Modelling for Engineering , & Human Behaviour 2014

In this research work, a practical new hybrid model to predictthe successful growth cycle of Spirulina platensis was proposed. Themodel was based on particle swarm optimization (PSO) in combina-tion with support vector machines (SVM). This optimization mecha-nism involved kernel parameter setting in the SVM training procedure,which significantly influences the regression accuracy. PSO–SVM–based models were successfully used here to predict the Chlorophylla (Chl-a) concentration (output variable) as a function of the fol-lowing input variables: pH, optical density, oxygen concentration, ni-trate concentration, phosphate concentration, salinity, water temper-ature and irradiance. Regression with three different kernels (linear,quadratic and RBF) was performed and determination coefficients of0.94, 0.97, and 0.99, respectively, were obtained. Finally, conclusionsof this study are exposed.∗e-mail: [email protected] (P.J. Garćıa Nieto)