Fast Independent Component Analysis Based Digital Modulation Recognition Method

This paper proposes an efficient independent component analysis (ICA) based modulation feature extraction method applied in digital modulation identification. In modulation identification, important information may be contained in the high-order relationship among sampling points. ICA is sensitive to high-order statistic in the data and finds not-necessarily orthogonal bases, so it may better identify and reconstruct high-dimensional communication signal data than traditional time and frequency domain features. ICA algorithms are time-consuming and sometimes converge difficultly. So a modified FastICA algorithm is developed in this paper, which only need to computer Jacobian Matrix once time in one iteration and achieves the correspondent effect of FastICA. After obtaining all independent components, a genetic algorithm is introduced to select optimal independent components (ICs). The experiment results show that modified FastICA algorithm fast convergence speed and genetic algorithm optimize recognition performance. ICA based features extraction method is innovative and promising for digital modulation identification.