• 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.

• Asian-Australasian Journal of Animal Sciences
• /
• v.27 no.2
• /
• pp.161-168
• /
• 2014

This study aimed to investigate dietary concentrate:forage ratios (C:F) and undegraded dietary protein (UDP) on nitrogen balance and urinary excretion of purine derivatives (PD) in lambs. Four Dorper${\times}$thin-tailed Han crossbred castrated lambs with $62.3{\pm}1.9$ kg body weight at 10 months of age were randomly assigned to four dietary treatments in a $2{\times}2$ factorial arrangement of two levels of C:F (40:60 and 60:40) and two levels of UDP (35% and 50% of CP), according to a complete $4{\times}4$ Latin-square design. Each experimental period lasted for 19 d. After a 7-d adaptation period, lambs were moved into individual metabolism crates for 12 d including 7 d of adaption and 5 d of metabolism trial. During the metabolism trial, total urine was collected for 24 h and spot urine samples were also collected at different times. Urinary PD was measured using a colorimetric method and creatinine was measured using an automated analyzer. Intake of dry matter (DM) (p<0.01) and organic matter (OM) (p<0.01) increased as the level of UDP decreased. Fecal N was not affected by dietary treatment (p>0.05) while urinary N increased as the level of UDP decreased (p<0.05), but decreased as dietary C:F increased (p<0.05). Nitrogen retention increased as dietary C:F increased (p<0.05). As dietary C:F increased, urinary excretion of PD increased (p<0.05), but was not affected by dietary UDP (p>0.05) or interaction between dietary treatments (p>0.05). Daily excretion of creatinine was not affected by dietary treatments (p<0.05), with an average value of $0.334{\times}0.005$ mmol/kg $BW^{0.75}$. A linear correlation was found between total PD excretion and PDC index ($R^2$ = 0.93). Concentrations of creatinine and PDC index in spot urine were unaffected by sampling time (p>0.05) and a good correlation was found between the PDC index (average value of three times) of spot urine and daily excretion of PD ($R^2$ = 0.88). These results suggest that for animals fed ad libitum, the PDC index in spot urine is effective to predict daily excretion of PD. In order to improve the accuracy of the spot sampling technique, an appropriate lag phase between the time of feeding and sampling should be determined so that the sampling time can coincide with the peak concentration of PD in the urine.

• Journal of Magnetics
• /
• v.20 no.4
• /
• pp.381-386
• /
• 2015

The purpose of this study is to improve diagnostic efficiency of clinical study by setting up guidelines for more precise examination with a comparative analysis of signal intensity and image distortion depending on the location of X axial of object when performing magnetic resonance diffusion weighted imaging (MR DWI) examination. We arranged the self-produced phantom with a 45 mm of interval from the core of 44 regent bottles that have a 16 mm of external diameter and 55 mm of height, and were placed in 4 rows and 11 columns in an acrylic box. We also filled up water and margarine to portrait the fat. We used 3T Skyra and 18 Channel Body array coil. We also obtained the coronal image with the direction of RL (right to left) by using scan slice thinkness 3 mm, slice gap: 0mm, field of view (FOV): $450{\times}450mm^2$, repetition time (TR): 5000 ms, echo time (TE): 73/118 ms, Matrix: $126{\times}126$, slice number: 15, scan time: 9 min 45sec, number of excitations (NEX): 3, phase encoding as a diffusion-weighted imaging parameter. In order to scan, we set b-value to $0s/mm^2$, $400s/mm^2$, and $1,400s/mm^2$, and obtained T2 fat saturation image. Then we did a comparative analysis on the differences between image distortion and signal intensity depending on the location of X axial based on iso-center of patient's table. We used "Image J" as a comparative analysis programme, and used SPSS v18.0 as a statistic programme. There was not much difference between image distortion and signal intensity on fat and water from T2 fat saturation image. But, the average value depends on the location of X axial was statistically significant (p < 0.05). From DWI image, when b-value was 0 and 400, there was no significant difference up to $2^{nd}$ columns right to left from the core of patient's table, however, there was a decline in signal intensity and image distortion from the $3^{rd}$ columns and they started to decrease rapidly at the $4^{th}$ columns. When b-value was 1,400, there was not much difference between the $1^{st}$ row right to left from the core of patient's table, however, image distortion started to appear from the $2^{nd}$ columns with no change in signal intensity, the signal was getting decreased from the $3^{rd}$ columns, and both signal intensity and image distortion started to get decreased rapidly. At this moment, the reagent bottles from outside out of 11 reagent bottles were not verified from the image, and only 9 reagent bottles were verified. However, it was not possible to verify anything from the $5^{th}$ columns. But, the average value depends on the location of X axial was statistically significant. On T2 FS image, there was a significant decline in image distortion and signal intensity over 180mm from the core of patient's table. On diffusion-weighted image, there was a significant decline in image distortion and signal intensity over 90 mm, and they became unverifiable over 180 mm. Therefore, we should make an image that has a diagnostic value from examinations that are hard to locate patient's position.

• Korean Journal of Soil Science and Fertilizer
• /
• v.37 no.4
• /
• pp.199-206
• /
• 2004

Factors of universal soil loss equation, USLE, and its revised version, RUSLE for Korean soils were reevaluated to estimate the national scale of soil loss based on digital soil maps. Rainfall erosivity factor, R, of 158 locations of cities and counties were spacially interpolated by the inverse distance weight method. Soil erodibility factor, K, of 1321 soil phases of 390 soil series were calculated using the data of soil survey and agri-environmental quality monitoring. Topographic factor, LS, was estimated using soil map of 1:25,000 scale with soil phase and land use type. Cover management factor, C, of major crops and support practice factor, P, were summarized by analyzing the data of lysimeter and field experiments for 27 years (1975-2001) in the National Institute of Agricultural Science and Technology. R factor varied between 2322 and 6408 MJ mm $ha^{-1}$ $yr^{-1}$ $hr^{-1}$ and the average value was 4276 MJ mm $ha^{-1}$ $yr^{-1}$ $hr^{-1}$. The average K value was evaluated as 0.027 MT hr $MJ^{-1}$ $mm^{-1}$. The highest K factor was found in paddy rice fields, 0.034 MT hr $MJ^{-1}$ $mm^{-1}$, and K factors in upland fields, grassland, and forest were 0.026, 0.019, and 0.020 MT hr $MJ^{-1}$ $mm^{-1}$, respectively. C factors of upland crops ranged from 0.06 to 0.45 and that of grassland was 0.003. P factor varied between 0.01 and 0.85.

• KSBB Journal
• /
• v.14 no.3
• /
• pp.309-314
• /
• 1999

In order to produce high concentration of sodium gluconate, optimization of the fermentation conditions, such as glucose concentration, inoculum size, dissolved oxygen concentration and glucose feeding method, was examined. When the glucose concentration was maintained in the range of 30∼50 g/L during the batch fermentation, glucose conversion yield and productivity were 92.2% and 6.0 g/L/hr, respectively. In the case of the low concentration below 30 g/L, the yield decreased by about 25%. As the inoculum size increased above 20%(w/v), lag phase was shortened but the productivity decreased. The dissolved oxygen level of 60∼70% was shown to be the threshold point for 75% of increase in the productivity of sodium gluconate. Finally, optimal glucose feeding rate was determined using various feeding methods such as exponential feeding, feeding based on the average glucose consumption rate and was determined using various feeding methods such as exponential feeding, feeding based on the average glucose consumption rate and on the oxygen uptake rate and etc. Our result shows that glucose feeding, based on the oxygen uptake rate is a very simple, efficient and robust method, especially when oxygen is consumed as a substrate for the bioconversion. Using the above glucose feeding strategy under the optimized condition, 255 g/L of sodium gluconate concentration, 12 g/L/hr of productivity and 95% of glucose conversion yield were achieved with A. niger ACM53.

• The Korean Journal of Nuclear Medicine
• /
• v.32 no.2
• /
• pp.151-160
• /
• 1998

Purpose: Piccolo et al. advocated the usefulness of $^{99m}Tc$-MDP breast scan in differential diagnosis of breast mass with high accuracy. But there are little or no follow-up studies about it as we know. We studied $^{99m}Tc$-MDP uptake pattern and lesion/background ratio in patients complaining palpable breast lesions to evaluate the clinical usefulness of $^{99m}Tc$-MDP scan. Materials and Methods: Total 34 patients were studied with physical examination, mammo-gram and $^{99m}Tc$-MDP scan prospectively. Anteroposterior and both lateral view of breast were obtained 5 minutes after iv injection of 740 MBq $^{99m}Tc$-MDP. Breast uptake pattern of $^{99m}Tc$-MDP was analyzed by a grade system: 0=no uptake, grade 1=bilateral diffuse uptake, grade 2=asymmetric faint uptake, grade 3=focal hot uptake. 20 cases were pathologically confirmed by excision biopsy or aspiration biopsy. 14 cases were normal in physical examination and mammogram. Results: Pathologic results showed 7 carcinomas, 6 benign solid tumors, and 7 fibrocystic changes. Grade 3 pattern of $^{99m}Tc$-MDP uptake was noted in 4/7 carcinomas, 3/6 benign solid tumors, and 1/7 fibrocystic changes. Grade 2 pattern was 217, 0/7, 3/7 respectively. The average L/B ratio was 1.66 in carcinomas, 1.68 in benign solid masses, 1.20 in fibrocystic diseases, 1.05 in normal patients. L/B ratio was higher in carcinoma and benign mass groups than in fibrocystic change and normal control groups(p=0.005). But there was no statistical difference between L/B ratio of malignant mass group and benign mass group. Conclusion: $^{99m}Tc$-MDP scan is not suitable to routine clinical use for breast mass diagnosis. It might be used in limited conditions when whole body bone scan is planned.

• The Korean Journal of Food And Nutrition
• /
• v.29 no.3
• /
• pp.301-306
• /
• 2016

Vitamin K (phylloquinone) is an essential cofactor in the synthesis of active blood-clotting factors II, VII, IX and X. Deficiency of vitamin K leads to inadequate activity of these factors, resulting in bleeding. In this study, we investigated vitamin $K_1$ content of agricultural products that are widely and specifically grown in Korea including 9 leaves and vegetables, 16 fruits, and 11 cereals and specialty crops. Vitamin $K_1$ analysis of the agro-samples was by a validated, modified, reversed phase-HPLC method with fluorescence detection after post-column derivatization. The vitamin $K_1$ content ranged from 1.83 to $682.73{\mu}g$/100 g in leaves and vegetables, 0.17 to $28.22{\mu}g$/100 g in fruits, and ND to $279{\mu}g$/100 g in cereals and specialty crops. Among the 36 samples, high content of vitamin $K_1$ were found in Gugija (Lycium chinense Miller) leaves (average $682.73{\mu}g$/100 g) and Hansan ramie leaves (average $423.12{\mu}g$/100 g); however, mushroom, amaranth and Chinese artichoke showed no detectable levels. The results of ourstudy provide reliable vitamin $K_1$ content of Korean grown agricultural products that expand nutritional information and food composition database.

• The Journal of the Korean bone and joint tumor society
• /
• v.3 no.2
• /
• pp.80-88
• /
• 1997

Malignant tumors of extremeties involving major neurovascular structures have been treated by amputation. However recent development of diagnostic tools(CT, MRI etc.), surgical techniques, anticancer chemotherapeutic agents, and radiation techniques allow surgeons to treat malignant tumors in the limb without amputation. It has been reported that a local application of low-heat to the tissue with tumor can kill tumor cells. It is, however, not known if the attendant neural and vascular injuries may be recovered. The present study was, therefore, undertakn to address this question in rabbit sciatic nerves. A low-heat injury to the sciatic nerve was induced by perfusing the nerve with $60^{\circ}C$ saline for 30 minutes and the courses of functional and morphological recovery of the nerve were evaluated for 16 weeks. The results are summerized as follows : 1. In the electromyographic nerve conduction test the average amplitude was markedly attenuated at 4 and 8 weeks after the low-heat treatment, but it progressively increased to the level 89.5% of the control at 16 week post-treatment. The average latency in the control group was 0.62 msec. The latency in the experimental group was much longer than this at 4 and 8 week post-treatment, but it progressively reverted to the control level, showing 0.622 msec at 16 weeks. 2. In the needle EMG, many fibrillation potentials and positive sharp waves were appeared until 8 weeks post-treatment. After 16 weeks, however, no fibrillation potential was observed. 3. In the early phase of post-treatment period, the myelinated nerve fibers contained many vacuoles and the number of myelinated nerve fibers appeared to be considerably reduced. However, as time goes myelinated nerve fibers were regenerated, such that after 16 weeks the histologic appearance of the nerve was similar to that of the control group.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.39 no.2
• /
• pp.97-104
• /
• 2019

This experiment was conducted to investigate the effect of whole crop rice (WCR) based TMR on growth performance and carcass characteristics of Hanwoo steers. WCR "Yeongwoo"was harvested at yellow ripen stage and ensiled for 60 days. The crude protein (CP), acid detergent fiber (ADF), neutral detergent fiber (NDF), in vitro dry matter digestibility (IVDMD) and total digestible nutrient (TDN) content was 8.4 %, 28.0 %, 53.8 %, 72.4 % and 66.8 %, respectively. For silage quality, pH was 4.37 and lactic and butyric acid content were 2.84 and 0.04 % in DM. Sixteen Hanwoo steers (8-mon-old) were allocated into either a control (commercial TMR) and WCR-TMR (WCR-based TMR) group. The TMR were fed according to the feeding stage phase: growing (Initiate~14 month), early fattening (15 month~21 month) and late fattening (22 month~30 month). The body weight of control group increased (P<0.05) until early fattening stage, but late growing stage of WCR-TMR group was higher than that of control (P<0.05). Average daily gain (ADG) was significantly greater (P<0.05) in WCR-TMR group (total 0.78 kg/head) compared to control (total 0.66 kg/head) except for late fattening stage. The marketing weight and carcass weight were higher in WCR-TMR group (726 vs 765 kg; 417.8 vs 450.4 kg). The back fat thickness (11.75 vs 13.00 mm), Longissimus dorsi area (88.00 vs $89.88cm^2$) and yield index (65.87 vs 64.30) were not different between the two groups (P>0.05) and also no difference in meat yield grade (A : B : C = 2 : 4 : 2). Marbling score (4.00 vs 4.13), meat color (4.75 vs 4.75), fat color (3.13 vs 2.88), texture (1.25 vs 1.50) and maturity (2.00 vs 2.00) were not significant difference between the two groups and meat quality grade ($1^{{+}{+}}:1^+:1:2:3=0:2:4:2:0$) was also not different. In conclusion, TMR feeding based on WCR silage showed superiority in carcass yield and ADG compared to control TMR. It is considered that the use of WCR for feed is a necessary option for the substitution of the imported forages and the government's policy for rice production adjustment.

• Journal of Food Hygiene and Safety
• /
• v.34 no.2
• /
• pp.115-123
• /
• 2019

An analytical method was developed for the determination of fenpropimorph, a morpholine fungicide, in hulled rice, potato, soybean, mandarin and green pepper using QuEChERS (Quick, Easy, Cheap, Effective, Rugged and Safe) sample preparation and LC-MS/MS (liquid chromatography-tandem mass spectrometry). The QuEChERS extraction was performed with acetonitrile followed by addition of anhydrous magnesium sulfate and sodium chloride. After centrifugation, d-SPE (dispersive solid phase extraction) cleanup was conducted using anhydrous magnesium sulfate, primary secondary amine sorbents and graphitized carbon black. The matrix-matched calibration curves were constructed using seven concentration levels, from 0.0025 to 0.25 mg/kg, and their correlation coefficient ($R^2$) of five agricultural products were higher than 0.9899. The limits of detection (LOD) and quantification (LOQ) were 0.001 and 0.0025 mg/kg, respectively, and the limits of quantification for the analytical method were 0.01 mg/kg. Average recoveries spiked at three levels (LOQ, $LOQ{\times}10$, $LOQ{\times}50$, n=5) and were in the range of 90.9~110.5% with associated relative standard deviation values less than 5.7%. As a result of the inter-laboratory validation, the average recoveries between the two laboratories were 88.6~101.4% and the coefficient of variation was also below 15%. All optimized results were satisfied the criteria ranges requested in the Codex guidelines and Food Safety Evaluation Department guidelines. This study could serve as a reference for safety management relative to fenpropimorph residues in imported and domestic agricultural products.