• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1582-1590
• /
• 2022

Due to the situation of the widespread of the coronavirus, which causes the problem of lack of face image data occluded by masks at recent time, in order to solve the related problems, this paper proposes a method to generate face images with masks using a combination of generative adversarial networks and spatial transformation networks based on CNN model. The system we proposed in this paper is based on the GAN, combined with multi-scale convolution kernels to extract features at different details of the human face images, and used Wasserstein divergence as the measure of the distance between real samples and synthetic samples in order to optimize Generator performance. Experiments show that the proposed method can effectively put masks on face images with high efficiency and fast reaction time and the synthesized human face images are pretty natural and real.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.47 no.7
• /
• pp.67-75
• /
• 2005

It has been well-known that the Nonpoint Source (NPS) pollutions are the primary contributors to water quality degradation in the receiving water bodies as well as the Point Source (PS) pollutions. To develop an effective management practice for water quality improvement, pollutant loads must be first estimated. In many studies, the Numeric Integration (NI) method has been used because of its ease of application, irrespective of the total number of samples collected for each storm event. Thus, there have been needs for more accurate pollutant load estimation with a limited number of water quality samples. In this study, NI method and regression method using the USGS ESTIMATOR model were comparatively used to calculate the pollutant loads for the Wolgokri watershed, Gangwon Province. The $NO_{3}$-N, T-N, and T-P loads using NI method and ESTIMATOR model were 13.85 kg/ha, 45.92 kg/ha, and 1.887 kg/ha, and 11.93 kg/ha,43.20 kg/ha, and 1.650 kg/ha, respectively. The estimated loads using ESTIMATOR model were lower than those using NI method by $86\%$, $94\%$, and $87\%$. These discrepancies in the estimated loads using a different load estimation method could be explained in that the total number of samples were not sufficient enough for NI method. Thus, ESTIMATOR model is recommended for the frequently stream discharge and less frequently measured water quality data.

• Advances in nano research
• /
• v.12 no.1
• /
• pp.73-79
• /
• 2022

Due to the extensive use of concrete structures in various applications, the improvement of their strength and quality has become of great importance. A new way of achieving this purpose is to add different types of nanoparticles to concrete admixtures. In this work, a mathematical model has been employed to analyze the vibration of concrete beams reinforced by graphene oxide (GO) nanoparticles. To verify the accuracy of the presented model, an experimental study has been conducted to compare the compressive strengths of these beams. Since GO nanoparticles are not readily dissolved in water, before producing the concrete samples, the GO nanoparticles are dispersed in the mixture by using a shaker, magnetic striker, ultrasonic devices, and finally, by means of a mechanical mixer. The sinusoidal shear deformation beam theory (SSDBT) is employed to model the concrete beams. The Mori-Tanaka model is used to determine the effective properties of the structure, including the agglomeration influences. The motion equations are calculated by applying the energy method and Hamilton's principle. The vibration frequencies of the concrete beam samples are obtained by an analytical method. Three samples containing 0.02% GO nanoparticles are made and their compressive strengths are measured and compared. There is a good agreement between our results and those of the mathematical model and other papers, with a maximum difference of 1.29% between them. The aim of this work is to investigate the effects of nanoparticle volume fraction and agglomeration and the influences of beam length and thickness on the vibration frequency of concrete structures. The results show that by adding the GO nanoparticles, the vibration frequency of the beams is increased.

• Geophysics and Geophysical Exploration
• /
• v.7 no.2
• /
• pp.130-135
• /
• 2004

This paper describes the physical properties of the factors controlling the electrical resistivity of the subsurface. Resistivities of various types of soil and rock samples saturated with sodium chloride solutions having nine different concentrations were measured, and the measured resistivities of these samples were compared with calculated resistivities obtained using the conventional empirical formulas. From the results obtained, we observed that the resistivity of the soil and rock samples increases with increasing in pore-fluids resistivity regardless of the media type. However, between 20 and 200 ohm-m, which is the normal range of resistivity of groundwater, the resistivity of the pore-fluids have little or no effect on the resistivities of the samples used. Below 10 ohm-m, the resistivities of the samples are mainly controlled by the pore-fluids, whereas, in the normal range of resistivity of groundwater, the sample resistivities are controlled by their intrinsic matrix resistivity more than by the pore-fluids resistivity. Also, the measured resistivity of rock and soil samples having more than $20\%$ clay contents showed a good agreement with the calculated resistivity using the parallel resistance model whereas, the calculated resistivities of glass beads correlate with that obtained using Archie's formula. When the pore-fluid resistivity is high, the computation of the resistivity values of the samples using the Archie's formula could not be carried out. Through this study, we were able to confirm that the tests are only applicable to the parallel resistance model considering the intrinsic matrix resistivity within the normal resistivity range of groundwater in the subsurface.

• Current Research on Agriculture and Life Sciences
• /
• v.32 no.1
• /
• pp.30-33
• /
• 2014

A simulation model was developed to monitor food contamination during the ripening process of Kimchi on a factory scale. The cabbages were divided into three groups: control (without salt or red pepper), samples with added salt, and samples with added salt and red pepper. The processed Kimchi was left to ripen in a refrigerator at $4^{\circ}C$ and five frog heads (contaminant) left on the surface of the cabbages in each group. For the control, the contaminant exhibited a long life span of 10 days or more, however, for the samples with salt and samples with salt and red pepper, the contaminant showed a relatively short life span. In particular, for the processed Kimchi that included salt and red pepper, the life-span of the contaminant was dramatically decreased to around 3 days. Therefore, the present results suggest that the proposed simulation trial is suitable for monitoring contamination during Kimchi production. Moreover, since the contaminant could not survive more than 3 days, this suggests that the salt concentration in the Kimchi damaged the permeability of the skin and other tissue membranes.

• Journal of Korean Society of Water and Wastewater
• /
• v.20 no.5
• /
• pp.737-745
• /
• 2006

The goal of this study is to present an external pit corrosion rate($p_{ecr}$) model with considering both the age of pipe and the soil characteristics. The correlation of nonlinear exponential model among conventional empirical models was a little higher than other empirical models in the prediction of $p_{ecr}$ according to the age of pipe. However, there has been a limit to predict Peer with the model by using only a pipe age since installation as a variable. The soil analysis results from sixty nine samples showed that all of the samples were non corrosive in the assessment of ANSI/AWWA scoring system. The correlation of soil corrosion factors and $p_{ecr}$ was also low. The application result of linear and nonlinear regression models that soil characteristics only showed a low correlation with $p_{ecr}$ Proposed nonlinear regression model in this study, with considering both the age of pipe and the soil characteristics, showed a little higher correlation ($R^2=0.46$) than conventional model.

• Journal of Biosystems Engineering
• /
• v.23 no.6
• /
• pp.571-582
• /
• 1998

The PLS(Partial Least Square) and ANN(Artificial Neural Network) were introduced to develop the soluble solids content prediction model of apples which is followed by making a subsequent selection of photosensor. For the optimal PLS model, number of factors needed for spectrum analysis were increased until the convergence of prediction residual error sum of squares. Analysis has shown that even part of the overall wavelength with no pretreatment may turn out better performing. The best PLS model was found in the 800 to 1,100nm wavelength region without pretreatment of second derivation, having $R^2$=0.9236, bias= -0.0198bx, SEP=0.2527bx for unknown samples. On the other hand, for the ANN model the second derivation led to higher performance. On partial range of 800 to 1,100nm wavelengh region, prediction model with second derivation for unknown samples reached $R^2$=0.9177, SEP=0.2903bx in contrast to $R^2$=0.7507, SEP =0.4622bx without pretreatment.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.48 no.4
• /
• pp.487-494
• /
• 2012

Acoustical backscattering characteristics of Japanese anchovy can be estimated by Kirchhoffray mode model (KRM model) due to estimate exact body and swim-bladder shape of the fish, the samples were rapidly frozen by dry-ice and alcohol. X-ray photos for ventral and lateral direction for 6 samples were taken and the 3D coordinates of the body swim-bladder were estimated by digitizing from the photos. The angles between the axis of body and swim-bladder were about $9^{\circ}$ at 38kHz and $7^{\circ}$ at 120kHz, 200kHz. General formula of TS and BL estimated were < $TS_{38kHz}$ >=20logBL-67.3, < $TS_{120kHz}$ >=20logBL-66.6, < $TS_{200kHz}$ >=20logBL-67.0. As a result, we confirmed KRM model is very useful to estimate TS (Target Strength) for design of experiment and it also can be applied to estimate the abundance of Japanese anchovy distributed by 2 frequency difference method in the survey area.

• Computers and Concrete
• /
• v.27 no.5
• /
• pp.489-512
• /
• 2021

In this study, two powerful techniques, namely particle swarm optimization (PSO) and imperialist competitive algorithm (ICA) were selected and combined with a pre-developed ANN model aiming at improving its performance prediction of the compressive strength of concrete modified with fly ash. To achieve this study's aims, a comprehensive database with 379 data samples was collected from the available literature. The output of the database is the compressive strength (CS) of concrete samples, which are influenced by 9 parameters as model inputs, namely those related to mix composition. The modeling steps related to ICA-ANN (or neuro-imperialism) and PSO-ANN (or neuro-swarm) were conducted through the use of several parametric studies to design the most influential parameters on these hybrid models. A comparison of the CS values predicted by hybrid intelligence techniques with the experimental CS values confirmed that the neuro-swarm model could provide a higher degree of accuracy than another proposed hybrid model (i.e., neuro-imperialism). The train and test correlation coefficient values of (0.9042 and 0.9137) and (0.8383 and 0.8777) for neuro-swarm and neuro-imperialism models, respectively revealed that although both techniques are capable enough in prediction tasks, the developed neuro-swarm model can be considered as a better alternative technique in mapping the concrete strength behavior.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.3
• /
• pp.1643-1647
• /
• 2013

Background: To identify the risk factors and assess the role of survivin in predicting progessivity precancerous cervical lesions. Materials and Methods: This case-control study was conducted from October 2009 until May 2010. We obtained 74 samples, classified according to the degree of cervical intraepithelial neoplasia (CIN): 19 samples for CIN 1, 18 samples for CIN 2, 18 samples for CIN 3, and 19 samples as controls. Demographic profiles and risk factors assesment, histopathologic examination, HPV DNA tests, immunocytochemistry (ICC) and immunohistochemistry (IHC) staining for survivin expression were performed on all samples. Data was analyzed with bivariate and multivariate analysis. Results: Multivariate analysis revealed significant risk factors for developing precancerous cervical lesions are age <41 years, women with ${\geq}2$ sexual partners, course of education ${\geq}13$ years, use of oral contraceptives, positive high-risk HPV DNA, and high survivin expression by ICC or IHC staining. These factors were fit to a prediction model and we obtained a scoring system to predict the progressivity of CIN lesions. Conclusions: Determination of survivin expression by immunocytochemistry staining, along with other significant risk factors, can be used in a scoring system to predict the progressivity of CIN lesions. Application of this scoring system may be beneficial in determining the action of therapy towards the patient.