간행물
한국산업경영시스템학회지 KCI 등재 Journal of Society of Korea Industrial and Systems Engineering
- 발행기관 한국산업경영시스템학회
- 자료유형 학술지
- 간기 계간
- ISSN 2005-0461 (Print)2287-7975 (Online)
- 수록기간 1978 ~ 2025
- 주제분류 공학 > 산업공학 공학 분류의 다른 간행물
- 십진분류KDC 530DDC 620
권호리스트/논문검색
Vol.48 No.1 (2025년 3월) 8건
1.
2025.03
구독 인증기관 무료, 개인회원 유료
This study presents a novel methodology for analyzing disease relationships from a network perspective using Large Language Model (LLM) embeddings. We constructed a disease network based on 4,489 diseases from the International Classification of Diseases (ICD-11) using OpenAI’s text-embedding-3-small model. Network analysis revealed that diseases exhibit small-world characteristics with a high clustering coefficient (0.435) and form 16 major communities. Notably, mental health-related diseases showed high centrality in the network, and a clear inverse relationship was observed between community size and internal density. The embedding-based relationship analysis revealed meaningful patterns of disease relationships, suggesting the potential of this methodology as a novel tool for studying disease associations. Results suggest that mental health conditions play a more central role in disease relationships than previously recognized, and disease communities show distinct organizational patterns. This approach shows promise as a valuable tool for exploring large-scale disease relationships and generating new research hypotheses.
4,000원
2.
2025.03
구독 인증기관 무료, 개인회원 유료
This study aims to improve the interpretability and transparency of forecasting results by applying an explainable AI technique to corporate default prediction models. In particular, the research addresses the challenges of data imbalance and the economic cost asymmetry of forecast errors. To tackle these issues, predictive performance was analyzed using the SMOTE-ENN imbalance sampling technique and a cost-sensitive learning approach. The main findings of the study are as follows. First, the four machine learning models used in this study (Logistic Regression, Random Forest, XGBoost, and CatBoost) produced significantly different evaluation results depending on the degree of asymmetry in forecast error costs between imbalance classes and the performance metrics applied. Second, XGBoost and CatBoost showed good predictive performance when considering variations in prediction cost asymmetry and diverse evaluation metrics. In particular, XGBoost showed the smallest gap between the actual default rate and the default judgment rate, highlighting its robustness in handling class imbalance and prediction cost asymmetry. Third, SHAP analysis revealed that total assets, net income to total assets, operating income to total assets, financial liability to total assets, and the retained earnings ratio were the most influential factors in predicting defaults. The significance of this study lies in its comprehensive evaluation of predictive performance of various ML models under class imbalance and cost asymmetry in forecast errors. Additionally, it demonstrates how explainable AI techniques can enhance the transparency and reliability of corporate default prediction models.
4,600원
3.
2025.03
구독 인증기관 무료, 개인회원 유료
This study aims to develop an AI-based analysis system that aligns with the international trend of AI legislation, including the EU's AI Act, while also addressing the analytical needs of the public sector. The focus is on providing timely and objective information to policymakers and specialized researchers by exploring advanced analytical methodologies. As the complexity and volume of data rapidly increase in the modern policy environment, these methods have become essential for governments to obtain the objective information needed for critical decision-making. To achieve this, the study integrates machine learning, natural language processing (NLP), and Large Language Models (LLM) to create a system capable of meeting the analytical demands of government entities. The target dataset consists of “quantum” field data collected from South Korea's National R&D Information System (NTIS). Machine learning was applied to this data to assess the validity of the analysis, while BERTopic, a natural language analysis package, was used for text analysis. With the introduction of LLMs, the extracted information from machine learning and natural language analysis was not merely listed but also connected in meaningful ways to provide policy insights. This approach enhanced the transparency and reliability of AI analysis, minimizing potential errors or distortions in the data analysis process. In conclusion, this study emphasizes the development of a system that enables rapid and accurate information provision while maintaining compatibility with international AI regulations such as the AI Act. The use of LLMs, in particular, contributed to enhancing the system’s capabilities for deeper and more multifaceted analysis.
4,800원
4.
2025.03
구독 인증기관 무료, 개인회원 유료
The demand for automated diagnostic facilities has increased due to the rise in high-risk infectious diseases. However, small and medium-sized centers struggle to implement full automation because of limited resources. An integrated molecular diagnostics automation system addresses this issue by integrating small-scale automated facilities for each diagnostic process. Nonetheless, determining the optimal number of facilities and human resources remains challenging. This study proposes a methodology combining discrete event simulation and a genetic algorithm to optimize job-shop facility layout in the integrated molecular diagnostics automation system. A discrete event simulation model incorporates the number of facilities, processing times, and batch sizes for each step of the molecular diagnostics process. Genetic algorithm operations, such as tournament, crossover, and mutation, are applied to derive the optimal strategy for facility layout. The proposed methodology derives optimal facility layouts for various scenarios, minimizing costs while achieving the target production volume. This methodology can serve as a decision support tool when introducing job-shop production in the integrated molecular diagnostics automation system
4,000원
5.
2025.03
구독 인증기관 무료, 개인회원 유료
This paper addresses a scheduling problem aimed at minimizing makespan in a permutation flow shop with two machines and an inspection process that must be conducted at least once every certain number of outcomes from the first machine. A mathematical programming approach and a genetic algorithm, incorporating Johnson's rule and a specific mutation process, were developed to solve this problem. Johnson's rule was used to generate an initial population, while the mutation process ensured compliance with the inspection constraints. The results showed that within a computation time limit of 300 seconds, the mathematical programming approach often failed to provide optimal or feasible solutions, especially for larger job sets. For instance, when the process times of both machines were similar and the inspection time was longer, the mathematical programming approach failed to solve all 10 experiments with just 15 jobs and only had a 50% success rate for 100 jobs. In contrast, the proposed genetic algorithm solved all instances and delivered equal or superior results compared to the mathematical programming approach.
4,000원
6.
2025.03
구독 인증기관 무료, 개인회원 유료
The study on the efficiency improvement of qualification procedures for low Earth orbit (LEO) satellites analyzed the differences between the European ECSS and the American NASA standards. ECSS allows flexible test tailoring to accommodate project-specific requirements, whereas NASA enforces strict standardized procedures to ensure high reliability. Additionally, ECSS prioritizes cost efficiency, while NASA emphasizes reliability. In terms of application scope, NASA focuses on private-sector collaborations, whereas ECSS is centered on cooperative projects within Europe. Based on this comparative analysis, this study proposes a qualification framework for Korean LEO satellites, categorizing 18 qualification test items into mandatory and optional groups. This approach is expected to enhance the reliability, performance, and stability of satellite systems. Therefore, the proposed Korean qualification test sequence should be implemented and incorporated into national defense standards. This will strengthen the systematic structure of the qualification process while maximizing efficiency in terms of testing time and cost.
4,000원
7.
2025.03
구독 인증기관 무료, 개인회원 유료
Global strategists emphasize leveraging capabilities developed in domestic markets when expanding into international markets, a strategy reflected in the entry of Korean startups into the Chinese market. Value appropriation refers to a company's ability to claim its share of the value created in a target market, with value appropriation factors being critical elements required for this process. Despite these strategies, many foreign companies fail to achieve expected performance in China, often attributed to their inability to secure the necessary value appropriation factors. Researchers posit that business guanxi can play a pivotal role in facilitating the acquisition of these factors in the Chinese market. This study examines the relationship between the network capabilities of global startups and value appropriation factors during the overseas expansion stage. It also explores the moderating effect of business guanxi through empirical research. The data was collected via surveys from Korean global startups targeting business operations in China. The results indicate that sub-components of network capability, specifically networking capability and international market resource securing capability, are significantly associated with the acquisition of value appropriation factors. Furthermore, business guanxi was found to positively moderate the relationship between networking capability and securing value appropriation factors. These findings suggest that Korean global startups should prioritize developing strong network capabilities and fostering business guanxi to enhance their ability to secure value appropriation factors during the overseas expansion stage. Chinese companies do not have deep trust in Korean startups. Therefore, startups should build a business guanxi based on emotional trust from the beginning of early entry. This effort will extend beyond the trust of startup products and services to corporate trust.
4,800원
8.
2025.03
구독 인증기관 무료, 개인회원 유료
Defense Modeling & Simulation (M&S) techniques are used for developing the efficiency and economics of national defense at operational level so that it maintains interoperability and reusability in sustainability for the following process of the war simulation. However, the lack of conceptual models was one cause of limiting the interoperability and reusability in defense M&S areas. In this paper, the Conceptual Model of the Mission Space (CMMS) is studied as preliminary process for the defense M&S. The conceptual modeling framework called CMMS-K (Conceptual Model of the Mission Space-Korea) is suggested using a case example in consideration of the Korean Army specification and characteristics. The practicality of CMMS-K is evaluated through the ontology development for military scenarios. It is expected that the gap between the theoretical approach and the practical perspective of defense M&S can be diminished through the use of these approaches.
4,000원
