Neural Networks Initial Weights Optimisation

Authors:
A. J. Al-Shareef;M. F. Abbod
Affiliations:
-;-
Venue:
UKSIM '10 Proceedings of the 2010 12th International Conference on Computer Modelling and Simulation
Year:
2010

Citing 0
Cited 2

Optimization the initial weights of artificial neural networks via genetic algorithm applied to hip bone fracture prediction

Advances in Fuzzy Systems - Special issue on Hybrid Biomedical Intelligent Systems
Global Artificial Bee Colony-Levenberq-Marquardt GABC-LM Algorithm for Classification

International Journal of Applied Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Artificial Neural Networks (ANN) have lately received much attention, and a great number of papers have reported successful experiments and practical tests. This paper presents the development of a simple ANN topology for load forecasting model with much improved accuracy for the Regional Power Control Centre of Saudi Electricity Company. The proposed system is based on optimising the initial random weights of the ANN using Particle Swarm Optimisation (PSO). Results have shown higher modelling accuracy compared to standard ANN, weight optimised ANN, and ANN committee machine models. The networks were trained with weather-related, time based and special events indexes for electric load data from the calendar years 2005 to 2007.