RBF neural networks prediction on weak electrical signals in Catharanthus roseus

Taking electrical signals in the Catharanthus roseus as the time series and using the Gaussian radial base function (RBF) and a delayed input window chosen at 50, an intelligent RBF forecast system is set up to forecast signals by the wavelet soft-threshold de-noised backward. It is obvious that the electrical signal in Catharanthus roseus is a sort of weak, unstable and low frequency signals. There is the maximum amplitude at 595.40 muV, minimum-145.35 muV, average value -2.01 muV; and below 0.3 Hz at frequency in the Catharanthus roseus respectively. A result shows that it is feasible to forecast plant electrical signals for the timing by using of the RBF neural network. The forecast data can be used as the important preferences for the intelligent automatic control system based on the adaptive characteristic of plants to achieve the energy saving on the agricultural production in the greenhouse and /or the plastic lookum.