Two constrained deconvolution methods using spline functions.

This paper describes two new methods to solve the following estimation problem. Given n1 noisy measurements (yi1, i = 1,..., n1) of the response of a system to a known input [A1(t) where t indicates time], and n2 noisy measurements (yi2, i = 1,..., n2) of the response of a system to an unknown input [A2(t)], obtain an estimate of A2(t) and K(t) (the unit impulse response function of the system) under the model: [formula: see text] where Eij are independent identically distributed random variables. Both methods use spline functions to represent the unknown functions, and they automatically select the spline functions representing the unknown input and unit impulse response functions. The first method estimates separately the unit impulse response function and the input, recasting the problem in terms of inequality-constrained linear regression. The second method jointly estimates the unit impulse response function and the input function, recasting the problem in terms of inequality-constrained nonlinear regression. Simulated and real data analysis are reported.