• Analytical Science and Technology
• /
• v.24 no.6
• /
• pp.544-555
• /
• 2011

The acute toxicity in the rainbow trout (Oncorhynchus mykiss) was analyzed and predicted using quantitative structure-activity relationships (QSAR). The aquatic toxicity, 96h $LC_{50}$ (median lethal concentration) of 275 organic pesticides, was obtained from EU-funded project DEMETRA. Prediction models were derived from 558 2D molecular descriptors, calculated in PreADMET. The linear (multiple linear regression) and nonlinear (support vector machine and artificial neural network) learning methods were optimized by taking into account the statistical parameters between the experimental and predicted p$LC_{50}$. After preprocessing, population based forward selection were used to select the best subsets of descriptors in the learning methods including 5-fold cross-validation procedure. The support vector machine model was used as the best model ($R^2_{CV}$=0.677, RMSECV=0.887, MSECV=0.674) and also correctly classified 87% for the training set according to EU regulation criteria. The MLR model could describe the structural characteristics of toxic chemicals and interaction with lipid membrane of fish. All the developed models were validated by 5 fold cross-validation and Y-scrambling test.

• Journal of Navigation and Port Research
• /
• v.41 no.6
• /
• pp.389-394
• /
• 2017

In this paper, the captive model test of a submarine using the RA test was carried out in a square basin. The target model submarine consisted of four types varying according to the position of conning tower and control planes. Hydrodynamic derivatives were acquired by multi-regression analysis. As a result, horizontal dynamic stability indexes of the four types presented positive values and satisfied dynamic stability requirements. In addition, the stability index of type 1 and type 4 - each with the same cruciform configuration of the aft planes - scored within the acceptable range of motion stability.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.1-12
• /
• 2022

In the event of a maritime distress accident, rapid search and rescue operations using rescue assets are very important to ensure the safety and life of drowning person's at sea. In this paper, we analyzed the surface layer current in the northwest sea area of Ulleungdo by applying machine learning such as multiple linear regression, decision tree, support vector machine, vector autoregression, and LSTM to the meteorological information collected from the maritime observation buoy. And we predicted the drowning person's route at sea based on the predicted current direction and speed information by constructing each prediction model. Comparing the various machine learning models applied in this paper through the performance evaluation measures of MAE and RMSE, the LSTM model is the best. In addition, LSTM model showed superior performance compared to the other models in the view of the difference distance between the actual and predicted movement point of drowning person.

• Journal of the Korean Geotechnical Society
• /
• v.24 no.4
• /
• pp.67-78
• /
• 2008

In this study, artificial cemented sand made of a few portland cement and Nak-Dong river sand was researched closely to investigate cementing effect quantitatively through unconfined tests and triaxial tests. The peak strength and elastic modulus increased and dilation of cemented sand was restricted by the cementation, but after breakage of the cementation, dilation and negative excess pore water pressure increased. In stress-strain curve, strain-softening behavior appeared in drained condition but strain-hardening behavior was appeared in undrained condition as a result of the increase of effective stress. The test was quantitatively analyzed by multiple regression models, correlating each response variable with input variable. The equations are valid only over the range investigated. Its adjusted coefficient of determination was $0.81{\sim}0.91$, and dry density is important factor for estimating strength of cemented sand.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.6
• /
• pp.548-556
• /
• 2019

The purpose of this study is to analyze the impact of dietary lifestyles and demographic characteristics on the Brand image of restaurants with Nutritional labeling to provide basic marketing data for establishing differentiated Brand image strategies for restaurant businesses. To that end, the SPSS21.0 (ver.) program, frequency analysis, descriptive statistics, factor analysis, reliability analysis, correlation analysis, and multiple linear regression analysis were conducted to verify the hypothesis. As a result, the Brand image of restaurants with Nutritional labeling improved as the metropolitan area sought safety, non-capital area sought taste, males sought health, and females sought safety. In terms of age, it was analyzed that as more people in their 20s sought taste, those their 30s and 40s sought safety, and both married and unmarried people sought safety, the Brand image of restaurants with Nutritional labeling improved. In other words, it could be seen that people with Dietary lifestyles who pursued health and safety had positive images of restaurants with Nutritional labeling regardless of residential area, age, gender, marital status, or whether they had children.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1739-1756
• /
• 2021

Atmospheric nitrogen dioxide (NO₂) is mainly caused by anthropogenic emissions. It contributes to the formation of secondary pollutants and ozone through chemical reactions, and adversely affects human health. Although ground stations to monitor NO₂ concentrations in real time are operated in Korea, they have a limitation that it is difficult to analyze the spatial distribution of NO₂ concentrations, especially over the areas with no stations. Therefore, this study conducted a comparative experiment of spatial interpolation of NO₂ concentrations based on two linear-regression methods(i.e., multi linear regression (MLR), and regression kriging (RK)), and two machine learning approaches (i.e., random forest (RF), and support vector regression (SVR)) for the year of 2020. Four approaches were compared using leave-one-out-cross validation (LOOCV). The daily LOOCV results showed that MLR, RK, and SVR produced the average daily index of agreement (IOA) of 0.57, which was higher than that of RF (0.50). The average daily normalized root mean square error of RK was 0.9483%, which was slightly lower than those of the other models. MLR, RK and SVR showed similar seasonal distribution patterns, and the dynamic range of the resultant NO₂ concentrations from these three models was similar while that from RF was relatively small. The multivariate linear regression approaches are expected to be a promising method for spatial interpolation of ground-level NO₂ concentrations and other parameters in urban areas.

• The Journal of the Korea Contents Association
• /
• v.15 no.3
• /
• pp.160-167
• /
• 2015

This study is to investigate the relationship between health promoting lifestyles around the psychosocial aspects such as depression, stress and self-esteem of young North Korean defectors. In particular, the purpose is mentally still less of a mature compared to adults, adolescents need greater understanding. For this purpose, North Korean Youth 150 people were surveyed, questionnaires 85 parts were used in the final analysis excluded from the additional 65. To analyze the factors affecting the health of life was performed multiple linear regression. Analysis result, general self, school self, stress had significant influence on health promoting lifestyles. The conclusion of this study is social psychology factors such as stress self-esteem of North Korean Adolescents refugees is addressed health promoting lifestyles and causal relationship, and promote health of adolescents shows wonderful self-esteem. It suggests that the necessary establishment. This effort is called for to reliably establish the North Korean youth to be part of a future South Korean society.

• The Korean Journal of Nuclear Medicine
• /
• v.34 no.1
• /
• pp.30-38
• /
• 2000

Purpose: We investigated the role of myocardial perfusion SPECT in prediction of ventricular dilatation and the role of revascularization including thrombolytic therapy and PTCA in prevention of ventricular dilatation after an acute myocardial infarction (AMI). Materials and Methods: We performed dipyridamole stress, 4 hour redistribution, and 24 hour reinjection Tl-201 SPECT in 16 patients with AMI two to nine days after attack. Perfusion and wall motion abnormalities were quantified by perfusion index (PI) and wall motion index (WMI). Left ventricular ejection fraction (LVEF), WMI and ventricular volume were measured within 1 week of AMI and after average of 6 months. According to serial changes of left ventricular end-diastolic volume (LVEDV), patients were divided into two groups. We compared WMI, PI and LVEF between the two groups. Relationships among degree of volume, stress-rest PI, WMI, CKMB, Q wave, LVEF and revascularization were analysed using multivariate analysis. Results: Only initial rest perfusion index was significantly different between the two groups (p<0.05). While initial LVEF, stress PI, CKMB, trial of revascularization procedure, presence of Q wave and WMI were not significantly different between the two groups. Eight of 16 patients (50%) showed LV dilatation on follow-up echocardiography. Three of 3 patients (100%) who did not undergo revascualrization procedure documented LV dilatation. And only 5 (38%) of the remaining 13 patients who underwent revascularization revealed LV dilatation. There was no difference in infarct location between the two groups. By multivariate linear regression analysis in patients only undergoing revascularization, rest perfusion index was the only significant factor. Conclusion: Myocardial perfusion SPECT performed prior to revascularization was useful in prediction of LV dilatation after an AMI. Rest perfusion index on myocardial perfusion plays as a significant predictor of left ventricular dilatation after AMI. And revascularization appears to be a valuable procedure in alleviating LV dilatation after AMI with or without viable myocardium in a limited number of patients studied retrospectively.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.713-719
• /
• 2009

In this paper, we develope a water demand forecasting algorithm using AR(Auto-regressive) and MLP(Multi-layer perceptron). To show effectiveness of the proposed method, we analyzed characteristics of time-series data collected in "A" purification plant at Jeon-Buk province during 2007-2008, and then performed the proposed method with various input factors selected through various analyses. As noted in experimental results, the performance of three types model such as multi-regressive, AR(Auto-regressive), and AR+MLP(Auto-regressive + Multi-layer perceptron) show 5.1%, 3.8%, and 3.6% with respect to MAPE(Mean Absolute Percentage Error), respectively. Thus, it is noted that the proposed method can be used to predict short-term water demand for the efficient operation of a water purification plant.

• The Journal of the Korea Contents Association
• /
• v.13 no.1
• /
• pp.456-466
• /
• 2013

The most important thing to develop real estate asset would be a feasibility study. To secure feasibility of development projects, reducing and minimizing the cost of land and construction also would be the important thing. To analyze optimal land-value for real estate development projects, I have collected 204 balance sheets of development projects in South Korea. With the help of statistical technology, I could have selected useful data from those balance sheets. After detailed analysis of statistical data, I could have reached conclusion that the most important factor to earning rate would be land cost per unit ground area under the constraint of given sale price. So far the main pattern of feasibility study of development projects was land cost and construction cost. However, by this study, I have found a new fact that construction cost has little effect to earning rate and land cost per unit ground area is the most effect to earning rate especially in residential facilities rather than commercial ones.