Stochastic subspace identification (SSI) is a process that linearizes the identification problem by utilizing singular value decomposition (SVD) and QR factorization. This technique enables the extraction of system matrices through linear least squares. However, the estimated systems in these methods are affected by the user-defined dimensions of the data space (Hankel matrix). Also, SSI does not explicitly minimize a cost function for estimating system matrices, making statistical analysis difficult. To enhance the accuracy of modal specifications obtained from SSI, especially the damping ratios, this research suggests using Output-Error methods (OEM). During OEM, the process involves iteratively adjusting the model parameters to match the Outputs of the simulated model with those of the observed system. The following steps are taken to enhance the OEM for extracting structural properties: Firstly, the initial term is derived using the SSI to reduce the number of optimization iterations. Secondly, by using the Gauss-Newton approach, the nonlinearity of the objective function is reduced by treating the second-order derivatives as a linear system. Finally, Gradient project minimization is utilized in SSI to ensure the injectivity of estimated systems. The OEM was validated by analyzing the response of a 3-DOF excited by white noise with an SNR of 1 db.  Then, the model was then applied to seismic observations of Pacoima Dam during the 2001 San Fernando and 2008 Chino Hills earthquakes. The two main modes of the structure were extracted, and they had the least Error compared to the developed finite element models.

The Error Correcting Output Codes (ECOC) represent any number of the binary classifiers to model the multiclass problems successfully. In this paper, we have used Curve Fitting as a binary classifier in ECOC algorithm to solve multiclass classification problems. Curve Fitting is a classifier based on a nonlinear decision boundary that separates two pattern classes by the curves of the best fit, and arriving at optimal boundary points between two classes. Since we need a coding and a decoding strategy to design an ECOC system, this paper gives five coding and eight decoding strategies of ECOC and compares the results of Curve Fitting with Adaboost classification and Nearest Mean Classifier (NMC). This evaluation has been performed on different data sets of UCI machine learning repository. The results indicate that One-versus-one, ECOC-ONE coding and LAP, BDEN decoding having the best results in contrast with another coding and decoding strategies and Curve Fitting is a good base classifier in ECOC, also it is comparable with the other ECOC approaches.