Time Series based Temperature Prediction using Back Propagation with Genetic Algorithm Technique
Shaminder Singh, Pankaj Bhambri, Jasmeen Gill · 2011
Temperature prediction is a temporal and time series based process. Accurate forecasting is important in today’s world as agricultural and industrial sectors are largely dependent on the temperature. Due to non-linearity in climatic physics, neural networks are suitable to predict these meteorological processes. Back propagation integrated with genetic algorithm is the most important algorithm to train neural networks. In this paper, in order to show the dependence of temperature on a particular data series, a time series based temperature prediction model using integrated back propagation with genetic algorithm technique is proposed. In the proposed technique, the effect of under training and over training the system is also shown. The test results of the technique are enlisted along with.