• Wind and Structures
• /
• v.19 no.4
• /
• pp.421-441
• /
• 2014

With the assistance of typhoon field data at aerial elevation level observed by meteorological satellites and wind velocity and direction records nearby the ground gathered in Guangzhou Weather Station between 1985 and 2001, some key wind field parameters under typhoon climate in Guangzhou region were calibrated based on Monte-Carlo stochastic algorithm and Meng's typhoon numerical model. By using Peak Over Threshold method (POT) and Generalized Pareto Distribution (GPD), Wind field characteristics during typhoons for various return periods in several typical engineering fields were predicted, showing that some distribution rules in relation to gradient height of atmosphere boundary layer, power-law component of wind profile, gust factor and extreme wind velocity at 1-3s time interval are obviously different from corresponding items in Chinese wind load Codes. In order to evaluate the influence of typhoon field parameters on long-span flexible bridges, 1:100 reduced-scale wind field of type B terrain was reillustrated under typhoon and normal conditions utilizing passive turbulence generators in TJ-3 wind tunnel, and wind-induced performance tests of aero-elastic model of long-span Guangzhou Xinguang arch bridge were carried out as well. Furthermore, aerodynamic admittance function about lattice cross section in mid-span arch lib under the condition of higher turbulence intensity of typhoon field was identified via using high-frequency force-measured balance. Based on identified aerodynamic admittance expressions, Wind-induced stochastic vibration of Xinguang arch bridge under typhoon and normal climates was calculated and compared, considering structural geometrical non-linearity, stochastic wind attack angle effects, etc. Thus, the aerodynamic response characteristics under typhoon and normal conditions can be illustrated and checked, which are of satisfactory response results for different oncoming wind velocities with resemblance to those wind tunnel testing data under the two types of climate modes.

• Journal of Convergence for Information Technology
• /
• v.11 no.10
• /
• pp.45-52
• /
• 2021

In this paper, we proposed an Atrous Residual U-Net (AR-UNet) to improve the segmentation accuracy of semantic segmentation method based on U-Net. The U-Net is mainly used in fields such as medical image analysis, autonomous vehicles, and remote sensing images. The conventional U-Net lacks extracted features due to the small number of convolution layers in the encoder part. The extracted features are essential for classifying object categories, and if they are insufficient, it causes a problem of lowering the segmentation accuracy. Therefore, to improve this problem, we proposed the AR-UNet using residual learning and ASPP in the encoder. Residual learning improves feature extraction ability and is effective in preventing feature loss and vanishing gradient problems caused by continuous convolutions. In addition, ASPP enables additional feature extraction without reducing the resolution of the feature map. Experiments verified the effectiveness of the AR-UNet with Cityscapes dataset. The experimental results showed that the AR-UNet showed improved segmentation results compared to the conventional U-Net. In this way, AR-UNet can contribute to the advancement of many applications where accuracy is important.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.3
• /
• pp.186-191
• /
• 2019

In this paper, we propose a implementation approach of the high-speed feature extraction algorithm. The proposed method is based on the block type classification algorithm which reduces the computation time when target macro block is divided to smooth block type that has no image features. It is quantitatively identified that occurs at 29.5% of the total image using 200 standard test images with $64{\times}64$ macro block size. This means that within a standard test image containing various image information, 29.5% can reduce the complexity of the operation. When the proposed approach is applied to the Canny edge detection, the required latency of the edge detection can be completely eliminated, such as 2D derivative filter, gradient magnitude/direction computation, non-maximal suppression, adaptive threshold calculation, hysteresis thresholding. Also, it is expected that operation time of the feature detection can be reduced by applying block type classification algorithm to various feature extraction algorithms in this way.

• Smart Structures and Systems
• /
• v.23 no.2
• /
• pp.141-153
• /
• 2019

This research deals with wave propagation of the functionally graded (FG) nano-beams based on the nonlocal elasticity theory considering surface and flexoelectric effects. The FG nano-beam is resting in Winkler-Pasternak foundation. It is assumed that the material properties of the nano-beam changes continuously along the thickness direction according to simple power-law form. In order to include coupling of strain gradients and electrical polarizations in governing equations of motion, the nonlocal non-classical nano-beam model containg flexoelectric effect is used. Also, the effects of surface elasticity, dielectricity and piezoelectricity as well as bulk flexoelectricity are all taken into consideration. The governing equations of motion are derived using Hamilton principle based on first shear deformation beam theory (FSDBT) and also considering residual surface stresses. The analytical method is used to calculate phase velocity of wave propagation in FG nano-beam as well as cut-off frequency. After verification with validated reference, comprehensive numerical results are presented to investigate the influence of important parameters such as flexoelectric coefficients of the surface, bulk and residual surface stresses, Winkler and shear coefficients of foundation, power gradient index of FG material, and geometric dimensions on the wave propagation characteristics of FG nano-beam. The numerical results indicate that considering surface effects/flexoelectric property caused phase velocity increases/decreases in low wave number range, respectively. The influences of aforementioned parameters on the occurrence cut-off frequency point are very small.

• Journal of The Korean Society of Emergency Medicine
• /
• v.29 no.5
• /
• pp.455-464
• /
• 2018

Objective: Machine learning is not yet widely used in the medical field. Therefore, this study was conducted to compare the performance of preexisting severity prediction models and machine learning based models (random forest [RF], gradient boosting [GB]) for mortality prediction in pneumonia patients. Methods: We retrospectively collected data from patients who visited the emergency department of a tertiary training hospital in Seoul, Korea from January to March of 2015. The Pneumonia Severity Index (PSI) and Sequential Organ Failure Assessment (SOFA) scores were calculated for both groups and the area under the curve (AUC) for mortality prediction was computed. For the RF and GB models, data were divided into a test set and a validation set by the random split method. The training set was learned in RF and GB models and the AUC was obtained from the validation set. The mean AUC was compared with the other two AUCs. Results: Of the 536 investigated patients, 395 were enrolled and 41 of them died. The AUC values of PSI and SOFA scores were 0.799 (0.737-0.862) and 0.865 (0.811-0.918), respectively. The mean AUC values obtained by the RF and GB models were 0.928 (0.899-0.957) and 0.919 (0.886-0.952), respectively. There were significant differences between preexisting severity prediction models and machine learning based models (P<0.001). Conclusion: Classification through machine learning may help predict the mortality of pneumonia patients visiting the emergency department.

• Structural Engineering and Mechanics
• /
• v.89 no.3
• /
• pp.225-238
• /
• 2024

In this paper, a quasi-3D hyperbolic shear deformation theory for the bending responses of a functionally graded (FG) porous micro-beam is based on a modified couple stress theory requiring only one material length scale parameter that can capture the size influence. The model proposed accounts for both shear and normal deformation effects through an illustrative variation of all displacements across the thickness and satisfies the zero traction boundary conditions on the top and bottom surfaces of the micro-beam. The effective material properties of the functionally graded micro-beam are assumed to vary in the thickness direction and are estimated using the homogenization method of power law distribution, which is modified to approximate the porous material properties with even and uneven distributions of porosity phases. The equilibrium equations are obtained using the virtual work principle and solved using Navier's technique. The validity of the derived formulation is established by comparing it with the ones available in the literature. Numerical examples are presented to investigate the influences of the power law index, material length scale parameter, beam thickness, and shear and normal deformation effects on the mechanical characteristics of the FG micro-beam. The results demonstrate that the inclusion of the size effects increases the microbeams stiffness, which consequently leads to a reduction in deflections. In contrast, the shear and normal deformation effects are just the opposite.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.27 no.3
• /
• pp.137-145
• /
• 2014

We present a design sensitivity analysis(DSA) method for multiscale problems based on bridging scale decomposition. In this paper, we utilize a bridging scale method for the coupled system analysis. Since the analysis of full MD systems requires huge amount of computational costs, a coupled system of MD-level and continuum-level simulation is usually preferred. The information exchange between the MD and continuum levels is taken place at the MD-continuum boundary. In the bridging scale method, a generalized Langevin equation(GLE) is introduced for the reduced MD system and the GLE force using a time history kernel is applied at the boundary atoms in the MD system. Therefore, we can separately analyze the MD and continuum level simulations, which can accelerate the computing process. Once the simulation of coupled problems is successful, the need for the DSA is naturally arising for the optimization of macro-scale design, where the macro scale performance of the system is maximized considering the micro scale effects. The finite difference sensitivity is impractical for the gradient based optimization of large scale problems due to the restriction of computing costs but the analytical sensitivity for the coupled system is always accurate. In this study, we derive the analytical design sensitivity to verify the accuracy and applicability to the design optimization of the coupled system.

• Journal of Biomedical Engineering Research
• /
• v.32 no.3
• /
• pp.237-244
• /
• 2011

In this paper, a feature-based registration technique is proposed for pre-contrast and post-contrast lung CT images. It utilizes three dimensional(3-D) features with their descriptors and estimates feature correspondences by nearest neighborhood matching in the feature space. We design a transformation model between the input image pairs using a free form deformation(FFD) which is based on B-splines. Registration is achieved by minimizing an energy function incorporating the smoothness of FFD and the correspondence information through a non-linear gradient conjugate method. To deal with outliers in feature matching, our energy model integrates a robust estimator which discards outliers effectively by iteratively reducing a radius of confidence in the minimization process. Performance evaluation was carried out in terms of accuracy and efficiency using seven pairs of lung CT images of clinical practice. For a quantitative assessment, a radiologist specialized in thorax manually placed landmarks on each CT image pair. In comparative evaluation to a conventional feature-based registration method, our algorithm showed improved performances in both accuracy and efficiency.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.9C
• /
• pp.895-904
• /
• 2007

This paper proposes a robust sub-optimal smart antenna in Code Division Multiple Access (CDMA) basestation. It makes use of the property of the Least Mean Square (LMS) algorithm and the Conjugate Gradient Method (CGM) algorithm for beamforming processes. The weight update takes place at symbol level which follows the PN correlators of receiver module under the assumption that the post correlation desired signal power is far larger than the power of each of the interfering signals. The proposed algorithm is simple and has as low computational load as five times of the number of antenna elements(O(5N)) as a whole per each snapshot. The output Signal to Interference plus Noise Ratio (SINR) of the proposed smart antenna system when the weight vector reaches the steady state has been examined. It has been observed in computer simulations that proposed beamforming algorithm improves the SINR significantly compared to the single antenna case. The convergence property of the weight vector has also been investigated to show that the proposed hybrid algorithm performs better than CGM and LMS during the initial stage of the weight update iteration. The Bit Error Rate (BER) characteristics of the proposed array has also been shown as the processor input Signal to Noise Ratio (SNR) varies.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.521-529
• /
• 2020

Forest fires are one of the most important environmental risks that have adverse effects on many aspects of life, such as the economy, environment, and health. The early detection, quick prediction, and rapid response of forest fires can play an essential role in saving property and life from forest fire risks. For the rapid discovery of forest fires, there is a method using meteorological data obtained from local sensors installed in each area by the Meteorological Agency. Meteorological conditions (e.g., temperature, wind) influence forest fires. This study evaluated a Data Mining (DM) approach to predict the burned area of forest fires. Five DM models, e.g., Stochastic Gradient Descent (SGD), Support Vector Machines (SVM), Decision Tree (DT), Random Forests (RF), and Deep Neural Network (DNN), and four feature selection setups (using spatial, temporal, and weather attributes), were tested on recent real-world data collected from Gyeonggi-do area over the last five years. As a result of the experiment, a DNN model using only meteorological data showed the best performance. The proposed model was more effective in predicting the burned area of small forest fires, which are more frequent. This knowledge derived from the proposed prediction model is particularly useful for improving firefighting resource management.