Jaeoh Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jaeoh Kim has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- Seongil Jo
Department of Statistics, Inha University, Incheon, South Korea
5 shared publications Seongil Jo
4 shared publications- Donghyeon Yu
Department of Statistics, Inha University, Incheon, Korea
3 shared publications Ji Hyun Nam
Department of Statistics and Data Science Inha University Incheon Republic of Korea
3 shared publications- Minseong Kim3 shared publications
Doowon Choi
2 shared publications
Latest Publications
- Open Access
- 5 August 2026
- Published by Wiley in Journal of Chemometrics
- Vol. 40 (8)
Reliable Identification and Out‐of‐Library Detection in Mass Spectra
Accurate molecular identification from mass spectra is essential in analytical workflows, yet conventional library search typically returns the closest match even when the true compound is absent, leading to overconfident false positives. We propose a probabilistic framework that supports both reliable identification of compounds represented in a reference library and model‐based flagging of spectra that may not be adequately represented in the reference library. Spectra are modeled within a Bayesian nonparametric method that does not predefine the number of clusters; instead, the model can allocate new clusters when incoming spectra are insufficiently explained by existing references. This property provides a statistical mechanism for flagging potentially unseen compounds while maintaining coherent grouping of known ones. Experiments on large‐scale electron ionization libraries demonstrate stable performance under diverse noise conditions, consistent grouping of replicate spectra, and the tendency of spectra absent from the reference database to form new clusters. The framework supports reliable identification while reducing forced matches for spectra that are poorly represented in the reference data.
- 5 August 2026
- Published by Wiley in Journal of Chemometrics
- Vol. 40 (8)
Open AccessReliable Identification and Out‐of‐Library Detection in Mass Spectra
Accurate molecular identification from mass spectra is essential in analytical workflows, yet conventional library search typically returns the closest match even when the true compound is absent, leading to overconfident false positives. We propose a probabilistic framework that supports both reliable identification of compounds represented in a reference library and model‐based flagging of spectra that may not be adequately represented in the reference library. Spectra are modeled within a Bayesian nonparametric method that does not predefine the number of clusters; instead, the model can allocate new clusters when incoming spectra are insufficiently explained by existing references. This property provides a statistical mechanism for flagging potentially unseen compounds while maintaining coherent grouping of known ones. Experiments on large‐scale electron ionization libraries demonstrate stable performance under diverse noise conditions, consistent grouping of replicate spectra, and the tendency of spectra absent from the reference database to form new clusters. The framework supports reliable identification while reducing forced matches for spectra that are poorly represented in the reference data.
- 30 July 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 203
Class-aware topology-guided graph attention for large-scale skeleton-based firefighter action recognition
- 30 July 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 203
Class-aware topology-guided graph attention for large-scale skeleton-based firefighter action recognition
- Open Access
- 28 May 2026
- Published by Elsevier in SSRN Electronic Journal
PDA-Based Interphase Engineering with CNT/GO Hybrid Nanofillers for Balanced Aramid/Epoxy Composites
Balancing interfacial shear transfer and damage-tolerant energy dissipation remains a key challenge in high-performance aramid/epoxy composites. In this study, a multiscale interphase engineering strategy was developed by combining polydopamine (PDA)- or polydopamine/poly(ethyleneimine) (PDA–PEI)-modified aramid fibers with carbon nanotube/graphene oxide hybrid fillers in an epoxy matrix. Surface characterization, impact testing, interlaminar shear evaluation, dynamic mechanical analysis, and fracture observations were employed to elucidate how the interphase chemistry and hybrid filler architecture govern the load transfer and failure behavior. The incorporation of hybrid fillers into the neat epoxy matrix alone resulted in a limited performance improvement, whereas their integration within the fiber/interphase architecture led to significantly enhanced composite properties. The PDA-based hybrid system exhibited the most balanced combination of impact resistance, viscoelastic stiffness, and fracture energy dissipation, indicating the formation of an optimized interphase that enabled both efficient load transfer and controlled energy dissipation. In contrast, the PDA–PEI-based interphase exhibited reduced interlaminar shear strength and impact performance despite the increased density of the interfacial functional groups, suggesting the formation of a relatively dense and constrained interphase that limited effective stress transfer and damage tolerance. These results demonstrate that the composite performance is governed by not only increasing interfacial functionalization but also controlling the interplay among interfacial rigidity, molecular mobility, and damage evolution. This study provides a practical interphase design strategy for tailoring the balance between the impact resistance and shear performance in advanced aramid/epoxy composites.
- 28 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessPDA-Based Interphase Engineering with CNT/GO Hybrid Nanofillers for Balanced Aramid/Epoxy Composites
Balancing interfacial shear transfer and damage-tolerant energy dissipation remains a key challenge in high-performance aramid/epoxy composites. In this study, a multiscale interphase engineering strategy was developed by combining polydopamine (PDA)- or polydopamine/poly(ethyleneimine) (PDA–PEI)-modified aramid fibers with carbon nanotube/graphene oxide hybrid fillers in an epoxy matrix. Surface characterization, impact testing, interlaminar shear evaluation, dynamic mechanical analysis, and fracture observations were employed to elucidate how the interphase chemistry and hybrid filler architecture govern the load transfer and failure behavior. The incorporation of hybrid fillers into the neat epoxy matrix alone resulted in a limited performance improvement, whereas their integration within the fiber/interphase architecture led to significantly enhanced composite properties. The PDA-based hybrid system exhibited the most balanced combination of impact resistance, viscoelastic stiffness, and fracture energy dissipation, indicating the formation of an optimized interphase that enabled both efficient load transfer and controlled energy dissipation. In contrast, the PDA–PEI-based interphase exhibited reduced interlaminar shear strength and impact performance despite the increased density of the interfacial functional groups, suggesting the formation of a relatively dense and constrained interphase that limited effective stress transfer and damage tolerance. These results demonstrate that the composite performance is governed by not only increasing interfacial functionalization but also controlling the interplay among interfacial rigidity, molecular mobility, and damage evolution. This study provides a practical interphase design strategy for tailoring the balance between the impact resistance and shear performance in advanced aramid/epoxy composites.
- Open Access
- 12 March 2026
- Published by Elsevier in SSRN Electronic Journal
Class-Aware Topology-Guided Graph Attention for Large-Scale Skeleton-Based Firefighter Action Recognition
State-of-the-art graph-based action recognition frameworks, such as Spatio-Temporal Graph Convolutional Networks (ST-GCN) and Two-Stream Adaptive Graph Convolutional Networks (2s-AGCN), have advanced skeleton-based spatio-temporal modeling by learning dynamic joint-wise dependencies across frames. Nevertheless, when applied to the high-variability firefighter behavior analysis---where complex tool-body interactions and subtle intent-driven motions coexist---these models often struggle with fine-grained separability across large action classes. To address this, we propose Class-Aware Topology-Guided Graph Convolutional Network (CATS-GCN). The novelty of our approach lies in a principled framework by integrating (i) anatomical topology constraints, (ii) class-prototype guided attention, and (iii) multi-head sparsity-diversity regularization into a unified learning objective. We evaluated the proposed framework on a large-scale firefighter action dataset comprising 341 fundamental and drill-specific actions. Experimental results demonstrate that CATS-GCN outperforms GCN-based baselines, achieving the highest classification accuracy. Beyond recognition performance, owing to its modular structure and interpretable attention patterns, our framework offers practical utility for automated training systems by facilitating correct posture maintenance, injury risk reduction, and enhanced operational readiness.
- 12 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessClass-Aware Topology-Guided Graph Attention for Large-Scale Skeleton-Based Firefighter Action Recognition
State-of-the-art graph-based action recognition frameworks, such as Spatio-Temporal Graph Convolutional Networks (ST-GCN) and Two-Stream Adaptive Graph Convolutional Networks (2s-AGCN), have advanced skeleton-based spatio-temporal modeling by learning dynamic joint-wise dependencies across frames. Nevertheless, when applied to the high-variability firefighter behavior analysis---where complex tool-body interactions and subtle intent-driven motions coexist---these models often struggle with fine-grained separability across large action classes. To address this, we propose Class-Aware Topology-Guided Graph Convolutional Network (CATS-GCN). The novelty of our approach lies in a principled framework by integrating (i) anatomical topology constraints, (ii) class-prototype guided attention, and (iii) multi-head sparsity-diversity regularization into a unified learning objective. We evaluated the proposed framework on a large-scale firefighter action dataset comprising 341 fundamental and drill-specific actions. Experimental results demonstrate that CATS-GCN outperforms GCN-based baselines, achieving the highest classification accuracy. Beyond recognition performance, owing to its modular structure and interpretable attention patterns, our framework offers practical utility for automated training systems by facilitating correct posture maintenance, injury risk reduction, and enhanced operational readiness.
- 2 March 2026
- Published by Springer Nature in Machine Vision and Applications
- Vol. 37 (3) , 42
Enhancing object detection algorithm for size-insensitive performance
- 2 March 2026
- Published by Springer Nature in Machine Vision and Applications
- Vol. 37 (3) , 42
Enhancing object detection algorithm for size-insensitive performance
- 4 February 2026
- Published by Elsevier in Neurocomputing
- Vol. 681
Frequency-aware priors for variational autoencoders under class imbalance
- 4 February 2026
- Published by Elsevier in Neurocomputing
- Vol. 681
Frequency-aware priors for variational autoencoders under class imbalance
- Open Access
- 11 January 2026
- Published by Springer Nature in Journal of Cheminformatics
- Vol. 18 (1)
Multimodal graph fusion with statistically guided parsimonious descriptor selection for molecular property prediction
Graph convolutional networks (GCN) are effective for learning molecular representations, but their reliance on local message passing and simple feature con
- 11 January 2026
- Published by Springer Nature in Journal of Cheminformatics
- Vol. 18 (1)
Open AccessMultimodal graph fusion with statistically guided parsimonious descriptor selection for molecular property prediction
Graph convolutional networks (GCN) are effective for learning molecular representations, but their reliance on local message passing and simple feature con
- Open Access
- 22 September 2025
- Published by Springer Nature in Research Square
Enhancing Object Detection Algorithm for Size-Insensitive Performance
Detecting tiny objects remains a challenge in computer vision, particularly in aerial imagery, due to limited resolution and scale variation. Conventional Intersection-over-Union (IoU)-based loss functions often lead to scale-sensitive optimization, degrading detection consistency across object sizes. Normalized Wasserstein Distance for Small Object Detection (NW-SOD) has addressed scale sensitivity, but still faces limitations in capturing the full distributional characteristics for robust multi-scale detection. This study proposes Bhattacharyya-distance-based Multi-scale Object Detection (B-MOD), a loss function that achieves balanced detection performance across varying object scales without modifying the network architecture. B-MOD utilizes the Bhattacharyya distance to measure distributional similarity between predicted and ground truth bounding boxes, enabling more accurate regression and confidence estimation. Comparative evaluations conducted on the DOTA dataset show that B-MOD demonstrates better performance than existing distribution-aware methods across diverse object scales. Results show improvements over both IoU-based metrics and NW-SOD across different object scales, with gains observed in small object detection accuracy. These findings indicate that distributional similarity-based loss functions can improve multi-scale object detection performance.
- 22 September 2025
- Published by Springer Nature in Research Square
Open AccessEnhancing Object Detection Algorithm for Size-Insensitive Performance
Detecting tiny objects remains a challenge in computer vision, particularly in aerial imagery, due to limited resolution and scale variation. Conventional Intersection-over-Union (IoU)-based loss functions often lead to scale-sensitive optimization, degrading detection consistency across object sizes. Normalized Wasserstein Distance for Small Object Detection (NW-SOD) has addressed scale sensitivity, but still faces limitations in capturing the full distributional characteristics for robust multi-scale detection. This study proposes Bhattacharyya-distance-based Multi-scale Object Detection (B-MOD), a loss function that achieves balanced detection performance across varying object scales without modifying the network architecture. B-MOD utilizes the Bhattacharyya distance to measure distributional similarity between predicted and ground truth bounding boxes, enabling more accurate regression and confidence estimation. Comparative evaluations conducted on the DOTA dataset show that B-MOD demonstrates better performance than existing distribution-aware methods across diverse object scales. Results show improvements over both IoU-based metrics and NW-SOD across different object scales, with gains observed in small object detection accuracy. These findings indicate that distributional similarity-based loss functions can improve multi-scale object detection performance.
- Open Access
- 10 February 2025
- Published by Wiley in Journal of Chemometrics
- Vol. 39 (2) , 1-19
Improving Vapor Pressure Prediction Through Integration of Multiple Molecular Representations: A Super Learner Approach
Accurate prediction of vapor pressure is essential in chemical engineering, environmental science, and pharmaceutical development, impacting the volatility and stability of compounds. Traditional methods often fall short for complex and new molecular structures. This study introduces an advanced machine learning approach, integrating graph neural networks (GNNs), and CHEM‐BERT models to improve prediction accuracy. Utilizing the largest dataset to date, we derived comprehensive chemical descriptors and fingerprints. We evaluated 19 predictive models, including ridge regression, random forest, support vector regression, and feed‐forward neural networks, trained on diverse features like PaDEL and Morgan fingerprints, chemical descriptors, and Chem‐BERT embeddings. Central to our methodology is the super learner architecture, which combines 19 multiple models to enhance accuracy. The super learner achieved a root mean squared error (RMSE) of 0.8200, outperforming individual models and previous reports. These successful results highlight the effectiveness of integrating GNNs and Chem‐BERT for capturing detailed molecular information, setting a new benchmark for vapor pressure prediction. This study underscores the value of advanced machine learning techniques and comprehensive datasets, offering a robust tool for researchers and paving the way for future advancements in chemical property prediction.
- 10 February 2025
- Published by Wiley in Journal of Chemometrics
- Vol. 39 (2) , 1-19
Open AccessImproving Vapor Pressure Prediction Through Integration of Multiple Molecular Representations: A Super Learner Approach
Accurate prediction of vapor pressure is essential in chemical engineering, environmental science, and pharmaceutical development, impacting the volatility and stability of compounds. Traditional methods often fall short for complex and new molecular structures. This study introduces an advanced machine learning approach, integrating graph neural networks (GNNs), and CHEM‐BERT models to improve prediction accuracy. Utilizing the largest dataset to date, we derived comprehensive chemical descriptors and fingerprints. We evaluated 19 predictive models, including ridge regression, random forest, support vector regression, and feed‐forward neural networks, trained on diverse features like PaDEL and Morgan fingerprints, chemical descriptors, and Chem‐BERT embeddings. Central to our methodology is the super learner architecture, which combines 19 multiple models to enhance accuracy. The super learner achieved a root mean squared error (RMSE) of 0.8200, outperforming individual models and previous reports. These successful results highlight the effectiveness of integrating GNNs and Chem‐BERT for capturing detailed molecular information, setting a new benchmark for vapor pressure prediction. This study underscores the value of advanced machine learning techniques and comprehensive datasets, offering a robust tool for researchers and paving the way for future advancements in chemical property prediction.
- Open Access
- 26 November 2024
- Published by Elsevier in NeuroImage
- Vol. 304, 120956
Sex differences in autism spectrum disorder using class imbalance adjusted functional connectivity
- 26 November 2024
- Published by Elsevier in NeuroImage
- Vol. 304, 120956
Open AccessSex differences in autism spectrum disorder using class imbalance adjusted functional connectivity