THE USE OF ARTIFICIAL INTELLIGENCE FOR TORPEDO DETECTION

DESPITE THE FACT THAT TORPEDO ACOUSTIC SIGNATURES HAVE VERY SPECIFIC CHARACTERISTICS, IT HAS BEEN DIFFICULT TO DEVELOP AN AUTOMATED TORPEDO DETECTION SYSTEM WITH A HIGH PROBABILITY OF DETECTION AND AT THE SAME TIME A LOW PROBABILITY OF FALSE ALARM. SCT BELIEVES THAT BY ADAPTING THE SES: A SONAR EXPERT SYSTEM TO ACOUSTIC TORPEDO DATA, IT WILL BE POSSIBLE TO PERFORM RELIABLE AUTOMATIC TORPEDO DETECTION. THE BASIS OF SES IS TO EXTRACTION THE RIGHT FEATURES FROM THE ACOUSTIC DATA AND APPLY THE PROPER LOGICAL COMBINATIONS TO THOSE FEATURES TO PERFORM ACCURATE SIGNATURE INTERPREATION. CURRENTLY SES IS BEING APPLIED TO THE PROBLEM OF INTERPRETING RECORDED REAL DATA FROM THE SQR-19 SENSOR AND HAS BEEN SUCCESSFULLY DEMONSTRATED IN THE USE OF ARTIFICIAL INTELLIGENCE TECHNOLOGY TO PERFORM LINE ASSOCIATION AND SIGNATURE CLASSIFICATION. THE STEPS NECESSARY TO ADAPT SES TO THE PROBLEM OF TORPEDO DETECTION ARE TO DEFINE TORPEDO SIGNATURE CHARACTERISTICS, ENHANCE THE LOGIC IN SES TO ACCURATELY DISCRIMINATE THESE CHARACTERISTICS FROM OTHER ACOUSTIC SIGNALS, AND TO DEMONSTRATE THE CAPABILITY TO PROVIDE A CLEAR CUT DECISION ABOUT THE PRESENCE OF A TORPEDO IN PASSIVE ACOUSTIC DATA.