Abstract
A current problem in the development of passive sonar is the classification of different noise sources. The existing Automatic Underwater Target Recognition Technique (AURT) is mainly based on spectrum analysis of radiated noise in passive sonar. However, with the development of noise control techniques, the radiated noise of underwater targets have been reduced enormously in the past few years, even the working states of the same target also weaken the stationarity of spectrum features of its radiated noise. The objective of this paper concentrates on the AURT with multi-method analysis on radiated noise and decision-makings fusion. A kind of multi-classifier decision-makings fusion model to overcome the non-stationarity is presented. Its application of the model on the data derived from sea trial confirms its validation even in the case of low SNR, and the classification rate is above 83%, better than that of spectrum analysis only.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
