A multilayered ANN architecture for underwater target tracking
Yuyang Jing, El-Hawary · 1994
A multilayered artificial neural network (ANN) is proposed for tracking underwater targets. A method using a feedforward network is presented to obtain state estimates from the time series of measurements. We shifted the time series observations before presentation to the ANN input and the simulation results show that the ANN tracker achieved a satisfactory degree of accuracy and robustness in dealing with noise in the measurements.>