• Geomechanics and Engineering
• /
• v.37 no.6
• /
• pp.539-554
• /
• 2024

This study explores development of prediction model for seismic site classification through the integration of machine learning techniques with horizontal-to-vertical spectral ratio (HVSR) methodologies. To improve model accuracy, the research employs outlier detection methods and, synthetic minority over-sampling technique (SMOTE) for data balance, and evaluates using seven machine learning models using seismic data from KiK-net. Notably, light gradient boosting method (LGBM), gradient boosting, and decision tree models exhibit improved performance when coupled with SMOTE, while Multiple linear regression (MLR) and Support vector machine (SVM) models show reduced efficacy. Outlier detection techniques significantly enhance accuracy, particularly for LGBM, gradient boosting, and voting boosting. The ensemble of LGBM with the isolation forest and SMOTE achieves the highest accuracy of 0.91, with LGBM and local outlier factor yielding the highest F1-score of 0.79. Consistently outperforming other models, LGBM proves most efficient for seismic site classification when supported by appropriate preprocessing procedures. These findings show the significance of outlier detection and data balancing for precise seismic soil classification prediction, offering insights and highlighting the potential of machine learning in optimizing site classification accuracy.

• Wind and Structures
• /
• v.13 no.1
• /
• pp.1-20
• /
• 2010

The recommended factored design wind load effects for overhead lattice transmission line towers by codes and standards are evaluated based on the applicable wind load factor, gust response factor and design wind speed. The current factors and design wind speed were developed considering linear elastic responses and selected notional target safety levels. However, information on the nonlinear inelastic responses of such towers under extreme dynamic wind loading, and on the structural capacity curves of the towers in relation to the design capacities, is lacking. The knowledge and assessment of the capacity curve, and its relation to the design strength, is important to evaluate the integrity and reliability of these towers. Such an assessment was performed in the present study, using a nonlinear static pushover (NSP) analysis and incremental dynamic analysis (IDA), both of which are commonly used in earthquake engineering. For the IDA, temporal and spatially varying wind speeds are simulated based on power spectral density and coherence functions. Numerical results show that the structural capacity curves of the tower determined from the NSP analysis depend on the load pattern, and that the curves determined from the nonlinear static pushover analysis are similar to those obtained from IDA.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.39 no.12
• /
• pp.1150-1159
• /
• 2011

Reliability is defined as a probability that a system will operate properly for a specified period of time under the design operating conditions without failure. Reliability-Redundancy Optimization Problem(RROP) involves selection of components with multiple choices, redundancy levels and redundancy strategy(Active or Standby) for maximizing system reliability with constraints such as cost, weight, etc. Based on the design configuration of Multi-Spectral Camera(MSC) system of KOMPSAT-2, the mathematical programming model for RROP is suggested in this study. Due to the nature of RROP, i.e. NP-hard problem, Parallel Particle Swarm Optimization(PPSO) algorithm is proposed to solve it. The result of the numerical experiment for RROP is presented as instance of recommended design configuration at some mission time.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.7A
• /
• pp.657-665
• /
• 2007

In this paper, it is investigated that the limitation due to the asymmetry of optical power and chromatic dispersion with respect to optical phase conjugator (OPC) for compensating optical signal distortion of WDM channels in mid-span spectral inversion (MSSI) technique is overcame by using OPC position offset and optimal dispersion coefficients of fiber sections, which depend on OPC position offset. It is confirmed that overall WDM channels are efficiently compensated by applying the optimal parameter values obtained from the proposed method into 24 channels ${\times}\;40\;Gbps$ WDM system with non zero - dispersion shifted fiber (NZ-DSF) of 1,000 km, such as power penalties of inter-channel are reduce to almost 3.5 dB from the infinite value. It is also confirmed that the flexible design of WDM system with OPC is possible by using the optimal parameters, in which OPC is placed at ${\pm}15\;km$ from 500 km for efficiently compensating overall channels.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.21 no.1
• /
• pp.1-11
• /
• 1997

Austomated visual inspection(AVI) capability has become an important key component in the automated manufacturing system. In such a visual inspection system an intensity(or color) image of a scene is quickly affected by optical property of objects, condition and roughness of surface, lens and filters, image sensor property and lighting system. In particular, the lighting system disign is the most important factor, since it affects overall performance of the visual system. For fast and cheap automated visual inspection system it is important to obtain the good image quality which results from careful attention to the design of the lighting system. In this paper, the lighting subsystem of AVI system is analysed for the inspection of printed circuit board(PCB) patterns. The spectral reflectance of materials, which are composed of PCB, is measured for choosing the light source. The reflection property is theoretically obtained by a reflection model and also obtained by experiments which measure intensity with varying the viewing direction of image sensor and the lighting direction of illuminator. The illumination uniformity of a ring-type illuminator. The lighting system is designed based upon the experimental results and theoretial analysis.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.41 no.5
• /
• pp.341-346
• /
• 2017

Knowing the mean free paths (MFPs) of thermal phonons is an essential step in performing heat transfer analysis for nanomaterials, and in determining the optimum design for tailoring the heat transfer characteristics of nanomaterials. In this study, we present a method that can be used to calculate accurately the phonon MFP spectra of nanostructures based on simple phonon kinetic theory. Here, the kinetic theory may be employed by extracting only the diffusive-transport part of the phonon spectrum (i.e., the MFPs are less than a thermal length). By considering phonon dispersion and polarization effects, the phonon MFP distributions of silicon at room temperature are calculated from phonon transport properties and the spectral MFP. Our results are validated by comparison with those of the first principle and MFP spectroscopy data.

• Journal of Korea Game Society
• /
• v.17 no.1
• /
• pp.7-16
• /
• 2017

The 3D game graphic technology has become an important factor in the contents field with the game contents development. In particular, game character technology provides a realistic technique and visual pleasure, as well as an intermediate step in the immersion of the game in which the game might create an optical illusion that enables the player to enjoy heroic adventure in the game. The high expression level of characters in 3D games is a key factor in the development process, with details and carefulness of the character setting work [3]. In this paper, we propose a character representative technique applied to mobile games using mathematical model of radiosity energy, spectral radiance model, and ray tracing model method using 3D unity game engine with sensible AI algorithm for game implementation. As a practical application to the game contents, it was found that the projection of the surface in the rendering process and the game simulation might change according to the lighting condition of the game content environment, so that the high quality of game characters was simulated.

• Journal of Korean Society of Steel Construction
• /
• v.14 no.2
• /
• pp.319-327
• /
• 2002

Development of high-strength and light-weight structural steel as well as advancement in steel structure analysis enable construction of long span steel arch bridge. In an economic viewpoint, however, the design values of long span steel arch bridge needs to be optimized to reduce construction cost and achieve proper levels of structural safety. This study investigated the girder depth and the rise-span ratio for optimum design values, as well as the spectral analysis for protection against earthquake. The relationship between rise-span ratio and girder depth was derived based on the parametric studies of the basic span lengths of 60, 70, 80, 90, and 100m using a commercial Cis SAP2000. The equation relating the two variables was derived using linear regression.

• Journal of the Korean Society for Railway
• /
• v.20 no.4
• /
• pp.440-447
• /
• 2017

Spectrum level for the acoustic roughness of wheels and rail surface should be periodically maintained under the limitation of ISO to reduce rolling noise of railway vehicles. Thus, in maintaining railway track, displacement sensor-based measuring devices are broadly used to measure the surface roughness and to perform spectral analysis. However, these measuring devices cause unexpected measuring errors since the displacement sensors are fixed at moving platforms and the main frame produces pitching motion during measurement. To increase the accuracy of the measured values, this paper has investigated the effects of design variables such as wheel base, additional wheels, and elastic deformation of wheels on the surface roughness and acoustic roughness spectrum.

• Journal of the Optical Society of Korea
• /
• v.17 no.4
• /
• pp.344-349
• /
• 2013

This paper proposes a simulation algorithm to assess the gradual yellowing vision of the elderly, which refers to the predominance of yellowness in their vision due to aging of the ocular optic media. This algorithm employed the spectral transmittance property of a yellow filter to represent the color appearance perceived by elderly people with yellow vision, and modeled the changes in the color space through a spectrum change in light using the yellow filter effect. The spectral reflectivity data of 1269 Munsell matte color chips were used as reference data. Under the standard conditions of a D65 illuminant and a $10^{\circ}$ observer of 1964 CIE, the spectrum of the 1269 Munsell colors were processed through the yellow filter effect to simulate yellow vision. Various degrees of yellow vision were modeled according to the transmittance percentage of the yellow filter. The color differences before and after the yellow filter effect were calculated using the DE2000 formula, and the color pairs were selected based on the color difference function. These color pairs are distinguishable through normal vision, but the color difference diminishes as the degree of yellow vision increases. Assuming 80% of yellow vision effect, 17 color pairs out of $(1269{\times}1268)/2$ pairs were selected, and for the 90% of yellow vision effect, only 3 color pairs were selected. The result of this study can be utilized for the diagnosis system of gradual yellow vision, making various types of test charts with selected color pairs.