Neural networks prediction of electrical signals at xylem in Osmanthus fragrans

Plant weak electrical signals in the xylem of Osmanthus fragrans were tested by a touching test system of self-made double shields with platinum sensors. Tested data of electrical signals denoised by the wavelet soft threshold and using Gaussian radial base function (RBF) as the time series at a delayed input window chosen at 50. An intelligent RBF forecasting system was constructed to forecast the signals in the xylem. Through the study of 1450 stylebooks that used the electrical signal after de-noised in the xylem, the effect on the inner examination of the obtained RBF neural network was very well in coincidence with and can be used for a forecast of the plant electrical signal at the time domain in the timing. Result shows that it is feasible to forecast the plant growth for a short period. The forecast data can be used as an important preference for the intelligent automatic control system based on the adaptive characteristic of xylem in plants to achieve the energy saving on agricultural production both the greenhouse and /or the plastic lookum.