• The Korean Journal of Applied Statistics
• /
• v.35 no.5
• /
• pp.657-666
• /
• 2022

An informative predictor subspace is useful to estimate the central subspace, when conditions required in usual suffcient dimension reduction methods fail. Recently, for multivariate regression, Ko and Yoo (2022) newly defined a projective-resampling informative predictor subspace, instead of the informative predictor subspace, by the adopting projective-resampling method (Li et al. 2008). The new space is contained in the informative predictor subspace but contains the central subspace. In this paper, a method directly to estimate the informative predictor subspace is proposed, and it is compapred with the method by Ko and Yoo (2022) through theoretical aspects and numerical studies. The numerical studies confirm that the Ko-Yoo method is better in the estimation of the central subspace than the proposed method and is more efficient in sense that the former has less variation in the estimation.

• ETRI Journal
• /
• v.32 no.6
• /
• pp.921-931
• /
• 2010

It has been shown that the principal subspace-based multichannel Wiener filter (MWF) provides better performance than the conventional MWF for suppressing interference in the case of a single target source. It can efficiently estimate the target speech component in the principal subspace which estimates the acoustic transfer function up to a scaling factor. However, as the input signal-to-interference ratio (SIR) becomes lower, larger errors are incurred in the estimation of the acoustic transfer function by the principal subspace method, degrading the performance in interference suppression. In order to alleviate this problem, a principal subspace modification method was proposed in previous work. The principal subspace modification reduces the estimation error of the acoustic transfer function vector at low SIRs. In this work, a frequency-band dependent interpolation technique is further employed for the principal subspace modification. The speech recognition test is also conducted using the Sphinx-4 system and demonstrates the practical usefulness of the proposed method as a front processing for the speech recognizer in a distant-talking and interferer-present environment.

• Journal of Information Technology Services
• /
• v.14 no.4
• /
• pp.121-135
• /
• 2015

Ensemble classification is to utilize multiple classifiers instead of using a single classifier. Recently ensemble classifiers have attracted much attention in data mining community. Ensemble learning techniques has been proved to be very useful for improving the prediction accuracy. Bagging, boosting and random subspace are the most popular ensemble methods. In random subspace, each base classifier is trained on a randomly chosen feature subspace of the original feature space. The outputs of different base classifiers are aggregated together usually by a simple majority vote. In this study, we applied the random subspace method to the bankruptcy problem. Moreover, we proposed a method for optimizing the random subspace ensemble. The genetic algorithm was used to optimize classifier subset of random subspace ensemble for bankruptcy prediction. This paper applied the proposed genetic algorithm based random subspace ensemble model to the bankruptcy prediction problem using a real data set and compared it with other models. Experimental results showed the proposed model outperformed the other models.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2143-2145
• /
• 2003

In the linear system identification using the discrete time constant coefficients, there is a subspace method based on 4SID recently much suggested instead of the parametric method like as the maximum likelihood method. The subspace method is not related with the impulse response and difference equation in its input-output equation, but with the system matrix of the direct state space model from the input-output data. The subspace method is a very useful tool to adopt in the multivariable system identification, but it has a shortage unable to adopt in the closed-loop system identification. In this paper, we are suggested the methods to get rid of the shortage of the subspace method in the closed-loop system identification. The subspace method is used in the estimate of the output prediction values from the estimating of the state space vector. And we have compared the results with the outputs of the recursive least square method in the numerical simulation.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.05a
• /
• pp.784-787
• /
• 2004

Modified version of subspace iteration method using accelerated starting vectors is proposed to efficiently calculate free vibration modes of structures. Proposed method employs accelerated Lanczos starting vectors that can reduce the number of iterations in the subspace iteration method. Proposed method is more efficient than the conventional method when the number of required modes is relatively small. To verify the efficiency of proposed method, two numerical examples are presented.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2003.10a
• /
• pp.503-508
• /
• 2003

This paper proposes modified subspace iteration method for efficient frequency analysis of structures. Proposed method uses accelerated Lanczos vectors as starting vectors in order to reduce the number of iterations in the subspace iteration method. Proposed method has better computing efficiency than the conventional method when the number of desired frequencies is relatively small. The efficiency of proposed method is verified through numerical examples.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.1
• /
• pp.105-115
• /
• 2016

Ensemble classification involves combining individually trained classifiers to yield more accurate prediction, compared with individual models. Ensemble techniques are very useful for improving the generalization ability of classifiers. The random subspace ensemble technique is a simple but effective method for constructing ensemble classifiers; it involves randomly drawing some of the features from each classifier in the ensemble. The instance selection technique involves selecting critical instances while deleting and removing irrelevant and noisy instances from the original dataset. The instance selection and random subspace methods are both well known in the field of data mining and have proven to be very effective in many applications. However, few studies have focused on integrating the instance selection and random subspace methods. Therefore, this study proposed a new hybrid ensemble model that integrates instance selection and random subspace techniques using genetic algorithms (GAs) to improve the performance of a random subspace ensemble model. GAs are used to select optimal (or near optimal) instances, which are used as input data for the random subspace ensemble model. The proposed model was applied to both Kaggle credit data and corporate credit data, and the results were compared with those of other models to investigate performance in terms of classification accuracy, levels of diversity, and average classification rates of base classifiers in the ensemble. The experimental results demonstrated that the proposed model outperformed other models including the single model, the instance selection model, and the original random subspace ensemble model.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1998.10a
• /
• pp.84-91
• /
• 1998

A numerically stable technique to remove tile limitation in choosing a shift in the subspace iteration method with shift is presented. A major difficulty of the subspace iteration method with shift is that because of singularity problem, a shift close to an eigenvalue can not be used, resulting in slower convergence. This study selves the above singularity problem using side conditions without sacrifice of convergence. The method is always nonsingular even if a shiht is an eigenvalue itself. This is one of tile significant characteristics of the proposed method. The nonsingularity is proved analytically. The convergence of the proposed method is at least equal to that of the subspace iteration method with shift, and the operation counts of above two methods are almost the same when a large number of eigenpairs are required. To show the effectiveness of the proposed method, two numerical examples are considered

• 한국전산유체공학회:학술대회논문집
• /
• 1999.05a
• /
• pp.106-112
• /
• 1999

In this article, combination of the FAS-FMG multi-grid method and the Krylov subspace method was presented in solving two dimensional driven-cavity flows. Three algorithms of the Krylov subspace method, CG, CGSTAB(Bi-CG Stabilized) and GMRES method were tested with MILU preconditioner. As a smoother of the pressure correction equation, the MILU-CG is recommended rather than MILU-GMRES(k) or MILU-CGSTAB, since the MILU-GMRES(k) preconditioner has too much computation on the coarse grid compared to the MILU-CG one. As for the momentum equation, relatively cheap smoother like SIP solver may be sufficient.

• Journal of applied mathematics & informatics
• /
• v.4 no.1
• /
• pp.243-248
• /
• 1997

A full multigrid scheme was used in computing some eigenvalues of the Laplace eigenvalues problem with the Dirichlet bound-ary condition. We get a system of algebraic equations with an aid of finite difference method and apply subspace iteration method to the system to compute first some eigenvalues. The result shows that this is very effective in calculating some eigenvalues of this problem.