Automatic recognition of multiple interferences and signals in the same channel based on ICA

It is a common problem in practice that automatic recognition of multiple interferences and signals in the same channel. This paper presents an automatic recognition method to deal with the problem of 2 signals (QPSK and 4FSK) and 4 interferences (single tone, multi-tone, gauss interference and pulse interference) mixing in the same channel. FastICA algorithm is adopted to separate the mixed interference signals at first, and then select the features of each signal and interference in time domain, frequency domain, high-order cumulant domain and time-frequency domain to complete the recognition of the interference signals. Finally, the computer simulation proves the automatic recognition algorithm´s correctness and validity.