ENHANCED ABC-LSSVM FOR ENERGY FUEL PRICE PREDICTION
Keywords:Artificial bee colony, least squares support vector machines, levy probability distribution, prediction
AbstractThis paper presents an enhanced Artificial Bee Colony (eABC) based on LÃ©vy Probability Distribution (LPD) and conventional mutation. The purposes of enhancement are to enrich the searching behavior of the bees in the search space and prevent premature convergence. Such an approach is used to improve the performance of the original ABC in optimizing the embedded hyper-parameters of Least Squares Support Vector Machines (LSSVM). Later on, a procedure is put forward to serve as a prediction tool to solve prediction task. To evaluate the efficiency of the proposed model, crude oil prices data was employed as empirical data and a comparison against four approaches were conducted, which include standard ABC-LSSVM, Genetic Algorithm-LSSVM (GA-LSSVM), Cross Validation-LSSVM (CV-LSSVM), and conventional Back Propagation Neural Network (BPNN). From the experiment that was conducted, the proposed eABC-LSSVM shows encouraging results in optimizing parameters of interest by producing higher prediction accuracy for employed time series data.
How to Cite
Mustaffa, Z., Yusof, Y., & Kamaruddin, S. S. (2013). ENHANCED ABC-LSSVM FOR ENERGY FUEL PRICE PREDICTION. Journal of Information and Communication Technology, 12, 73–101. Retrieved from https://e-journal.uum.edu.my/index.php/jict/article/view/8138