Ulsan National Institute of Science and Technology · Computer Science
Professor Junghye Lee's research lab specializes in data-driven technology innovation and intelligent systems, focusing on advanced analytics for healthcare informatics, blockchain technology trends, and gene expression data mining. The lab develops cutting-edge methods in natural language processing, topic modeling, and knowledge graph construction to support technology opportunity discovery and federated data analysis in a privacy-preserving manner. Key research directions include deep learning-based text mining, feature selection in high-dimensional biological data, and the integration of multi-source data (e.g., technology, startups, and investor information) for strategic decision-making. The lab also emphasizes practical applications in precision medicine, Industry 4.0, and emerging technology forecasting.
Figures are computed from collected data and may differ slightly.
The proposed algorithm can help search similar patients across institutions effectively to support federated data analysis in a privacy-preserving manner.
Blockchain has become one of the core technologies in Industry 4.0. To help decision-makers establish action plans based on blockchain, it is an urgent task to analyze trends in blockchain technology. However, most of existing studies on blockchain trend analysis are based on effort demanding full-text investigation or traditional bibliometric methods whose study scope is limited to a frequency-based statistical analysis. Therefore, in this paper, we propose a new topic modeling method called Wo
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MEST) (No. 2019M3E5D1A02070863 and 2022R1C1C1005458). This work was also supported by the 2020 Research Fund (1.200098.01) of UNIST (Ulsan National Institute of Science & Technology).
Classification of microarray data plays a significant role in the diagnosis and prediction of cancer. However, its high-dimensionality (>tens of thousands) compared to the number of observations (<tens of hundreds) may lead to poor classification accuracy. In addition, only a fraction of genes is really important for the classification of a certain cancer, and thus feature selection is very essential in this field. Due to the time and memory burden for processing the high-dimensional data, univa
To capture emerging technologies in the fast-changing technology market, use of information concerning new technology-based firms (NTBFs) is strongly encouraged, in addition to the information about the technology itself. Especially, NTBFs rapidly respond to technological change, and their investment information is a significant criterion of technology valuation. Therefore, this study proposes a new technology opportunity discovery (TOD) framework that exploits text mining by deep learning and a
A classification task requires an exponentially growing amount of computation time and number of observations as the variable dimensionality increases. Thus, reducing the dimensionality of the data is essential when the number of observations is limited. Often, dimensionality reduction or feature selection leads to better classification performance than using the whole number of features. In this paper, we study the possibility of utilizing the Markov blanket discovery algorithm as a new feature
This study revealed that condylar remodeling exhibited a tendency towards bone resorption, especially in the lateral areas. Condylar surface changes occurred, but were small.
The Bayesian network is a useful method for modeling healthcare issues since it can graphically represent causal relationships among variables and provide probabilistic information. We apply this method to conduct hypertension and hypertension complications incidence analyses using the National Health Insurance Corporation (NHIC) sample cohort database from 2002 to 2010, which contains more than a million prescribers' information, including socio-demographic information, health check-up records,
Recommendation systems have required centralized storage of user data, but due to privacy concerns, recent studies adopted federated learning (FL) that discloses intermediate statistics instead of raw data to build privacy-preserving federated recommendation systems. However, they suffer from inefficiencies in privacy-preserving mechanisms and inaccuracies in simple algorithms that ignore sequential information. This study proposes an extension of Word2Vec for a privacy-preserving federated sequ
Abstract Porous materials have attracted considerable interest as water sorbents due to their potential in a broad range of water sorption‐related applications. Metal–organic frameworks (MOFs) are particularly notable for their high porosity and tunability. However, their limited hydrolytic stability often results in pore collapse, which significantly hinders their water sorption performance. To address this issue, an innovative design strategy based on reticular chemistry is essential to enhanc
Open papers in the app to read, cite, and organize with AI.
