• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.439-448
• /
• 2006

Previous recognition/clustering algorithms such as Kohonen SOM(Self-Organizing Map), MLP(Multi-Layer Percecptron) and SVM(Support Vector Machine) might not adapt to unexpected input pattern. And it's recognition rate depends highly on the complexity of own training patterns. We could make up for and improve the weak points with lowering complexity of original problem without losing original characteristics. There are so many ways to lower complexity of the problem, and we chose a kernel concepts as an approach to do it. In this paper, using a kernel concepts, original data are mapped to hyper-dimension space which is near infinite dimension. Therefore, transferred data into the hyper-dimension are distributed spasely rather than originally distributed so as to guarantee the rate to be risen. Estimating ratio of recognition is based on a new similarity-probing and learning method that are proposed in this paper. Using CEDAR DB which data is written in cursive letters, 0 to 9, we compare a recognition/clustering performance of kSOM that is proposed in this paper with previous SOM.

• Computational Structural Engineering
• /
• v.7 no.2
• /
• pp.69-75
• /
• 1994

The procedure for the stress and displacement analysis of realistic viscoelastic materials by time domain boundary element method(BEM) has been discussed. The fundamental solutions and stress kernels have been obtained using the elastic-viscoelastic correspondence principle. The relaxation function is expanded in a sum of exponentials and the transformed fundamental solutions and stress kernels are inverted numerically into real time space. The proposed procedure requires a small computational effort and it is applicable in time domain boundary element analysis of realistic viscoelastic problems. Numerical results of example problem show the effectiveness and applicability of the proposed method.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.3
• /
• pp.201-220
• /
• 2023

Power cable tunnels is one of the underground structures meant for electricity transmission and are constructed using shield TBM method when transitting across urban and subsea regions. With the increasing shaft depth for tunnels excavation when the shield TBM excavated the rock mass, the review of selecting closed-type shield TBM in rocks becomes necessary. A simplified shield TBM design method is also necessary based on conventional geotechnical survey results. In this respect, design method and related design program are developed based on combined results of full-scale tests, considerable amount of accumulated TBM data, and numerical simulation results. In order to validate the program results, excavation data of a completed power cable tunnel project are utilized. Thrust force, torque, and power of shield TBM specification are validated using Kernel density concept which estimates the population data. The robustness of design expertise is established through this research which will help in stable provision of electricity supply.

• The Korean Journal of Nuclear Medicine
• /
• v.32 no.3
• /
• pp.225-237
• /
• 1998

Purpose: We investigated the statistical methods to compose the functional brain map of human working memory and the principal factors that have an effect on the methods for localization. Materials and Methods: Repeated PET scans with successive four tasks, which consist of one control and three different activation tasks, were performed on six right-handed normal volunteers for 2 minutes after bolus injections of 925 MBq $H_2^{15}O$ at the intervals of 30 minutes. Image data were analyzed using SPM96 (Statistical Parametric Mapping) implemented with Matlab (Mathworks Inc., U.S.A.). Images from the same subject were spatially registered and were normalized using linear and nonlinear transformation methods. Significant difference between control and each activation state was estimated at every voxel based on the general linear model. Differences of global counts were removed using analysis of covariance (ANCOVA) with global activity as covariate. Using the mean and variance for each condition which was adjusted using ANCOVA, t-statistics was performed on every voxel To interpret the results more easily, t-values were transformed to the standard Gaussian distribution (Z-score). Results: All the subjects carried out the activation and control tests successfully. Average rate of correct answers was 95%. The numbers of activated blobs were 4 for verbal memory I, 9 for verbal memory II, 9 for visual memory, and 6 for conjunctive activation of these three tasks. The verbal working memory activates predominantly left-sided structures, and the visual memory activates the right hemisphere. Conclusion: We conclude that rCBF PET imaging and statistical parametric mapping method were useful in the localization of the brain regions for verbal and visual working memory.