• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.65-82
• /
• 2021

Stock market investors are generally split into foreign investors, institutional investors, and individual investors. Compared to individual investor groups, professional investor groups such as foreign investors have an advantage in information and financial power and, as a result, foreign investors are known to show good investment performance among market participants. The purpose of this study is to propose an investment strategy that combines investor-specific transaction information and machine learning, and to analyze the portfolio investment performance of the proposed model using actual stock price and investor-specific transaction data. The Korea Exchange offers daily information on the volume of purchase and sale of each investor to securities firms. We developed a data collection program in C# programming language using an API provided by Daishin Securities Cybosplus, and collected 151 out of 200 KOSPI stocks with daily opening price, closing price and investor-specific net purchase data from January 2, 2007 to July 31, 2017. The self-organizing map model is an artificial neural network that performs clustering by unsupervised learning and has been introduced by Teuvo Kohonen since 1984. We implement competition among intra-surface artificial neurons, and all connections are non-recursive artificial neural networks that go from bottom to top. It can also be expanded to multiple layers, although many fault layers are commonly used. Linear functions are used by active functions of artificial nerve cells, and learning rules use Instar rules as well as general competitive learning. The core of the backpropagation model is the model that performs classification by supervised learning as an artificial neural network. We grouped and transformed investor-specific transaction volume data to learn backpropagation models through the self-organizing map model of artificial neural networks. As a result of the estimation of verification data through training, the portfolios were rebalanced monthly. For performance analysis, a passive portfolio was designated and the KOSPI 200 and KOSPI index returns for proxies on market returns were also obtained. Performance analysis was conducted using the equally-weighted portfolio return, compound interest rate, annual return, Maximum Draw Down, standard deviation, and Sharpe Ratio. Buy and hold returns of the top 10 market capitalization stocks are designated as a benchmark. Buy and hold strategy is the best strategy under the efficient market hypothesis. The prediction rate of learning data using backpropagation model was significantly high at 96.61%, while the prediction rate of verification data was also relatively high in the results of the 57.1% verification data. The performance evaluation of self-organizing map grouping can be determined as a result of a backpropagation model. This is because if the grouping results of the self-organizing map model had been poor, the learning results of the backpropagation model would have been poor. In this way, the performance assessment of machine learning is judged to be better learned than previous studies. Our portfolio doubled the return on the benchmark and performed better than the market returns on the KOSPI and KOSPI 200 indexes. In contrast to the benchmark, the MDD and standard deviation for portfolio risk indicators also showed better results. The Sharpe Ratio performed higher than benchmarks and stock market indexes. Through this, we presented the direction of portfolio composition program using machine learning and investor-specific transaction information and showed that it can be used to develop programs for real stock investment. The return is the result of monthly portfolio composition and asset rebalancing to the same proportion. Better outcomes are predicted when forming a monthly portfolio if the system is enforced by rebalancing the suggested stocks continuously without selling and re-buying it. Therefore, real transactions appear to be relevant.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.5 no.3 s.18
• /
• pp.47-55
• /
• 2005

In order to design and manage the urban streams, the change of hydraulic characteristics by vegetation must be analyzed clearly. Planting criteria of vegetation in a urban stream were investigated and the design method of vegetation permission map was analyzed in this study. In addition, variations of water level due to vegetation are calculated by quasi two dimensional numerical model, HEC-RAS model and FESWMS model. Joongrang stream(Gunja bridge${\sim}$Jangan bridge reach) was selected as the case study stream. According to the criteria of vegetation, it is decided that vegetation density was $0.5{\sim}1.0$ tree/ha for selected tall tree in right floodplain and shrubs can be planted in the right and left floodplain area except the important hydraulic structures site. The selected shrubs planting simulations with three models show that water level in selected floodplain area increase approximately 12cm for the 100 year return period flood. The applicability of vegetation permission map in Korean urban stream was analyzed in this paper.

• New & Renewable Energy
• /
• v.17 no.4
• /
• pp.1-8
• /
• 2021

To determine the wind turbine class in the offshore of the Korean Peninsula, the reference wind speed for a 50-y return period at the hub height of a wind turbine was estimated using the reanalysis data sets. The most recent reanalysis data, ERA5, showed the highest correlation coefficient (R) of 0.82 with the wind speed measured by the Southwest offshore meteorological tower. However, most of the reanaysis data sets except CFSR underestimated the annual maximum wind speed. The gust factor of converting the 1 h-average into the 10 min-average wind speed was 1.03, which is the same as the WMO reference, using several meteorological towers and lidar measurements. Because the period, frequency, and path of typhoons invading the Korean Peninsula has been changing owing to the climate effect, significant differences occurred in the estimation of the extreme wind speed. Depending on the past data period and length, the extreme wind speed differed by more than 30% and the extreme wind speed decreased as the data period became longer. Finally, a reference wind speed map around the Korean Peninsula was drawn using the data of the last 10 years at the general hub-height of 100 m above the sea level.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.3
• /
• pp.501-509
• /
• 2011

In this paper, we offer a new strategic Portfolio Model for national IT R&D project selection in Korea. A risk and return (R-R) Portfolio Model was developed using an objectively quantified index on the two axes of risk and return, in order to select a strategic project and allocate resources in compliance with a national IT R&D strategy. We strategize using the R-R Portfolio Model to solve the non-strategy and subjectivity problems of the existing national R&D project selection Model. We also use the quantified evaluation index of the IT technology road map (TRM) and the technology level Survey (TLS) for the subjectivity of project selection, and try to discover the weights using the analytic hierarchy process (AHP). In addition, we intend to maximize the chance for a successful national IT R&D project, by selecting a strategic Portfolio project and balancing the allocation of resources effectively and objectively.

• Journal of the Korean GEO-environmental Society
• /
• v.20 no.5
• /
• pp.5-12
• /
• 2019

On November 15, 2017, a unpredictable liquefaction damage was occurred at the $M_L=5.4$ Pohang earthquake and after, many researches have been conducted in Korea. In Korea, where there were no cases of earthquake damage, it has been extremely neglectable in preparing earthquake risk maps and building earthquake systems that corresponded to prevention and preparation. Since it is almost impossible to observe signs and symptoms of drought, floods, and typhoons in advance, it is very effective to predict the impacts and magnitudes of seismic events. In this study, 14,040 borehole data were collected in the metropolitan area and liquefaction evaluation was performed using the amplification factor. Based on this data, liquefaction hazard maps were prepared for ground accelerations of 0.06 g, 0.14 g, 0.22 g, and 0.30 g, including 200years return period to 4,800years return period. Also, the correlation analysis between the earthquake acceleration and LPI was carried out to draw a real-time predictable liquefaction hazard map. As a result, 707 correlation equations in every cells in GIS map were proposed. Finally, the simulation for liquefaction risk mapping against artificial earthquake was performed in the metropolitan area using the proposed correlation equations.

• The Journal of the Korea Contents Association
• /
• v.7 no.6
• /
• pp.195-205
• /
• 2007

The steel industry plays an important role in the entire Korean Economy. However, little empirical research has analyzed the efficiency of steel companies. The purpose of this paper is to measure and analyze their efficiency using DEA models. We evaluate the CCR and BCC efficiency and the return to scale of 28 Korean steel companies. We also provide their envelopment map and the projection, which are valuable information for inefficient companies to find benchmarking companies and to improve their efficiency.

• Journal of Korea Water Resources Association
• /
• v.45 no.10
• /
• pp.983-995
• /
• 2012

In this study, it was intended to analyze the spatio-temporal distribution of historical drought events occurred in Korea by way of drought frequency analysis using SPI (Standardized Precipitation Index), and Drought spell was executed to estimate drought frequency as per drought severity and regions. Also, SDF (severity-duration-frequency) curves were prepared per each weather stations to estimate spatial distribution characteristics for the severe drought areas of Korea, and Potential Drought Hazard Map was prepared based on the derived SDF curves. Drought frequency analysis per drought stage revealed that severe drought as well as extreme drought frequency were prominently high at Geum River, Nakdong River, and Seomjin River basin as can be seen from SDF curves, and drought severity was found as severer per each drought return period in the data located at Geum River, Nakdong River, and Seomjin River basins as compared with that of Seoul weather station at Han River basin. In the Potential Drought Hazard Map, it showed that Geum River, Seomjin River, and Yeongsan River basins were drought vulnerable areas as compared to upper streams of Nakdong River basin and Han River basin, and showed similar result in drought frequency per drought stage. Drought was occurred frequently during spring seasons with tendency of frequent short drought spell as indicated in Potential Drought Hazard Map of different season.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.473-476
• /
• 2014

최근 여성, 아동을 대상으로 한 범죄 발생률이 증가 하고 있다. 이러한 통계를 기반으로 우리 생활 깊숙이 자리 매김한 스마트 폰 애플리케이션을 활용하여 범죄를 예방에 도움을 줄 수 있는 애플리케이션을 개발 하였다. SQLite를 이용한 Database기능과 Google API Package의 MapView를 사용하여 지인의 정보를 놓고 언제든지 사용자의 위치정보를 빠르게 전달할 수 있는 앱을 구현 하여 주기적인 위치전송으로 인한 사용자의 위치파악이 가능하고, 위급상황 시 긴급전화를 이용하여 사고 대처가 가능하며, GPS를 이용한 본인의 위치 주변 지리 파악이 용이하다. 또한 수신자가 발신자의 이동경로를 한눈에 봄으로써 위치파악에 용이 함으로 안전한 귀가 서비스를 제공한다.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1999.11a
• /
• pp.139-144
• /
• 1999

본 논문에서는 45명의 남자 대학생들에게 연산을 수행하게 한 후, 연산스트레스를 측정하기 위한 생리 파라메터의 추출에 대하여 연구하였다. 파라메터를 추출하기 위해서 1) 정규분포화를 위한 변환 2) 상관관계를 통해 상호관련성이 높은 파라메터를 조사 3) 휴식기간과 연산작업간의 파라메터의 값 비교를 통한 파라메터 표준화 4) 각 파라메터에 대해서 반복측정자료의 분산분석법을 통하여 검정함으로써 통계적으로 유의적인 차이가 있는 파라메터를 선정하였다. 위와 같은 절차를 통하여 연산스트레스의 지수화에 필요한 생리 파라메터로 Heart Rate, HRV의 LF/HF, HRV의 MF/(LF+HF), Return Map의 분산, Mean Temperature, GSR-Mean과 호흡수가 최종적으로 선정되었다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.6
• /
• pp.839-850
• /
• 2018

The flood damage in urban areas due to torrential rain is increasing with urbanization. For this reason, accurate and rapid flooding forecasting and expected inundation maps are needed. Predicting the extent of flooding for certain rainfalls is a very important issue in preparing flood in advance. Recently, government agencies are trying to provide expected inundation maps to the public. However, there is a lack of quantifying the extent of inundation caused by a particular rainfall scenario and the real-time prediction method for flood extent within a short time. Therefore the real-time prediction of flood extent is needed based on rainfall-runoff-inundation analysis. One/two dimensional model are continued to analyize drainage network, manhole overflow and inundation propagation by rainfall condition. By applying the various rainfall scenarios considering rainfall duration/distribution and return periods, the inundation volume and depth can be estimated and stored on a database. The Rainfall-Duration-Flooding Quantity (RDF) relationship curve based on the hydraulic analysis results and the Self-Organizing Map (SOM) that conducts unsupervised learning are applied to predict flooded area with particular rainfall condition. The validity of the proposed methodology was examined by comparing the results of the expected flood map with the 2-dimensional hydraulic model. Based on the result of the study, it is judged that this methodology will be useful to provide an unknown flood map according to medium-sized rainfall or frequency scenario. Furthermore, it will be used as a fundamental data for flood forecast by establishing the RDF curve which the relationship of rainfall-outflow-flood is considered and the database of expected inundation maps.