• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.147-155
• /
• 2022

In this study, we developed a system to dynamically balance a daily stock portfolio and performed trading simulations using gradient boosting and genetic algorithms. We collected various stock market data from stocks listed on the KOSPI and KOSDAQ markets, including investor-specific transaction data. Subsequently, we indexed the data as a preprocessing step, and used feature engineering to modify and generate variables for training. First, we experimentally compared the performance of three popular gradient boosting algorithms in terms of accuracy, precision, recall, and F1-score, including XGBoost, LightGBM, and CatBoost. Based on the results, in a second experiment, we used a LightGBM model trained on the collected data along with genetic algorithms to predict and select stocks with a high daily probability of profit. We also conducted simulations of trading during the period of the testing data to analyze the performance of the proposed approach compared with the KOSPI and KOSDAQ indices in terms of the CAGR (Compound Annual Growth Rate), MDD (Maximum Draw Down), Sharpe ratio, and volatility. The results showed that the proposed strategies outperformed those employed by the Korean stock market in terms of all performance metrics. Moreover, our proposed LightGBM model with a genetic algorithm exhibited competitive performance in predicting stock price movements.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.1D
• /
• pp.17-23
• /
• 2009

Due to the rapid increase of vehicles on the street, Korean society is facing worsening traffic congestions and air pollutions. Also, the oil price pickup has led to increasing need for the use of public transportation. In particular, transfering among public transportation may be a main factor for riders who are commuting for a long distance journey. In order to ensure such connectivity, transfer stations have been actively built in Korea. However, it would be necessary to shift those vehicles, from cars to public transportations by enhancing the users' satisfaction with public transportation through strategies for minimizing the users' waiting cost by building an efficient connective system between transportation modes as well as the preparation of aforementioned transfer stations. Therefore, this study aimed to develop an algorithm for minimizing transferring passengers' waiting costs based on service intervals of linked buses within the transfer facilities. In order to adjust the service interval, we calculated the total costs, involving the wait cost of transfer passengers and bus operation costs, and produced an allocation interval, that would minimize the costs. We selected a KTX departing from Seoul station, and a No. 6014 bus route in Gwangmyeong city where it starts from the Gwangmyeong station in order to for verifying the model. Then, the transfer passengers' total waitting cost was reduced equivalent to the maximum of 212 minutes, and it revealed that the model performed very effectively.

• Journal of the Microelectronics and Packaging Society
• /
• v.25 no.1
• /
• pp.1-10
• /
• 2018

Recently, there has been rapid development in the field of flexible electronic devices, such as organic light emitting diodes (OLEDs), organic solar cells and flexible sensors. Encapsulation process is added to protect the flexible electronic devices from exposure to oxygen and moisture in the air. Using numerical simulation, we investigated the effects of the encapsulation layer on mechanical stability of the silicon chip, especially the fracture performance of center crack in multi-layer package for various loading condition. The multi-layer package is categorized in two type - a wide chip model in which the chip has a large width and encapsulation layer covers only the chip, and a narrow chip model in which the chip covers both the substrate and the chip with smaller width than the substrate. In the wide chip model where the external load acts directly on the chip, the encapsulation layer with high stiffness enhanced the crack resistance of the film chip as the thickness of the encapsulation layer increased regardless of loading conditions. In contrast, the encapsulation layer with high stiffness reduced the crack resistance of the film chip in the narrow chip model for the case of external tensile strain loading. This is because the external load is transferred to the chip through the encapsulation layer and the small load acts on the chip for the weak encapsulation layer in the narrow chip model. When the bending moment acts on the narrow model, thin encapsulation layer and thick encapsulation layer show the opposite results since the neutral axis is moving toward the chip with a crack and load acting on chip decreases consequently as the thickness of encapsulation layer increases. The present study is expected to provide practical design guidance to enhance the durability and fracture performance of the silicon chip in the multilayer package with encapsulation layer.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1341-1352
• /
• 2023

The normalized difference vegetation index (NDVI) derived from satellite images is a crucial tool to monitor forests and agriculture for broad areas because the periodic acquisition of the data is ensured. However, optical sensor-based vegetation indices(VI) are not accessible in some areas covered by clouds. This paper presented a synthetic aperture radar (SAR) based approach to retrieval of the optical sensor-based NDVI using machine learning. SAR system can observe the land surface day and night in all weather conditions. Radar vegetation indices (RVI) from the Sentinel-1 vertical-vertical (VV) and vertical-horizontal (VH) polarizations, surface elevation, and air temperature are used as the input features for an automated machine learning (AutoML) model to conduct the gap-filling of the Sentinel-2 NDVI. The mean bias error (MAE) was 7.214E-05, and the correlation coefficient (CC) was 0.878, demonstrating the feasibility of the proposed method. This approach can be applied to gap-free nationwide NDVI construction using Sentinel-1 and Sentinel-2 images for environmental monitoring and resource management.

• Toxicological Research
• /
• v.18 no.1
• /
• pp.13-22
• /
• 2002

In Korea, 2,320 tonnes of acetanilide were mostly wed as intermediates for synthesis in phar-maceuticals or additives in synthesizing hydrogen peroxide, varnishes, polymers and rubber. Only small amount of 120 kg were wed as a stabilizer for hydrogen peroxide solution for hair colouring agents in 1998. Readily available environmental or human exposure data do not exist in Korea at the present time. However, potential human exposures from drinking water, food, ambient water and in work places are expected to be negligible because this chemical is produced in the closed system in only one company in Korea and the processing factory is equipped with local ventilation and air filtering system. Acetanilide could be distributed mainly to water based on EQC model. This substance is readily biodegradable and its bioaccumulation is low. Acute toxicity of acetanilide is low since the L $D_{50}$ of oral exposure in rats is 1,959 mg/kg bw. The chemical is not irritating to skin, but slightly irritating to the eyes of rabbits. horn repeated dose toxicity, the adverse effects in rats were red pulp hyperplasia of spleen, bone marrow hyperplasia of femur and decreased hemoglobin, hematocrit and mean corpuscular hemoglobin concentration. The LOAEL for repeated dose toxicity in rats was 22 mg/kg/day for both sexes. Acetanilide is not considered to be genotoxic. In a reproductive/developmental toxicity study, no treatment-related changes in precoital time and rate of copulation, impregnation, pregnancy were shown in all treated groups. The NOAELs for reproduction and developmental toxicity (off-spring toxicity) are considered to be 200 mg/kg bw/day and 67 mg/kg bw/day, respectively. Ecotoxicity data has been generated in a limited number of aquatic species of algae (72 hr- $E_{b}$ $C_{50}$; 13.5 mg/l), daphnid (48hr-E $C_{50}$ > 100 mg/l) and fish (Oryzias latipes, 96hr-L $C_{50}$; 100 mg/l). Form the acute toxicity values, the predicted no effect concentration (PNEC) of 0.135 mg/1 was derived win an assessment factor of 100. On the basis of these data, acetanilide was suggested as currently of low priority for further post-SIDS work in OECD.in OECD.D.

• Journal of the Korean earth science society
• /
• v.28 no.7
• /
• pp.857-870
• /
• 2007

The structure and evolution of a thunderstorm outflow in two dimensions with no environmental wind are investigated using a cloud-resolving model with explicit liquid-ice phase microphysical processes (ARPS: Advanced Regional Prediction System). The turbulence structure of the outflow is explicitly resolved with a high-resolution grid size of 50m. The simulated single-cell storm and its associated Kelvin-Helmholtz (KH) billows are found to have the lift stages of development maturity, and decay. The secondary pulsation and splitting of convective cells resulted from interactions between cloud dynamics and microphysics are observed. The cooled downdrafts caused by the evaporation of rain and hail in the relatively dry lower atmosphere result in thunderstorm cold-air outflow. The outflow head propagates with almost constant speed. The KH billows formed by the KH instability cause turbulence mixing from the top of the outflow and control the structure of the outflow. Ihe KH billows are initiated at the outflow head, and pow and decay as moving rearward relative to the gust front. The numerical simulation results of the ratio of the horizontal wavelength of the fastest growing perturbation to the critical shear-layer depth and the ratio of the horizontal wavelength of the billow to its maximum amplitude are matched well with the results of other studies.

• Journal of the Korean Chemical Society
• /
• v.37 no.11
• /
• pp.923-928
• /
• 1993

The series of solid solutions in the $Sr_{1+x}Ho_{1-x}FeO_{4-y}$ (x = 0.00, 0.25, 0.50, 0.75 and 1.00) systems with $K_2NiF_4$ type structure have been prepared at 1550$^{\circ}$C under an atmospheric air pressure. The X-ray powder diffraction spectra of these samples assign that the crystallographic phases are tetragonal system over the whole x range. The lattice volume was increased with increasing the substitution amount of the $Sr^{2+}$ ion. The mole ratio of the $Fe^{4+}$ ion to total iron ions or ${\tau}$ value has been determined by Mohr salt titration of the sample and then the y value was calculated from x and ${\tau}$ values. The ${\tau}$ and y values have been increased with x values. The nonstoichiometric chemical formula are formulated from the general formula of $Sr_{1+x}Ho_{1-x}Fe^3_{1-}\;^+_{\tau}Fe_{\tau}^{4+}O_{4-y}$ replaced by x,${\tau}$ and y values. Mossbauer spectra show the mixed valence state and coordination state of $Fe^{3+}\;and\;Fe^{4+}$ ions. It is found out that the magnetic property of the samples is paramagnetic at room temperature. Electrical conductivity varied within the semiconductivity range of 1.0 to 1 ${\times}\;10^{-9}{\Omega}^{-1}cm^{-1}$. Activation energy of the electrical conductivity was decreased with the $\tau$ value. The conduction mechanism should be explained by the hopping model of the conduction electrons between the valence states of $Fe^{3+}\;and\;Fe^{4+}$ ions.

• Journal of Food Hygiene and Safety
• /
• v.19 no.2
• /
• pp.74-83
• /
• 2004

Raw-fish food contains a lot of moisture and is a high-protein food. It is a first-stage processed food taking a lot of manual work. Therefore, it is classified as a PHF food, very liable to cause a bacterial food-poisoning. But its manufacturers are usually small-sized and a systematic sanitation management is difficult to expect. But the manufacturer participating in this study produces chilled fresh raw-fish food. Fish are sliced into two fillets, which are packaged under vacuum, kept and distributed in refrigerators, and sold within a day. It is a newly-developed kind of raw-fish food, and a more improved kind of raw-fish food making possible a systematic sanitation management. The HACCP (Hazard Analysis and Critical Control Point) is a systematic and continuous process-control method which is very efficient for controling food sanitation and reducing the expenses. A new HACCP model has been developed to be applied to a large-sized chilled fresh raw-fish food manufacturer. To ascertain its efficiency, the baterial examination was done to its workplace and products. The significance test was done on its data by "SPSS 12.0 for Window" and "Mann-Whitney U Test". The numbers of bacteria on its final products were significantly different in flatfish and porgy. The number of bacteria tended to decrease in each time-differential sampling (P＜.00l). The final food products showed no food-poisoning bacteria in all the time-differential tests and in all the samplings, which proves that the CCP of the HACCP system is under control. After the SSOP program was applied, no pathogenic bacteria were found in the work-place, and the kinds and numbers of bacteria decreased. The numbers of general bacteria and colon bacilli also showed a significant difference from those before the SSOP program in the filleting board (P＜.05), in the skinning board (P＜.0l), in the neck-removing knife (P＜.05), and in the filleting knife (P＜.01). The working equipments, periodically disinfected, also showed a significant difference in sanitary conditions (in the dehydrator, P＜.05). The number of bacteria found on the food-touching surface was within the standard (below 500/l00 cm$^2$) After the SSOP program was applied, the general bacteria and colon bacilli were not found. The quality of water used in the food processing was also within the standard. The numbers of bacteria falling from the air in the work-place were negligible in all the samplings (＜30CFU/l000ι). The staphylococci and fungi were not found.

• Journal of the Korean GEO-environmental Society
• /
• v.8 no.5
• /
• pp.5-14
• /
• 2007

The quantity of noxious wastes generated by the growth in industrialization and population in all over the world and its potential hazards in subsurface environments are becoming increasingly significant. The extraction of the contaminant from the soil and movement of the water are restricted due to the low permeability and adsorption characteristics of the reclaimed soils. Incorporated technique with PVDs have been used for dewatering from fine-grained soils for the purpose of ground improvement by means of soil flushing and soil vapor extraction systems. This paper is to evaluate several key parameters that affected to the performance of the PVDs specifically with regard to: well resistance of PVD, zone of influence, and smear effects. In the feasibility of contaminant remediation was evaluated in pilot-scale laboratory experiments. Well resistance is affected on the vertical discharge capacity of the PVDs under the various vacuum pressures. The discharge capacity increases consistently in areal extents with higher applied vacuum up to a limiting vacuum pressure. The head values for each piezometer at different vacuum pressures show that the largest head loss occurs within 14 cm of the PVD. Air flow rates and head losses were measured for the PVD placed in the model test box and the gas permeability of the silty soils was calculated. Increasing the equivalent diameter results in a decrease in the calculated gas permeability. It is concluded that the gas permeability determined over the 1,500 to 2,000 $cm^3/s$ flow rates are the most accurate values which yields gas permeability of about 3.152 Darcy.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.5
• /
• pp.571-577
• /
• 2012

In this study, a small movable batch treatment system for dredging soil deposited in a rain water tube is proposed; further, a vacuum silo sorting separation device with a vacuum silo, first-stage sorting separator, and conveyor is designed. The vacuum silo sorting separation device also consists of a storage tank, transferring screw, vacuum gate, screen bar, screen bar cleaner, and vacuum discharging device. In view of the fact that the flow of drawn air in the storage tank is a major factor influencing the sorting separation performance, the optimum shape of the tank is determined by CFD flow analysis. In addition, by using CAE structure analysis, the safety of a storage tank made of boards is examined. The specifications of the vacuum silo sorting separation device are determined by conducting mechanical and dynamic simulations of the driving mechanism of the vacuum silo sorting separation device through 3D-CAD modeling. Following this study, we will design a drum-screen-type second sorter, a decanter-type dehydration device, and waste water tank and pump as a secondary device. Further, on the basis of this design, we will construct a prototype model and carry out a field test.