• Wind and Structures
• /
• v.21 no.6
• /
• pp.693-707
• /
• 2015

The efficiency of wind turbines (WT) is primarily reflected in their ability to generate electricity at any time. Downtimes of WTs due to "conventional" inspections are cost-intensive and undesirable for investors. For this reason, there is a need for structural health monitoring (SHM) systems, to enable service and maintenance on demand and to increase the inspection intervals. In general, monitoring increases the cost effectiveness of WTs. This publication concentrates on the application of two vibration-based SHM algorithms for stability and structural change monitoring of offshore WTs. Only data driven, output-only algorithms based on stochastic subspace identification (SSI) in time domain are considered. The centerpiece of this paper deals with the rough mathematical description of the dynamic behavior of offshore WTs and with the basic presentation of stochastic subspace-based algorithms and their application to these structures. Due to the early stage of the industrial application of SHM on offshore WT on the one side and the required confidentiality to the plant manufacturer and operator on the other side, up to now it is not possible to analyze different isolated structural damages resp. changes in a systematic manner, directly by means of in-situ measurement and to make these "acknowledgements" publicly available. For this reason, the sensitivity of the methods for monitoring purposes are demonstrated through their application on long time measurements from a 1:10 large scale test rig of an offshore WT under different conditions: undamaged, different levels of loosened bolt connections between tower parts, different levels of fouling, scouring and structure inclination. The limitation and further requirements for the approaches and their applicability on real foundations are discussed along the paper.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.7C
• /
• pp.428-434
• /
• 2011

Recently, subspace analysis has raised its performance to a higher level through the adoption of kernel-based nonlinearity. Especially, the radial basis function, based on its nonparametric nature, has shown promising results in face recognition. However, due to the endemic small sample size problem of face data, the conventional kernel-based feature extraction methods have difficulty in data representation. In this paper, we introduce a novel variant of the RBF kernel to alleviate this problem. By adopting the concept of the nearest feature line classifier, we show both effectiveness and generalizability of the proposed method, particularly regarding the small sample size issue.

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 2006.06a
• /
• pp.251-257
• /
• 2006

The performance of face recognition methods using subspace projection is directly related to the characteristics of their basis images, especially in the cases of local distortion or partial occlusion. In order for a subspace projection method to be robust to local distortion and partial occlusion, the basis images generated by the method should exhibit a part-based local representation. We propose an effective part-based local representation method named locally salient ICA (LS-ICA) method for face recognition that is robust to local distortion and partial occlusion. The LS-ICA method only employs locally salient information from important facial parts in order to maximize the benefit of applying the idea of 'recognition by parts.' It creates part-based local basis images by imposing additional localization constraint in the process of computing ICA architecture I basis images. We have contrasted the LS-ICA method with other part-based representations such as LNMF (Localized Non-negative Matrix Factorization)and LFA (Local Feature Analysis). Experimental results show that the LS-ICA method performs better than PCA, ICA architecture I, ICA architecture II, LFA, and LNMF methods, especially in the cases of partial occlusions and local distortion

• Smart Structures and Systems
• /
• v.23 no.1
• /
• pp.15-29
• /
• 2019

This paper addresses the problem of damage detection in suspension bridge hangers, with an emphasis on the modal flexibility method. It aims at evaluating the capability and the accuracy of the modal flexibility method to detect and locate single and multiple damages in suspension bridge hangers, with different level of severity and various locations. The study is conducted numerically and experimentally on a laboratory suspension bridge mock-up. First, the covariance-driven stochastic subspace identification is used to extract the modal parameters of the bridge from experimental data, using only output measurements data from ambient vibration. Then, the method is demonstrated for several damage scenarios and compared against other classical methods, such as: Coordinate Modal Assurance Criterion (COMAC), Enhanced Coordinate Modal Assurance Criterion (ECOMAC), Mode Shape Curvature (MSC) and Modal Strain Energy (MSE). The paper demonstrates the relative merits and shortcomings of these methods which play a significant role in the damage detection ofsuspension bridges.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.25-34
• /
• 2010

Robust face recognition under various illumination environments is difficult to achieve. For robust face recognition with respect to illumination variations, illumination normalization of face images is usually applied as a preprocessing step. Most of previously proposed illumination normalization methods cannot handle cast shadows in face images effectively. In this paper, We propose a new face illumination normalization method based on the illumination-separated face identity texture subspace. Since the face identity texture subspace is constructed so as to be separated from the effects of illumination variations, the projection of face images into the subspace produces a good illumination-normalized face images. Through experiments, it is shown that the proposed face illumination normalization method can effectively eliminate cast shadows as well as attached shadows and achieves a good face illumination normalization.

• Journal of International Society for Simulation Surgery
• /
• v.2 no.2
• /
• pp.64-66
• /
• 2015

Purpose : In this paper we proposed cascade feature filter and projection method for rapid human face recognition for the large-scale high-dimensional face database. Materials and Methods : The relevant features are selected from the large feature set using Fast Correlation-Based Filter method. After feature selection, project them into discriminant using Principal Component Analysis or Linear Discriminant Analysis. Their cascade method reduces the time-complexity without significant degradation of the performance. Results : In our experiments, the ORL database and the extended Yale face database b were used for evaluation. On the ORL database, the processing time was approximately 30-times faster than typical approach with recognition rate 94.22% and on the extended Yale face database b, the processing time was approximately 300-times faster than typical approach with recognition rate 98.74 %. Conclusion : The recognition rate and time-complexity of the proposed method is suitable for real-time face recognition system on the large-scale high-dimensional face database.

• Communications for Statistical Applications and Methods
• /
• v.11 no.2
• /
• pp.275-285
• /
• 2004

We explore classification analysis using graphical methods such as sliced inverse regression and sliced average variance estimation based on dimension reduction. Some useful information about classification analysis are obtained by sliced inverse regression and sliced average variance estimation through dimension reduction. Two examples are illustrated, and classification rates by sliced inverse regression and sliced average variance estimation are compared with those by discriminant analysis and logistic regression.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.177-187
• /
• 2014

This paper proposes a fast subspace tracking methods, which is called GVFF FAPI, based on FAPI (Fast Approximated Power Iteration) method and GVFF RLS (Gradient-based Variable Forgetting Factor Recursive Lease Squares). Since the conventional FAPI uses a constant forgetting factor for estimating covariance matrix of source signals, it has difficulty in applying to non-stationary environments such as continuously changing DOAs of source signals. To overcome the drawback of conventioanl FAPI method, the GVFF FAPI uses the gradient-based variable forgetting factor derived from an improved means square error (MSE) analysis of RLS. In order to achieve the decreased subspace error in non-stationary environments, the GVFF-FAPI algorithm used an improved forgetting factor updating equation that can produce a fast decreasing forgetting factor when the gradient is positive and a slowly increasing forgetting factor when the gradient is negative. Our numerical simulations show that GVFF-FAPI algorithm offers lower subspace error and RMSE (Root Mean Square Error) of tracked DOAs of source signals than conventional FAPI based MUSIC (MUltiple SIgnal Classification).

• Journal of KIISE:Software and Applications
• /
• v.33 no.5
• /
• pp.481-488
• /
• 2006

The performance of face recognition methods using subspace projection is directly related to the characteristics of their basis images, especially in the cases of local distortion or partial occlusion. In order for a subspace projection method to be robust to local distortion and partial occlusion, the basis images generated by the method should exhibit a part-based local representation. We propose an effective part-based local representation method named locally salient ICA (LS-ICA) method for face recognition that is robust to local distortion and partial occlusion. The LS-ICA method only employs locally salient information from important facial parts in order to maximize the benefit of applying the idea of 'recognition by parts.' It creates part-based local basis images by imposing additional localization constraint in the process of computing ICA architecture I basis images. We have contrasted the LS-ICA method with other part-based representations such as LNMF (Localized Non-negative Matrix Factorization) and LFA (Local Feature Analysis). Experimental results show that the LS-ICA method performs better than PCA, ICA architecture I, ICA architectureII, LFA, and LNMF methods, especially in the cases of partial occlusions and local distortions.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.166-172
• /
• 2014

Image classification is an important problem in computer vision. However, it is a very challenging problem due to the variability, ambiguity and scale change that exists in images. In this paper, we propose a method of a hypergraph based modeling can consider the higher-order relationships of semantic attributes of a scene image and apply it to a scene image classification. In order to generate the hypergraph optimized for specific scene category, we propose a novel search method based on a probabilistic subspace method and also propose a method to aggregate the expression values of the member semantic attributes that belongs to the searched subsets based on a linear transformation method via likelihood based estimation. To verify the superiority of the proposed method, we showed that the discrimination power of the feature vector generated by the proposed method is better than existing methods through experiments. And also, in a scene classification experiment, the proposed method shows a competitive classification performance compared with the conventional methods.