Augustine D. Pwasong

Work place: Universiti Sains Malaysia/School of Mathematical Sciences, Pulau Pinang, 11800, Malaysia

E-mail: davougus@gmail.com

Website:

Research Interests: Neural Networks, Analysis of Algorithms, Models of Computation

Biography

Augustine D. Pwasong was born on October 13, 1974. He obtained a Bachelor of Science degree in Mathematics from the University of Jos, Nigeria and a Masters of Science degree in Statistics from Abubakar Tafawa Balewa University Bauchi, Nigeria, in 2004. Presently, he is a Ph.d student with Universiti Sains Malaysia, in the School of Mathematical Sciences. Currently, he works as a lecture in the department of Mathematics, University of Jos, Nigeria.

He has published several articles in different journals in the fields of Statistics and Neural Networks, some of which include:

Statistical Neural Networks in the Classification of Alcoholic Liver Disease and Nonalcoholic Fatty Liver Disease (International Journal of Computational and Electronic Aspects in Engineering, volume 1, issue 2, 2015); Acceleration of Reverse Analysis Method using Hyperbolic Activation Function (a paper presented at the 22nd Malaysian National Symposium in Mathematics, Shaalam 2014 ); On Fitting a Nonlinear Regression Model for Predicting the Degree of Long Term Recovery after Discharge from the Hospital for Patients with Paralysis, Icastor Journal of Mathematical Sciences, volume 3, issue1, 2009); The Action of the Latin Square Design In Background Music on the Production of Bank Tellers, Journal of Computer Science, volume 10, issue 1)

Author Articles
Forecasting Performance of Random Walk with Drift and Feed Forward Neural Network Models

By Augustine D. Pwasong Saratha Sathasivam

DOI: https://doi.org/10.5815/ijisa.2015.09.07, Pub. Date: 8 Aug. 2015

In this study, linear and nonlinear methods were used to model forecasting performances on the daily crude oil production data of the Nigerian National Petroleum Corporation (NNPC). The linear model considered here is the random walk with drift, while the nonlinear model is the feed forward neural network model. The results indicate that nonlinear methods have better forecasting performance greater than linear methods based on the mean error square sense. The root mean square error (RMSE) and the mean absolute error (MAE) were applied to ascertain the assertion that nonlinear methods have better forecasting performance greater than linear methods. Autocorrelation functions emerging from the increment series, that is, log difference series and difference series of the daily crude oil production data of the NNPC indicates significant autocorrelations. As a result of the foregoing assertion we deduced that the daily crude oil production series of the NNPC is not firmly a random walk process. However, the original daily crude oil production series of the NNPC was considered to be a random walk with drift when we are not trying to forecast immediate values. The analysis for this study was simulated using MATLAB software, version 8.03.

[...] Read more.
Other Articles