• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.127-146
• /
• 2017

Services using artificial intelligence have begun to emerge in daily life. Artificial intelligence is applied to products in consumer electronics and communications such as artificial intelligence refrigerators and speakers. In the financial sector, using Kensho's artificial intelligence technology, the process of the stock trading system in Goldman Sachs was improved. For example, two stock traders could handle the work of 600 stock traders and the analytical work for 15 people for 4weeks could be processed in 5 minutes. Especially, big data analysis through machine learning among artificial intelligence fields is actively applied throughout the financial industry. The stock market analysis and investment modeling through machine learning theory are also actively studied. The limits of linearity problem existing in financial time series studies are overcome by using machine learning theory such as artificial intelligence prediction model. The study of quantitative financial data based on the past stock market-related numerical data is widely performed using artificial intelligence to forecast future movements of stock price or indices. Various other studies have been conducted to predict the future direction of the market or the stock price of companies by learning based on a large amount of text data such as various news and comments related to the stock market. Investing on commodity asset, one of alternative assets, is usually used for enhancing the stability and safety of traditional stock and bond asset portfolio. There are relatively few researches on the investment model about commodity asset than mainstream assets like equity and bond. Recently machine learning techniques are widely applied on financial world, especially on stock and bond investment model and it makes better trading model on this field and makes the change on the whole financial area. In this study we made investment model using Support Vector Machine among the machine learning models. There are some researches on commodity asset focusing on the price prediction of the specific commodity but it is hard to find the researches about investment model of commodity as asset allocation using machine learning model. We propose a method of forecasting four major commodity indices, portfolio made of commodity futures, and individual commodity futures, using SVM model. The four major commodity indices are Goldman Sachs Commodity Index(GSCI), Dow Jones UBS Commodity Index(DJUI), Thomson Reuters/Core Commodity CRB Index(TRCI), and Rogers International Commodity Index(RI). We selected each two individual futures among three sectors as energy, agriculture, and metals that are actively traded on CME market and have enough liquidity. They are Crude Oil, Natural Gas, Corn, Wheat, Gold and Silver Futures. We made the equally weighted portfolio with six commodity futures for comparing with other commodity indices. We set the 19 macroeconomic indicators including stock market indices, exports & imports trade data, labor market data, and composite leading indicators as the input data of the model because commodity asset is very closely related with the macroeconomic activities. They are 14 US economic indicators, two Chinese economic indicators and two Korean economic indicators. Data period is from January 1990 to May 2017. We set the former 195 monthly data as training data and the latter 125 monthly data as test data. In this study, we verified that the performance of the equally weighted commodity futures portfolio rebalanced by the SVM model is better than that of other commodity indices. The prediction accuracy of the model for the commodity indices does not exceed 50% regardless of the SVM kernel function. On the other hand, the prediction accuracy of equally weighted commodity futures portfolio is 53%. The prediction accuracy of the individual commodity futures model is better than that of commodity indices model especially in agriculture and metal sectors. The individual commodity futures portfolio excluding the energy sector has outperformed the three sectors covered by individual commodity futures portfolio. In order to verify the validity of the model, it is judged that the analysis results should be similar despite variations in data period. So we also examined the odd numbered year data as training data and the even numbered year data as test data and we confirmed that the analysis results are similar. As a result, when we allocate commodity assets to traditional portfolio composed of stock, bond, and cash, we can get more effective investment performance not by investing commodity indices but by investing commodity futures. Especially we can get better performance by rebalanced commodity futures portfolio designed by SVM model.

• Journal of Animal Science and Technology
• /
• v.51 no.5
• /
• pp.369-378
• /
• 2009

Protein fractionation was evaluated from whole crop silages of rye (RS), wheat (WS), triticale (TS), oat (OS), barley (BS), and rice straw silage (RSS), and in vitro trial was carried out to examine the effect of silage and extraction of soluble protein on fermentation characteristics, total gas production and degradation. Soluble protein of silages was extracted with borate-phosphate buffer, and fermentation characteristics, gas production and degradation of silages were estimated by incubating anaerobically the mixed solution of strained rumen fluid and artificial saliva (1:1, v/v) containing dried and ground silages placed in nylon bag at $39^{\circ}C$ up to 48h. Soluble protein (SP) content was lowest for RSS as 2.11% in total CP compared to those for other silages. Highest A fraction (NPN) was observed from RS (74.33% of total CP) while those from TS and RSS were relatively low (48%). B2 fraction was relatively higher for RS, RSS and WS than for TS and BS. $B_3$ fraction was lowest in WS among silages. C fraction (27.07) in RSS was higher than in other silages (1.40~9.93%). pH in incubation solution was increased (P<0.01~P<0.001) for extracted silages up to 12h but decreased (P<0.01) at 48h for non-extracted ones. Contents of ammonia-N (P<0.001) and total VFA (P<0.01~P<0.001) were higher for non-extracted silages than for extracted ones. Acetate proportion was increased (P<0.001) in buffer extracted silages while those of propionate and butyrate were decreased (P<0.001) up to 24h incubation. Increased (P<0.001) total gas production was obtained from non-extracted silages up to 12h while gas production was increased (P<0.01) in extracted ones thereafter. In vitro degradation of dry matter and CP was increased (P<0.001) in non-extracted silages but that of neutral detergent fiber was increased (P<0.001) in extracted ones without difference among silages. Difference in mean values of degradability for each silage prior to- and post extraction with borate buffer, however, was not found among silages. It may be concluded that high NPN content of silages may reduce the protein availability in silages and borate buffer soluble components in silages can stimulate the early stage of fermentation.

• Economic and Environmental Geology
• /
• v.40 no.5
• /
• pp.605-622
• /
• 2007

Elemental, Rock-Eval pyrolysis and isotopic analysis of the core sediments from the northwestern and eastern Ulleung Basin of the East were carried out to identify their geochemical characteristics, spatial and vertical variation and origin of organic matter in Upper Quaternary sediments from the northwestern and eastern Ulleung Basin of the East Sea. TOC, m and TS did not show spatial variation between the sampling locations whereas they showed systematic vertical variation associated with MIS stages related to the sea-level change of the East Sea. It is suggested that these past changes of sea-level influenced the sedimentary depositional environments and/or diagenesis which resulted the patterns observed in this study. Based on the results of TOC/N, TS/TOC, ${\delta}^{13}C_{org}\;and\;{\delta}^{15}N_{org}$ analysis, organic matters in the study area appears to be predominantly originated from the marine algae rather than land plant and deposited under normal marine oxic condition during MIS I and MIS III period, and under euxinic/anoxic condition during MIS II period. TOC/N, ${\delta}^{13}C_{org}\;and\;{\delta}^{15}N_{org}$ have a relatively constant value irrespective of MIS stages, implying that the organic matter source does not change by the sea-level fluctuations. However, the results of Rock-Eval pyrolysis indicates that the organic matter is in immature stage and originated from land-plant (Type III), locating in the immature stage land plant (Type III). Similar differences were reported from other areas such as the Atlantic Ocean, Iberia Abyssal Plain, Mediterranean Sea, suggesting that Rock-Eval method does not exactly reflect the characteristic of immature organic matters. Accordingly, the application of Rock-Eval pyrolysis for delineating the source of immature organic matters should be approached with caution and all other geochemical proxies should be considered altogether at the same time.

• Tuberculosis and Respiratory Diseases
• /
• v.46 no.6
• /
• pp.803-810
• /
• 1999

Background : The patient's work of breathing(WOBp) during assisted ventilation may vary according to many factors including ventilatory demand of the patients and applied ventilatory setting by the physician. Pressure-controlled ventilation(PCV) which delivers gas with decelerating flow may better meet patients' demand to improve patient-ventilator synchrony compared with volume-controlled ventilation(VCV) with constant flow. This study was conducted to compare the difference in WOBp in two assisted modes of ventilation, PCV and VCV with constant flow. Methods : Ten patients with respiratory failure were included in this study. Initially, the patients were placed on VCV with constant flow at low tidal volume($V_{T,\;LOW}$)(6-8 ml/kg) or high tidal volume($V_{T,\;HIGH}$)(10-12 ml/kg). After a 15 minute stabilization period, VCV with constant flow was switched to PCV and pressure was adjusted to maintain the same tidal volume($V_T$) received on VCV. Other ventilator settings were kept constant. Before changing the ventilatory mode, WOBp, $V_T$, minute ventilation($V_E$), respiratory rate(RR), peak airway pressure (Ppeak), peak inspiratory flow rate(PIFR) and pressure-time product(PTP) were measured. Results : The mean $V_E$ and RR were not different between PCV and VCV during the study period. The Ppeak was significantly lower in PCV than in VCV during $V_{T,\;HIGH}$. HIGH ventilation(p<0.05). PIFR was significantly higher in PCV than in VCV at both $V_T$ (p<0.05). During $V_{T,\;LOW}$ ventilation, WOBp and PTP in PCV($0.80{\pm}0.37\;J/min$, $164.5{\pm}74.4\;cmH_2O.S$) were significantly lower than in VCV($1.06{\pm}0.39J/mm$, $256.4{\pm}107.5\;cmH_2O.S$)(p<0.05). During $V_{T,\;HIGH}$ ventilation, WOBp and PTP in PCV($0.33{\pm}0.14\;J/min$, $65.7{\pm}26.3\;cmH_2O.S$) were also significantly lower than in VCV($0.40{\pm}0.14\;J/min$, $83.4{\pm}35.1\;cmH_2O.S$)(p<0.05). Conclusion : During assisted ventilation, PCV with decelerating flow was more effective in reducing WOBp than VCV with constant flow. But since individual variability was shown, further studies are needed to confirm these results.

• Tuberculosis and Respiratory Diseases
• /
• v.54 no.1
• /
• pp.71-79
• /
• 2003

Background : A bronchoalveolar lavage(BAL) is useful in diagnosing the etiology of bilateral pulmonary infiltrations, but may worsen the oxygenation and clinical status in severely hypoxemic patients. This study assessed the safety and efficacy of the continuous positive airway pressure(CPAP) using a conventional mechanical ventilator via a face mask as a tool for maintaining the oxygenation level during BAL. Methods : Seven consecutive patients with the bilateral pulmonary infiltrates and severe hypoxemia ($PaO_2/FIO_2$ ratio ${\leq}200$ on oxygen 10 L/min via mask with reservoir bag) were enrolled. The CPAP 5-6 $cmH_2O(F_IO_2\;1.0)$ was delivered through an inflatable face mask using a conventional mechanical ventilator. The CPAP began 10 min before starting the BAL and continued for 30 min after the procedure was completed. A bronchoscope was passed through a T-adapter and advanced through the mouth. BAL was performed using the conventional method. The vital signs, pulse oxymetry values, and arterial blood gases were monitored during the study. Results : (1) Median age was 56 years(male:female=4:3). (2) The baseline $PaO_2$ was $78{\pm}16mmHg$, which increased significantly to $269{\pm}116mmHg$(p=0.018) with CPAP. After the BAL, the $PaO_2$ did not decrease significantly but returned to the baseline level after the CPAP was discontinued. The $SpO_2$ showed a similar trend with the $PaO_2$ and did not decrease to below 90 % during the duration of the study. (3) The $PaCO_2$ increased and the pH decreased significantly after the BAL but returned to the baseline level within 30 min after the BAL. (5) No complications directly related to the BAL procedure were encountered. However, intubation was necessary in 3 patients(43 %) due to the progression of the underlying diseases. Conclusion : In severe hypoxemic patients, CPAP using a face mask and conventional mechanical ventilator during a BAL might allow minimal alterations in oxygenation and prevent subsequent respiratory failure.

• Journal of Gastric Cancer
• /
• v.5 no.1
• /
• pp.16-22
• /
• 2005

Purpose: In Korea, the number of laparoscopy-assisted distal gastrectomies for early gastric cancer patients has been increasing lately. Although minimally invasive surgery is more beneficial, no reported case of a totally laparoscopic distal gastrectomy has been reported because of difficulty with intracorporeal anastomosis. This study attempts, through our experiences, to determine the feasibility of a totally laparoscopic distal gastrectomy using an intracorporeal gastroduodenostomy in treating early gastric carcinoma. Materials and Methods: We investigated surgical results and clinicopatholgic characteristics of eight(8) patients with an early gastric carcinoma who underwent a totally laparoscopic distal gastrectomy at the Department of Surgery, Our Lady of Mercy Hospital, The Catholic University of Korea, between June 2004 and September 2004. The intracorporeal gastroduodenostomy was performed with a delta-shaped ananstomosis by using only laparoscopic linear staplers (Endocutter 45mm; Ethicon Endosurgery, OH, USA). Results: The operative time was $369.4\pm62.5$ minutes (range $275\∼465$ minutes), and the anastomotic time was 45.1\pm14.4$ minutes (range $32\∼70$ minutes). The anastomotic time was shortened as surgical experience was gained. The number of laparoscopic linear staplers for an operation was $7.1\pm0.6$. The number of lymph nodes harvested was $31.9\pm13.1$. There was 1 case of transfusion and no case of conversion to an open procedure. The time to the first flatus was 2.8$\pm$0.5 days, and the time to the first food intake was $4.1\pm0.8$ days. There were no early postoperative complications, and the postoperative hospital stay was $10.0\pm3.9$ days. Conclusion: A totally laparoscopic distal gastrectomy using an intracorporeal gastroduodenostomy with a delta-shaped anastomosis is technically feasible and can maximize the benefit of laparoscopic surgery for early gastric cancer.

• Tuberculosis and Respiratory Diseases
• /
• v.48 no.6
• /
• pp.932-943
• /
• 2000

Background : Nonspecific interstitial pneumonitis (NSIP) is most likely to be confused with usual interstitial pneumonitis (UIP). Unlike patients witþ UIP, the majority of patients with NSIP have a good prognosis, with most patients improving after treatment with corticosteroids. Therefore it is clinically important to differentiate NSIP from UIP. Up to now, the only means of differentiating these two diseases was by means of surgical lung biopsy. American Thoracic Society (ATS) proposed a clinical diagnostic criteria for UIP to provide assistance to clinicians in its diagnosis without surgical lung biopsy. This study is aimed to investigate whether there were clinical and radiological differences between NSIP and UIP, and the usefulness of ATS clinical diagnostic criteria for UIP in Korea. Methods : We studied 60 patients with UIP and NSIP confirmed by surgical lung biopsy. Clinical manifestations, pulmonary function test, arterial blood gas analysis, bronchoalveolar lavage (BAL), and high resolution computed tomography (HRCT) were evaluated and analyzed by Chi-square test or t-test. The clinical criteria for UIP proposed by ATS were applied to all patients with idiopathic interstitial pneumonia. Results : Forty-two patients with UIP and 18 with NSIP were pathologically identified. Among the 18 patients with NSIP (M : F=1 : 17), the mean age was 55.2$\pm$8.4 (44~73) yr. Among the 42 patients with UIP (M : F=33 : 9), the mean age was 59.5$\pm$7.1 (45~74) yr (p=0.046). Fever was more frequent in NSIP (39%) (p=0.034), but clubbing was frequently observed in UIP (33%) (p=0.023). BAL lymphocytosis was more frequent (23%) (p=0.0001) and CD4/CD8 ratio was lower in NSIP (p=0.045). On HRCT, UIP frequently showed honeycomb appearance (36 of 42 patients) though not in NSIP (p=0.0001). Six of 42 UIP patients (14.3%) met the ATS clinical criteria for IPF, and 3 of 16 NSIP patients (18.8%) met the diagnostic criteria. Conclusion : Being a relatively young female and having short duration of illness, fever, BAL lymphocytosis, low CD4/CD8 ratio with the absence of clubbing and honeycomb appearance in HRCT increase the likelihood of the illness being NSIP. The usefulness of ATS clinical diagnostic criteria for UIP may be low in Korea.

• Tuberculosis and Respiratory Diseases
• /
• v.49 no.5
• /
• pp.601-613
• /
• 2000

Background : Idiopathic pulmonary fibrosis (IPF) is a fatal progressive fibrous disease of the lung of unknown etiology. Recently it has been classified into several distinct entities on the basis of pathologic and clinical characteristics, ie : usual interstitial pneumonia (UIP), desquamative interstitial pneumonia (DIP), acute interstitial pneumonia (AIP), bronchiolitis obliterans with organizing pneumonia (BOOP), and nonspecific interstitial pneumonia (NSIP). IPF is now applied only for UIP, which has the worst prognosis. The previous reports of 3-5 year median survival appears to be overoptimistic because other types with better prognosis like NSIP or BOOP might have been included. Therefore, this study was performed to determine the clinical course and the prognostic factors of UIP as diagnosed by surgical lung biopsy. Methods : The subjects were 72 UIP patients (age $58.2{\pm}11.6$ years, M : F=45 : 27, median follow up period : 18.1 months (0.7-103.6) diagnosed by surgical lung biopsy at the Asan Medical Center (68 patients) and the Paik Hospital in Seoul (4 patients). Clinical scores (level of dyspnea : 1-20 points), radiologic score (honeycombing : HC score 0-5 points, ground glass : GG score 0-5 points), and physiologic scores (FVC : 1-12 points, $FEV_1$ : 0-3 points, TLC : 0-10 points, $D_{LCO)$ : 0-5 points, $AaDO_2$ : 0-10 points) were summed into a total CRP score. Results : 1) The one year survival rate was 78.3%, while the rate for three year survival was 58.1%, and the median survival period was 42.5months. 2) Short term (1 year) prognosis : The patients who died within one year of diagnosis (14 patients) had the higher initial total CRP score ($28.6{\pm}8.3$ vs. $16.6{\pm}9.7$) than those who lived longer than one year (46 patients). The difference in the total CRP score was attributed to the symptom score ($8.4{\pm}2.1$ vs. $5.7{\pm}3.9$) and the physiologic score ($15.7{\pm}7.1$ vs. $6.7{\pm}5.7$) including FVC, $D_{LCO)$ and $AaDO_2$. 3) Long-term (3year) prognosis : The total CRP score ($12.2{\pm}6.7$ vs. $28.7{\pm}7.9$ : including symptom score, FVC, $D_{LCO)$ and $AaDO_2$) at the time of diagnosis were also different for the long-term survivors and those who lived less than 3 years. 4) Cox regression analysis showed $D_{LCO)$ (${\geq}$60%) (Hazard ratio : 4.56, 95% CI : 2.30-16.04) was the independent prognostic factors of UIP (P<0.05). Conclusion : These results suggest that $D_{LCO)$ at the time of diagnosis seem to be a prognostic markers of biopsy-proven UIP.

• Tuberculosis and Respiratory Diseases
• /
• v.45 no.4
• /
• pp.795-804
• /
• 1998

Background: Chronic eosinophilic pneumonia(CEP) is interstitial lung disease characterized by multiple infiltration on radiographic study, accumulation of eosinophils in the alveolar space and interstitium of the lung, chronic persistent symptoms and possible relapse. Acute eosinophilic pneumonia(AEP) is a recently described illness, characterized by rapid clinical course, acute respiratory insufficiency and no relapse. Method : To better characterize acute and chronic eosinophilic pneumonia, we studied the clinical and laboratory features of 16 patients(AEP : 7 patients, CEP : 9 patients), which were clinico-pathohistologically diagnosed and not to be associated with organic disorders producing peripheral blood eosinophilia. Results: The mean age was higher for patients with CEP than for patients with AEP ($55.4{\pm}15.1$ vs. $24.6{\pm}7.9$ years, p<0.05). High fever(above $38^{\circ}C$) was presented in all patients of AEP and in one patient(11%) of CEP. All patients of AEP and eight patients (89%) of CEP showed bilateral pulmonary infiltrates, and 6 patients(86%) of AEP and 2 patients(22%) of CEP showed pleural effusion in chest radiograph. The mean white blood cell count of AEP and CEP were $17,186/mm^3$ and $12,867/mm^3$, respectively. The mean peripheral blood eosinophil count of AEP and CEP were $939/mm^3$ and $2,104/mm^3$, respectively. The mean eosinophil fraction of BAL fluid of AEP and CEP were 32.4% (range: 18~47%) and 35.8% (range: 15.3~88.2%), respectively. The mean $PaO_2$ was lower for patients with AEP than for patients with CEP ($44.1{\pm}15.5$ vs. $62.7{\pm}6.9$mmHg, p<0.05). All patients of AEP and CEP were initially treated with antibiotics. All patients of CEP and one patients of AEP were finally required systemic steroid therapy. 6 patients of AEP were improved without steroid therapy. Relapse was observed in 3 patients(33%) of CEP. Conclusion : Compair with of chronic eosinophilic pneumonia, acute eosinophilic pneumonia was characterized by relatively young age, acute onset, high fever, severe hypoxemia, diffuse pulmonary infiltrates with pleural effusion, steroid therapy is effective but spontaneous improvement with conservative therapy was frequent.

• Tuberculosis and Respiratory Diseases
• /
• v.45 no.1
• /
• pp.57-67
• /
• 1998

Purpose : This study was undertaken to determine the preoperative predictors of mortality and morbidity after lung cancer resection. Method: During the period from October 1, 1995 to August 31, 1996, a prospective study was conducted in 92 lung resection candidates diagnosed as lung cancer. For preoperative predictors of nonpulmonary factors, we considered age, sex, weight loss, hematocrit, serum albumin, EKG and concomitant illness, and for those of pulmonary factors, smoking history, presence of pneumonia, dyspnea scale(1 to 4), arterial blood gas analysis with room air breathing, routine pulmonary function test. And predicted postoperative(ppo) pulmonary factors such as PPO-$FEV_1$, ppo-diffusing capacity(DLco), predicted postoperative product(PPP) of ppo-$FEV_1%{\times}ppo$-DLco% and ppo-maximal $O_2$ uptake($VO_2$max) were also considered. Results: There were 78 men and 14 women with a median age of 62 years(range 42 to 82) and a mean $FEV_1$ of $2.37\pm0.06L$. Twenty nine patients had a decreased $FEV_1$ less than 2.0L. Pneumonectomy was performed in 26 patients, bilobectomy in 12, lobectomy in 54. Pulmonary complications developed in 10 patients, cardiac complications in 9, other complications(empyema, air leak, bleeding) in 11, and 16 patients were managed in intensive care unit for more than 48hours. Three patients died within 30 days after operation. The ppo-$VO_2$max was less than 10ml/kg/min in these three patients, but its statistical significance could not be determined due to small number of patients. In multivariate analysis, the predictor related to postoperative death was weight loss(p<0.05), and as for pulmonary complications, weight loss, dyspnea scale, ppo-DLco and extent of resection(p<0.05). Conclusions: Based on this study, preoperative nonpulmonary factors such as weight loss and dyspnea scale are more important than the pulmonary factors in the prediction of postoperative mortality and/or morbodity in lung resection candidates, but exercise pulmonary fuction test may be useful Our study suggests that ppo-$VO_2$max value less than 10ml/kg/min is associated with death after lung cancer resection but further studies are needed to validate this result.