M. Karny et K. Warwick, SYSTEM-IDENTIFICATION USING PARTITIONED LEAST-SQUARES, IEE proceedings. Control theory and applications, 142(3), 1995, pp. 223-228
A novel partitioned least squares (PLS) algorithm is presented, in whi
ch estimates from several simple system models are combined by means o
f a Bayesian methodology of pooling partial knowledge. The method has
the added advantage that, when the simple models are of a similar stru
cture, it lends itself directly to parallel processing procedures, the
reby speeding up the entire parameter estimation process by several fa
ctors.