Jeongsam Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jeongsam Yang has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
Jinwon Lee
Department of Industrial and Management Engineering, Gangneung-Wonju National University, Wonju, Republic of Korea
5 shared publicationsSang-Uk Cheon
5 shared publications- In-Ho Song
Carnegie Mellon University
3 shared publications - Duhwan Mun
School of Mechanical Engineering, Korea University, Seoul, Republic of Korea
2 shared publications Gun-Yeol Na
Center for Artificial Intelligence, Korea Institute of Science and Technology, Seoul, Republic of Korea
2 shared publicationsJeongho Han
Optimus System Co. Ltd., Yongin-si, Gyeonggi-do, Korea
2 shared publications
Latest Publications
- 9 February 2026
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 40 (2) , 1393-1402
Alarm sequence pattern analysis techniques for alarm prediction in automated manufacturing processes
- 9 February 2026
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 40 (2) , 1393-1402
Alarm sequence pattern analysis techniques for alarm prediction in automated manufacturing processes
- 5 October 2024
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 38 (10) , 5617-5625
Graph-structured data generation and analysis for anomaly detection in an automated manufacturing process
- 5 October 2024
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 38 (10) , 5617-5625
Graph-structured data generation and analysis for anomaly detection in an automated manufacturing process
- 30 September 2023
- Published by Society for Computational Design and Engineering in Korean Journal of Computational Design and Engineering
- Vol. 28 (3) , 260-272
B-Rep Shape Simplification for Data Conversion between Ship CAD Model and VR Mesh Model
Shipbuilders and suppliers, through their engineering activities, generate an extensive array of shape data for ship structures. However, visualizing the entire shape of a ship on a computer for design optimization or digital evaluation poses a practical challenge. Additionally, it becomes necessary to simplify the boundary representation (B-Rep) shape during data exchange between partners using different computer-aided design (CAD) systems and when creating lightweight shape contents for digital twin implementation. In this paper, we propose a shape simplification method for converting shapes between ship CAD model and virtual reality (VR) mesh model. During the process of reconstructing the ship CAD model into a B-Rep shape, topology decimation is performed to remove unnecessary elements. Furthermore, bounding boxes are created for the sub-primitives of the reconstructed B-Rep shape, and the level of detail for shape simplification is determined by calculating threshold values for these boxes. Sub-primitives with the applied level of detail can be dynamically removed from the assembly model. By utilizing this method, our shape simplification system, ShipCADOptimizer, allows users to review model simplification results in real-time through its simplification functionality. Users can simplify the model while preserving its characteristics by setting appropriate weights and thresholds based on the intended use.
- 30 September 2023
- Published by Society for Computational Design and Engineering in Korean Journal of Computational Design and Engineering
- Vol. 28 (3) , 260-272
B-Rep Shape Simplification for Data Conversion between Ship CAD Model and VR Mesh Model
Shipbuilders and suppliers, through their engineering activities, generate an extensive array of shape data for ship structures. However, visualizing the entire shape of a ship on a computer for design optimization or digital evaluation poses a practical challenge. Additionally, it becomes necessary to simplify the boundary representation (B-Rep) shape during data exchange between partners using different computer-aided design (CAD) systems and when creating lightweight shape contents for digital twin implementation. In this paper, we propose a shape simplification method for converting shapes between ship CAD model and virtual reality (VR) mesh model. During the process of reconstructing the ship CAD model into a B-Rep shape, topology decimation is performed to remove unnecessary elements. Furthermore, bounding boxes are created for the sub-primitives of the reconstructed B-Rep shape, and the level of detail for shape simplification is determined by calculating threshold values for these boxes. Sub-primitives with the applied level of detail can be dynamically removed from the assembly model. By utilizing this method, our shape simplification system, ShipCADOptimizer, allows users to review model simplification results in real-time through its simplification functionality. Users can simplify the model while preserving its characteristics by setting appropriate weights and thresholds based on the intended use.
- 26 August 2023
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 35 (7) , 3169-3184
Two-dimensional polygon classification and pairwise clustering for pairing in ship parts nesting
- 26 August 2023
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 35 (7) , 3169-3184
Two-dimensional polygon classification and pairwise clustering for pairing in ship parts nesting
- Open Access
- 20 July 2023
- Published by Springer Nature in Scientific Reports
- Vol. 13 (1) , 1-12
Multi-class semantic segmentation of breast tissues from MRI images using U-Net based on Haar wavelet pooling
MRI images used in breast cancer diagnosis are taken in a lying position and therefore are inappropriate for reconstructing the natural breast shape in a standing position. Some studies have proposed methods to present the breast shape in a standing position using an ordinary differential equation of the finite element method. However, it is difficult to obtain meaningful results because breast tissues have different elastic moduli. This study proposed a multi-class semantic segmentation method for breast tissues to reconstruct breast shapes using U-Net based on Haar wavelet pooling. First, a dataset was constructed by labeling the skin, fat, and fibro-glandular tissues and the background from MRI images taken in a lying position. Next, multi-class semantic segmentation was performed using U-Net based on Haar wavelet pooling to improve the segmentation accuracy for breast tissues. The U-Net effectively extracted breast tissue features while reducing image information loss in a subsampling stage using multiple sub-bands. In addition, the proposed network is robust to overfitting. The proposed network showed a mIOU of 87.48 for segmenting breast tissues. The proposed networks demonstrated high-accuracy segmentation for breast tissue with different elastic moduli to reconstruct the natural breast shape.
- 20 July 2023
- Published by Springer Nature in Scientific Reports
- Vol. 13 (1) , 1-12
Open AccessMulti-class semantic segmentation of breast tissues from MRI images using U-Net based on Haar wavelet pooling
MRI images used in breast cancer diagnosis are taken in a lying position and therefore are inappropriate for reconstructing the natural breast shape in a standing position. Some studies have proposed methods to present the breast shape in a standing position using an ordinary differential equation of the finite element method. However, it is difficult to obtain meaningful results because breast tissues have different elastic moduli. This study proposed a multi-class semantic segmentation method for breast tissues to reconstruct breast shapes using U-Net based on Haar wavelet pooling. First, a dataset was constructed by labeling the skin, fat, and fibro-glandular tissues and the background from MRI images taken in a lying position. Next, multi-class semantic segmentation was performed using U-Net based on Haar wavelet pooling to improve the segmentation accuracy for breast tissues. The U-Net effectively extracted breast tissue features while reducing image information loss in a subsampling stage using multiple sub-bands. In addition, the proposed network is robust to overfitting. The proposed network showed a mIOU of 87.48 for segmenting breast tissues. The proposed networks demonstrated high-accuracy segmentation for breast tissue with different elastic moduli to reconstruct the natural breast shape.
- Open Access
- 18 January 2023
- Published by Springer Nature in Research Square
Multi-class semantic segmentation of breast tissues from MRI images using U-Net based on Haar wavelet pooling
MRI images for breast cancer diagnosis are inappropriate for reconstructing the natural breast shape in a standing position because they are taken in a lying position. Some studies have proposed methods to present the breast shape in a standing position using ordinary differential equation of the finite element method. However, it is difficult to obtain meaningful results because breast tissues have different elastic moduli. This study proposed a multi-class semantic segmentation method for breast tissues to reconstruct breast shape using U-Net based on Haar wavelet pooling. First, a dataset was constructed by labeling the skin, fat, and fibro-glandular tissues and the background from MRI images taken in a lying position. Next, multi-class semantic segmentation was performed using U-Net based on Haar wavelet pooling to improve the segmentation accuracy for breast tissues. The U-Net based on Haar wavelet pooling effectively extracted breast tissue features while reducing information loss of the image in a subsampling stage using multiple sub-bands. In addition, the proposed network is robust to overfitting. The proposed network showed an mIOU of 87.48 for segmenting breast tissues. The proposed networks showed high-accuracy segmentation for breast tissue with different elastic moduli to reconstruct the natural breast shape.
- 18 January 2023
- Published by Springer Nature in Research Square
Open AccessMulti-class semantic segmentation of breast tissues from MRI images using U-Net based on Haar wavelet pooling
MRI images for breast cancer diagnosis are inappropriate for reconstructing the natural breast shape in a standing position because they are taken in a lying position. Some studies have proposed methods to present the breast shape in a standing position using ordinary differential equation of the finite element method. However, it is difficult to obtain meaningful results because breast tissues have different elastic moduli. This study proposed a multi-class semantic segmentation method for breast tissues to reconstruct breast shape using U-Net based on Haar wavelet pooling. First, a dataset was constructed by labeling the skin, fat, and fibro-glandular tissues and the background from MRI images taken in a lying position. Next, multi-class semantic segmentation was performed using U-Net based on Haar wavelet pooling to improve the segmentation accuracy for breast tissues. The U-Net based on Haar wavelet pooling effectively extracted breast tissue features while reducing information loss of the image in a subsampling stage using multiple sub-bands. In addition, the proposed network is robust to overfitting. The proposed network showed an mIOU of 87.48 for segmenting breast tissues. The proposed networks showed high-accuracy segmentation for breast tissue with different elastic moduli to reconstruct the natural breast shape.
- 8 July 2022
- Published by Elsevier in Computers in Industry
- Vol. 142
Machine learning iterative filtering algorithm for field defect detection in the process stage
- 8 July 2022
- Published by Elsevier in Computers in Industry
- Vol. 142
Machine learning iterative filtering algorithm for field defect detection in the process stage
- 28 May 2022
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 36 (6) , 3109-3117
Development of a robot OLP system for the continuous motion control of a mandrel in the radial braiding process
- 28 May 2022
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 36 (6) , 3109-3117
Development of a robot OLP system for the continuous motion control of a mandrel in the radial braiding process
- 1 April 2021
- Published by Elsevier in Pattern Recognition
- Vol. 112
Connectivity-based convolutional neural network for classifying point clouds
- 1 April 2021
- Published by Elsevier in Pattern Recognition
- Vol. 112
Connectivity-based convolutional neural network for classifying point clouds
- 2 July 2019
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 33 (7) , 3445-3455
Development of a feature-recognition and measurement path generation system based on NURBS surfaces for 5-axis on-machine measurement
- 2 July 2019
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 33 (7) , 3445-3455
Development of a feature-recognition and measurement path generation system based on NURBS surfaces for 5-axis on-machine measurement