Skip to main content

Yurang Park

Yonsei University · 生化学・遺伝学・分子生物学

研究室紹介

Professor Yurang Park's research lab specializes in biomedical data integration, pharmacogenomics, and intelligent health informatics, with a focus on developing web-based knowledge platforms and advanced analytics for genomic and clinical data. The lab pioneers tools for meta-analysis visualization, toxicogenomics, and mobile personal health records (mPHR), emphasizing data-driven insights in precision medicine. Recent work also extends into AI-powered cybersecurity for IoT systems, particularly deep learning-based intrusion detection using structured data transformation. The lab integrates bioinformatics, machine learning, and health technology to address challenges in data heterogeneity, patient engagement, and predictive toxicology.

pharmacogenomicshealth informaticstoxicogenomicsmobile PHRAI for cybersecurity

Research Overview

Papers
9
Total Citations
41
Papers (5y)
7
Primary Field
生化学・遺伝学・分子生物学

Research Output Trend

Figures are computed from collected data and may differ slightly.

Publications per year (5y)
7total
2016
2017
2021
2022
2026
Citations per year (5y)
40total
20162017202120222026

Selected Papers

9
1
Article|35 citations·2016
ForestPMPlot: A Flexible Tool for Visualizing Heterogeneity Between Studies in Meta-analysis
Eun Yong Kang, Yurang Park, Xiao Li, Ayellet V. Segrè, Buhm Han, Eleazar Eskin
SJR Q2G3 Genes Genomes GeneticsOA

Meta-analysis has become a popular tool for genetic association studies to combine different genetic studies. A key challenge in meta-analysis is heterogeneity, or the differences in effect sizes between studies. Heterogeneity complicates the interpretation of meta-analyses. In this paper, we describe ForestPMPlot, a flexible visualization tool for analyzing studies included in a meta-analysis. The main feature of the tool is visualizing the differences in the effect sizes of the studies to unde

GeneticsBiochemistry, Genetics and Molecular Biology
2
Article|5 citations·2021
Review of National-Level Personal Health Records in Advanced Countries
이지산, 박영택, 박유랑, 이재호
https://doi.org/10.4258/hir.2021.27.2.102

Objectives: This review article examines international examples of personal health records (PHRs) in advanced countriesand discusses the implications of these examples for the establishment and utilization of PHRs in South Korea. Methods:This article synthesized PHR case reports of Organization for Economic Co-operation and Development (OECD) membercountries, the Global Digital Health Partnership website on PHRs, and patient portals of individual countries to review thestatus of PHR services. Th

3
Article|1 citations·2005
Development of a Knowledge Base for Korean Pharmacogenomics Research Network
Chanhee Park, Suyeon Lee, Jung Yong, Yurang Park, Hyewon Lee, Ju-Han Kim
SJR Q2Genomics & Informatics

Abstract Pharmacogenomics research requires an intelligent in-tegration of large-scale genomic and clinical data with public and private knowledge resources. We developed a web-based knowledge base for KPRN (Korea Pharmacogenomics Research Network, http://kprn.snubi. org/). Four major types of information is integrated; ge-netic variation, drug information, disease information, and literature annotation. Eighteen Korean pharmacoge-nomics research groups in collaboration have submitted 859 genoty

Molecular BiologyBiochemistry, Genetics and Molecular Biology
4
Article|0 citations·2006
GraPT: Genomic InteRpreter about Predictive Toxicology
Woo Jung-Hoon, Yurang Park, Jung Yong, Jihun Kim, Ju-Han Kim
SJR Q2Genomics & Informatics

Toxicogenomics has recently emerged in the field of toxicology and the DNA microarray technique has become common strategy for predictive toxicology which studies molecular mechanism caused by exposure of chemical or environmental stress. Although microarray experiment offers extensive genomic information to the researchers, yet high dimensional characteristic of the data often makes it hard to extract meaningful result. Therefore we developed toxicant enrichment analysis similar to the common e

Molecular BiologyBiochemistry, Genetics and Molecular Biology
5
Book Chapter|0 citations·2021
AIM in Endocrinology
Namki Hong, Yurang Park, Seng Chan You, Yumie Rhee
SJR Q1Artificial Intelligence in Medicine
Health InformaticsMedicine
6
Book Chapter|0 citations·2022
AIM in Endocrinology
Namki Hong, Yurang Park, Seng Chan You, Yumie Rhee
SJR Q1Artificial Intelligence in Medicine
Health Information ManagementHealth Professions
7
Article|0 citations·2017
Is a Mobile Personal Health Record Effective Tool for Managing Patient-Generated Health Data?
Jae‐Ho Lee, Yura Lee, Yurang Park, Jiyoung Kim, Jeong Hoon Kim, Woo Sung Kim
IproceedingsOA

Background: Mobile health applications and personal health records (PHRs) are considered essential tools to ensure patient engagement. Mobile PHR (mPHR) can be a platform to integrate patient-generated health data (PGHD) and patient medical information. Objective: An mPHR developed by a tertiary hospital in South Korea has been used from Dec 2010 to Dec 2015. Patients could manage their own health data through the mPHR. By analyzing five years’ PGHD, we wanted to evaluate how the PGHD were manag

Health Information ManagementHealth Professions
8
Article|0 citations·2026
의미론적 정형-이미지 변환 및 대조 학습을 활용한 경량 침입 탐지
박준영, 강건우, 이호인, 이승은, 박유랑
한국컴퓨터정보학회논문지

사물인터넷의 확산으로 엣지 환경에서의 고성능 침입 탐지 시스템(IDS)의 필요성이 강조됨에 따라, 딥러닝 기반의 IDS 연구가 활발히 진행되고 있다. 그러나 정형 데이터를 딥러닝 모델의 입력으로 직접 사용하는 기존 접근 방식은 네트워크 트래픽에 내재된 복잡한 관계를 포착하는 데 한계가있다. 이에 본 연구는 정형 데이터를 이미지로 변환하여 CNN을 활용하는 3단계 경량 침입 탐지 사전학습 프레임워크를 제안한다. (1) 먼저, SHAP기반의 특징 선택을 통해 침입 탐지에 중요한 특징만을 유지함으로써 데이터를 압축한다. (2) 선별된 데이터는 LVFP 기법을 통해 이미지로 변환된다. 이 기법은 의미론적으로 범주화된 특징 그룹을 RGB 채널에 할당하고 소용돌이 특징 배치를 통해재배열함으로써, 정형 데이터를 CNN에 최적화된 공간적 패턴으로 재구성한다. (3) 이후 경량 CNN 인코더를 구축하여 변환된 이미지에 대해 대조 학습으로 사전학습시킴으로써, 일반화 가능한 특징표현을 구축한다. 다운스

9
Article|0 citations·2026
도메인 증분 학습에서 도메인 불변 표현 학습을 통한 도메인 쉬프트 완화
임민택, 이주현, 김진용, 박유랑
한국컴퓨터정보학회논문지

도메인 점진적 학습 (DIL)에서 모델은 치명적 망각을 완화하여 도메인 이동에 적응해야 한다. 사전 학습 모델 (PTMs)이 널리 사용되나, 기존 전략들은 관찰된 도메인에 편향되어 미관찰 도메인에도메인 쉬프트 문제를 효과적으로 줄이지 못해 표현 표류를 유발한다. 이를 해결하고자, 도메인 불변 및 클래스 변별적 표현을 학습하는 듀얼 인코더 프레임워크를 제안한다. 도메인 특이적 인코더로프로토타입을 추출하고 안정적인 지식을 학습 가능한 도메인 불변 인코더로 증류한다. 프로토타입정렬과 가중치 정규화는 표류를 방지하고 과거 지식을 보존한다. 또한 표현 압축과 GRL을 통해 클래스 내 군집을 조밀하게 형성하고 도메인 불변 학습을 유도한다. 4개 벤치마크 실험 결과, 본 프레임워크는 미관찰 도메인 평균 정확도를 1~6% 향상시켰다. 특히 Office-Home에서 Last 86.32%, Avg 86.25%를 달성했으며, 미관찰 평균 정확도 83.17%, 망각 수치 3.83%를 기록하였다.

Research Areas

Molecular BiologyHealth Information ManagementGeneticsHealth Informatics

Yurang Parkの研究をNubintでさらに深く

この研究室の論文をアプリで開き、AIと共に読み、要約し、引用しましょう。