Filtering of stochastic signal sets: A new piecewise interpolation technique

A new non-linear filtering technique based on an extension of the device of piecewise linear function interpolation is developed. Using the same initial information as is usually used for the Wiener filter (samples of signals), our filter achieves any desired accuracy in signal estimation. The proposed technique provides a single filter to process any signal from an infinite signal set. The filter is determined in terms of pseudo-inverse matrices so that it always exists.