Channel state information (CSI) is fundamental to the performance of massive multiple-input multiple-output systems. However, systems that rely on pilots for the CSI estimation are susceptible to pilot contamination, as neighboring cells may reuse the same pilot sequences. Independent component analysis (ICA) has been widely used in recent studies to perform blind decoding, in order to circumvent the effects of pilot contamination. In this letter, we introduce a modified version of fastICA, the phase corrected ICA that reduces phase rotation on the estimated constellations, and thus, results in better performance of blind receivers. Through simulations, we show that our method significantly reduces symbol error rates compared to standard ICA based methods. Furthermore, we show that the increase in complexity is small at high signal-to-noise rate.

The computation of the achievable sum rate for integer-forcing (IF) linear receivers requires the search for the shortest set of linearly independent lattice vectors (SIVP). Since SIVP is considered an NP-hard problem, we propose two approximations to the IF achievable sum rate. The first approximation is suitable for systems with two antennas at both transmitter and receiver (2 × 2 arrays) and is based on the analysis of the Gauss-Lagrange algorithm. The second approximation considers n × n array systems and is based on Minkowski's second theorem. Assuming a block-fading channel with Rayleigh distribution, we have derived the exact probability density function of both approximations. We have used these results to obtain the mean sum-rate, outage probability, and outage rate for uncorrelated fading channels. For the second approximation, the effect of channel correlation on these metrics was also analyzed. An exhaustive series of simulations have been conducted to assess the tightness and robustness of both solutions.