Weak Electrical Signals of the Jasmine Processed by RBF Neural Networks Forecast

A touching test system of self-made double shields with platinum sensors was constructed to test original weak electrical signals in the jasmine. Tested data of electrical signals denoised by the wavelet soft threshold firstly and then using Gaussian radial base function (RBF) as 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 spectrum of signals of the jasmine was <4.0 Hz. The signal of the jasmine is a sort of weak, low frequency and un-placidity signals. The de-noised method for processing the weak electric signal of plants is effectively and it is feasible to forecast the plant electrical signals for a short period. The forecast data can be used as an important preference for the intelligent 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. It is not only an important calculating parameter, but also provides a novel content and method in microelectronics and bioinformatics respectively.