RBF neural networks analysis on electrical signal in Chrysanthemum coronarium

Original weak electrical signals in Chrysanthemum coronarium 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 set up to forecast the signal in plants. Testing result shows that the signal in C. coronarium is a sort of weak, low frequency and un-placidity signals. It is feasible to forecast the plant electrical signal for a short period. The forecast data can be used as an important preferences for the intelligent automatic control system based on the adaptive characteristic of plants to achieve the energy saving on agricultural production both the greenhouse and /or the plastic lookum.