Changheun Oh

Prof. Changheun Oh

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
12 September 2018
Verified
Book Chapter
Closed access
PDF file
COChangheun Oh
Changheun Oh
DKDongchan Kim
Dongchan Kim
JCJun-Young Chung
Jun-Young Chung
YHYeji Han
Yeji Han
HPHyunWook Park
HyunWook Park

29 April 2026 in Sensors
Verified
Journal Article
Open access
PDF file
YWYu Wu
Yu Wu
COChangheun Oh
Changheun Oh
HNHongshan Nie
Hongshan Nie
Byung-Seo KimByung-Seo Kim
Byung-Seo Kim
Unmanned aerial vehicle (UAV) swarms face significant performance degradation when operating on a single-frequency channel, as the Statistical Priority-based Multiple Access (SPMA) protocol suffers from intensified contention conflicts due to scarce frequency resources. To address this issue, this paper proposes a joint clustering and power optimization method for the SPMA protocol in frequency-constrained scenarios. First, a utility function centered on the end-to-end transmission success rate is constructed, and the optimal clustering scheme selection is formulated as a constrained combinatorial optimization problem. Second, a three-stage heuristic algorithm is designed; all iterations are executed virtually at network initialization. K-means is used to perform initial clustering and determine the minimum power required for intra-cluster services, GPSR is used to establish multi-hop routes for inter-cluster services, and the ant colony algorithm refines the transmission power of forwarding nodes, achieving joint optimization of cluster structure and power configuration. Simulation results show that, compared with the standalone SPMA protocol and the typical clustering algorithm ICW, the proposed algorithm reduces transmission power by 90.4% relative to SPMA (with slightly higher power than ICW) and achieves a comprehensive improvement over both benchmarks. Specifically, the success rate is improved by 63.5% compared with SPMA and 162.3% compared with ICW under high traffic loads, thus achieving a well-balanced compromise between power consumption and transmission reliability. This verifies the feasibility and effectiveness of the proposed optimization method in frequency-constrained scenarios.

26 December 2025 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
COChangheun Oh
Changheun Oh
Long scan times remain a fundamental challenge in Magnetic Resonance Imaging (MRI). Accelerated MRI, which undersamples k-space, requires robust reconstruction methods to solve the ill-posed inverse problem. Recent methods have shown promise by processing image-domain features to capture global spatial context. However, these approaches are often limited, as they fail to fully leverage the unique, sequential characteristics of the k-space data themselves, which are critical for disentangling aliasing artifacts. This study introduces a novel, hybrid, dual-domain deep learning architecture that combines a ViT-based autoencoder with Bidirectional Recurrent Neural Networks (BiRNNs). The proposed architecture is designed to synergistically process information from both domains: it uses the ViT to learn features from image patches and the BiRNNs to model sequential dependencies directly from k-space data. We conducted a comprehensive comparative analysis against a standard ViT with only an MLP head (Model 1), a ViT autoencoder operating solely in the image domain (Model 2), and a competitive UNet baseline. Evaluations were performed on retrospectively undersampled neuro-MRI data using R = 4 and R = 8 acceleration factors with both regular and random sampling patterns. The proposed architecture demonstrated superior performance and robustness, significantly outperforming all other models in challenging high-acceleration and random-sampling scenarios. The results confirm that integrating sequential k-space processing via BiRNNs is critical for superior artifact suppression, offering a robust solution for accelerated MRI.

29 April 2026 in Diagnostics
Verified
Journal Article
Open access
PDF file
CYChang-Soo Yun
Chang-Soo Yun
COChangheun Oh
Changheun Oh
KKKyuseok Kim
Kyuseok Kim
SKSeong-Hyeon Kang
Seong-Hyeon Kang
HKHajin Kim
Hajin Kim
Gun ChoiGun Choi
Gun Choi
Background/Objectives: Most brain magnetic resonance imaging (MRI) is performed in supine position, although posture may influence cerebrovascular signal characteristics through gravity-related physiological changes. However, posture-dependent vascular signal alterations on low-field MRI have not been sufficiently quantified. This study aimed to quantify posture-related internal carotid artery (ICA) signal alterations using low-field MRI by comparing seated and supine images with intensity-, noise-, and texture-based metrics. Methods: Nine healthy adults (20–69 years old; one female) underwent 0.25 T tilting MRI in supine and seated postures. 3D gradient echo T1-weighted images were obtained. The bilateral ICA regions of interest (ROI) and adjacent reference ROI were manually delineated. The signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), signal intensity ratio (SIR), gray-level co-occurrence matrix (GLCM) texture features (contrast, correlation, energy, and homogeneity) were extracted and compared between postures using Wilcoxon signed-rank tests. Results: Seated posture produced significantly higher ICA signal intensity metrics than the supine posture, with increased SNR (median 17.11 vs. 13.48), CNR (median 21.94 vs. 18.36), and SIR (median 10.84 vs. 9.54) (p = 0.004). GLCM texture analysis demonstrated a significant decrease in contrast in the seated position (median 62.01 vs. 145.92; p = 0.004), whereas correlation, energy, and homogeneity showed no significant between-posture differences. Conclusions: Low-field MRI was sensitive to posture-dependent ICA signal alterations. ICA-based metrics may provide quantitative markers of gravity-related cerebrovascular adaptation.