• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.7
• /
• pp.848-857
• /
• 2018

Recently, around the world, active development of new renewable energy sources including solar power, waves, and fuel cells, etc. has taken place. Particularly, floating offshore wind farms have been developed for saving costs through large scale production, using high-quality wind power and minimizing noise damage in the ocean area. The development of floating wind farms requires an evaluation of the Maritime Safety Audit Scheme under the Maritime Safety Act in Korea. Floating wind farms shall be assessed by applying the line and area concept for systematic development, management and utilization of specified sea water. The development of appropriate evaluation methods and standards is also required. In this study, proper standards for marine traffic surveys and assessments were established and a systemic treatment was studied for assessing marine spatial area. First, a marine traffic data collector using AIS or radar was designed to conduct marine traffic surveys. In addition, assessment methods were proposed such as historical tracks, traffic density and marine traffic pattern analysis applying the line and area concept. Marine traffic density can be evaluated by spatial and temporal means, with an adjusted grid-cell scale. Marine traffic pattern analysis was proposed for assessing ship movement patterns for transit or work in sea areas. Finally, conceptual design of a Marine Traffic and Safety Assessment Solution (MaTSAS) was competed that can be analyzed automatically to collect and assess the marine traffic data. It could be possible to minimize inaccurate estimation due to human errors such as data omission or misprints through automated and systematic collection, analysis and retrieval of marine traffic data. This study could provides reliable assessment results, reflecting the line and area concept, according to sea area usage.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.20 no.1
• /
• pp.73-87
• /
• 2018

A variety of micro meteorological variables such as air temperature, wind, solar radiation and latent heat at Gwangneung forests (conifer and broadleaved forests) and AWS (Automated Weather Station) of Pocheon urban area were used to quantify the air temperature reduction effect of forests, which is considered to be an eco-friendly solution for reducing the urban heat island intensity during summer. In June, July and August of 2016 and 2017, the average maximum air temperature differences between above and below canopy of forests, and between the forests and urban areas were $-1.9^{\circ}C$ and $-3.4^{\circ}C$ respectively, and they occurred at 17:00. However, there was no difference between conifer and broadleaved forests. The effect of air temperature reduction by the forests was positively correlated with accumulated evapotranspiration and solar radiation from 14:00 to 17:00 and showed a negative correlation with wind speed. We have developed a model to quantify the effect of air temperature reduction by forests using these variables. The nighttime air temperature reduction effect by forests was due to the generation of cold air from radiative cooling and the air temperature inversion phenomenon that occurs when the generated cold air moves down the side of mountain. The model was evaluated in Seoul by using 28 AWSs. The evaluation shows that the air temperature of each district in Seoul was negatively correlated with the area and size of the surrounding tall vegetation that drives vegetation evapotranspiration during the day. During the night, however, the size of the surrounding tall vegetation and the elevations of nearby mountains were the main influencing factors on the air temperature. Our research emphasizes the importance of the establishment and management of urban forests and the composition of wind roads from mountains for urban air temperature reduction.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.14 no.2
• /
• pp.208-211
• /
• 2010

Purpose: $TFB^{(R)}$ CA19-9 IRMA kit uses beads coated with CA19-9 antibody. However, this mathod can not use automated equipment, and requires a long time test. Recently, CA19-9 IRMA kit developed by $TFB^{(R)}$ is coated with CA19-9 antibody to the polystyrene test tube and reaction at room temperature, and also reduced test time. This study evaluated the performance of a newly developed $TFB^{(R)}$ CA19-9 IRMA kit. Materials and Methods: This study were measured by using 56 patients sample of Boramae Medical Center and Seoul National University Hospital. We evaluated intra-and inter-assay precision, recovery rate, linearity, sensitivity and high dose hook effect of coated tube CA19-9 IRMA kit developed by $TFB^{(R)}$. The values of CA19-9 measured by $TFB^{(R)}$ bead kit were compared with those measured by $TFB^{(R)}$ coated tube kit. Results: ntra-assay coefficients of variation on three different levels were 4.1%, 4.0% and 4.2%. Inter-assay coefficients of variation were 7.6%, 4.3% and 7.8%. Recovery tests on all three different levels showed within $100{\pm}10%$. Linearity was good and sensitivity was 0.3 U/mL. High dose hook effect is not observed. There was strong correlation between bead kit and coated tube kit by $TFB^{(R)}$ CA19-9 IRMA kit. (y=0.9185x-0.953, $R^2$=0.9779) Conclusion: Coated tube CA19-9 IRMA kit developed by $TFB^{(R)}$ showed satisfactory precision, recovery rate, linearity, sensitivity and high dose hook effect.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.34 no.3
• /
• pp.254-259
• /
• 2014

A pressurized heavy water reactor (PHWR) core has 380 fuel channels contained and supported by a horizontal cylindrical vessel known as the calandria, whereas a pressurized water reactor (PWR) has only a single reactor vessel. The pressure tube, which is a pressure-retaining component, has a 103.4 mm inside diameter ${\times}$ 4.19 mm wall thickness, and is 6.36 m long, made of a zirconium alloy (Zr-2.5 wt% Nb). This provides support for the fuel while transporting the $D_2O$ heat-transfer fluid. The simple tubular geometry invites highly automated inspection, and good approach for all inspection. Similar to all nuclear heat-transfer pressure boundaries, the PHWR pressure tube requires a rigorous, periodic inspection to assess the reactor integrity in accordance with the Korea Nuclear Safety Committee law. Volumetric-based nondestructive evaluation (NDE) techniques utilizing ultrasonic and eddy current testing have been adopted for use in the periodic inspection of the fuel channel. The eddy current testing, as a supplemental NDE method to ultrasonic testing, is used to confirm the flaws primarily detected through ultrasonic testing, however, eddy current testing offers a significant advantage in that its ability to detect surface flaws is superior to that of ultrasonic testing. In this paper, effectiveness of flaw detection and the depth sizing capability by eddy current testing for the inside surface of a pressure tube, will be introduced. As a result of this examination, the ET technique is found to be useful only as a detection technique for defects because it can detect fine defects on the surface with high resolution. However, the ET technique is not recommended for use as a depth sizing method because it has a large degree of error for depth sizing.

• The Journal of Korean Society for Radiation Therapy
• /
• v.21 no.2
• /
• pp.83-88
• /
• 2009

Purpose: Cone beam computed tomography (CBCT) using an on board imager (OBI) can check the movement and setup error in patient position and target volume by comparing with the image of computer simulation treatment in real.time during patient treatment. Thus, this study purposed to check the change and movement of patient position and target volume using CBCT in IMRT and calculate difference from the treatment plan, and then to correct the position using an automated match system and to test the accuracy of position correction using an electronic portal imaging device (EPID) and examine the usefulness of CBCT in IMRT and the accuracy of the automatic match system. Materials and Methods: The subjects of this study were 3 head and neck patients and 1 pelvis patient sampled from IMRT patients treated in our hospital. In order to investigate the movement of treatment position and resultant displacement of irradiated volume, we took CBCT using OBI mounted on the linear accelerator. Before each IMRT treatment, we took CBCT and checked difference from the treatment plan by coordinate by comparing it with the image of CT simulation. Then, we made correction through the automatic match system of 3D/3D match to match the treatment plan, and verified and evaluated using electronic portal imaging device. Results: When CBCT was compared with the image of CT simulation before treatment, the average difference by coordinate in the head and neck was 0.99 mm vertically, 1.14 mm longitudinally, 4.91 mm laterally, and 1.07o in the rotational direction, showing somewhat insignificant differences by part. In testing after correction, when the image from the electronic portal imaging device was compared with DRR image, it was found that correction had been made accurately with error less than 0.5 mm. Conclusion: By comparing a CBCT image before treatment with a 3D image reconstructed into a volume instead of a 2D image for the patient's setup error and change in the position of the organs and the target, we could measure and correct the change of position and target volume and treat more accurately, and could calculate and compare the errors. The results of this study show that CBCT was useful to deliver accurate treatment according to the treatment plan and to increase the reproducibility of repeated treatment, and satisfactory results were obtained. Accuracy enhanced through CBCT is highly required in IMRT, in which the shape of the target volume is complex and the change of dose distribution is radical. In addition, further research is required on the criteria for match focus by treatment site and treatment purpose.

• Journal of Korea Water Resources Association
• /
• v.53 no.9
• /
• pp.701-715
• /
• 2020

This study compared several reference evapotranspiration estimated using eight methods such as FAO-56 Penman-Monteith (FAO PM), Hamon, Hansen, Hargreaves-Samani, Jensen-Haise, Makkink, Priestley-Taylor, and Thornthwaite. In addition, by analyzing the monthly deviations of the results by the FAO PM and the remaining seven methods, monthly optimized correction coefficients were derived and the improvement effect was evaluated. These methods were applied to 73 automated synoptic observation system (ASOS) stations of the Korea Meteorological Administration, where the climatological data are available at least 20 years. As a result of evaluating the reference evapotranspiration by applying the default coefficients of each method, a large fluctuation happened depending on the method, and the Hansen method was relatively similar to FAO PM. However, the Hamon and Jensen-Haise methods showed more large values than other methods in summer, and the deviation from FAO PM method was also large significantly. When comparing based on the region, the comparison with FAO PM method provided that the reference evapotranspiration estimated by other methods was overestimated in most regions except for eastern coastal areas. Based on the deviation from the FAO PM method, the monthly correction coefficients were derived for each station. The monthly deviation average that ranged from -46 mm to +88 mm before correction was improved to -11 mm to +1 mm after correction, and the annual average deviation was also significantly reduced by correction from -393 mm to +354 mm (before correction) to -33 mm to +9 mm (after correction). In particular, Hamon, Hargreaves-Samani, and Thornthwaite methods using only temperature data also produced results that were not significantly different from FAO PM after correction. It can be also useful for forecasting long-term reference evapotranspiration using temperature data in climate change scenarios or predicting evapotranspiration using monthly or seasonal temperature forecasted values.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.627-646
• /
• 2022

Recently, the seriousness of climate change-related problems caused by global warming is growing, and the average temperature is also rising. As a result, it is affecting the environment in which various temperature-sensitive creatures and creatures live, and changes in the ecosystem are also being detected. Seasons are one of the important factors influencing the types, distribution, and growth characteristics of creatures living in the area. Among the most popular and easily recognized plant seasonal phenomena among the indicators of the climate change impact evaluation, the blooming day of flower and the peak day of autumn leaves were modeled. The types of plants used in the modeling were forsythia and cherry trees, which can be seen as representative plants of spring, and maple and ginkgo, which can be seen as representative plants of autumn. Weather data used to perform modeling were temperature, precipitation, and solar radiation observed through the ASOS Observatory of the Korea Meteorological Administration. As satellite data, MODIS NDVI was used for modeling, and it has a correlation coefficient of about -0.2 for the flowering date and 0.3 for the autumn leaves peak date. As the model used, the model was established using multiple regression models, which are linear models, and Random Forest, which are nonlinear models. In addition, the predicted values estimated by each model were expressed as isopleth maps using spatial interpolation techniques to express the trend of plant seasonal changes from 2003 to 2020. It is believed that using NDVI with high spatio-temporal resolution in the future will increase the accuracy of plant phenology modeling.

• Journal of the Korean Society of Radiology
• /
• v.82 no.5
• /
• pp.1207-1217
• /
• 2021

Purpose To evaluate the safety and efficacy of ultrasound-guided percutaneous core needle biopsy (USPCB) of pancreatic and peripancreatic lesions adjacent to critical vessels. Materials and Methods Data were collected retrospectively from 162 patients who underwent USPCB of the pancreas (n = 98), the peripancreatic area adjacent to the portal vein, the paraaortic area adjacent to pancreatic uncinate (n = 34), and lesions on the third duodenal portion (n = 30) during a 10-year period. An automated biopsy gun with an 18-gauge needle was used for biopsies under US guidance. The USPCB results were compared with those of the final follow-up imaging performed postoperatively. The diagnostic accuracy and major complication rate of the USPCB were calculated. Multiple factors were evaluated for the prediction of successful biopsies using univariate and multivariate analyses. Results The histopathologic diagnosis from USPCB was correct in 149 (92%) patients. The major complication rate was 3%. Four cases of mesenteric hematomas and one intramural hematoma of the duodenum occurred during the study period. The following factors were significantly associated with successful biopsies: a transmesenteric biopsy route rather than a transgastric or transenteric route; good visualization of targets; and evaluation of the entire US pathway. In addition, the number of biopsies required was less when the biopsy was successful. Conclusion USPCB demonstrated high diagnostic accuracy and a low complication rate for the histopathologic diagnosis of pancreatic and peripancreatic lesions adjacent to critical vessels.

• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.109-125
• /
• 2020

The Ministry of National Defense is pushing for the Defense Acquisition Program to build strong defense capabilities, and it spends more than 10 trillion won annually on defense improvement. As the Defense Acquisition Program is directly related to the security of the nation as well as the lives and property of the people, it must be carried out very transparently and efficiently by experts. However, the excessive diversification of laws and regulations related to the Defense Acquisition Program has made it challenging for many working-level officials to carry out the Defense Acquisition Program smoothly. It is even known that many people realize that there are related regulations that they were unaware of until they push ahead with their work. In addition, the statutory statements related to the Defense Acquisition Program have the tendency to cause serious issues even if only a single expression is wrong within the sentence. Despite this, efforts to establish a sentence comparison system to correct this issue in real time have been minimal. Therefore, this paper tries to propose a "Comparison System between the Statement of Military Reports and Related Laws" implementation plan that uses the Siamese Network-based artificial neural network, a model in the field of natural language processing (NLP), to observe the similarity between sentences that are likely to appear in the Defense Acquisition Program related documents and those from related statutory provisions to determine and classify the risk of illegality and to make users aware of the consequences. Various artificial neural network models (Bi-LSTM, Self-Attention, D_Bi-LSTM) were studied using 3,442 pairs of "Original Sentence"(described in actual statutes) and "Edited Sentence"(edited sentences derived from "Original Sentence"). Among many Defense Acquisition Program related statutes, DEFENSE ACQUISITION PROGRAM ACT, ENFORCEMENT RULE OF THE DEFENSE ACQUISITION PROGRAM ACT, and ENFORCEMENT DECREE OF THE DEFENSE ACQUISITION PROGRAM ACT were selected. Furthermore, "Original Sentence" has the 83 provisions that actually appear in the Act. "Original Sentence" has the main 83 clauses most accessible to working-level officials in their work. "Edited Sentence" is comprised of 30 to 50 similar sentences that are likely to appear modified in the county report for each clause("Original Sentence"). During the creation of the edited sentences, the original sentences were modified using 12 certain rules, and these sentences were produced in proportion to the number of such rules, as it was the case for the original sentences. After conducting 1 : 1 sentence similarity performance evaluation experiments, it was possible to classify each "Edited Sentence" as legal or illegal with considerable accuracy. In addition, the "Edited Sentence" dataset used to train the neural network models contains a variety of actual statutory statements("Original Sentence"), which are characterized by the 12 rules. On the other hand, the models are not able to effectively classify other sentences, which appear in actual military reports, when only the "Original Sentence" and "Edited Sentence" dataset have been fed to them. The dataset is not ample enough for the model to recognize other incoming new sentences. Hence, the performance of the model was reassessed by writing an additional 120 new sentences that have better resemblance to those in the actual military report and still have association with the original sentences. Thereafter, we were able to check that the models' performances surpassed a certain level even when they were trained merely with "Original Sentence" and "Edited Sentence" data. If sufficient model learning is achieved through the improvement and expansion of the full set of learning data with the addition of the actual report appearance sentences, the models will be able to better classify other sentences coming from military reports as legal or illegal. Based on the experimental results, this study confirms the possibility and value of building "Real-Time Automated Comparison System Between Military Documents and Related Laws". The research conducted in this experiment can verify which specific clause, of several that appear in related law clause is most similar to the sentence that appears in the Defense Acquisition Program-related military reports. This helps determine whether the contents in the military report sentences are at the risk of illegality when they are compared with those in the law clauses.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.83-102
• /
• 2021

The government recently announced various policies for developing big-data and artificial intelligence fields to provide a great opportunity to the public with respect to disclosure of high-quality data within public institutions. KSURE(Korea Trade Insurance Corporation) is a major public institution for financial policy in Korea, and thus the company is strongly committed to backing export companies with various systems. Nevertheless, there are still fewer cases of realized business model based on big-data analyses. In this situation, this paper aims to develop a new business model which can be applied to an ex-ante prediction for the likelihood of the insurance accident of credit guarantee. We utilize internal data from KSURE which supports export companies in Korea and apply machine learning models. Then, we conduct performance comparison among the predictive models including Logistic Regression, Random Forest, XGBoost, LightGBM, and DNN(Deep Neural Network). For decades, many researchers have tried to find better models which can help to predict bankruptcy since the ex-ante prediction is crucial for corporate managers, investors, creditors, and other stakeholders. The development of the prediction for financial distress or bankruptcy was originated from Smith(1930), Fitzpatrick(1932), or Merwin(1942). One of the most famous models is the Altman's Z-score model(Altman, 1968) which was based on the multiple discriminant analysis. This model is widely used in both research and practice by this time. The author suggests the score model that utilizes five key financial ratios to predict the probability of bankruptcy in the next two years. Ohlson(1980) introduces logit model to complement some limitations of previous models. Furthermore, Elmer and Borowski(1988) develop and examine a rule-based, automated system which conducts the financial analysis of savings and loans. Since the 1980s, researchers in Korea have started to examine analyses on the prediction of financial distress or bankruptcy. Kim(1987) analyzes financial ratios and develops the prediction model. Also, Han et al.(1995, 1996, 1997, 2003, 2005, 2006) construct the prediction model using various techniques including artificial neural network. Yang(1996) introduces multiple discriminant analysis and logit model. Besides, Kim and Kim(2001) utilize artificial neural network techniques for ex-ante prediction of insolvent enterprises. After that, many scholars have been trying to predict financial distress or bankruptcy more precisely based on diverse models such as Random Forest or SVM. One major distinction of our research from the previous research is that we focus on examining the predicted probability of default for each sample case, not only on investigating the classification accuracy of each model for the entire sample. Most predictive models in this paper show that the level of the accuracy of classification is about 70% based on the entire sample. To be specific, LightGBM model shows the highest accuracy of 71.1% and Logit model indicates the lowest accuracy of 69%. However, we confirm that there are open to multiple interpretations. In the context of the business, we have to put more emphasis on efforts to minimize type 2 error which causes more harmful operating losses for the guaranty company. Thus, we also compare the classification accuracy by splitting predicted probability of the default into ten equal intervals. When we examine the classification accuracy for each interval, Logit model has the highest accuracy of 100% for 0~10% of the predicted probability of the default, however, Logit model has a relatively lower accuracy of 61.5% for 90~100% of the predicted probability of the default. On the other hand, Random Forest, XGBoost, LightGBM, and DNN indicate more desirable results since they indicate a higher level of accuracy for both 0~10% and 90~100% of the predicted probability of the default but have a lower level of accuracy around 50% of the predicted probability of the default. When it comes to the distribution of samples for each predicted probability of the default, both LightGBM and XGBoost models have a relatively large number of samples for both 0~10% and 90~100% of the predicted probability of the default. Although Random Forest model has an advantage with regard to the perspective of classification accuracy with small number of cases, LightGBM or XGBoost could become a more desirable model since they classify large number of cases into the two extreme intervals of the predicted probability of the default, even allowing for their relatively low classification accuracy. Considering the importance of type 2 error and total prediction accuracy, XGBoost and DNN show superior performance. Next, Random Forest and LightGBM show good results, but logistic regression shows the worst performance. However, each predictive model has a comparative advantage in terms of various evaluation standards. For instance, Random Forest model shows almost 100% accuracy for samples which are expected to have a high level of the probability of default. Collectively, we can construct more comprehensive ensemble models which contain multiple classification machine learning models and conduct majority voting for maximizing its overall performance.