Abstract:
Provided herein is a method and apparatus for realizing a frequency-spatial filter with variable bandwidth, the method including generating M number of FFT channel blocks having N number of channels by performing an N point FFT (Fast Fourier Transform) processing using M number of array antenna inputs; combining some of the N number of channels of each FFT channel block according to a frequency bandwidth variable parameter value; combining some of spatial response vector channels in a combined channel of each FFT channel block according to a spatial bandwidth variable parameter value; and combining all the channels and outputting the same.
Abstract:
In the present invention, in classifying modulation types of a plurality of modulation signals by using a classifier (an artificial neural network model based on machine learning), the classifier may classify the modulation types of the modulation signals by using pieces of I/Q data, sampled with one sampling frequency, as input data, and thus, may quickly classify the modulation signals.