- Full text PDF available (2)
—We consider one single antenna transmitter communicating with a receiver with a large number of antennas. Motivated by the optimal noncoherent detector in a Rayleigh fading channel, we propose a noncoherent energy-based communication scheme that does not require knowledge of instantaneous CSI (channel state information) at either the transmitter or the… (More)
In this paper we examined four different methods for time series forecasting: Random Forests, Gradient Boosting, Hidden Markov Models, and Recurrent Neural Networks. We found that using Gradient Boosting yielded the best results with root-mean-square percent error (RMPSE) of 10.439% (785 of 3429).