Multi-label spacecraft electrical signal classification method based on DBN and random forest
Fig 2
Flow chart of wavelet denoising.
The principle is that the wavelet coefficients of the original signal are processed by using the threshold value function. The threshold function reflects whether the signal is above or below the threshold of the wavelet coefficients with respect to different processing strategies, and according to different spacecraft electrical characteristic data, hard or soft threshold functions are used to obtain a better filtering denoising effect. The flow chart of wavelet denoising is shown as Fig 2.