Artificial neural network robustness for on-board satellite image processing: Results of upset simulations and ground tests

被引：13

作者：

Velazco, R

Cheynet, P

Muller, JD

Ecoffet, R

Buchner, S

机构：

[1] IMAG, LSR, Lab Logiciels, F-38031 Grenoble, France

[2] CEA, DAM, DRIF, DCRE,SEIM, F-91680 Bruyeres Le Chatel, France

[3] Ctr Natl Etud Spatiales, CT, AQ, CE, F-31055 Toulouse, France

[4] USN, Res Labs, SFA Inc, Largo, MD 20774 USA

来源：

IEEE TRANSACTIONS ON NUCLEAR SCIENCE | 1997年 / 44卷 / 06期

关键词：

D O I：

10.1109/23.659057

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

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.

引用

页码：2337 / 2344

页数：8

共 15 条

[1]

ANDERSPIEGEL J, 1994, P IEEE INT C NEUR NE, P1830

[2]

[Anonymous], 1986, PARALLEL DISTRIBUTED

[3] Robustness against SEU of an artificial neural network space application [J].

Assoum, A ;

Radi, NE ;

Velazco, R ;

Elie, F ;

Ecoffet, R .

IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 1996, 43 (03) :973-978

[4]

DEVILLE Y, 1995, P INT C ART NEUR NET

[5]

KERLIRZIN P, 1994, THESIS U PARIS 11 OR

[6]

Kilpatricks D., 1995, P IEEE INT C NEUR NE, P32

[7]

KWIATKOWSKA IS, 1995, P IEEE INT C NEUR NE, P1907

[8] A HIGH-SPEED ANALOG NEURAL PROCESSOR [J].

MASA, P ;

HOEN, K ;

WALLINGA, H .

IEEE MICRO, 1994, 14 (03) :40-50

[9] EQUATION OF STATE CALCULATIONS BY FAST COMPUTING MACHINES [J].

METROPOLIS, N ;

ROSENBLUTH, AW ;

ROSENBLUTH, MN ;

TELLER, AH ;

TELLER, E .

JOURNAL OF CHEMICAL PHYSICS, 1953, 21 (06) :1087-1092

[10] A neural network approach to the classification of electron and proton whistlers [J].

Miniere, X ;

Pincon, JL ;

Lefeuvre, F .

JOURNAL OF ATMOSPHERIC AND TERRESTRIAL PHYSICS, 1996, 58 (07) :911-924

← 1 2 →