• Journal of the Korean Data and Information Science Society
• /
• v.28 no.4
• /
• pp.721-731
• /
• 2017

In this study, principal component analysis methods using Lasso penalty are introduced. There are two popular methods that apply Lasso penalty to principal component analysis. The first method is to find an optimal vector of linear combination as the regression coefficient vector of regressing for each principal component on the original data matrix with Lasso penalty (elastic net penalty in general). The second method is to find an optimal vector of linear combination by minimizing the residual matrix obtained from approximating the original matrix by the singular value decomposition with Lasso penalty. In this study, we have reviewed two methods of principal components using Lasso penalty in detail, and shown that these methods have an advantage especially in applying to data sets that have more variables than cases. Also, these methods are compared in an application to a real data set using R program. More specifically, these methods are applied to the crime data in Ahamad (1967), which has more variables than cases.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.11a
• /
• pp.209-212
• /
• 2009

본 논문에서는 MDCT기반의 오디오 특징과 영상 특징을 이용하여 축구 동영상의 하이라이트를 효과적으로 요약하는 방식을 제안한다. 제안하는 방식에서는 입력되는 축구 동영상을 비디오 신호와 오디오 신호로 분리한 후에, 분리된 연속적인 오디오 신호를 압축영역의 MDCT계수를 통해 이벤트 사운드별로 분류하여 오디오 이벤트 후보구간을 추출한다. 입력된 비디오 신호에서는 장면 전환점을 추출하고 추출된 장면 전환점으로부터 페널티 영역을 검출한다. 검출된 오디오 이벤트 후보구간과 검출된 페널티 영역장면을 함께 결합하여 축구 동영상의 이벤트 장면을 검출한다. 검출된 페널티 영역 장면을 통해 검출된 이벤트 구간을 다른 이벤트 구간보다 더 높은 우선순위를 갖는 하이라이트로 선정하여 요약본이 생성된다. 생성된 하이라이트 요약본의 평가는 precision과 recall을 통해 정확도를 평가하였다.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.14 no.3
• /
• pp.503-512
• /
• 1990

In this study, a penalty method effective for the case that has no snap-back phenomenon, is proposed and an adaptive method which choose the penalty method or Riks' type method, is suggested for the case of snap-back problem. And for the case that loads are applied to one or more points of a structure, the Riks' method is applied in general, but under certain condition choice of new incremental load parameter is suggested to accelerate the convergence rate. Finally, for the case that displacements of a structure are controlled at one or more points Riks' type method is proposed. In this case, the proposed method is applied in general but under certain condition it is recommended to choose other incremental displacement parameter to eliminate probable divergence. Five examples are analysed and compared with the result of published literature.

• Proceedings of the KIEE Conference
• /
• 1999.11b
• /
• pp.206-209
• /
• 1999

This paper presents an improved method of calculating the penalty factors for economic load dispatch based on B-coefficient and AC load flow and their performance comparison. The algorithm for calculating B-coefficients by Meyer is improved and its performance is compared with that of AC load flow. The B-coefficient method is superior to the load flow method in its simplicity and computation speed. However accuracy of the B-coefficient method is not satisfactory when it is applied to the ill-conditioned systems where generators produce excessive reactive power.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.25 no.6
• /
• pp.469-476
• /
• 2012

In this paper, a finite element domain decomposition method using local and mixed Lagrange multipliers for a large scal structural analysis is presented. The proposed algorithms use local and mixed Lagrange multipliers to improve computational efficiency. In the original FETI method, classical Lagrange multiplier technique was used. In the dual-primal FETI method, the interface nodes are used at the corner nodes of each sub-domain. On the other hand, the proposed FETI-local analysis adopts localized Lagrange multipliers and the proposed FETI-mixed analysis uses both global and local Lagrange multipliers. The numerical analysis results by the proposed algorithms are compared with those obtained by dual-primal FETI method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.11
• /
• pp.283-290
• /
• 2020

Porous asphalt pavement is used widely in advanced countries to reduce traffic accidents and noise. On the other hand, it is not applied widely in Korea due to concerns about its durability. This study aims to find a statistical method to improve the durability of porous asphalt pavement. A Cantabro test was selected to test the durability. The Cantabro test was performed on an asphalt mixture made of a binder and aggregate. This test was repeated three times for each of the four groups to obtain the Cantabro loss rate. The average values of each of the four groups satisfied all the reference values. In addition, through an analysis of variance (ANOVA), it was possible to quantitatively classify test groups with differences in durability, thereby finding problems and improving the durability. Furthermore, the Pay Factor method can lead to voluntary improvements in quality, and the Pay factor can be calculated through statistical analysis of limited data. Through the Pay factor, it is possible to induce definite quality improvement of the contractor and continuously improve the durability of the porous asphalt mixture by evaluating the adequacy of the quality standard.

• Journal of Korean Society of Steel Construction
• /
• v.30 no.2
• /
• pp.115-126
• /
• 2018

Internationally representative steel design standards have forbidden or limited the application of high-strength steels to tubular joints, partly because of concerns about their unique material characteristics such as high yield ratio. Most of design standards stipulate that for steels whose yield strengths exceed 355 or 360 MPa, the strength equations cannot be utilized or strength reduction factor below 1.0 should be multiplied. However, the mechanical background behind these limitations is not clear. Experimental testing of high-strength steel CHS (circular hollow section) X-joints recently conducted by the authors also clearly indicated that the current limitations might be unduly conservative. As a continuing work, extensive, test-validated numerical analyses were made to investigate the behavior of high-strength steel CHS X-joint under axial compression. Three steel grades covering ordinary to very high strength steels were considered in the analysis. Again it was found that the high strength penalty to the joint strength in current standards is too severe and needs to be relaxed. The high-strength steel joints under the effects of chord stress generally showed higher strength than the ordinary steel joints and their strengths were conservatively predicted by current standards. It is also emphasized that current format of the CHS X-joint strength equation does not reflect observed behavior and needs to be recast.