• Journal of Bio-Environment Control
• /
• v.31 no.4
• /
• pp.384-392
• /
• 2022

The objective of this study was to estimated nitrogen content and chlorophyll using RGB, Hyperspectral sensors to diagnose of nitrogen nutrition in apple tree leaves. Spectral data were acquired through image processing after shooting with high resolution RGB and hyperspectral sensor for two-year-old 'Hongro/M.9' apple. Growth data measured chlorophyll and leaf nitrogen content (LNC) immediately after shooting. The growth model was developed by using regression analysis (simple, multi, partial least squared) with growth data (chlorophyll, LNC) and spectral data (SPAD meter, color vegetation index, wavelength). As a result, chlorophyll and LNC showed a statistically significant difference according to nitrogen fertilizer level regardless of date. Leaf color became pale as the nutrients in the leaf were transferred to the fruit as over time. RGB sensor showed a statistically significant difference at the red wavelength regardless of the date. Also hyperspectral sensor showed a spectral difference depend on nitrogen fertilizer level for non-visible wavelength than visible wavelength at June 10th and July 14th. The estimation model performance of chlorophyll, LNC showed Partial least squared regression using hyperspectral data better than Simple and multiple linear regression using RGB data (Chlorophyll R²: 81%, LNC: 81%). The reason is that hyperspectral sensor has a narrow Full Half at Width Maximum (FWHM) and broad wavelength range (400-1,000 nm), so it is thought that the spectral analysis of crop was possible due to stress cause by nitrogen deficiency. In future study, it is thought that it will contribute to development of high quality and stable fruit production technology by diagnosis model of physiology and pest for all growth stage of tree using hyperspectral imagery.

• Journal of Korea Water Resources Association
• /
• v.55 no.10
• /
• pp.761-774
• /
• 2022

Accurate hydrologic prediction is essential to analyze the effects of drought, flood, and climate change on flow rates, water quality, and ecosystems. Disentangling the uncertainty of the hydrological model is one of the important issues in hydrology and water resources research. Hydrologic data assimilation (DA), a technique that updates the status or parameters of a hydrological model to produce the most likely estimates of the initial conditions of the model, is one of the ways to minimize uncertainty in hydrological simulations and improve predictive accuracy. In this study, the two ensemble-based sequential DA techniques, ensemble Kalman filter, and particle filter are comparatively analyzed for the daily discharge simulation at the Yongdam catchment using airGRdatassim. The results showed that the values of Kling-Gupta efficiency (KGE) were improved from 0.799 in the open loop simulation to 0.826 in the ensemble Kalman filter and to 0.933 in the particle filter. In addition, we analyzed the effects of hyper-parameters related to the data assimilation methods such as precipitation and potential evaporation forcing error parameters and selection of perturbed and updated states. For the case of forcing error conditions, the particle filter was superior to the ensemble in terms of the KGE index. The size of the optimal forcing noise was relatively smaller in the particle filter compared to the ensemble Kalman filter. In addition, with more state variables included in the updating step, performance of data assimilation improved, implicating that adequate selection of updating states can be considered as a hyper-parameter. The simulation experiments in this study implied that DA hyper-parameters needed to be carefully optimized to exploit the potential of DA methods.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.121-142
• /
• 2023

As the number and weight of imported food are steadily increasing, safety management of imported food to prevent food safety accidents is becoming more important. The Ministry of Food and Drug Safety conducts on-site inspections of foreign food facilities before customs clearance as well as import inspection at the customs clearance stage. However, a data-based safety management plan for imported food is needed due to time, cost, and limited resources. In this study, we tried to increase the efficiency of the on-site inspection by preparing a machine learning prediction model that pre-selects the companies that are expected to fail before the on-site inspection. Basic information of 303,272 foreign food facilities and processing businesses collected in the Integrated Food Safety Information Network and 1,689 cases of on-site inspection information data collected from 2019 to April 2022 were collected. After preprocessing the data of foreign food facilities, only the data subject to on-site inspection were extracted using the foreign food facility_code. As a result, it consisted of a total of 1,689 data and 103 variables. For 103 variables, variables that were '0' were removed based on the Theil-U index, and after reducing by applying Multiple Correspondence Analysis, 49 characteristic variables were finally derived. We build eight different models and perform hyperparameter tuning through 5-fold cross validation. Then, the performance of the generated models are evaluated. The research purpose of selecting companies subject to on-site inspection is to maximize the recall, which is the probability of judging nonconforming companies as nonconforming. As a result of applying various algorithms of machine learning, the Random Forest model with the highest Recall_macro, AUROC, Average PR, F1-score, and Balanced Accuracy was evaluated as the best model. Finally, we apply Kernal SHAP (SHapley Additive exPlanations) to present the selection reason for nonconforming facilities of individual instances, and discuss applicability to the on-site inspection facility selection system. Based on the results of this study, it is expected that it will contribute to the efficient operation of limited resources such as manpower and budget by establishing an imported food management system through a data-based scientific risk management model.

• Journal of the Korean Geotechnical Society
• /
• v.26 no.12
• /
• pp.19-30
• /
• 2010

Bentonite-based grout has been widely used to seal a borehole constructed for a closed-loop vertical ground heat exchanger in a geothermal heat pump system (GHP) because of its high swelling potential and low hydraulic conductivity. Three types of bentonites were compared one another in terms of viscosity and thermal conductivity in this paper. The viscosity and thermal conductivity of the grouts with bentonite contents of 5%, 10%, 15%, 20% and 25% by weight were examined to take into account a variable water content of bentonite grout depending on field conditions. To evaluate the effect of salinity (i.e., concentration of NaCl : 0.1M, 0.25M, and 0.5M) on swelling potential of the bentonite-based grouts, a series of volume reduction tests were performed. In addition, if the viscosity of bentonite-water mixture is relatively low, particle segregation can occur. To examine the segregation phenomenon, the degree of segregation has been evaluated for the bentonite grouts especially in case of relatively low viscosity. From the experimental results, it is found that (1) the viscosity of the bentonite mixture increased with time and/or with increasing the mixing ratio. However, the thermal conductivity of the bentonite mixture did not increase with time but increased with increasing the mixing ratio; (2) If bentonite grout has a relatively high swelling index, the volume reduction ratio in the saline condition will be low; (3) The additive, such as a silica sand, can settle down on the bottom of the borehole if the bentonite has a very low viscosity. Consequently, the thermal conductivity of the upper portion of the ground heat exchanger will be much smaller than that of the lower portion.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.4
• /
• pp.398-403
• /
• 2023

Process-based K-cabbage model is based on physiological processes such as photosynthesis and phenology, making it possible to predict crop growth under different climate conditions that have never been experienced before. Current first-stage process-based models can be used to assess climate impact through yield prediction based on climate change scenarios, but no comparison has been performed between big data obtained from the main production area and model prediction so far. The aim of this study was to find out the direction of model improvement when using the current model for yield prediction. For this purpose, model performance evaluation was conducted based on data collected from farmers growing 'Chungwang' cabbage in Taebaek and Samcheok, the main producing areas of Chinese cabbage in highland region. The farms surveyed in this study had different cultivation methods in terms of planting date and soil water and nutrient management. The results showed that the potential biomass estimated using the K-cabbage model exceeded the observed values in all cases. Although predictions and observations at the time of harvest did not show a complete positive correlation due to limitations caused by the use of fresh weight in the model evaluation process (R²=0.74, RMSE=866.4), when fitting the model based on the values 2 weeks before harvest, the growth suitability index was different for each farm. These results are suggested to be due to differences in soil properties and management practices between farms. Therefore, to predict attainable yields taking into account differences in soil and management practices between farms, it is necessary to integrate dynamic soil nutrient and moisture modules into crop models, rather than using arbitrary growth suitability indices in current K-cabbage model.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.655-667
• /
• 2023

Algal bloom outbreaks are frequently reported around the world, and serious water pollution problems arise every year in Korea. It is necessary to protect the aquatic ecosystem through continuous management and rapid response. Many studies using satellite images are being conducted to estimate the concentration of chlorophyll-a (Chl-a), an indicator of algal bloom occurrence. However, machine learning models have recently been used because it is difficult to accurately calculate Chl-a due to the spectral characteristics and atmospheric correction errors that change depending on the water system. It is necessary to consider the factors affecting algal bloom as well as the satellite spectral index. Therefore, this study constructed a dataset by considering water quality, hydrological and meteorological factors, and sentinel-2 images in combination. Representative ensemble models random forest and extreme gradient boosting (XGBoost) were used to predict the concentration of Chl-a in eight weirs located on the Nakdong river over the past five years. R-squared score (R²), root mean square errors (RMSE), and mean absolute errors (MAE) were used as model evaluation indicators, and it was confirmed that R² of XGBoost was 0.80, RMSE was 6.612, and MAE was 4.457. Shapley additive expansion analysis showed that water quality factors, suspended solids, biochemical oxygen demand, dissolved oxygen, and the band ratio using red edge bands were of high importance in both models. Various input data were confirmed to help improve model performance, and it seems that it can be applied to domestic and international algal bloom detection.

• Journal of Chest Surgery
• /
• v.41 no.5
• /
• pp.598-604
• /
• 2008

Background: The improvements in endoscopic equipment and surgical robots has encouraged the performance of minimally invasive cardiac operations. Yet only a few Korean studies have compared this procedure with the sternotomy approach. Material and Method: Between December 2005 and July 2007, 48 patients (group A) underwent minimally invasive cardiac surgery with AESOP through a small right thoracotomy. During the same period, 50 patients (group B) underwent conventional surgery. We compared the operative time, the operative results, the post-operative pain and the recovery of both groups. Result: There was no hospital mortality and there were no significant differences in the incidence of operative complications between the two groups. The operative $(292.7{\pm}61.7\;and\;264.0{\pm}47.9min$, respectively; p=0.01) and CPB times ($128.4{\pm}37.6\;and\;101.7{\pm}32.5min$, respectively; <0.01) were longer for group A, whereas there was no difference between the aortic cross clamp times ($82.1{\pm}35.0\;and\;87.8{\pm}113.5min$, respectively; p=0.74) and ventilator times ($18.0{\pm}18.4\;and\;19.7{\pm}9.7$ hr, respectively; p=0.57) between the groups. The stay on the ICU $(53.2{\pm}40.2\;and\;72.8{\pm}42.1hr$, respectively; p=0.02) and the hospitalization time ($9.7{\pm}7.2\;and\;14.8{\pm}11.9days$, respectively; p=0.01) were shorter for group A. The Patients in group B had more transfusions, but the difference was not significant. For the overall operative intervals, which ranged from one to four weeks, the pair score was significantly lower for the patients of group A than for the patients of group B. In terms of the postoperative activities, which were measured by the Duke Activity Scale questionnaire, the functional status score was clearly higher for group A compared to group B. The analysis showed no difference in the severity of either post-repair of mitral ($0.7{\pm}1.0\;and\;0.9{\pm}0.9$, respectively; p=0.60) and tricuspid regurgitation ($1.0{\pm}0.9\;and\;1.1{\pm}1.0$, respectively; p=0.89). In both groups, there were no valve related complications, except for one patient with paravalvular leakage in each group. Conclusion: These results show that compared with the median sternotomy patients, the patients who underwent minimally invasive surgery enjoyed significant postoperative advantages such as less pain, a more rapid return to full activity, improved cosmetics and a reduced hospital stay. The minimally invasive surgery can be done with similar clinical safety compared to the conventional surgery that's done through a median sternotomy.

• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.59-77
• /
• 2012

This study focuses on predicting which firms will increase capital by issuing new stocks in the near future. Many stakeholders, including banks, credit rating agencies and investors, performs a variety of analyses for firms' growth, profitability, stability, activity, productivity, etc., and regularly report the firms' financial analysis indices. In the paper, we develop predictive models for rights issues using these financial analysis indices and data mining techniques. This study approaches to building the predictive models from the perspective of two different analyses. The first is the analysis period. We divide the analysis period into before and after the IMF financial crisis, and examine whether there is the difference between the two periods. The second is the prediction time. In order to predict when firms increase capital by issuing new stocks, the prediction time is categorized as one year, two years and three years later. Therefore Total six prediction models are developed and analyzed. In this paper, we employ the decision tree technique to build the prediction models for rights issues. The decision tree is the most widely used prediction method which builds decision trees to label or categorize cases into a set of known classes. In contrast to neural networks, logistic regression and SVM, decision tree techniques are well suited for high-dimensional applications and have strong explanation capabilities. There are well-known decision tree induction algorithms such as CHAID, CART, QUEST, C5.0, etc. Among them, we use C5.0 algorithm which is the most recently developed algorithm and yields performance better than other algorithms. We obtained data for the rights issue and financial analysis from TS2000 of Korea Listed Companies Association. A record of financial analysis data is consisted of 89 variables which include 9 growth indices, 30 profitability indices, 23 stability indices, 6 activity indices and 8 productivity indices. For the model building and test, we used 10,925 financial analysis data of total 658 listed firms. PASW Modeler 13 was used to build C5.0 decision trees for the six prediction models. Total 84 variables among financial analysis data are selected as the input variables of each model, and the rights issue status (issued or not issued) is defined as the output variable. To develop prediction models using C5.0 node (Node Options: Output type = Rule set, Use boosting = false, Cross-validate = false, Mode = Simple, Favor = Generality), we used 60% of data for model building and 40% of data for model test. The results of experimental analysis show that the prediction accuracies of data after the IMF financial crisis (59.04% to 60.43%) are about 10 percent higher than ones before IMF financial crisis (68.78% to 71.41%). These results indicate that since the IMF financial crisis, the reliability of financial analysis indices has increased and the firm intention of rights issue has been more obvious. The experiment results also show that the stability-related indices have a major impact on conducting rights issue in the case of short-term prediction. On the other hand, the long-term prediction of conducting rights issue is affected by financial analysis indices on profitability, stability, activity and productivity. All the prediction models include the industry code as one of significant variables. This means that companies in different types of industries show their different types of patterns for rights issue. We conclude that it is desirable for stakeholders to take into account stability-related indices and more various financial analysis indices for short-term prediction and long-term prediction, respectively. The current study has several limitations. First, we need to compare the differences in accuracy by using different data mining techniques such as neural networks, logistic regression and SVM. Second, we are required to develop and to evaluate new prediction models including variables which research in the theory of capital structure has mentioned about the relevance to rights issue.

• Radiation Oncology Journal
• /
• v.20 no.2
• /
• pp.108-115
• /
• 2002

Purpose : A retrospective study was undertaken to determine the role of conventional radiotherapy with or without surgery for treating a supraglottic carcinoma in terms of the local control and survival. Materials and Methods : From Jan. 1986 to Oct. 1996, a total of 134 patients were treated for a supraglottic carcinoma by radiotherapy with or without surgery. Of them, 117 patients who had completed the radiotherapy formed the base of this study. The patients were redistributed according to the revised AJCC staging system (1997). The number of patients of stage I, II, III, IVA, IVB were $6\;(5\%),\;16\;(14\%),\;53\;(45\%),\;32\;(27\%),\;10\;(9\%)$, respectively. Eighty patients were treated by radical radiotherapy in the range of $61.2\~79.2\;Gy$ (mean : 69.2 Gy) to the primary tumor and $45.0\~93.6\;Gy$ (mean : 54.0 Gy) to regional lymphatics. All patients with stage I and IVB were treated by radiotherapy alone. Thirty-seven patients underwent surgery plus postoperative radiotherapy in the range of $45.0\~68.4\;Gy$ (mean : 56.1 Gy) to the primary tumor bed and $45.0\~59.4\;Gy$ (mean : 47.2 Gy) to the regional lymphatics. Of them, 33 patients received a total laryngectomy (${\pm}lymph$ node dissection), three had a supraglottic horizontal laryngectomy (${\pm}lymph$ node dissection), and one had a primary excision alone. Results : The 5-year survival rate (5YSR) of all patients was $43\%$. The 5YSRs of the patients with stage I+II, III+IV were $49.9\%,\;41.2\%$, respectively (p=0.27). However, the disease-specific survival rate of the patients with stage I (n=6) was $100\%$. The 5YSRs of patients who underwent surgery plus radiotherapy (S+RT) vs radiotherapy alone (RT) in stage II, III, IVA were $100\%\;vs\;43\%$ (p=0.17), $62\%\;vs\;52\%$ (p=0.32), $58\%\;vs\;6\%$ (p<0.001), respectively. The 5-year actuarial locoregional control rate (5YLCR) of all the patients was $57\%$. The 5YLCR of the patients with stage I, II, III, IVA, IVB was $100\%,\;74\%,\;60\%,\;44\%,\;30\%$, respectively (p=0.008). The 5YLCR of the patients with S+RT vs RT in stage II, III, IVA was $100\%\;vs\;68\%$ (p=0.29), $67\%\;vs\;55\%$ (p=0.23), $81\%\;vs\;20\%$ (p<0.001), respectively. In the radiotherapy alone group, the 5YLCR of the patients with a complete, partial, and minimal response were $76\%,\;20\%,\;0\%$, respectively (p<0.001). In all patients, multivariate analysis showed that the N-stage, surgery or not, and age were significant factors affecting the survival rate and that the N-stage, surgery or not, and the ECOG performance index were significant factors affecting the locoregional control. In the radiotherapy alone group, multivariate analysis showed that the radiation response and N-stage were significant factors affecting the overall survival rate as well as locoregional control. Conclusion : In early stage supraglottic carcinoma, conventional radiotherapy alone is an equally effective modality compared to surgery plus radiotherapy and could preserve the laryngeal function. However, in the advanced stages, radiotherapy combined with concurrent chemotherapy for laryngeal preservation or surgery should be considered. In bulky neck disease, all the possible planned neck dissections after induction chemotherapy or before radiotherapy should be attempted.

• Korean Journal of Poultry Science
• /
• v.35 no.2
• /
• pp.143-151
• /
• 2008

This study was conducted to identify the correlation of bacterial phytase ($Transphos^{(R)}$) to the calcium level in feed. Of all 21-week-old 720 HyLine brown laying hens, 2 birds of similar weight were placed on each individual cage. The experiment was conducted by $3{\times}2{\times}3$ factorial design with including 3 different levels of phytase (0, 300, and 1,000 DPU/kg), 2 different levels of calcium (3.5% and 4.0%), and 3 different levels of no NPP addition 0% (0.095 NPP), 0.5% (0.185% NPP), and 1.0% (0.275% NPP). The feeding trial maintained the ME level of 2,800 kcal/kg and 16% for crude protein. The diet was fed ad libitum and 17 hours of lighting was provided throughout the experimental period. Egg production seemed to increase, in the 300 DPU of bacterial phytase added group and the cracked egg tended to reduce in Transphos added group. The egg productivity between treatment groups did not show significant difference by dietary calcium level, whereas non NPP added group (0.095% NPP) was found to be low compared to NPP added groups (P<0.05). The highest mean egg weight and the highest daily egg mass were detected in 300 DPU phytase added group. Although the mean egg weight was significantly higher in treatment groups fed with 3.5% calcium containing feeds (P<0.05), daily egg mass was no among treatment groups. The mean egg weight and daily egg mass were the lowest in non NPP added group (0.095% NPP) compared to other treatment groups (P<0.05). The feed intake showed similar pattern regardless of the bacterial phytase and calcium levels in the diet. However, the treatment groups fed diets containing NPP level of 0.275% and 0.165% showed significantly higher feed intake than the group fed with 0.095% NPP (P<0.05). Although the feed conversion was not affected by calcium and NPP levels in the diet, the most improved result was obtained from 300 DPU phytase added group (P<0.05). The eggshell breaking strength and thickness increased as dietary calcium level increase the level of calcium increases in diet. The treatment groups fed diet containing 0.275% and 0.165% NPP revealed to show improvement in eggshell breaking strength and yolk color index compared to the NPP non added (0.095% NPP) treatment group. The result of the present study suggests that the appropriate level of microbial phytase is 300 DPU and at this level, tricalciumphosphate supplementation in feed can be reduced to 40% of NRC recommendation. Higher calcium level in feed fail to show synergistic effect by adding microbial phytase.