• Korean Chemical Engineering Research
• /
• v.62 no.3
• /
• pp.214-224
• /
• 2024

Valves play an essential role in a chemical plant such as regulating fluid flow and pressure. Therefore, optimal selection of the valve size and type is essential task. Valve size and type have been selected based on theoretical formulas about calculating valve sizing coefficient (Cv). However, this approach has limitations such as requiring expert knowledge and consuming substantial time and costs. Herein, this study developed a model for predicting valve sizes and types using machine learning. We developed models using four algorithms: ANN, Random Forest, XGBoost, and Catboost and model performances were evaluated using NRMSE & R² score for size prediction and F1 score for type prediction. Additionally, a case study was conducted to explore the impact of phases on valve selection, using four datasets: total fluids, liquids, gases, and steam. As a result of the study, for valve size prediction, total fluid, liquid, and gas dataset demonstrated the best performance with Catboost (Based on R², total: 0.99216, liquid: 0.98602, gas: 0.99300. Based on NRMSE, total: 0.04072, liquid: 0.04886, gas: 0.03619) and steam dataset showed the best performance with RandomForest (R²: 0.99028, NRMSE: 0.03493). For valve type prediction, Catboost outperformed all datasets with the highest F1 scores (total: 0.95766, liquids: 0.96264, gases: 0.95770, steam: 1.0000). In Engineering Procurement Construction industry, the proposed fluid-specific machine learning-based model is expected to guide the selection of suitable valves based on given process conditions and facilitate faster decision-making.

• Korean Chemical Engineering Research
• /
• v.62 no.3
• /
• pp.225-232
• /
• 2024

The reduction of CO₂ emissions in the energy production sector, which accounts for 86.8% of total greenhouse gas emissions, is important to achieve carbon-neutrality. At present, 60% of total power generation in South Korea is coal and natural gas. Replacing fossil fuel with renewable energy such as wind and solar has disadvantages of unstable energy supply and high costs. Therefore, this study was conducted through the co-firing of natural gas, ammonia and hydrogen utilizing the natural gas combined cycle process. The results demonstrated reduction in CO₂ emissions and 34%~238% of the power production compared to using only natural gas. Case studies on mass fractions of natural gas, ammonia and hydrogen indicated that power production and NO_x emissions were inversely proportional to the ammonia ratio and directly proportional to the hydrogen ratio. This study provides guidelines for the use of various fuel mixtures and economic analysis in co-firing power generation.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.4
• /
• pp.178-185
• /
• 2023

Rapid urbanization and advancements in technology have led to a surge in the number of automobiles, resulting in frequent traffic accidents, and consequently, an increase in human casualties and economic losses. Therefore, there is a need for technology that can predict the risk of traffic accidents to prevent them and minimize the damage caused by them. Traffic accidents occur due to various factors including traffic congestion, the traffic environment, and road conditions. These factors give traffic accidents spatiotemporal characteristics. This paper analyzes traffic accident data to understand the main characteristics of traffic accidents and reconstructs the data in a time series format. Additionally, an LSTM-MLP based model that excellently captures spatiotemporal characteristics was developed and utilized for traffic accident prediction. Experiments have proven that the proposed model is more rational and accurate in predicting the risk of traffic accidents compared to existing models. The traffic accident risk prediction model suggested in this paper can be applied to systems capable of real-time monitoring of road conditions and environments, such as navigation systems. It is expected to enhance the safety of road users and minimize the social costs associated with traffic accidents.

• Land and Housing Review
• /
• v.15 no.3
• /
• pp.25-43
• /
• 2024

Using the 2021 Korea Housing Survey Data, this study compared and analyzed the factors influencing the residential mobility of residents in public and private rental housing by population and social characteristics, economic characteristics, and housing characteristics. The analysis results are as follows. As a result of descriptive statistics analysis, it was found that private rental households were young and economically active. While the proportion of apartment residents and new housing, and the level of housing satisfaction were low, the level of housing insecurity was high. Through logistic regression analysis, significant factors influencing the residential mobility of private and public leases were analyzed. In terms of demographic and social characteristics, private leases were affected by marital status, the number of household members, the age of the household head, and the residential area, while public leases were affected by marital status and the age of the household head. In terms of economic characteristics, private leases were affected by assets, debt, and housing management costs, while public leases were affected only by debt. In terms of residential characteristics, private leases were affected by periods of homelessness, housing satisfaction, housing insecurity, and a sense of homeownership, while public leases were affected by housing type, years of construction, housing satisfaction, housing insecurity, and a sense of homeownership.

• Journal of Venture Innovation
• /
• v.7 no.3
• /
• pp.159-182
• /
• 2024

The study aimed to analyze the factors influencing customer experience and satisfaction in home meal replacement (HMR) subscription services through the lens of the Value-based Adoption Model (VAM). Specifically, the study examined the mediating role of customer value co-creation. A survey was conducted among users of HMR subscription services within the last three months, yielding 200 valid responses for analysis using AMOS 24.0. The findings revealed that the factors of usefulness, entertainment, convenience, and curation positively impacted customer value co-creation, while perceived anxiety had a negative effect. Interestingly, the influence of perceived costs on customer value co-creation was not significant, potentially indicating that cost concerns may be overshadowed by other factors in this service context. Among the variables, curation emerged as the most influential factor, followed by convenience, usefulness, and entertainment. Customer value co-creation was found to significantly enhance both customer experience and satisfaction, with customer experience also directly contributing to increased customer satisfaction. The study underscored the importance of customer value co-creation as a mediating factor, bridging the gap between service features and customer outcomes. This mediation highlights how effectively managed interactions between the service provider and customers can transform perceived value into tangible satisfaction. From a practical standpoint, the results emphasize the critical role of curation services in driving customer value and satisfaction in HMR subscription services. Companies should focus on refining curation and enhancing convenience to maximize customer engagement and satisfaction. The study provides valuable academic insights into the dynamics of customer value co-creation and its implications for service management, contributing to the broader understanding of how modern subscription services can optimize customer relationships.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.4
• /
• pp.763-780
• /
• 2024

As the domestic and international landscape undergoes rapid changes, the importance of implementing security measures in response to the growing threats that businesses face is increasing. In this context, the need for Security by Design (SbD), integrating security from the early design stages, is becoming more pronounced, with threat modeling recognized as a fundamental tool of SbD. Particularly, to save costs and time by detecting and resolving security issues early, the application of the Shift Left strategy requires the involvement of personnel with limited security expertise, such as software developers, in threat modeling. Although various automated threat modeling tools have been released, their lack of user-friendliness for personnel lacking security expertise poses challenges in conducting threat modeling effectively. To address this, we conducted an analysis of research related to threat modeling tools and derived usability evaluation criteria based on the GQM(Goal-Question-Metric) approach. An expert survey was conducted to validate both the validity and objectivity of the derived criteria. We performed usability evaluations of three threat modeling tools (MS TMT, SPARTA, PyTM), and the evaluation results led to the conclusion that MS TMT exhibited superior usability compared to other tools. This study aims to contribute to the creation of an environment where personnel with limited security expertise can effectively conduct threat modeling by proposing usability evaluation criteria.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.125-131
• /
• 2023

Globally, drug side effects rank among the top causes of death. To effectively respond to these adverse drug reactions, a shift towards an active real-time monitoring system, along with the standardization and quality improvement of data, is necessary. Integrating individual institutional data and utilizing large-scale data to enhance the accuracy of drug side effect predictions is critical. However, data sharing between institutions poses privacy concerns and involves varying data standards. To address this issue, our research adopts a federated learning approach, where data is not shared directly in compliance with privacy regulations, but rather the results of the model's learning are shared. We employ the Common Data Model (CDM) to standardize different data formats, ensuring accuracy and consistency of data. Additionally, we propose a drug monitoring system that enhances security and scalability management through a cloud-based federated learning environment. This system allows for effective monitoring and prediction of drug side effects while protecting the privacy of data shared between hospitals. The goal is to reduce mortality due to drug side effects and cut medical costs, exploring various technical approaches and methodologies to achieve this.

• Journal of the Korean Society for Heat Treatment
• /
• v.37 no.4
• /
• pp.163-171
• /
• 2024

SCR420H steel is a low-carbon chromium alloy steel designed for carburizing heat treatment. Recently, research is being conducted on high-temperature carburization heat treatment to reduce costs and CO₂ emissions by shortening the carburization time to meet the international carbon neutral policy. However, this high-temperature carburization heat treatment coarsens the steel grains and causes a decrease in mechanical properties. In this study, a large amount of Ti was added to increase the grain refinement effect in the high-temperature carburizing process. We investigated the microstructure and precipitates of SCR420H steel without Ti (Al steel) and with Ti (AlTi steel). Thermodynamic calculations showed that the AlN and (Ti,Nb)(C,N) precipitated in Al steel, while (Ti,Nb)(C,N) and Ti₄C₂S₂ precipitated in AlTi steel. Addition of Ti increases the fraction of bainite after reheating process. Transmission electron microscopy analysis shows that small amounts of AlN and (Ti,Nb)(C,N) precipitates are formed in the Al steel. The addition of Ti increases the density of (Ti,Nb)(C,N) precipitates and induces the formation of Ti₄C₂S₂ precipitates, increasing the grain coarsening temperature (GCT) under all heat treatment conditions. Higher reheating temperatures also resulted in higher GCT values due to increased precipitation.

• Korean Journal of Construction Engineering and Management
• /
• v.25 no.4
• /
• pp.34-44
• /
• 2024

In defense and military facility projects, adjustments to contract amounts due to design changes directly or indirectly affect factors such as increased construction costs and extended construction periods. Moreover, they can lead to differences of opinion and conflicts between the military and contracting parties. This case study analyzed the integrated management of defense and military facility projects by the Gyeonggi Southern Facilities Division, which oversees projects in Seoul and the southern Gyeonggi Province region for the Army, Navy, Marine Corps, and Air Force. Out of 388 completed projects, 103 cases with design changes were selected for analysis, aiming to ensure the reliability of data regarding the proportion of design changes in project completion. The study classified samples by the causes of design changes specified in the Ministry of Planning and Finance's contract regulations, assigning rankings based on the occurrence rates of each cause. Furthermore, it analyzed detailed factors for each cause of design change and derived implications to propose improvement measures. Considering the limited access to military primary data, this case study is expected to contribute to minimizing design changes in defense and military facility projects. Additionally, it is anticipated to be practically useful for subsequent research on contract amount adjustments resulting from design changes.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.73-82
• /
• 2023

With 78% of current fisheries workers being elderly, there's a pressing need to address labor shortages. Consequently, active research on smart aquaculture technologies, centered on object detection and tracking algorithms, is underway. These technologies allow for fish size analysis and behavior pattern forecasting, facilitating the development of real-time monitoring and automated systems. Our study utilized video data from cameras outside aquaculture facilities and implemented fish detection and tracking algorithms. We aimed to tackle high maintenance costs due to underwater conditions and camera corrosion from ammonia and pH levels. We evaluated the performance of a real-time system using YOLOv7 for fish detection and the SORT algorithm for movement tracking. YOLOv7 results demonstrated a trade-off between Recall and Precision, minimizing false detections from lighting, water currents, and shadows. Effective tracking was ascertained through re-identification. This research holds promise for enhancing smart aquaculture's operational efficiency and improving fishery facility management.