• Wind and Structures
• /
• v.19 no.3
• /
• pp.249-270
• /
• 2014

Through comparing the mean wind profiles observed overland during the passages of four typhoons, and the gradient wind speeds calculated based on the sea level pressure data provided by a numerical model, the present paper discusses, (a) whether the gradient balance is a valid assumption to estimate the wind speed in the height range of 1250 m ~ 1750 m, which is defined as the upper-level mean wind speed, in a tropical cyclone over land, and (b) if the super-gradient feature is systematically observed below the height of 1500 m in the tropical cyclone wind field over land. It has been found that, (i) the gradient balance is a valid assumption to estimate the mean upper-level wind speed in tropical cyclones in the radial range from the radius to the maximum wind (RMW) to three times the RMW, (ii) the super-gradient flow dominates the wind field in the tropical cyclone boundary layer inside the RMW and is frequently observed in the radial range from the RMW to twice the RMW, (iii) the gradient wind speed calculated based on the post-landfall sea level pressure data underestimates the overall wind strength at an island site inside the RMW, and (iv) the unsynchronized decay of the pressure and wind fields in the tropical cyclone might be the reason for the underestimation.

• Advances in nano research
• /
• v.9 no.4
• /
• pp.221-235
• /
• 2020

The following composition establishes a nonlocal strain gradient plate model that is essentially related to mass sensors laying on Winkler-Pasternak medium for the vibrational analysis from graphene sheets. To achieve a seemingly accurate study of graphene sheets, the posited theorem actually accommodates two parameters of scale in relation to the gradient of the strain as well as non-local results. Model graphene sheets are known to have double variant shear deformation plate theory without factors from shear correction. By using the principle of Hamilton, to acquire the governing equations of a non-local strain gradient graphene layer on an elastic substrate, Galerkin's method is therefore used to explicate the equations that govern various partition conditions. The influence of diverse factors like the magnetic field as well as the elastic foundation on graphene sheet's vibration characteristics, the number of nanoparticles, nonlocal parameter, nanoparticle mass as well as the length scale parameter had been evaluated.

• Journal of the Korean Ceramic Society
• /
• v.43 no.11 s.294
• /
• pp.724-727
• /
• 2006

It has long been known that the oxidation kinetics of Zr-based alloys undergoes a crossover from parabolic to cubic in the pretransition period (before breakaway of the oxide scale). This kinetic crossover, however, is not fully understood yet. We have earlier proposed a model for the Zr-oxidation kinetics, in a closed form for the first time, by taking into account a compressive strain energy gradient as a diffusional driving force in addition to a chemical potential gradient of component oxygen across the ZrO$_2$ scale upon Zr [J. Nucl. Mater., 299 (2001) 235]. In this paper, we experimentally reconfirm the validity of the proposed model by using the thermogravimetric data on mass gain of Zr in a plate and wire form, respectively, in air atmosphere at different temperatures in the range of 500$^{\circ}$ to 800$^{\circ}C$, and subsequently report on the numerical values for oxygen chemical diffusivity and strain energy gradient across the oxide scale.

• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.901-911
• /
• 2009

In this paper, we propose a construction technique of two-level composite gradient map to automatically track a face with large movement in successive frames. Our method is composed of three main steps. First, the gradient maps with two-level resolution are generated for fast convergence of active contour. Second, to recognize the variations of face between successive frames and remove the neighbor background, weighted composite gradient map is generated by combining the composite gradient map and difference mask of previous and current frames. Third, to prevent active contour from converging local minima, the energy slope is generated by using closing operation. In addition, the fast closing operation is proposed to accelerate the processing time of closing operation. For performance evaluation, we compare our method with previous active contour model-based face tracking methods using a visual inspection, robustness test and processing time. Experimental results show that our method can effectively track the face with large movement and robustly converge to the optimal position even in frames with complicated background.

• Structural Engineering and Mechanics
• /
• v.64 no.6
• /
• pp.683-693
• /
• 2017

According to a generalized nonlocal strain gradient theory (NSGT), dynamic modeling and free vibrational analysis of nanoporous inhomogeneous nanoplates is presented. The present model incorporates two scale coefficients to examine vibration behavior of nanoplates much accurately. Porosity-dependent material properties of the nanoplate are defined via a modified power-law function. The nanoplate is resting on a viscoelastic substrate and is subjected to hygro-thermal environment and in-plane linearly varying mechanical loads. The governing equations and related classical and non-classical boundary conditions are derived based on Hamilton's principle. These equations are solved for hinged nanoplates via Galerkin's method. Obtained results show the importance of hygro-thermal loading, viscoelastic medium, in-plane bending load, gradient index, nonlocal parameter, strain gradient parameter and porosities on vibrational characteristics of size-dependent FG nanoplates.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.87-92
• /
• 2021

Bias, variance, error and learning are important factors for performance in modeling a big data based recommendation system. The recommendation model in this system must reduce complexity while maintaining the explanatory diagram. In addition, the sparsity of the dataset and the prediction of the system are more likely to be inversely proportional to each other. Therefore, a product recommendation model has been proposed through learning the similarity between products by using a factorization method of the sparsity of the dataset. In this paper, the generalization ability of the model is improved by applying the max-norm regularization as an optimization method for the loss function of this model. The solution is to apply a stochastic projection gradient descent method that projects a gradient. The sparser data became, it was confirmed that the propsed regularization method was relatively effective compared to the existing method through lots of experiment.

• Steel and Composite Structures
• /
• v.28 no.3
• /
• pp.381-388
• /
• 2018

In this paper, forced vibration of micro cylindrical shell reinforced by functionally graded carbon nanotubes (FG-CNTs) is presented. The structure is subjected to transverse harmonic load and modeled by beam model. The size effects are considered based on strain gradient theory containing three small scale parameters. The mixture rule is used for obtaining the effective material properties of the structure. Based on sinusoidal shear deformation theory of beam, energy method and Hamilton's principle, the motion equations are derived. Applying differential quadrature method (DQM) and Newmark method, the frequency curves of the structure are plotted. The effect of different parameters including, CNTs volume percent and distribution type, boundary conditions, size effect and length to thickness ratio on the frequency curves of the structure is studied. Numerical results indicate that the dynamic deflection of the FGX-CNT-reinforced cylindrical is lower with respect to other type of CNT distribution.

• Journal of Information Processing Systems
• /
• v.15 no.3
• /
• pp.694-706
• /
• 2019

In this study, we applied the long short-term memory (LSTM) model to classify the cryptocurrency price time series. We collected historic cryptocurrency price time series data and preprocessed them in order to make them clean for use as train and target data. After such preprocessing, the price time series data were systematically encoded into the three-dimensional price tensor representing the past price changes of cryptocurrencies. We also presented our LSTM model structure as well as how to use such price tensor as input data of the LSTM model. In particular, a grid search-based k-fold cross-validation technique was applied to find the most suitable LSTM model parameters. Lastly, through the comparison of the f1-score values, our study showed that the LSTM model outperforms the gradient boosting model, a general machine learning model known to have relatively good prediction performance, for the time series classification of the cryptocurrency price trend. With the LSTM model, we got a performance improvement of about 7% compared to using the GB model.

• The Journal of Information Systems
• /
• v.31 no.4
• /
• pp.145-160
• /
• 2022

Purpose The purpose of this study is to develop a virtual try-on deep learning model that can efficiently learn front and back clothes images. It is expected that the application of virtual try-on clothing service in the fashion and textile industry field will be vitalization. Design/methodology/approach The data used in this study used 232,355 clothes and product images. The image data input to the model is divided into 5 categories: original clothing image and wearer image, clothing segmentation, wearer's body Densepose heatmap, wearer's clothing-agnosting. We advanced the HR-VITON model in the way of Mixed-Precison, Gradient Accumulation, and sharing model weights. Findings As a result of this study, we demonstrated that the weight-shared MP-GA HR-VITON model can efficiently learn front and back fashion images. As a result, this proposed model quantitatively improves the quality of the generated image compared to the existing technique, and natural fitting is possible in both front and back images. SSIM was 0.8385 and 0.9204 in CP-VTON and the proposed model, LPIPS 0.2133 and 0.0642, FID 74.5421 and 11.8463, and KID 0.064 and 0.006. Using the deep learning model of this study, it is possible to naturally fit one color clothes, but when there are complex pictures and logos as shown in <Figure 6>, an unnatural pattern occurred in the generated image. If it is advanced based on the transformer, this problem may also be improved.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.29-36
• /
• 2022

In this paper, we propose an efficient agricultural products price prediction model based on dataset which provided in DACON. This model is XGBoost and CatBoost, and as an algorithm of the Gradient Boosting series, the average accuracy and execution time are superior to the existing Logistic Regression and Random Forest. Based on these advantages, we design a machine learning model that predicts prices 1 week, 2 weeks, and 4 weeks from the previous prices of agricultural products. The XGBoost model can derive the best performance by adjusting hyperparameters using the XGBoost Regressor library, which is a regression model. The implemented model is verified using the API provided by DACON, and performance evaluation is performed for each model. Because XGBoost conducts its own overfitting regulation, it derives excellent performance despite a small dataset, but it was found that the performance was lower than LGBM in terms of temporal performance such as learning time and prediction time.