A Novel GEP Algorithm Based on PCA and Its Application in Predicting the Amount of Gas Emitted from Coalface
Jun Du · Yingyong jichu yu gongcheng kexue xuebao · 2007
Through analyzing Principal Component Analysis(PCA) and Gene Expression Programming(GEP),a novel GEP Algorithm based on PCA is proposed and applied to predict the amount of gas emitted from coalface.The PCA technology is utilized to preprocess the input data and to reduce the dimensionality of the feature space,which thus improves the input factors and eliminates the correlation among the inputs.The GEP technology is then applied to construct the prediction model.The experiment results show that our algorithm is more accurate and stable than several other algorithms,i.e.Genetic Programming(GP) and GEP.