A biologically inspired adaptive underwater target classification using a multi-aspect decision feedback unit

This paper presents a sequential decision feedback approach for target classification in a changing environment. An adaptive target classification system is developed that uses the decisions of multiple aspects (which may not be separated with a fixed known interval) of an object through a tapped delay line mechanism to impact the final decision of the current aspect. This system minimizes the error of the classifier while it maps the new feature vector to a familiar feature space for the classifier. The test results presented are obtained on a wideband acoustic backscattered data set collected using four different objects with 1 degree of aspect separation for two different bottom (smooth and rough) conditions.