We apply independent component analysis (ICA) to the real data of gravita- tional wave detector for the first time. ICA separates various sources of signals from multiple detection channels making use of non-Gaussian natures of the statistical distributions of the sources. Specifically we use iKAGRA data taken in April 2016, and calculate the correlations between the gravitational wave strain channel and 13000 environmental channels. Using a couple of seismic channels which are found to be strongly correlated with the strain, we perform ICA. Specifically, injecting sinusoidal continuous signal in the strain channel, we find that ICA recovers correct parameters with enhanced signal-to-noise ratio, which demonstrates usefulness of this method.