• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.12-22
• /
• 2021

This article suggests the machine learning model, i.e., classifier, for predicting the production quality of free-machining 303-series stainless steel(STS303) small rolling wire rods according to the operating condition of the manufacturing process. For the development of the classifier, manufacturing data for 37 operating variables were collected from the manufacturing execution system(MES) of Company S, and the 12 types of derived variables were generated based on literature review and interviews with field experts. This research was performed with data preprocessing, exploratory data analysis, feature selection, machine learning modeling, and the evaluation of alternative models. In the preprocessing stage, missing values and outliers are removed, and oversampling using SMOTE(Synthetic oversampling technique) to resolve data imbalance. Features are selected by variable importance of LASSO(Least absolute shrinkage and selection operator) regression, extreme gradient boosting(XGBoost), and random forest models. Finally, logistic regression, support vector machine(SVM), random forest, and XGBoost are developed as a classifier to predict the adequate or defective products with new operating conditions. The optimal hyper-parameters for each model are investigated by the grid search and random search methods based on k-fold cross-validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with an accuracy of 0.9929, specificity of 0.9372, F₁-score of 0.9963, and logarithmic loss of 0.0209. The classifier developed in this study is expected to improve productivity by enabling effective management of the manufacturing process for the STS303 small rolling wire rods.

• Transactions of the Korean hydrogen and new energy society
• /
• v.32 no.6
• /
• pp.573-584
• /
• 2021

Hydrogen is evaluated as one of the new energy sources that can overcome the limitations and pollution problems of conventional fossil fuels. Although hydrogen is CO₂-free, attention is required in NO_x emission and flame stability in order to use hydrogen in existing gas fuel system. However, use of electric grids is an unrealistic strategy for decarbonization for residential and commercial heating. Instead, use of H₂ that utilizes city gas grid is suggested as a reasonable alternative in terms of compatibility with existing systems, economic feasibility, and accessibility. In this study, the thermal efficiency and NO_x performance of the boiler according to the H₂ mixture ratio and vapor humidified ratio are reviewed for a humidified NG-H₂ boiler that vapor humidity to combustion air. Mixed fuel with H₂ (20%) is almost similar to NG in terms of efficiency, flame temperature, and pollution performance. Thus, it is expected to be directly compatible with the existing NG system. If the exhaust temperature of the H₂ boiler is lowered to around 60℃ at a humidified ratio of 15-20%, the NO_x emission concentration can be suppressed to about 5-10 ppm. The level of efficiency reaches 87% of the rated load efficiency, which is equivalent to the highest grade achievable.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.5
• /
• pp.1003-1012
• /
• 2022

The horizontal force transfer to the turbine and substructure of a wind power generation system is a very important factor in maintaining the safety of the system, but it is inevitably vulnerable to large-scale coastal disasters such as earthquakes and typhoons. Wind power generation systems built on the coast or far offshore are very disadvantageous in terms of economic feasibility due to an increase in initial investment cost because a more robust design is required when installed in areas vulnerable to coastal disasters. In this study, the GIS method was used to select the optimal site for a wind farm from the viewpoint of reducing the risk of coastal disasters. The current status of earthquakes in the West and South Seas of Korea, and the path and intensity of typhoons affecting or passing through the West and South Seas were also analyzed. Accordingly, the optimal offshore wind farm site with the lowest risk of coastal disasters has been selected and will be used as basic research data for offshore wind power projects in the region in the future.

• Transactions of the Korean hydrogen and new energy society
• /
• v.34 no.4
• /
• pp.334-341
• /
• 2023

The purity of hydrogen finally purified in the hydrogen purification process system is greatly influenced by the uniformity of the purification temperature of the dry tower. A in-house code that can be easily used by field designers has been developed to predict the capacity of the appropriate heat source and the time to reach the temperature of the dry tower. A code was developed to predict unsteady heat transfer using Visual Basic for Applications. To verify the developed code, a grid independence test was performed, and finally, calculations were performed for two cases. In the first case, the time for the temperature of the heater jacket to reach 360℃ was about 1,400 seconds when the supply heat source was 1,000 W. And in the second case, the time for the temperature of the heater jacket to reach 360℃ was about 710 seconds when the supply heat source was 2,000 W. It was confirmed that the developed code well describes the actual test data of the regeneration process of adsorption and desorption, and it is judged that the code developed in the design process of various capacity systems will be effectively applied to the heat capacity calculation in the future.

• Journal of ILASS-Korea
• /
• v.28 no.1
• /
• pp.16-23
• /
• 2023

The objective of this numerical study is to investigate the effect of the shape and material of the blower blade for the electrified speed sprayer on the blowing performance. The shape of the blade was changed to the bonding angle, the number of blades, the width of the blade, and the blade length based on the existing model. In order to obtain the reliability of the numerical model, the analysis of the grid dependence was performed in the numerical analysis. The numerical analysis results were compared and analyzed in terms of the agricultural chemical penetration length characteristics, flow uniformity characteristics, and velocity distribution characteristics. Furthermore, the effect of material change on weight reduction and structural characteristics was also compared and analyzed. As a result of the analysis, it was found that the optimal condition was that the blade angle was 45°, the number of blades was 12, and the width was 115 mm, which was confirmed through a comparison of the inlet mass flow rate. As a result of the equivalent stress lower than the yield strength due to the material change from aluminum to steel compared to the existing steel, structural defects do not appear, and it is judged that the operation time compared to the battery capacity will be improved through the weight reduction of the blade.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1123-1146
• /
• 2023

In South Korea, there have been many studies on efficient building-energy management using renewable energy facilities in single zero-energy houses or buildings. However, such management was limited due to spatial and economic problems. To realize a smart zero-energy city, studying efficient energy integration for the entire city, not just for a single house or building, is necessary. Therefore, this study was conducted in the eco-friendly energy town of Chungbuk Innovation City. Chungbuk successfully realized energy independence by converging new and renewable energy facilities for the first time in South Korea. This study analyzes energy data collected from public buildings in that town every minute for a year. We propose a smart city building-energy management model based on the results that combine various renewable energy sources with grid power. Supervised learning can determine when it is best to sell surplus electricity, or unsupervised learning can be used if there is a particular pattern or rule for energy use. However, it is more appropriate to use reinforcement learning to maximize rewards in an environment with numerous variables that change every moment. Therefore, we propose a power distribution algorithm based on reinforcement learning that considers the sales of Energy Storage System power from surplus renewable energy. Finally, we confirm through economic analysis that a 10% saving is possible from this efficiency.

• International Journal of Computer Science & Network Security
• /
• v.23 no.5
• /
• pp.148-162
• /
• 2023

Classification systems can significantly assist the medical sector by allowing for the precise and quick diagnosis of diseases. As a result, both doctors and patients will save time. A possible way for identifying risk variables is to use machine learning algorithms. Non-surgical technologies, such as machine learning, are trustworthy and effective in categorizing healthy and heart-disease patients, and they save time and effort. The goal of this study is to create a medical intelligent decision support system based on machine learning for the diagnosis of heart disease. We have used a mixed feature creation (MFC) technique to generate new features from the UCI Cleveland Cardiology dataset. We select the most suitable features by using Least Absolute Shrinkage and Selection Operator (LASSO), Recursive Feature Elimination with Random Forest feature selection (RFE-RF) and the best features of both LASSO RFE-RF (BLR) techniques. Cross-validated and grid-search methods are used to optimize the parameters of the estimator used in applying these algorithms. and classifier performance assessment metrics including classification accuracy, specificity, sensitivity, precision, and F1-Score, of each classification model, along with execution time and RMSE the results are presented independently for comparison. Our proposed work finds the best potential outcome across all available prediction models and improves the system's performance, allowing physicians to diagnose heart patients more accurately.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.2
• /
• pp.45.1-45.1
• /
• 2021

Horizon Run 5 (HR5) is a cosmological hydrodynamical simulation which captures the properties of the Universe on aGpc scale while achieving a resolution of 1kpc. This enormous dynamic range allows us to simultaneously capture the physics of the cosmic web on very large scales and account for the formation and evolution of dwarf galaxies on much smaller scales. On the back of a remarkable achievement of this, we have finished to run follow-up simulations which have 2 times larger volume than before and are expected to complementary to some limitations of previous HR simulations both for the study on the large scale features and the expansion history in a distant Universe. For these simulations, we consider the sub-grid physics of radiative heating/cooling, reionization, star formation, SN/AGN feedbacks, chemical evolution and the growth of super-massive blackholes. In order to do this project, we implemented a hybrid MPI-OpenMP version of the RAMSES code, 'RAMSES-OMP', which is specifically designed for modern many-core many thread parallel systems. These simulation successfully reproduce various observation result and provide a large amount of statistical samples of Lyman-alpha emitters and protoclusters which are important to understand the formation and expansion history of early universe. These are invaluable assets for the interpretation of current ΛCDM cosmology and current/upcoming deep surveys of the Universe, such as the world largest narrow band imaging survey, ODIN (One-hundred-square-degree Dark energy camera Imaging in Narrow band).

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.1
• /
• pp.1-12
• /
• 2023

It is very time-intensive to obtain data with labels on anomaly detection tasks for multivariate time series. Therefore, several studies have been conducted on unsupervised learning that does not require any labels. However, a well-done integrative survey has not been conducted on in-depth discussion of learning architecture and property for multivariate time series anomaly detection. This study aims to explore the characteristic of well-known architectures in anomaly detection of multivariate time series. Additionally, architecture was categorized by using top-down and bottom-up approaches. In order toconsider real-world anomaly detection situation, we trained models with dataset such as power grids or Cyber Physical Systems that contains realistic anomalies. From experimental results, we compared and analyzed the comprehensive performance of each architecture. Quantitative performance were measured using precision, recall, and F1 scores.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2768-2787
• /
• 2023

As an important research direction of the application of computer science in the medical field, the automatic generation technology of radiology report has attracted wide attention in the academic community. Because the proportion of normal regions in radiology images is much larger than that of abnormal regions, words describing diseases are often masked by other words, resulting in significant feature loss during the calculation process, which affects the quality of generated reports. In addition, the huge difference between visual features and semantic features causes traditional multi-modal fusion method to fail to generate long narrative structures consisting of multiple sentences, which are required for medical reports. To address these challenges, we propose a multi-feature optimization Transformer (MFOT) for generating radiology reports. In detail, a multi-dimensional mapping attention (MDMA) module is designed to encode the visual grid features from different dimensions to reduce the loss of primary features in the encoding process; a feature pre-fusion (FP) module is constructed to enhance the interaction ability between multi-modal features, so as to generate a reasonably structured radiology report; a detail enhanced attention (DEA) module is proposed to enhance the extraction and utilization of key features and reduce the loss of key features. In conclusion, we evaluate the performance of our proposed model against prevailing mainstream models by utilizing widely-recognized radiology report datasets, namely IU X-Ray and MIMIC-CXR. The experimental outcomes demonstrate that our model achieves SOTA performance on both datasets, compared with the base model, the average improvement of six key indicators is 19.9% and 18.0% respectively. These findings substantiate the efficacy of our model in the domain of automated radiology report generation.