A data extrapolation algorithm using a complex domain neural network

Abstract

Many applications make use of the discrete Fourier transform (DFT) during data manipulation. The resolution for such applications is inversely proportional to the available data length used during the DFT. Resolution can be improved by modeling and then implicitly or explicitly extrapolating the known data to increase its effective length prior to the application of the DFT. A new data extrapolation algorithm based on a complex-domain feedforward neural network is detailed in this brief. The complex back-propagation algorithm used to train the network includes adaptive learning and momentum methods normally found in real-valued neural networks. Approaches to increase the extrapolation stability are discussed. The success of the algorithm is demonstrated by using short data sets to reconstruct phantom and medical magnetic resonance images which suffer from severe artifacts when reconstructed by the standard Fourier technique.