• Geomechanics and Engineering
• /
• v.6 no.4
• /
• pp.359-376
• /
• 2014

Thermal conductivity of ground has a great influence on the performance of Ground Heat Exchangers (GHEs). In general, the ground thermal conductivity significantly depends on the density (or porosity) and the moisture content since they are decisive factors that determine the interface area between soil particles which is available for heat transfer. In this study, a large number of thermal conductivity experiments were conducted for soils of varying porosity and moisture content, and a database of thermal properties for the weathered granite soils was set up. Based on the database, a 3D Curved Surface Model and an Artificial Neural Network Model (ANNM) were proposed for estimating the thermal conductivity. The new models were validated by comparing predictions by the models with new thermal conductivity data, which had not been used in developing the models. As for the 3D CSM, the normalized average values of training and test data were 1.079 and 1.061 with variations of 0.158 and 0.148, respectively. The predictions became somewhat unreliable in a low range of thermal conductivity values in considering the distribution pattern. As for the ANNM, the 'Logsig-Tansig' transfer function combination with nine neurons gave the most accurate estimates. The normalized average values of training data and test data were 1.006 and 0.954 with variations of 0.026 and 0.098, respectively. It can be concluded that the ANNM gives much better results than the 3D CSM.

• Geomechanics and Engineering
• /
• v.37 no.1
• /
• pp.49-64
• /
• 2024

Rocks undergoing repeated loading and unloading over an extended period, such as due to earthquakes, human excavation, and blasting, may result in the gradual accumulation of stress and deformation within the rock mass, eventually reaching an unstable state. In this study, a CNN-CCM is proposed to address the mechanical behavior. The structure and hyperparameters of CNN-CCM include Conv2D layers × 5; Max pooling2D layers × 4; Dense layers × 4; learning rate=0.001; Epoch=50; Batch size=64; Dropout=0.5. Training and validation data for deep learning include 71 rock samples and 122,152 data points. The AI Rock Constitutive Model learned by CNN-CCM can predict strain values(ε₁) using Mass (M), Axial stress (σ₁), Density (ρ), Cyclic number (N), Confining pressure (σ₃), and Young's modulus (E). Five evaluation indicators R², MAPE, RMSE, MSE, and MAE yield respective values of 0.929, 16.44%, 0.954, 0.913, and 0.542, illustrating good predictive performance and generalization ability of model. Finally, interpreting the AI Rock Constitutive Model using the SHAP explaining method reveals that feature importance follows the order N > M > σ₁ > E > ρ > σ₃.Positive SHAP values indicate positive effects on predicting strain ε₁ for N, M, σ₁, and σ₃, while negative SHAP values have negative effects. For E, a positive value has a negative effect on predicting strain ε₁, consistent with the influence patterns of conventional physical rock constitutive equations. The present study offers a novel approach to the investigation of the mechanical constitutive model of rocks under cyclic loading and unloading conditions.

• Ecology and Resilient Infrastructure
• /
• v.9 no.2
• /
• pp.100-106
• /
• 2022

The relationships between river length and weir density versus fish species observed were analyzed for 210 local rivers in the Seomjin River system (SJR). A nonlinear exponential relationship between river length and number of fish species were observed. Model coefficient was 0.03 and coefficient of determinant (R²) was 0.59, meaning that about 59.0% of total variance was explained by river length variable. Predicted value by model and observed number of species showed a difference. About 110 local rivers (about 52.4%) showed lower value than predictive value. The average index of weir's density (IWD) in the SJR was about 2.7/km, which was significantly higher than that of other river basins. As a result of nonparametric 2-Kimensional Kolmogorov-Smirnov (2-DKS) analysis based on the IWD, the threshold value affecting fish diversity was about 2.5/km (D_max=0.048, p<0.05). Above the threshold value, it means that the number of fish species would be decreased. In fact, the ratio of the expected species to the observed species was lowered to less than 70%, when the IWD is higher than the threshold value. To maintain aquatic ecological connectivity in future, it is necessary to manage IWD below the threshold value.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.43 no.8
• /
• pp.1296-1303
• /
• 2014

This study was conducted to develop predictive models for the growth of Bacillus cereus on carrot treated with slightly acidic electrolyzed water (SAcEW) and ultrasonication (US) at different storage temperatures. In addition, the inactivation of B. cereus by US with SAcEW was investigated. US treatment with a frequency of 40 kHz and an acoustic energy density of 400 W/L at $40^{\circ}C$ for 3 min showed the maximum reduction of 2.87 log CFU/g B. cereus on carrot, while combined treatment of US (400 W/L, $40^{\circ}C$, 3 min) with SAcEW reached to 3.1 log CFU/g reduction. Growth data of B. cereus on carrot treated with SAcEW and US at different temperatures (4, 10, 15, 20, 25, 30, and $35^{\circ}C$) were collected and used to develop predictive models. The modified Gompertz model was found to be more suitable to describe the growth data. The specific growth rate (SGR) and lag time (LT) obtained from the modified Gompertz model were employed to establish the secondary models. The newly developed secondary models were validated using the root mean square error, bias factor, and accuracy factor. All results of these factors were in the acceptable range of values. After compared SGR and LT of B. cereus on carrot, the results showed that the growth of B. cereus on carrot treated with SAcEW and US was slower than that of single treatment. This result indicates that shelf life of carrot treated with SAcEW and US could be extended. The developed predictive models might also be used to assess the microbiological risk of B. cereus infection in carrot treated with SAcEW and US.

• Journal of the Korean Geosynthetics Society
• /
• v.16 no.3
• /
• pp.51-62
• /
• 2017

For the purpose of the study, of the 76 areas subject to preliminary concentrated management on sediment disaster in the downtown area, 9 areas were selected as research areas. They were classified into three stratified rock areas (Gyeongsan City, Goheung-gun and Daegu Metropolitan City), three igneous rock areas (Daejeon City, Sejong Special Self-Governing City and Wonju City) and three metamorphic rock areas (Namyangju City, Uiwang City and Inje District) according to the characteristics of the bedrock in the research areas. As for the 9 areas, analyses were conducted based on tests required to calculate soil characteristics, a predictive model for root adhesive power, loading of trees and on-the-spot research. As for a rainfall scenario (rainfall intensity), the probability of rainfall was applied as offered by APEC Climate Center (APCC) in Busan. As for the prediction of landslide risks in the 9 areas, TRIGRS and LSMAP were applied. As a result of TRIGRIS prediction, the risk rate was recorded 30.45% in stratified rock areas, 41.03% in igneous rock areas and 45.04% in metamorphic rock areas on average. As a result of LSMAP prediction based on root cohesion and the weight of trees according to crown density, it turned out to a 1.34% risk rate in the stratified rock areas, 2.76% in the igneous rock areas and 1.64% in the metamorphic rock areas. Analysis through LSMAP was considered to be relatively local predictive rather than analysis using TRIGRS.

• Elastomers and Composites
• /
• v.59 no.1
• /
• pp.34-41
• /
• 2024

In this study, the effects of the type and content of silica on the mechanical and tear properties of chloroprene rubber (CR), which is mainly used as a jacket material for mining cables, were studied. The crosslinking density (ΔM) and reinforcing factor (α_f) defined using cure characteristics increased with increasing silica content, whereas the cure rate decreased. The hardness, tensile strength, and modulus of the CR compounds increased depending on the silica content and structural development. The reinforcing behavior of the silica-filled CR compounds according to the silica type and content showed the best fit with the Thomas equation of the predictive model. Tear strength was evaluated using two standard test methods, ASTM D470 and DIN VDE 0472-613, and the results were compared. The tear strength increased as the silica content increased, regardless of the test method, and the different tear strengths obtained by the two standard test methods showed a linear relationship with each other, indicating a high correlation.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.5
• /
• pp.61-69
• /
• 2014

Collaborative filtering recommendation creates similar item subset or similar user subset based on user preference about items and predict user preference to particular item by using them. Thus, if preference matrix has low density, reliability of recommendation will be sharply decreased. To solve these problems we suggest Hybrid Preference Prediction Technique Using Weighting based Data Reliability. Preference prediction is carried out by creating similar item subset and similar user subset and predicting user preference by each subset and merging each predictive value by weighting point applying model condition. According to this technique, we can increase accuracy of user preference prediction and implement recommendation system which can provide highly reliable recommendation when density of preference matrix is low. Efficiency of this system is verified by Mean Absolute Error. Proposed technique shows average 21.7% improvement than Hao Ji's technique when preference matrix sparsity is more than 84% through experiment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.4
• /
• pp.558-564
• /
• 2021

With the recent introduction of 5G, electromagnetic radiation sources are spreading throughout life, so it is necessary to establish a citizen-centered electromagnetic safety management system. In particular, the beamforming method of the 5G antenna increases the power density measurement of electromagnetic waves by more than 10 times when the wireless base station is installed, so it is unreasonable to determine the safety by physical measurement. Therefore, it is necessary to determine the presence or absence of electromagnetic wave safety in daily life through a predictive method by calculation through systematic model analysis. In this paper, in order to check the possibility of a 5G wireless base station using an electromagnetic wave numerical analysis tool as a way to solve this problem, we compared the measured values of the actual base stations and the predicted values through the prediction model to compare the reliability. A method of constructing a real-time base station electromagnetic wave strength prediction evaluation system combined with software was also proposed.

• The Korean Journal of Applied Statistics
• /
• v.36 no.1
• /
• pp.49-62
• /
• 2023

Solar energy, which is rapidly increasing in proportion, is being continuously developed and invested. As the installation of new and renewable energy policy green new deal and home solar panels increases, the supply of solar energy in Korea is gradually expanding, and research on accurate demand prediction of power generation is actively underway. In addition, the importance of solar radiation prediction was identified in that solar radiation prediction is acting as a factor that most influences power generation demand prediction. In addition, this study can confirm the biggest difference in that it attempted to predict solar radiation using medium-term forecast weather data not used in previous studies. In this paper, we combined the multi-linear regression model, KNN, random fores, and SVR model and the clustering technique, K-means, to predict solar radiation by hour, by calculating the probability density function for each cluster. Before using medium-term forecast data, mean absolute error (MAE) and root mean squared error (RMSE) were used as indicators to compare model prediction results. The data were converted into daily data according to the medium-term forecast data format from March 1, 2017 to February 28, 2022. As a result of comparing the predictive performance of the model, the method showed the best performance by predicting daily solar radiation with random forest, classifying dates with similar climate factors, and calculating the probability density function of solar radiation by cluster. In addition, when the prediction results were checked after fitting the model to the medium-term forecast data using this methodology, it was confirmed that the prediction error increased by date. This seems to be due to a prediction error in the mid-term forecast weather data. In future studies, among the weather factors that can be used in the mid-term forecast data, studies that add exogenous variables such as precipitation or apply time series clustering techniques should be conducted.

• Genomics & Informatics
• /
• v.11 no.4
• /
• pp.263-271
• /
• 2013

We investigated the contribution of genetic variations of KLF5 to basal metabolic rate (BMR) and resting metabolic rate (RMR) and the inhibition of obesity in Korean children. A variation of KLF5 (rs3782933) was genotyped in 62 Korean children. Using multiple linear regression analysis, we developed a model to predict BMR in children. We divided them into several groups; normal versus overweight by body mass index (BMI) and low BMR versus high BMR by BMR. There were no differences in the distributions of alleles and genotypes between each group. The genetic variation of KLF5 gene showed a significant correlation with several clinical factors, such as BMR, muscle, low-density lipoprotein cholesterol, and insulin. Children with the TT had significantly higher BMR than those with CC (p=0.030). The highest muscle was observed in the children with TT compared with CC (p=0.032). The insulin and C-peptide values were higher in children with TT than those with CC (p=0.029 vs. p=0.004, respectively). In linear regression analysis, BMI and muscle mass were correlated with BMR, whereas insulin and C-peptide were not associated with BMR. In the high-BMR group, we observed that higher muscle, fat mass, and C-peptide affect the increase of BMR in children with TT (p < 0.001, p < 0.001, and p=0.018, respectively), while Rohrer's index could explain the usual decrease in BMR (adjust $r^2$=1.000, p < 0.001, respectively). We identified a novel association between TT of KLF5 rs3782933 and BMR in Korean children. We could make better use of the variation within KLF5 in a future clinical intervention study of obesity.