Title :
Artificial neural network robustness for on-board satellite image processing: results of upset simulations and ground tests
Author :
Velazco, R. ; Cheynet, P.H. ; Muller, J.D. ; Ecoffet, R. ; Buchner, S.
Author_Institution :
Lab. Logiciels, Syst., Reseaux, IMAG, Grenoble, France
fDate :
12/1/1997 12:00:00 AM
Abstract :
Artificial Neural Networks have been shown to possess fault tolerant properties. We present the architecture of a neural network designed to process satellite images (SPOT photos). Computer simulations and ground tests performed on a digital implementation of this neural network prove its robustness with respect to bit errors
Keywords :
digital integrated circuits; image texture; integrated circuit testing; neural chips; radiation effects; space vehicle electronics; SPOT photos; artificial neural network robustness; bit errors; fault tolerant properties; ground tests; on-board satellite image processing; upset simulations; Artificial neural networks; Artificial satellites; Computer architecture; Computer errors; Computer simulation; Fault tolerance; Performance evaluation; Process design; Robustness; Testing;
Journal_Title :
Nuclear Science, IEEE Transactions on
