• 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.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.631-636
• /
• 2022

Alcohol content, which is an important standard for Takju, a traditional multiple parallel fermentation liquor called makgeolli, is a factor that can affect the flavor. For alcohol content analysis, the distillation/hydrometry technique is mainly used. In this study, we analyzed the alcohol content of 14 commercially available Takju by the distillation/hydrometry technique and the improved GC method, respectively, after verifying the reliability of improved GC method. The precision and accuracy of the GC method were satisfactory, and LOQ and LOD were evaluated as 0.5% and 0.1% of ethanol contents, respectively. Among the three Takju exceeding the labelled alcohol content ±1, one Takju was quantitated as alcohol content 9.9% (by GC method) and 10.1% (distillation/hydrometry technique) exceeding labelled 6.0%. It was within the analytical error range of alcohol content for other two Takju, where the alcohol contents were exceeded -1.1%. The average precision (%RSD) of 14 Takju analyzed by the distillation/hydrometry technique (36.2%) and the GC method (12.8%), confirming that the GC method was better than the other. The improved GC method was evaluated to be effective in managing and improving the alcohol content standard of Takju with the wide range of alcohol content.

• Computers and Concrete
• /
• v.31 no.3
• /
• pp.267-276
• /
• 2023

The main purpose of the current research is to develop an efficient two variables trigonometric shear deformation beam theory to investigate the buckling behavior of symmetric and non-symmetric functionally graded carbon nanotubes reinforced composite (FG-CNTRC) beam resting on an elastic foundation with various boundary conditions. The proposed theory obviates the use to shear correction factors as it satisfies the parabolic variation of through-thickness shear stress distribution. The composite beam is made of a polymeric matrix reinforced by aligned and distributed single-walled carbon nanotubes (SWCNTs) with different patterns of reinforcement. The material properties of the FG-CNTRC beam are estimated by using the rule of mixture. The governing equilibrium equations are solved by using new analytical solutions based on the Galerkin method. The robustness and accuracy of the proposed analytical model are demonstrated by comparing its results with those available by other researchers in the existing literature. Moreover, a comprehensive parametric study is presented and discussed in detail to show the effects of CNTs volume fraction, distribution patterns of CNTs, boundary conditions, length-to-thickness ratio, and spring constant factors on the buckling response of FG-CNTRC beam. Some new referential results are reported for the first time, which will serve as a benchmark for future research.

• Composites Research
• /
• v.36 no.1
• /
• pp.48-52
• /
• 2023

Fiber-reinforced composites have anisotropic material properties, so the mechanical properties of composite structures can vary depending on the stacking sequence. Therefore, it is essential to design the proper stacking sequence of composite structures according to the functional requirements. However, depending on the manufacturing condition or the shape of the structure, there are many cases where the designed stacking angle is out of range, which can affect structural performance. Accordingly, it is important to analyze the stacking angle in order to confirm that the composite structure is correctly fabricated as designed. In this study, the stacking angle was predicted from real cross-sectional images of fiber-reinforced composites using convolutional neural network (CNN)-based deep learning. Carbon fiber-reinforced composite specimens with several stacking angles were fabricated and their cross-sections were photographed on a micro-scale using an optical microscope. The training was performed for a CNN-based deep learning model using the cross-sectional image data of the composite specimens. As a result, the stacking angle can be predicted from the actual cross-sectional image of the fiber-reinforced composite with high accuracy.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.77-82
• /
• 2023

The Ministry of Agriculture, Food and Rural Affairs established the FarmMap, an digital map of agricultural land. In this study, using deep learning, we suggest the application of farm map reading to farmland such as paddy fields, fields, ginseng, fruit trees, facilities, and uncultivated land. The farm map is used as spatial information for planting status and drone operation by digitizing agricultural land in the real world using aerial and satellite images. A reading manual has been prepared and updated every year by demarcating the boundaries of agricultural land and reading the attributes. Human reading of agricultural land differs depending on reading ability and experience, and reading errors are difficult to verify in reality because of budget limitations. The farmmap has location information and class information of the corresponding object in the image of 5 types of farmland properties, so the suitable AI technique was tested with ResNet50, an instance segmentation model. The results of attribute reading of agricultural land using deep learning and attribute reading by humans were compared. If technology is developed by focusing on attribute reading that shows different results in the future, it is expected that it will play a big role in reducing attribute errors and improving the accuracy of digital map of agricultural land.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.99-110
• /
• 2023

This study proposed a classification of malicious network traffic using the cyber threat framework(Mitre ATT&CK) and machine learning to solve the real-time traffic detection problems faced by current security monitoring systems. We applied a network traffic dataset called UNSW-NB15 to the Mitre ATT&CK framework to transform the label and generate the final dataset through rare class processing. After learning several boosting-based ensemble models using the generated final dataset, we demonstrated how these ensemble models classify network traffic using various performance metrics. Based on the F-1 score, we showed that XGBoost with no rare class processing is the best in the multi-class traffic environment. We recognized that machine learning ensemble models through Mitre ATT&CK label conversion and oversampling processing have differences over existing studies, but have limitations due to (1) the inability to match perfectly when converting between existing datasets and Mitre ATT&CK labels and (2) the presence of excessive sparse classes. Nevertheless, Catboost with B-SMOTE achieved the classification accuracy of 0.9526, which is expected to be able to automatically detect normal/abnormal network traffic.

• Journal of Applied Biological Chemistry
• /
• v.65 no.4
• /
• pp.343-348
• /
• 2022

This study was performed to establish an analytical method for the standardization of Angelicae Dahuricae Radix as a functional ingredient. We established six compounds including oxypeucedanin hydrate (1), byakangelcol (2), oxypeucedanin (3), imperatorin (4), phellopterin (5) and isoimperatorin (6) as marker compounds of Angelicae Dahuricae Radix. An analytical method using Ultra Performance Liquid Chromatography (UPLC) was established and validated for marker compounds of Angelicae Dahuricae Radix. The specificity was confirmed by the chromatogram from UPLC and the value of coefficient determination was also higher than 0.999, indicating high linearity. The relative standard deviation (RSD) and recovery of marker compounds were less than 5% and in the range of 90- 110%, respectively, which means that this method has high accuracy and precision. Therefore, this analytical method could be used as basic data for the development of functional ingredients for health functional food of Angelicae Dahuricae Radix.

• Journal of Animal Reproduction and Biotechnology
• /
• v.37 no.4
• /
• pp.292-297
• /
• 2022

Direct injection of CRISPR/Cas9 into zygotes enables the production of genetically modified nonhuman primates (NHPs) essential for modeling specific human diseases, such as Usher syndrome, and for developing novel therapeutic strategies. Usher syndrome is a rare genetic disease that causes loss of hearing, retinal degeneration, and problems with balance, and is attributed to a mutation in MYO7A, a gene that encodes an uncommon myosin motor protein expressed in the inner ear and retinal photoreceptors. To produce an Usher syndrome type 1B (USH1B) rhesus macaque model, we disrupted the MYO7A gene in developing zygotes. Identification of appropriately edited MYO7A embryos for knockout embryo transfer requires sequence analysis of material recovered from a trophectoderm (TE) cell biopsy. However, the TE biopsy procedure is labor intensive and could adversely impact embryo development. Recent studies have reported using cell-free DNA (cfDNA) from embryo culture media to detect aneuploid embryos in human in vitro fertilization (IVF) clinics. The cfDNA is released from the embryo during cell division or cell death, suggesting that cfDNA may be a viable resource for sequence analysis. Moreover, cfDNA collection is not invasive to the embryo and does not require special tools or expertise. We hypothesized that selection of appropriate edited embryos could be performed by analyzing cfDNA for MYO7A editing in embryo culture medium, and that this method would be advantageous for the subsequent generation of genetically modified NHPs. The purpose of this experiment is to determine whether cfDNA can be used to identify the target gene mutation of CRISPR/Cas9 injected embryos. In this study, we were able to obtain and utilize cfDNA to confirm the mutagenesis of MYO7A, but the method will require further optimization to obtain better accuracy before it can replace the TE biopsy approach.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.26 no.3
• /
• pp.37-51
• /
• 2023

Spatial information is essential for interpreting urban phenomena. Methodologies for spatializing urban information, especially when it lacks location details, have been consistently developed. Typical methods include Geocoding using structured address information or place names, spatial integration with existing geospatial data, and manual tasks utilizing reference data. However, a vast number of documents produced by administrative agencies have not been deeply dealt with due to their unstructured nature, even when there's demand for spatialization. This research utilizes the natural language processing model BERT to spatialize public documents related to urban planning. It focuses on extracting sentence elements containing addresses from documents and converting them into structured data. The study used 18 years of urban planning public announcement documents as training data to train the BERT model and enhanced its performance by manually adjusting its hyperparameters. After training, the test results showed accuracy rates of 96.6% for classifying urban planning facilities, 98.5% for address recognition, and 93.1% for address cleaning. When mapping the result data on GIS, it was possible to effectively display the change history related to specific urban planning facilities. This research provides a deep understanding of the spatial context of urban planning documents, and it is hoped that through this, stakeholders can make more effective decisions.

• Journal of Korea Water Resources Association
• /
• v.56 no.9
• /
• pp.529-541
• /
• 2023

Due to the growing concern over forecasting extreme weather events such as droughts caused by climate change, there has been a rising interest in seasonal meteorological forecasts that offer ensemble predictions for the upcoming seven months. Nonetheless, limited research has been conducted in South Korea, particularly in assessing their effectiveness at the catchment-scale. In this study, we assessed the accuracy of ECMWF's seasonal forecasts (including precipitation, temperature, and evapotranspiration) for the period of 2011 to 2020. We focused on 12 multi-purpose reservoir catchments and compared the forecasts to climatology data. Continuous Ranked Probability Skill Score method is adopted to assess the forecast skill, and the linear scaling method was applied to evaluate its impact. The results showed that while the seasonal meteorological forecasts have similar skill to climatology for one month ahead, the skill decreased significantly as the forecast lead time increased. Compared to the climatology, better results were obtained in the Wet season than the Dry season. In particular, during the Wet seasons of the dry years (2015, 2017), the seasonal meteorological forecasts showed the highest skill for all lead times.