A NONLINEAR ADAPTIVE ESTIMATION METHOD BASED ON LOCAL APPROXIMATION

One of the most important problems in signal processing is to estimate the output for a query from the input/output (I/O) data seen so far. This paper presents a nonlinear adaptive estimation method based on th e n-nearest neighbor approach. In this method, observed I/O data are s tored in a database in the form of a k-dimensional binary digital sear ch trie (k-D trie), and a nonlinear local model to answer each query i s derived based on regularization theory, The database contents are ef ficiently time updated to follow nonstationary data, A storage procedu re allowing a simple and efficient update is developed for reduction i n processing time and storage requirement, The effectiveness of the pr oposed method is demonstrated with both simulation data and real speec h signals.