This study describes an application of Neural Networks for transmission errors identification and correction in binary messages. The network is used as a classifier of detected hydro-acoustic signals into one of a possible alphabet of symbols. The algorithm used is a Hamming-type Neural Networks classifier associated with the transmission of a Hamming code. This system can detect and correct all transmission errors if the number of errors is less than or equal to half the Hamming distance between transmitted symbols minus one. Symbols to be transmitted are chosen and associated to messages, assuring that bit to bit non similarities result on the prescribed Hamming distance. The autoassociative error correcting scheme can be used to generate a teaching signal to a supervised learning equalizer tracking the channel non-stationary characteristics. The proposed system is intended for in hydro-acoustic communication applications, and it is currently undergoing sea tests.
Date of this Version