https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/872 2026-07-03T23:40:13Z 2026-07-03T23:40:13Z Shin, Seung-Jun Kim, Seong-Eun Kwon, Min-Joon Kang, Yeoung-Sin Eom, Jeong-Hoon https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/210859 2026-02-20T01:30:35Z 2026-02-01T00:00:00Z

Title: Digitalization and automation for supply chain resilience using asset administration shell Authors: Shin, Seung-Jun; Kim, Seong-Eun; Kwon, Min-Joon; Kang, Yeoung-Sin; Eom, Jeong-Hoon Abstract: Coronavirus disease 2019 (COVID-19) revealed the vulnerability of supply chains worldwide. This disruption has forced manufacturers to establish systematic strategies for supply chain resilience (SCRES) to restore the original performance while minimizing recovery time. SCRES largely relies on human labor via on/off-line methods. Relevant studies have dominantly suggested concepts, methodologies, and mathematical models from a theoretical perspective; however, few empirical solutions have been derived to recover supply chain disconnection. This paper proposes an SCRES method to reconstruct a supply chain at the machine level in a semi-automated manner based on an asset administration shell (AAS), that is, a standardized model that identifies the digital representation of assets to ensure interoperability. In this method, web scraping is used to collect machine data provided by manufacturers on webpages. AASs are created to digitalize machine agents based on the proposed AAS structure with ECLASS-driven semantic classification and mapping. AASs are retrieved to search for alternative machines in a digitalized machine network when a machine breaks down. A supply chain is reconstructed using a path search algorithm by deriving the best alternative machine to substitute the broken machine. The proposed method is demonstrated in a case study of crankshaft production using a prototype implementation. The proposed method is a machine-level approach to implement independent and interconnected machine agents, whose actions and interactions affect the reaction of a supply chain based on complex adaptive system theory in SCRES.

2026-02-01T00:00:00Z Seo, Jaehyun Jin, Semin Choi, Kyungah Hyun, Kyung Hoon Joung, Junegak https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/208924 2026-02-04T07:01:31Z 2026-01-01T00:00:00Z

Title: An explainable AI-based approach for identifying interior design style principles Authors: Seo, Jaehyun; Jin, Semin; Choi, Kyungah; Hyun, Kyung Hoon; Joung, Junegak Abstract: Interior design is crucial in shaping the characteristics of built environments. While designers often draw on expertise and intuition to define interior-styles such as Natural or Modern, formalized principles to systematically analyze these styles remain limited. This study presents a data-driven approach for identifying design principles that differentiate interior-styles by recognizing furnishing types and analyzing their color and material (FCM) using explainable AI (XAI). First, furnishing objects with FCM information were identified from user-generated interior images from two culturally distinct datasets—South Korea (N = 2,979) and the U.S. (N = 2,000)—using object, material, and color recognition. Second, classification models were built to distinguish interior-styles, forming a basis for analyzing how FCM combinations contribute to style differentiation. Third, a Style Explanation Value (SEV) was proposed to interpret the impact of FCM combinations on classification. The method identified distinctive and diverse FCM combinations, interpreted theoretically to reveal cultural variation. Additionally, simplified computation was introduced for practical use. To the best of our knowledge, this is the first study to use XAI in interior design analysis, offering object-level interpretation of how FCM combinations define stylistic identity.

2026-01-01T00:00:00Z Lee, Geun-cheol Lee, Heejung Koo, Hoon-Young https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/210918 2026-02-25T02:00:23Z 2026-01-01T00:00:00Z

Title: Feature Selection for High-Dimensional Data: A Case Study of NFT Valuation Authors: Lee, Geun-cheol; Lee, Heejung; Koo, Hoon-Young Abstract: In this study, we propose hedonic models for valuing Non-Fungible Tokens (NFTs) from the Azuki collection. We first analyze the NFT’s metadata and introduce a market volatility-robust dependent variable. Specific information of Azuki attributes is encoded via Term Frequency-Inverse Document Frequency (TF-IDF) to reflect both presence and collection-wide scarcity, yielding hundreds of features for each token. Two hedonic models are considered: a linear model and a squared model. To address high dimensionality, we tailor three variable-selection procedures—forward, backward, and stepwise—and compare them with regularization benchmarks and machine-learning methods. Using actual Azuki transaction data, we evaluate performance on a train-validation partition. The squared model overfits out of sample, while the linear model generalizes better and is adopted as the baseline. Applying variable selection to the linear baseline improves both parsimony and predictive performance. Machine-learning models exhibit very high training fit but notable performance degradation on the validation set, indicating overfitting in this setting. Overall, carefully specified hedonic models combined with principled variable selection offer competitive, interpretable, and more generalizable NFT valuation.

2026-01-01T00:00:00Z 양재용 박광태 https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/210418 2026-01-22T01:30:18Z 2025-12-01T00:00:00Z

Title: AI 동료 수용성 요인에 관한 연구: 직무 특성의 조절효과와 산업 특성에 따른 차이를 중심으로 Authors: 양재용; 박광태 Abstract: 본 연구는 AI 로봇에 대해서 인간 작업자가 느낄 수 있는 수용성 요인을 파악하고 직무 특성의 조절효과와 산업 특성에 따른 수용성 수준의 차이를 분석하는 것을 목적으로 한다. 이와 관련하여 기술수용모델, 알고리즘 회피 이론, 인간-로봇 상호작용 이론, 사회적 존재 이론, 직무-기술 적합성 이론 등 학제 간 이론적 논의를 통합적으로 고찰하여 측정모형과 측정지표를 개발하였다. AI 동료에 대한 수용성 요인으로는 신뢰도, 공정성 인식, 외형적 유사성, 감정적 거리감을 측정지표로 도출하였다. 국내 산업체 종사자들을 대상으로 설문조사를 실시한 결과, 공정성 인식과 감정적 거리감이 수용성에 유의한 영향을 미치는 것으로 나타났으며, 직무 특성이 신뢰도와 공정성 인식에 조절효과가 있는 것으로 나타났다. 또한 산업 특성의 측면에서 금융업은 제조업과 공공기관보다 높은 수용성을 보였고, 서비스업은 제조업보다 높은 수용성을 보였다. 본 연구는 AI 로봇의 수용성 결정요인과 직무 특성의 조절효과 및 산업 특성에 따른 차이를 규명함으로써 조직 설계와 AI 도입전략에 대한 함의를 도출할 수 있을 것으로 기대한다.; This study aims to identify the factors that influence human workers' acceptance of AI robots and to analyze the moderating effect of job characteristics and differences across industrial sectors. To this end, a measurement model and corresponding indicators were developed by comprehensively reviewing interdisciplinary theoretical backgrounds, including the Technology Acceptance Model, Algorithm Aversion Theory, Human–Robot Interaction Theory, Media Equation Theory, and Task–Technology Fit Theory. The acceptance factors for AI colleagues were operationalized using measurement indicators reflecting trustworthiness, perception of fairness, external similarity, and emotional distance. Based on a survey conducted among workers in Korean industries, the perception of fairness and emotional distance were found to have a significant effect on acceptance. Job characteristics were found to exert a moderating effect on the relationship between trustworthiness and acceptance, and between the perception of fairness and acceptance. Furthermore, the financial industry exhibited higher acceptance than both the manufacturing and public sectors, and the service industry showed higher acceptance than the manufacturing sector. This study is expected to provide practical implications for organizational design and AI adoption strategies by identifying the determinants of AI robot acceptance, validating the moderating role of job characteristics, and quantifying industry-specific differences in acceptance levels.

2025-12-01T00:00:00Z