• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.23-48
• /
• 2021

The Korean economy has achieved continuous economic growth for the past several decades thanks to the government's export strategy policy. This increase in exports is playing a leading role in driving Korea's economic growth by improving economic efficiency, creating jobs, and promoting technology development. Traditionally, the main factors affecting Korea's exports can be found from two perspectives: economic factors and industrial structural factors. First, economic factors are related to exchange rates and global economic fluctuations. The impact of the exchange rate on Korea's exports depends on the exchange rate level and exchange rate volatility. Global economic fluctuations affect global import demand, which is an absolute factor influencing Korea's exports. Second, industrial structural factors are unique characteristics that occur depending on industries or products, such as slow international division of labor, increased domestic substitution of certain imported goods by China, and changes in overseas production patterns of major export industries. Looking at the most recent studies related to global exchanges, several literatures show the importance of cultural aspects as well as economic and industrial structural factors. Therefore, this study attempted to develop a forecasting model by considering cultural factors along with economic and industrial structural factors in calculating the import volume of each country from Korea. In particular, this study approaches the influence of cultural factors on imports of Korean products from the perspective of PUSH-PULL framework. The PUSH dimension is a perspective that Korea develops and actively promotes its own brand and can be defined as the degree of interest in each country for Korean brands represented by K-POP, K-FOOD, and K-CULTURE. In addition, the PULL dimension is a perspective centered on the cultural and psychological characteristics of the people of each country. This can be defined as how much they are inclined to accept Korean Flow as each country's cultural code represented by the country's governance system, masculinity, risk avoidance, and short-term/long-term orientation. The unique feature of this study is that the proposed final prediction model can be selected based on Design Principles. The design principles we presented are as follows. 1) A model was developed to reflect interest in Korea and cultural characteristics through newly added data sources. 2) It was designed in a practical and convenient way so that the forecast value can be immediately recalled by inputting changes in economic factors, item code and country code. 3) In order to derive theoretically meaningful results, an algorithm was selected that can interpret the relationship between the input and the target variable. This study can suggest meaningful implications from the technical, economic and policy aspects, and is expected to make a meaningful contribution to the export support strategies of small and medium-sized enterprises by using the import forecasting model.

• The Journal of Korean Society for Radiation Therapy
• /
• v.33
• /
• pp.127-135
• /
• 2021

Purpose : The purpose of the study is to evaluate the efficiency of Vertical MLC VMAT plan(VMV plan) Using 273° and 350° collimator angle compare to Complemental MLC VMAT plan(CMV plan) using 20° and 340° collimator angle for nasopharyngeal carcinoma. Materials & Methods : Thirty patients treated for nasopharyngeal carcinoma with the VMAT technique were retrospectively selected. Those cases were planned by Eclipse, PO and AcurosXB Algorithm with two 6MV 360° arcs and Each arc has 273° and 350° of collimator angle. The Complemental MLC VMAT plans are based on existing treatment plans. Those plans have the same parameters of existing treatment plans but collimator angle. For dosimetric evaluation, the dose-volumetric(DV) parameters of the planning target volume (PTV) and organs at risk (OARs) were calculated for all VMAT plans. MCSv(Modulation complexity score of VMAT), MU and treatment time were also compared. In addition, Pearson's correlation analysis was performed to confirm whether there was a correlation between the difference in the MCSv and the difference in each evaluation index of the two treatment plans. Result : In the case of PTV evaluation index, the CI of PTV_67.5 was improved by 3.76% in the VMV Plan, then for OAR, the dose reduction effect of the spinal cord (-14.05%) and brain stem (-9.34%) was remarkable. In addition, the parotid glands (left parotid : -5.38%, right : -5.97%) and visual organs (left optic nerve: -4.88%, right optic nerve: -5.80%, optic chiasm : -6.12%, left lens: -6.12%, right lens: -5.26%), auditory organs (left: -11.74%, right: -12.31%) and thyroid gland (-2.02%) were also confirmed. The difference in MCSv of the two treatment plans showed a significant negative (-) correlation with the difference in CI (r=-0.55) of PTV_54 and the difference in CI (r=-0.43) of PTV_48. Spinal cord (r=0.40), brain stem (r=0.34), and both salivary glands (left: r=0.36, right: r=0.37) showed a positive (+) correlation. (For all the values, p<.05) Conclusion : Compared to the CMV plan, the VMV plan is considered to be helpful in improving the quality of the treatment plan by allowing the MLC to be modulated more efficiently

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.69-88
• /
• 2022

One of the characteristics of South Korea's economic structure is that it is highly dependent on exports. Thus, many businesses are closely related to the global economy and diplomatic situation. In addition, small and medium-sized enterprises(SMEs) specialized in exporting are struggling due to the spread of COVID-19. Therefore, this study aimed to develop a model to forecast exports for next year to support SMEs' export strategy and decision making. Also, this study proposed a strategy to recommend promising export countries of each item based on the forecasting model. We analyzed important variables used in previous studies such as country-specific, item-specific, and macro-economic variables and collected those variables to train our prediction model. Next, through the exploratory data analysis(EDA) it was found that exports, which is a target variable, have a highly skewed distribution. To deal with this issue and improve predictive performance, we suggest a separated learning method. In a separated learning method, the whole dataset is divided into homogeneous subgroups and a prediction algorithm is applied to each group. Thus, characteristics of each group can be more precisely trained using different input variables and algorithms. In this study, we divided the dataset into five subgroups based on the exports to decrease skewness of the target variable. After the separation, we found that each group has different characteristics in countries and goods. For example, In Group 1, most of the exporting countries are developing countries and the majority of exporting goods are low value products such as glass and prints. On the other hand, major exporting countries of South Korea such as China, USA, and Vietnam are included in Group 4 and Group 5 and most exporting goods in these groups are high value products. Then we used LightGBM(LGBM) and Exponential Moving Average(EMA) for prediction. Considering the characteristics of each group, models were built using LGBM for Group 1 to 4 and EMA for Group 5. To evaluate the performance of the model, we compare different model structures and algorithms. As a result, it was found that the separated learning model had best performance compared to other models. After the model was built, we also provided variable importance of each group using SHAP-value to add explainability of our model. Based on the prediction model, we proposed a second-stage recommendation strategy for potential export countries. In the first phase, BCG matrix was used to find Star and Question Mark markets that are expected to grow rapidly. In the second phase, we calculated scores for each country and recommendations were made according to ranking. Using this recommendation framework, potential export countries were selected and information about those countries for each item was presented. There are several implications of this study. First of all, most of the preceding studies have conducted research on the specific situation or country. However, this study use various variables and develops a machine learning model for a wide range of countries and items. Second, as to our knowledge, it is the first attempt to adopt a separated learning method for exports prediction. By separating the dataset into 5 homogeneous subgroups, we could enhance the predictive performance of the model. Also, more detailed explanation of models by group is provided using SHAP values. Lastly, this study has several practical implications. There are some platforms which serve trade information including KOTRA, but most of them are based on past data. Therefore, it is not easy for companies to predict future trends. By utilizing the model and recommendation strategy in this research, trade related services in each platform can be improved so that companies including SMEs can fully utilize the service when making strategies and decisions for exports.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.207-221
• /
• 2023

This study suggests deep neural network models for estimating air temperature with Level 1B (L1B) datasets of GEO-KOMPSAT-2A (GK-2A). The temperature at 1.5 m above the ground impact not only daily life but also weather warnings such as cold and heat waves. There are many studies to assume the air temperature from the land surface temperature (LST) retrieved from satellites because the air temperature has a strong relationship with the LST. However, an algorithm of the LST, Level 2 output of GK-2A, works only clear sky pixels. To overcome the cloud effects, we apply a deep neural network (DNN) model to assume the air temperature with L1B calibrated for radiometric and geometrics from raw satellite data and compare the model with a linear regression model between LST and air temperature. The root mean square errors (RMSE) of the air temperature for model outputs are used to evaluate the model. The number of 95 in-situ air temperature data was 2,496,634 and the ratio of datasets paired with LST and L1B show 42.1% and 98.4%. The training years are 2020 and 2021 and 2022 is used to validate. The DNN model is designed with an input layer taking 16 channels and four hidden fully connected layers to assume an air temperature. As a result of the model using 16 bands of L1B, the DNN with RMSE 2.22℃ showed great performance than the baseline model with RMSE 3.55℃ on clear sky conditions and the total RMSE including overcast samples was 3.33℃. It is suggested that the DNN is able to overcome cloud effects. However, it showed different characteristics in seasonal and hourly analysis and needed to append solar information as inputs to make a general DNN model because the summer and winter seasons showed a low coefficient of determinations with high standard deviations.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.979-995
• /
• 2023

As wildfires are difficult to predict, real-time monitoring is crucial for a timely response. Geostationary satellite images are very useful for active fire detection because they can monitor a vast area with high temporal resolution (e.g., 2 min). Existing satellite-based active fire detection algorithms detect thermal outliers using threshold values based on the statistical analysis of brightness temperature. However, the difficulty in establishing suitable thresholds for such threshold-based methods hinders their ability to detect fires with low intensity and achieve generalized performance. In light of these challenges, machine learning has emerged as a potential-solution. Until now, relatively simple techniques such as random forest, Vanilla convolutional neural network (CNN), and U-net have been applied for active fire detection. Therefore, this study proposed an active fire detection algorithm using state-of-the-art (SOTA) deep learning techniques using data from the Advanced Himawari Imager and evaluated it over East Asia and Australia. The SOTA model was developed by applying EfficientNet and lion optimizer, and the results were compared with the model using the Vanilla CNN structure. EfficientNet outperformed CNN with F1-scores of 0.88 and 0.83 in East Asia and Australia, respectively. The performance was better after using weighted loss, equal sampling, and image augmentation techniques to fix data imbalance issues compared to before the techniques were used, resulting in F1-scores of 0.92 in East Asia and 0.84 in Australia. It is anticipated that timely responses facilitated by the SOTA deep learning-based approach for active fire detection will effectively mitigate the damage caused by wildfires.

• Korean Chemical Engineering Research
• /
• v.61 no.4
• /
• pp.523-541
• /
• 2023

As accessibility to 3D printers increases, there is a growing frequency of exposure to chemicals associated with 3D printing. However, research on the toxicity and harmfulness of chemicals generated by 3D printing is insufficient, and the performance of toxicity prediction using in silico techniques is limited due to missing molecular structure data. In this study, quantitative structure-activity relationship (QSAR) model based on data-centric AI approach was developed to predict the toxicity of new 3D printing materials by imputing missing values in molecular descriptors. First, MissForest algorithm was utilized to impute missing values in molecular descriptors of hazardous 3D printing materials. Then, based on four different machine learning models (decision tree, random forest, XGBoost, SVM), a machine learning (ML)-based QSAR model was developed to predict the bioconcentration factor (Log BCF), octanol-air partition coefficient (Log Koa), and partition coefficient (Log P). Furthermore, the reliability of the data-centric QSAR model was validated through the Tree-SHAP (SHapley Additive exPlanations) method, which is one of explainable artificial intelligence (XAI) techniques. The proposed imputation method based on the MissForest enlarged approximately 2.5 times more molecular structure data compared to the existing data. Based on the imputed dataset of molecular descriptor, the developed data-centric QSAR model achieved approximately 73%, 76% and 92% of prediction performance for Log BCF, Log Koa, and Log P, respectively. Lastly, Tree-SHAP analysis demonstrated that the data-centric-based QSAR model achieved high prediction performance for toxicity information by identifying key molecular descriptors highly correlated with toxicity indices. Therefore, the proposed QSAR model based on the data-centric XAI approach can be extended to predict the toxicity of potential pollutants in emerging printing chemicals, chemical process, semiconductor or display process.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.17 no.1
• /
• pp.13-28
• /
• 2022

Korean Government Budget Supports for startups have been spiked and resulted in increasing the number and scaling up Startup Accelerating managers. It have skyrocketed the strong demand for their qualified roles. However, unclear role description and gap between required role and their capability have discouraged startup manager's self-efficacy resulted in declining their full commitment and causing poor role performance. The focus of this research falls on empirical analysis to the effect of startup accelerating manager's capability characteristics on their full commitment and performance to start-up support groups. This research is expected to deliver diverse policy alternatives to build up manager's core competencies to accelerate their self-efficacy leading their full role commitments and finally pushing up policy performance. In addition, this research will found more strong literature review for the following researches in this emerging fields. This research is brought four highlighting results with respect to four research problems. First, it propose proper concept of startup accelerating manager based upon its legal entitlement. Second, it drive required core competencies of manager for successful their accountability. Third, it analyze the unique features of startup accelerating manger's capabilities against business incubation manger. Fourth, it empirically analyze in coming with government startup funding, the effect of self-efficacy including employment status, job environment, etc. on their organizational commitment and job performance. This research reveal the required unique core competencies of manger into founder sourcing ability, project managing ability, startup proving and pivoting ability, consulting ability for successful investment raising. As of this empirical research results, First, manager's ability have positively effect on their job performance, full commitment, and self-efficacy. Second, self-efficacy have a mediating effect on manager's ability, job performance, full commitment. This research derive key policy implication of requiring to build up more accelerating ability, of manager from the basics to advance level by customized and algorithm based traing program. This accelerating ability buildup program will not only surge self-efficacy of manger resulting in making full commitment and better job performance, but also devote to categorizing the unique new feature and position of manger as seed investment and supporter.

• Korean Journal of Heritage: History & Science
• /
• v.57 no.1
• /
• pp.82-108
• /
• 2024

With the transition of archaeological recording method's transition from analog to digital, the 3D scanning technology has been actively adopted within the field. Research on the digital archaeological digital data gathered from 3D scanning and photogrammetry is continuously being conducted. However, due to cost and manpower issues, most buried cultural heritage organizations are hesitating to adopt such digital technology. This paper aims to present a digital recording method of relics utilizing open-source software and photogrammetry technology, which is believed to be the most efficient method among 3D scanning methods. The digital recording process of relics consists of three stages: acquiring a 3D model, creating a joining map with the edited 3D model, and creating an digital drawing. In order to enhance the accessibility, this method only utilizes open-source software throughout the entire process. The results of this study confirms that in terms of quantitative evaluation, the deviation of numerical measurement between the actual artifact and the 3D model was minimal. In addition, the results of quantitative quality analysis from the open-source software and the commercial software showed high similarity. However, the data processing time was overwhelmingly fast for commercial software, which is believed to be a result of high computational speed from the improved algorithm. In qualitative evaluation, some differences in mesh and texture quality occurred. In the 3D model generated by opensource software, following problems occurred: noise on the mesh surface, harsh surface of the mesh, and difficulty in confirming the production marks of relics and the expression of patterns. However, some of the open source software did generate the quality comparable to that of commercial software in quantitative and qualitative evaluations. Open-source software for editing 3D models was able to not only post-process, match, and merge the 3D model, but also scale adjustment, join surface production, and render image necessary for the actual measurement of relics. The final completed drawing was tracked by the CAD program, which is also an open-source software. In archaeological research, photogrammetry is very applicable to various processes, including excavation, writing reports, and research on numerical data from 3D models. With the breakthrough development of computer vision, the types of open-source software have been diversified and the performance has significantly improved. With the high accessibility to such digital technology, the acquisition of 3D model data in archaeology will be used as basic data for preservation and active research of cultural heritage.

• Journal of the Korean Society of Radiology
• /
• v.84 no.5
• /
• pp.1123-1133
• /
• 2023

Purpose Our study aimed to evaluate the association between automated quantified body composition on CT and pulmonary function or quantitative lung features in patients with chronic obstructive pulmonary disease (COPD). Materials and Methods A total of 290 patients with COPD were enrolled in this study. The volume of muscle and subcutaneous fat, area of muscle and subcutaneous fat at T12, and bone attenuation at T12 were obtained from chest CT using a deep learning-based body segmentation algorithm. Parametric response mapping-derived emphysema (PRM^emph), PRM-derived functional small airway disease (PRM^fSAD), and airway wall thickness (AWT)-Pi10 were quantitatively assessed. The association between body composition and outcomes was evaluated using Pearson's correlation analysis. Results The volume and area of muscle and subcutaneous fat were negatively associated with PRM^emph and PRM^fSAD (p < 0.05). Bone density at T12 was negatively associated with PRM^emph (r = -0.1828, p = 0.002). The volume and area of subcutaneous fat and bone density at T12 were positively correlated with AWT-Pi10 (r = 0.1287, p = 0.030; r = 0.1668, p = 0.005; r = 0.1279, p = 0.031). However, muscle volume was negatively correlated with the AWT-Pi10 (r = -0.1966, p = 0.001). Muscle volume was significantly associated with pulmonary function (p < 0.001). Conclusion Body composition, automatically assessed using chest CT, is associated with the phenotype and severity of COPD.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.135-149
• /
• 2020

Artificial intelligences are changing world. Financial market is also not an exception. Robo-Advisor is actively being developed, making up the weakness of traditional asset allocation methods and replacing the parts that are difficult for the traditional methods. It makes automated investment decisions with artificial intelligence algorithms and is used with various asset allocation models such as mean-variance model, Black-Litterman model and risk parity model. Risk parity model is a typical risk-based asset allocation model which is focused on the volatility of assets. It avoids investment risk structurally. So it has stability in the management of large size fund and it has been widely used in financial field. XGBoost model is a parallel tree-boosting method. It is an optimized gradient boosting model designed to be highly efficient and flexible. It not only makes billions of examples in limited memory environments but is also very fast to learn compared to traditional boosting methods. It is frequently used in various fields of data analysis and has a lot of advantages. So in this study, we propose a new asset allocation model that combines risk parity model and XGBoost machine learning model. This model uses XGBoost to predict the risk of assets and applies the predictive risk to the process of covariance estimation. There are estimated errors between the estimation period and the actual investment period because the optimized asset allocation model estimates the proportion of investments based on historical data. these estimated errors adversely affect the optimized portfolio performance. This study aims to improve the stability and portfolio performance of the model by predicting the volatility of the next investment period and reducing estimated errors of optimized asset allocation model. As a result, it narrows the gap between theory and practice and proposes a more advanced asset allocation model. In this study, we used the Korean stock market price data for a total of 17 years from 2003 to 2019 for the empirical test of the suggested model. The data sets are specifically composed of energy, finance, IT, industrial, material, telecommunication, utility, consumer, health care and staple sectors. We accumulated the value of prediction using moving-window method by 1,000 in-sample and 20 out-of-sample, so we produced a total of 154 rebalancing back-testing results. We analyzed portfolio performance in terms of cumulative rate of return and got a lot of sample data because of long period results. Comparing with traditional risk parity model, this experiment recorded improvements in both cumulative yield and reduction of estimated errors. The total cumulative return is 45.748%, about 5% higher than that of risk parity model and also the estimated errors are reduced in 9 out of 10 industry sectors. The reduction of estimated errors increases stability of the model and makes it easy to apply in practical investment. The results of the experiment showed improvement of portfolio performance by reducing the estimated errors of the optimized asset allocation model. Many financial models and asset allocation models are limited in practical investment because of the most fundamental question of whether the past characteristics of assets will continue into the future in the changing financial market. However, this study not only takes advantage of traditional asset allocation models, but also supplements the limitations of traditional methods and increases stability by predicting the risks of assets with the latest algorithm. There are various studies on parametric estimation methods to reduce the estimated errors in the portfolio optimization. We also suggested a new method to reduce estimated errors in optimized asset allocation model using machine learning. So this study is meaningful in that it proposes an advanced artificial intelligence asset allocation model for the fast-developing financial markets.