경수 오

Mr. 경수 오

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 June 2025 in Expert Systems with Applications
Verified
Journal Article
Open access
DKDohyoung Kim
Dohyoung Kim
경오경수 오
경수 오
YLYoungho Lee
Youngho Lee
HWHyekyung Woo
Hyekyung Woo

29 February 2024
Verified
Book Chapter
Closed access
PDF file
DKDohyoung Kim
Dohyoung Kim
경오경수 오
경수 오
SKSeok-Hwan Kang
Seok-Hwan Kang
YLYoungho Lee
Youngho Lee

29 April 2025 in Electronics
Verified
Journal Article
Open access
PDF file
경오경수 오
경수 오
YLYoungho Lee
Youngho Lee
HWHyekyung Woo
Hyekyung Woo
Text summarization plays a crucial role in processing extensive textual data, particularly in low-resource languages such as Korean. However, abstractive summarization faces persistent challenges, including semantic distortion and inconsistency. This study addresses these limitations by proposing a multi-knowledge-enhanced abstractive summarization model tailored for Korean texts. The model integrates internal knowledge, specifically keywords and topics that are extracted using a context-aware BERT-based approach. Unlike traditional statistical extraction methods, our approach utilizes the semantic context to ensure that the internal knowledge is both diverse and representative. By employing a multi-head attention mechanism, the proposed model effectively integrates multiple types of internal knowledge with the original document embeddings. Experimental evaluations on Korean datasets (news and legal texts) demonstrate that our model significantly outperforms baseline methods, achieving notable improvements in lexical overlap, semantic consistency, and structural coherence, as evidenced by higher ROUGE and BERTScore metrics. Furthermore, the method maintains information consistency across diverse categories, including dates, quantities, and organizational details. These findings highlight the potential of context-aware multi-knowledge integration in enhancing Korean abstractive summarization and suggest promising directions for future research into broader knowledge-incorporation strategies.

21 January 2026 in Digital Health
Verified
Journal Article
Open access
SKSiyeon Ko
Siyeon Ko
경오경수 오
경수 오
UWUhyeong Won
Uhyeong Won
JOJung-A Oh
Jung-A Oh
NKNak-Jung Kwon
Nak-Jung Kwon
HWHyekyung Woo
Hyekyung Woo
Objective: Adolescence is a critical developmental stage during which mental health vulnerabilities often emerge. Traditional self-report methods are insufficient to capture the complexity of emotional and physiological responses, underscoring the need for data-driven, personalized mental health strategies. This study aimed to develop and validate a structured multimodal data collection system for adolescents to support the future advancement of precision mental health care. Methods: This study was conducted as the baseline phase of a longitudinal panel study designed to construct and validate a structured multimodal dataset for adolescent mental health research. A total of 74 adolescents aged 11–15 years from schools and community facilities in Korea was selected through convenience sampling. Multimodal data were collected by integrating six data types: self-reported surveys, electroencephalography (EEG), heart rate variability (HRV), genotyping, microbiome data, and video-based psychological counseling. Data collection was standardized through a three-phase protocol (pre-, on-site, and post-assessment), and participant privacy was protected via pseudonymization based on international standards. Variables were systematically labeled and structured to enable cross-modality analysis. Statistical analyses, including correlation and descriptive statistics, were performed to examine preliminary relationships across modalities. Results: The study successfully constructed a comprehensive dataset encompassing biological and psychosocial indicators from 74 adolescents. Preliminary analysis revealed statistically significant associations between survey-based BMI and both genomic data (ρ = 0.30, p < 0.01) and microbiome-based obesity indicators (ρ = 0.27, p < 0.05), whereas other psychological constructs (e.g., stress, resilience) showed non-significant cross-modal correlations. Conclusions: This study presents a replicable framework for collecting rich, multimodal data from adolescents in real-world settings. By enabling integrative analysis of biological and psychosocial variables, the dataset lays the groundwork for personalized mental health prediction and intervention strategies. Future research should expand longitudinally and optimize context alignment to improve predictive precision and clinical utility.