Fast greedy optimization of sensor selection in measurement with correlated noise

A greedy algorithm is proposed for sparse-sensor selection in reduced-order sensing that contains correlated noise measurement. The sensor carried out by maximizing the determinant of Fisher information matrix a Bayesian estimation operator.The with covariance measurement and prior probability distribution estimating parameters, which are given modal decomposition high dimensional data, robustly works even presence noise. After computational efficiency improved low-rank approximation matrix, algorithms applied to various problems. method yields more accurate reconstruction than previously presented determinant-based algorithm, reasonable increase time.