Yongsuk Kim

Dr. Yongsuk Kim

Department of AI, Konyang University, Daejeon, Republic of Korea
+1
orcid

Research Focus & Metrics

Academic Career Length

37Years (1990-Present)

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

Representative Publications

View All Publications
19 July 2024 in Sensors
Verified
Journal Article
Open access
PDF file
YCYou-Sang Cho
You-Sang Cho
HSHo Jung Song
Ho Jung Song
JHJu-Hyuck Han
Ju-Hyuck Han
Yongsuk KimYongsuk Kim
Yongsuk Kim
This paper presents a classification model for eye diseases utilizing attention mechanisms to learn features from fundus images and structures. The study focuses on diagnosing glaucoma by extracting retinal vessels and the optic disc from fundus images using a ResU-Net-based segmentation model and Hough Circle Transform, respectively. The extracted structures and preprocessed images were inputted into a CNN-based multi-input model for training. Comparative evaluations demonstrated that our model outperformed other research models in classifying glaucoma, even with a smaller dataset. Ablation studies confirmed that using attention mechanisms to learn fundus structures significantly enhanced performance. The study also highlighted the challenges in normal case classification due to potential feature degradation during structure extraction. Future research will focus on incorporating additional fundus structures such as the macula, refining extraction algorithms, and expanding the types of classified eye diseases.

11 February 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YVYuriy Vashpanov
Yuriy Vashpanov
GHGwanghee Heo
Gwanghee Heo
Yongsuk KimYongsuk Kim
Yongsuk Kim
TVTetiana Venkel
Tetiana Venkel
Jung-Young SonJung-Young Son
Jung-Young Son
Hyperspectral images in the spectral wavelength range of 500 nm to 650 nm are used to detect green mold pathogens, which are parasitic on the surface of lemons. The images reveal that the spectral range of 500 nm to 560 nm is appropriate for detecting the early stage of development of the pathogen in the lemon, because the spectral intensity is proportional to the infection degree. Within the range, it was found that the dominant spectral wavelengths of the fresh lemon and the green mold pathogen are 580 nm and 550 nm, respectively, with the 550 nm being the most sensitive in detecting the pathogen with spectral imaging. The spectral intensity ratio of the infected lemon to the fresh one in the spectral range of 500 nm to 560 nm increases with the increasing degree of the infection. Therefore, the ratio can be used to effectively estimate the degree of lemons infecting by the green mold pathogens. It also shows that the sudden decrease of the spectral intensity corresponding to the dominant spectral wavelength of the fresh lemon, together with the neighboring spectral wavelengths can be used to classify fresh and contaminated lemons. The spectral intensity ratio of discriminating the fresh lemon from the infected one is calculated as 1.15.

7 November 2024 in Diagnostics
Verified
Journal Article
Open access
PDF file
HSHo Jung Song
Ho Jung Song
JHJu Hyuck Han
Ju Hyuck Han
SCSung Pil Cho
Sung Pil Cho
SIsungil im
sungil im
Yongsuk KimYongsuk Kim
Yongsuk Kim
JPJong-Uk Park
Jong-Uk Park
Background: In this study, we explored the potential of predicting dysglycemia in patients who need to continuously manage blood glucose levels using a non-invasive method via electrocardiography (ECG). Methods: The data were collected from patients with diabetes, and heart rate variability (HRV) features were extracted via ECG processing. A residual block-based one-dimensional convolution neural network model was used to predict dysglycemia. Results: The dysglycemia prediction results at each time point, including at the time of blood glucose measurement, 15 min prior to measurement, and 30 min prior to measurement, exhibited no significant differences compared with the blood glucose measurement values. This result confirmed that the proposed artificial intelligence model for dysglycemia prediction performed well at each time point. Additionally, to determine the optimal number of features required for predicting dysglycemia, 77 HRV features were individually eliminated in the order of decreasing importance with respect to the prediction accuracy; the optimal number of features for the model to predict dysglycemia was determined to be 12. The dysglycemia prediction results obtained 30 min prior to measurement, which exhibited the highest prediction range in this study, were as follows: accuracy = 90.5, sensitivity = 87.52, specificity = 92.74, and precision = 89.86. Conclusions: Furthermore, we determined that no significant differences exist in the blood glucose prediction results reported in previous studies, wherein various vital signs and blood glucose values were used as model inputs, and the results obtained in this study, wherein only ECG data were used to predict dysglycemia.

28 June 2025 in Sensors
Verified
Journal Article
Open access
PDF file
JHJu Hyuck Han
Ju Hyuck Han
Yongsuk KimYongsuk Kim
Yongsuk Kim
JLJong Bin Lee
Jong Bin Lee
HKHantai Kim
Hantai Kim
JKJong-Yeup Kim
Jong-Yeup Kim
YCYongseok Cho
Yongseok Cho
Motivation: Benign paroxysmal positional vertigo (BPPV) is characterized by torsional nystagmus induced by changes in head position, where accurate quantitative assessment of subtle torsional eye movements is essential for precise diagnosis. Conventional videonystagmography (VNG) techniques face challenges in accurately capturing the rotational components of pupil movements, and existing automated methods typically exhibit limited performance in identifying torsional nystagmus. Methodology: The objective of this study was to develop an automated system capable of accurately and quantitatively detecting torsional nystagmus. We introduce the Torsion Transformer model, designed to directly estimate torsion angles from iris images. This model employs a self-supervised learning framework comprising two main components: a Decoder module, which learns rotational transformations from image data, and a Finder module, which subsequently estimates the torsion angle. The resulting torsion angle data, represented as time-series, are then analyzed using a 1-dimensional convolutional neural network (1D-CNN) classifier to detect the presence of nystagmus. The performance of the proposed method was evaluated using video recordings from 127 patients diagnosed with BPPV. Findings: Our Torsion Transformer model demonstrated robust performance, achieving a sensitivity of 89.99%, specificity of 86.36%, an F1-score of 88.82%, and an area under the receiver operating characteristic curve (AUROC) of 87.93%. These results indicate that the proposed model effectively quantifies torsional nystagmus, with performance levels comparable to established methods for detecting horizontal and vertical nystagmus. Thus, the Torsion Transformer shows considerable promise as a clinical decision support tool in the diagnosis of BPPV. Key Findings: Technical performance improvement in torsional nystagmus detection; System to support clinical decision-making for healthcare professionals.

1 July 1990 in Materials Science and Engineering: A
Verified
Journal Article
Open access
Yongsuk KimYongsuk Kim
Yongsuk Kim
WNW.D. Nix
W.D. Nix

15 January 2006 in Materials Science Forum
Verified
Journal Article
Closed access
PDF file
KPKyung Tae Park
Kyung Tae Park
Chong Soo LeeChong Soo Lee
Chong Soo Lee
Yongsuk KimYongsuk Kim
Yongsuk Kim
DSDonghyuk Shin
Donghyuk Shin
Superplastic behavior of an ultrafine grained (UFG) 5154 Al alloy processed by ECAP and cold rolling (ECAP+CR sample) was investigated and compared with that of the alloy processed by only ECAP without rolling (ECAP sample) in the strain rate range of 10-4~5×10-1 s-1 at 723 K. Processing of the ECAP+CR sample consisted of ECAP of 4 passes, which was less than that showing the optimum microstructure for high strain rate superplasticity of UFG Al alloys (i.e. 8 passes), with route Bc and subsequent cold rolling (70% thickness reduction). The superplastic elongation was remarkably enhanced by post-rolling. An analysis of the mechanical data revealed that deformation of the ECAP+CR sample was dominated by grain boundary sliding, but dislocation viscous glide was the main deformation mechanism for the ECAP sample. In addition, cavitation in the ECAP+CR sample was insignificant up to ∼300% elongation.