Full-Duplex Gigabit Ethernet Signal Separation Using LSTM

This research explores the ability of machine learning to perform signal separation of an Ethernet style encoded, full-duplex communication. Typical signal separation currently requires an active tap of the communication line, followed by a recombination and retransmission of the data. The purpose of this research is to study a passive approach to the acquisition of data from a full-duplex signal. The machine learning model used in this research is a long-short-term memory recurrent neural network (LSTM-RNN). The results show that the LSTM able to recreate the transmission signal from the measured data points, with a point-wise error having a mean of 0.00186 V and standard deviation of 0.102 V. The separated signals have not yet been tested using a decoding method.