Blind Source Separation with a Time-Varying Mixing Matrix

Blind source separation (BSS) is the process of using multiple sensors to separate multiple random signals from a received linear combination. In this paper, we apply blind source separation techniques to mixtures of digital communications signals. We predict the achievable symbol error rate when the signals are received on the same carrier frequency and blindly separated. In a wireless environment where the sources are mobile or the environment is changing, the mixing matrix will vary with time. Our primary contribution is that we identify the major source of error in separation. We extend an adaptive step size algorithm to the complex-valued case to mitigate the errors in a dynamic environment.