• 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.

• Journal of Chest Surgery
• /
• v.39 no.3 s.260
• /
• pp.208-213
• /
• 2006

Background: The prevalence of anastomotic complication is related to anastomotic procedure or site in esophageal cancer operation. We studied the anastomotic leakage and stricture related to the anastomotic procedure & site in patients who received the esophageal resection and reconstruction for esophageal cancer. Material and Method: The anastomotic procedure, site and complication of 321 patients who received the esophageal reconstruction from August 1993 to May 2003 were investigated. Mean age was 64.5$\pm$4.9 (37${\~}$94) years, 300 patients ($93.5\%$) were male and 21 patients were female ($6.5\%$). Result: There were 7 anastomotic leakages ($2.2\%$) and no difference in anastomotic site (cervical anastomosis $4.1\%$, thoracic anastomosis $1.6\%$) and procedure (stapler technique $1.6\%$, semi-staple technique $9.1\%$, hand-sewn technique $0.0\%$). There were 52 anastomotic strictures ($16.2\%$), differences in sites (cervical anastomosis $2.7\%$, thoracic anastomosis $20.2\%$) (p < 0.001) and procedure (stapler technique $20.0\%$, semi-stapler technique $3.0\%$, hand-sewn technique $4.7\%$). And the stapler technique showed higher stricture rate (p < 0.001). Conclusion: Anastomotic technique was less related to anastomotic leakage in esophageal reconstruction for esophageal cancer. However, stapler technique had higher stricture rate than other techniques. Therefore, we suggest that the anastomotic technique be improved to reduce anastomotic stricture.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.26 no.4
• /
• pp.343-355
• /
• 2021

Eelgrass, Zostera marina L., was widely distributed around Sinyangseopji Beach in Bangdu Bay, on the eastern coast of Jeju Island, until breakwater construction in the late 1990s resulted in its complete loss. Six experimental sites were identified for restoration of the Z. marina bed in Bangdu Bay. Using the staple method, 500 Z. marina shoots were transplanted at each site in January 2019 and 2020. The transplants, along with environmental parameters, were monitored for 10 months following transplantation. There were significant differences in underwater irradiance, water temperature, and salinity among the sites, but all were suitable for Z. marina growth. The Ulva species, an opportunistic alga, appeared in spring and accumulated during summer at all sites; however, there was no significant effect of Ulva species on the survival and growth of the eelgrass transplants. Most of the transplanted Z. marina survived, and after 3 months, the density increased by 112.5-300% due to vegetative propagation, with a rapid rate of increase observed during spring and early summer at all sites. For 1-2 months after transplanting, the Z. marina shoots showed signs of transplant shock, after which the shoot density increased at all sites, confirming that all transplants adapted well to the new environment. However, in both 2019 and 2020, during late summer to early fall, the sites experienced heavy damage from typoons (twice in 2019 and three times in 2020) that hit Bangdu Bay. The transplants at two sites located in the center of Bangdu Bay were completely destroyed, but those at three sites located to the west of the bay showed a 192-312% increase in density. Thus, we confirmed that the Bangdu Bay Z. marina bed can be restored, with the highest probability of success for Z. marina restoration on the western side of Bangdu Bay, which is protected from typhoons.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.67 no.1
• /
• pp.9-16
• /
• 2022

Rice is one of the most important staple foods in Wnju, Jeonbuk, South Korea. However, rice consumption has dramatically decreased as eating habits have diversified owing to rapid economic growth. Recently, floury endosperm rice varieties have been developed to invigorate the rice processing industry, because dry-milled rice flour is economically and environmentally suitable for massive rice flour distribution. The National Institute of Crop Science has developed 'AromaT', an early-maturing black rice with floury-endosperm, suitable for tea and dry milling. 'AromaT' was derived from a cross between 'Suweon542' as the floury endosperm source and 'Heugjinju' as the black and aromatic source. In this study, 'AromaT' and its parents, 'Suweon542' and 'Heugjinju', were analyzed for agronomic traits, anthocyanin content, and their major physicochemical properties by different planting date. The field experiment was conducted in Wanju, Jeollabuk-do Province, South Korea, in 2019. The transplanting dates were May 30 (ordinary season), June 25 (double-cropping season), and July 10 (late season). The yield performance of brown rice 'AromaT' was 330 kg/10 a in the double-cropping cultivation method and was the highest among the transplanting dates. The floury endosperm of 'AromaT' was derived from 'Suweon542' containing 'flo7', located on chromosome 5 and known to control floury endosperm. With the late planting date, the anthocyanin content of 'AromaT' was 570.5 mg/100 g, much higher than that of 'Heugjinju' (376.3 mg/100 mg). The brown rice of 'AromaT' also exhibited the pop-corn-flavoring 2-acetyl-1-pyrroline, exclusively detected in aroma rice varieties. The average particle sizes of 'AromaT' and 'Suweon542' were 67.12 ㎛ and 70.9 ㎛, respectively, lower than that of 'Heugjinju' (95.5 ㎛) with a black transparent endosperm. The average damaged starch content of 'AromaT' was 8.1%, lower than that of 'Heugjinju' (10.05%) and Suweon542 (9.5%). As a result, 'AromaT' with high anthocyanin content, fine particle size, and low damaged starch content is expected to provide a new rice material in various processing fields.