability of the models were measured. Results demonstrate that the neural network model outperformed regression analysis, which can be considered as alternative in modeling of oil palm yield.
The Effects of Outliers Data on Neural Network Performance
Azme Khamis,Zuhaimy Ismail,Khalid Haron,Ahmad Tarmizi Mohammed
Journal of Applied Sciences , 2005,
Abstract: The study was carried out to investigate the influence of outliers on neural network performance in two ways; by examining the percentage outliers and secondly the magnitude outliers. The results of two experiments, training and test data are reported. For training data set, shows that the percentage outliers (ranging from 5 to 30%) and the magnitude of outliers (ranging from μ ± 2 to ± 4 σ ) are statistically significant affected on the modeling accuracy. For test data set, the results show that percentage outliers and magnitude outliers in the used to build the model affect the neural network performance.
Modeling Oil Palm Yield Using Multiple Linear Regression and Robust M-regression
Azme Khamis,Zuhaimy Ismail,Khalid Haron,Ahmad Tarmizi Mohammed
Journal of Agronomy , 2006,
Abstract: This study shows how a multiple linear regression model can be used to model palm oil yield. The methods are illustrated by examining the time series data of foliar nutrient compositions as one of the independent variable and fresh fruit bunch as dependent variable. Other independent variables include the nutrient balance ratio and major nutrient composition. This modeling approach is capable of identifying the significant contribution of each independent variable in the improving the modeling performance. We find that the quantile-quantile plot demonstrates the existing of outlier and this directs us to use robust M-regression for removing the negative impact of outliers. Results show that robust regression in this case gives a better results than conventional regression in modeling oil palm yield.
Page 1 /3255
Display every page Item

Copyright © 2008-2017 Open Access Library. All rights reserved.