• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1143-1154
• /
• 2021

The selection of activation function has a great influence on the groundwater level prediction performance of artificial neural network (ANN) model. In this study, five activation functions were applied to ANN model for two groundwater level observation wells in the middle mountainous area of the Pyoseon watershed in Jeju Island. The results of the prediction of the groundwater level were compared and analyzed, and the optimal activation function was derived. In addition, the results of LSTM model, which is a widely used recurrent neural network model, were compared and analyzed with the results of the ANN models with each activation function. As a result, ELU and Leaky ReLU functions were derived as the optimal activation functions for the prediction of the groundwater level for observation well with relatively large fluctuations in groundwater level and for observation well with relatively small fluctuations, respectively. On the other hand, sigmoid function had the lowest predictive performance among the five activation functions for training period, and produced inappropriate results in peak and lowest groundwater level prediction. The ANN-ELU and ANN-Leaky ReLU models showed groundwater level prediction performance comparable to that of the LSTM model, and thus had sufficient potential for application. The methods and results of this study can be usefully used in other studies.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.123-139
• /
• 2019

The Korean NPL market was formed by the government and foreign capital shortly after the 1997 IMF crisis. However, this market is short-lived, as the bad debt has started to increase after the global financial crisis in 2009 due to the real economic recession. NPL has become a major investment in the market in recent years when the domestic capital market's investment capital began to enter the NPL market in earnest. Although the domestic NPL market has received considerable attention due to the overheating of the NPL market in recent years, research on the NPL market has been abrupt since the history of capital market investment in the domestic NPL market is short. In addition, decision-making through more scientific and systematic analysis is required due to the decline in profitability and the price fluctuation due to the fluctuation of the real estate business. In this study, we propose a prediction model that can determine the achievement of the benchmark yield by using the NPL market related data in accordance with the market demand. In order to build the model, we used Korean NPL data from December 2013 to December 2017 for about 4 years. The total number of things data was 2291. As independent variables, only the variables related to the dependent variable were selected for the 11 variables that indicate the characteristics of the real estate. In order to select the variables, one to one t-test and logistic regression stepwise and decision tree were performed. Seven independent variables (purchase year, SPC (Special Purpose Company), municipality, appraisal value, purchase cost, OPB (Outstanding Principle Balance), HP (Holding Period)). The dependent variable is a bivariate variable that indicates whether the benchmark rate is reached. This is because the accuracy of the model predicting the binomial variables is higher than the model predicting the continuous variables, and the accuracy of these models is directly related to the effectiveness of the model. In addition, in the case of a special purpose company, whether or not to purchase the property is the main concern. Therefore, whether or not to achieve a certain level of return is enough to make a decision. For the dependent variable, we constructed and compared the predictive model by calculating the dependent variable by adjusting the numerical value to ascertain whether 12%, which is the standard rate of return used in the industry, is a meaningful reference value. As a result, it was found that the hit ratio average of the predictive model constructed using the dependent variable calculated by the 12% standard rate of return was the best at 64.60%. In order to propose an optimal prediction model based on the determined dependent variables and 7 independent variables, we construct a prediction model by applying the five methodologies of discriminant analysis, logistic regression analysis, decision tree, artificial neural network, and genetic algorithm linear model we tried to compare them. To do this, 10 sets of training data and testing data were extracted using 10 fold validation method. After building the model using this data, the hit ratio of each set was averaged and the performance was compared. As a result, the hit ratio average of prediction models constructed by using discriminant analysis, logistic regression model, decision tree, artificial neural network, and genetic algorithm linear model were 64.40%, 65.12%, 63.54%, 67.40%, and 60.51%, respectively. It was confirmed that the model using the artificial neural network is the best. Through this study, it is proved that it is effective to utilize 7 independent variables and artificial neural network prediction model in the future NPL market. The proposed model predicts that the 12% return of new things will be achieved beforehand, which will help the special purpose companies make investment decisions. Furthermore, we anticipate that the NPL market will be liquidated as the transaction proceeds at an appropriate price.

• Journal of Bio-Environment Control
• /
• v.29 no.2
• /
• pp.141-152
• /
• 2020

The rapid on-site measurement of hydroponic nutrients allows for the more efficient use of crop fertilizers. This paper reports on the development of an embedded on-site system consisting of multiple ion-selective electrodes (ISEs) for the real-time measurement of the concentrations of macronutrients in hydroponic solutions. The system included a combination of PVC ISEs for the detection of NO₃, K, and Ca ions, a cobalt-electrode for the detection of H₂PO₄, a double-junction reference electrode, a solution container, and a sampling system consisting of pumps and valves. An Arduino Due board was used to collect data and to control the volume of the sample. Prior to the measurement of each sample, a two-point normalization method was employed to adjust the sensitivity followed by an offset to minimize potential drift that might occur during continuous measurement. The predictive capabilities of the NO₃ and K ISEs based on PVC membranes were satisfactory, producing results that were in close agreement with the results of standard analyzers (R² = 0.99). Though the Ca ISE fabricated with Ca ionophore II underestimated the Ca concentration by an average of 55%, the strong linear relationship (R² > 0.84) makes it possible for the embedded system to be used in hydroponic NO₃, K, and Ca sensing. The cobalt-rod-based phosphate electrodes exhibited a relatively high error of 24.7±9.26% in the phosphate concentration range of 45 to 155 mg/L compared to standard methods due to inconsistent signal readings between replicates, illustrating the need for further research on the signal conditioning of cobalt electrodes to improve their predictive ability in hydroponic P sensing.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1095-1105
• /
• 2021

The advancement of dam operation is further required due to the upcoming rainy season, typhoons, or torrential rains. Besides, physical models based on specific rules may sometimes have limitations in controlling the release discharge of dam due to inherent uncertainty and complex factors. This study aims to forecast the water level of the nearest station to the dam multi-timestep-ahead and evaluate the availability when it makes a decision for a release discharge of dam based on LSTM (Long Short-Term Memory) of deep learning. The LSTM model was trained and tested on eight data sets with a 1-hour temporal resolution, including primary data used in the dam operation and downstream water level station data about 13 years (2009~2021). The trained model forecasted the water level time series divided by the six lead times: 1, 3, 6, 9, 12, 18-hours, and compared and analyzed with the observed data. As a result, the prediction results of the 1-hour ahead exhibited the best performance for all cases with an average accuracy of MAE of 0.01m, RMSE of 0.015 m, and NSE of 0.99, respectively. In addition, as the lead time increases, the predictive performance of the model tends to decrease slightly. The model may similarly estimate and reliably predicts the temporal pattern of the observed water level. Thus, it is judged that the LSTM model could produce predictive data by extracting the characteristics of complex hydrological non-linear data and can be used to determine the amount of release discharge from the dam when simulating the operation of the dam.

• Korean Journal of Psychosomatic Medicine
• /
• v.28 no.1
• /
• pp.29-35
• /
• 2020

Objectives : Evidence regarding the association between untreated depression in adolescence and suicidal risk in male young adults is scarce. We aimed to assess the effect of untreated illness during adolescence on the suicidal risk and attempt after that first episode. Methods : As part of a cross-sectional study, between May 2017 and April 2018, a total of 260 patients with currently unipolar or bipolar depression were included in the final analysis. Multiple linear and logistic regression analysis were performed to evaluate the association between untreated mood disorder in adolescence and its effect on the suicidal risk and attempt. Results : In total 260 patients, 189 were classified as untreated group. The proportion of suicide attempts, total depression score, suicidal risk and number of suicide attempts were significantly higher in the untreated group. The most predictive factors of suicide attempts were history of untreated depression [Adjusted Odds Ratio (AOR)=4.19, 95% Confidence Interval (CI)=2.25-7.81, p<0.001] and diagnosis of bipolar depression (AOR=2.60, 95% CI=1.52-4.46, p<0.001). Conclusions : Although the untreated depression suggests higher rates of suicidality, a significant proportion (86.7%) of adolescent depression in this study did not receive psychiatric treatment. Future research should be needed to find better ways to decrease barriers in using mental health treatment and its contribution to reduction and prevention of adverse outcome.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.10
• /
• pp.4623-4629
• /
• 2016

Introduction: Breast cancer is multifactorial therefore more recognition of risk factors is important in its prevention. Objective: This study was conducted in order to determine the factors influencing breast cancer in women referred to health centers in Guilan province in 2015-2016. Method: In a case- control study, 225 women with breast cancer were investigated. The control group consisted of 225 healthy women of the relatives (third-rank) whose phone numbers were obtained from the patients. Data were collected through telephone interviews. Results: The risk of breast cancer raised in women who have a family history of other cancers (OR= 3.5; 95% CI= 1.96-6.6), exposure to X-Ray (OR= 2.5; 95% CI=1.1-5.5), having more than 4 children (OR= 2.695% CI=1.2-4.8), age more than 36 years at first pregnancy(OR=2.3; 95% CI=0.7-5.1),primary levelof education (OR= 5.4;95% CI=2.8-11.2) and inadequate intake of fruit (OR=1.5; 95% CI=1-2.2). Also, presence of the following factors reduced breast cancer risk: regular menstruation (OR= 0.66; CI=0.4-0.9), duration of breastfeeding more than 12 months, less than 6 months and 7-12 months (OR=0.23; 95% CI=0.09-0.59, OR=0.29; 95% CI=0.17-0.49 and OR=0.03; 95% CI=0.01-0.08) and parity (OR=0.4; 95% CI=0.27-0.83) In multiple linear regression analysis of higher education (OR=0.16; 95% CI=0.03-0.77), using contraceptives for more than 16 years (OR=2.3; 95% CI=1.4-3.9), family history of other cancers (OR=6.1; 95% CI=1.9-19.3) and a history of X-Ray exposure (OR=4.4; 95% CI=1.07-18.1) were considered as predictive factors. Conclusion: The results of this study emphasize the importance of informing women about breast cancer risk factors. So, identification of these risk factors is required as important means of prevention and treatment of breast cancer.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.5 no.1
• /
• pp.44-58
• /
• 1994

The formants of the 9 Korean standard vowels(which used by the average people of Seoul, central-area of the Korean peninsula) were measured by analysis with the linear predictive coding(LPC) and fast Fourier transform(FFT). The author already had reported the constriction area for the Korean standard vowels, and with the existing data, the distance from glottis to the constriction area in the vocal tract of each vowel was newly measured with videovelopharyngograms and lateral Rontgenograms of the vocal tract. We correlated the formant frequencies with the distance from glottis to the constriction area of the vocal tract. Also we tried to correlate the formant frequencies with the position of tongue in the vocal tract which is divided into 2 categories : The position of tongue in oral cavity by the distance from imaginary palatal line to the highest point of tongue and the position in pharyngeal cavity by the distance from back of tongue to posterior pharyngeal wall. This study was performed with 10 adults(male : 5, female : 5) who spoke primary 9 Korean standard vowels. We had already reported that the Korean vowel [i], [e], $[{\varepsilon}]$ were articulated at hard palate level, [$\dot{+}$], [u] were at soft palate level, [$\wedge$] was at upper pharynx level and the [$\wedge$], [$\partial$], [a] in a previous article. Also we had noted that the significance of pharyngeal cavity in vowel articulation. From this study we have concluded that ; 1) The F$_1$ is related with the oral cavity articulated vowel [i, e, $\varepsilon$, $\dot{+}$, u]. 2) Within the oral cavity articulated vowel [i, e, $\varepsilon$, $\dot{+}$, u] and the upper pharynx articulated vowel [o], the F$_2$ is elevated when the diatance from glottis to the constriction area is longer. But within the lower pharynx articulated vowel [$\partial$, $\wedge$, a], the F$_2$ is elevated when the distance from glottis to the constriction area is shorter. 3) With the stronger tendency of back-vowel, the higher the elevation of the F$_1$ and F$_2$ frequencies. 4) The F$_3$ and F$_4$ showed no correaltion with the constriction area nor the position of tongue in the vocal tract 5) The parameter F$_2$- F$_1$, which is the difference between F$_2$ frequency and F$_1$ frequency showed an excellent indicator of differenciating the oral cavity articulated vowels from pharyngeal cavity articulated vowels. If the F$_2$-F$_1$ is less than about 600Hz which indicates the vowel is articulated in the pharyngeal cavity, and more than about 600Hz, which indicates that the vowel is articulated in the oral cavity.

• The Korean Journal of Applied Statistics
• /
• v.27 no.4
• /
• pp.645-653
• /
• 2014

P-value is the probability of observing a current sample and possibly other samples departing equally or more extremely from the null hypothesis toward postulated alternative hypothesis. When p-value is less than a certain level called ${\alpha}$(= 0:05), researchers claim that the alternative hypothesis is supported empirically. Unfortunately, some findings discovered in that way are not reproducible, partly because the p-value itself is a statistic vulnerable to random variation. Boos and Stefanski (2011) suggests calculating the upper limit of p-value in hypothesis testing, using a bootstrap predictive distribution. To determine the sample size of a replication study, this study proposes thought experiments by simulating boosted bootstrap samples of different sizes from given observations. The method is illustrated for the cases of two-group comparison and multiple linear regression. This study also addresses the reproducibility of the points in the given 95% confidence interval. Numerical examples show that the center point is covered by 95% confidence intervals generated from bootstrap resamples. However, end points are covered with a 50% chance. Hence this study draws the graph of the reproducibility rate for each parameter in the confidence interval.

• Journal of Broadcast Engineering
• /
• v.17 no.2
• /
• pp.400-410
• /
• 2012

In recent years, 3D displays are used in many media including 3D movies, TV, mobile phones, and PC games. Although 3D displays provide realistic viewing experience as compared with 2D displays, they also carry issues such as visual fatigue or size distortion. Focusing on the latter, we developed prediction function of object size perception as a function of object depth in 3D display. In Experiment 1, subjects observed 3D square of a fixed size of varying depth, and manipulated 2D square to make it as large as the 3D square. Conversely, in Experiment 2, subjects observed 2D square of a fixed size, and manipulated 3D square of varying depth to make it as large as the 2D square. In both Experiments 1 and 2, we found that size perception of 3D square linearly changed depending on depth of the square, and the linear relationship between depth and size was identical in both experiments. The predictive regression function, which predicts object size perception based on object depth, obtained in this research will be very useful in the creation of 3D media contents.

• Quality Improvement in Health Care
• /
• v.7 no.2
• /
• pp.230-242
• /
• 2000

Background : The measuring instruments for customer satisfaction in hospitals are often composed of some dimensions reflecting the conceptive complexity of them. Then, overall satisfaction would be expected to be equal the 'weighted' sum of scores by dimensions because the importance rated by customers may be different across the dimensions. But the issue of how to weight the dimensions with importance is not yet solved. We examined 3 sets of weighting methods as to make effect on predictive power against overall satisfaction. Methods : We conducted a survey included 483 subjects who had visited or admitted to a university hospital, using the short form questionnaire being developed by The Korean Society of Quality Assurance in Health Care for out-patient and in-patient. By using a multiple linear regression model, we compared among changes of explanatory powers against overall satisfaction as dependent variable after weighting 4 dimensions of the survey questionnaire as independent variables with importance scores of dimensions perceived by consumers. And we compared the feasibility of each weighting, methods by checking missing cases. Results : There were no weighting methods increasing the explanatory power after applying them. The method of absolute scoring was found higher explanatory-power than others, but this finding had no statistical significance. Regarding the number of missing value, method of absolutely scoring had the least cases. Conclusion : Our findings suggested that weighting the dimensions with importance might have little significance in the cases of scales having items highly correlated, such as consumers' satisfaction. Though asking with items to be answered absolutely, customers might be rating relatively in some degree and this method produced least missing cases. Considering these points, in the cases when weighting the dimensions with importance would be required, we suggest that weighting method by absolute scoring might be better than others.