A PARAFAC-based channel estimation method was proposed for two-hop amplify-and-forward (AF) multiple-input multiple-output (MIMO) relay systems. Through constructing PARAFAC model to the received signal matrices,full channel state information (CSI) involved in the communication can be estimated at the destination node by using the proposed optimal complex value alternating least-squares (CALS) algorithm.Comparison with existing approaches showed that the proposed method requires less number of training data blocks and has higher channel estimation accuracy.Simulation results demonstrated the effectiveness of the proposed channel estimation method.
