Su-Jin Shin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Su-Jin Shin has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Changmin Shin
Department of Nuclear and Quantum Engineering Korea Advanced Institute of Science and Technology 291 Daehak‐ro Yuseong‐gu Daejeon 34141 Republic of Korea
2 shared publications - Dongho Lee
School of Aerospace Engineering Georgia Institute of Technology Atlanta GA 30332 USA
2 shared publications - Guentae Doh
Satellite Research Directorate Korea Aerospace Research Institute 169‐84 Gwahak‐ro Yuseong‐gu Daejeon 34133 Republic of Korea
2 shared publications - Jaehong Park
Department of Nuclear and Quantum Engineering Korea Advanced Institute of Science and Technology 291 Daehak‐ro Yuseong‐gu Daejeon 34141 Republic of Korea
2 shared publications - Sanghoo Park
Department of Nuclear and Quantum Engineering, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea
2 shared publications - Sungho Kim
Agency for Defense Development, Institute of Defense Advanced Technology Research, Daejeon 34186, Korea
2 shared publications
Latest Publications
- 16 March 2025
- Published by Wiley in Advanced Intelligent Systems
- Vol. 7 (3)
Predicting Performance of Hall Effect Ion Source Using Machine Learning
- 16 March 2025
- Published by Wiley in Advanced Intelligent Systems
- Vol. 7 (3)
Predicting Performance of Hall Effect Ion Source Using Machine Learning
- Open Access
- 25 December 2024
- Published by Wiley in Advanced Intelligent Systems
- Vol. 7 (3)
Predicting Performance of Hall Effect Ion Source Using Machine Learning
Accurate performance prediction methods are essential for the development of high‐efficiency Hall effect ion sources, which are employed in industries ranging from material surface treatment to spacecraft electric propulsion (known as Hall thrusters). Traditional methods rely on simplified scaling laws and computationally intensive numerical simulations. Herein, a robust machine learning model is introduced that uses a neural network ensemble to predict the performance of Hall effect ion sources based on design parameters such as discharge channel dimensions and magnetic field structure. The neural networks are trained using 18 000 data points generated from numerical simulations with input powers ranging from sub‐kW‐ to kW‐class. The accuracy of the developed machine learning model is demonstrated using untrained 700 W‐ and 1 kW‐class Hall effect ion sources, producing results with deviations of less than 10% compared to the experimentally measured thrust and discharge current, thus surpassing the accuracy of conventional scaling laws. As a high‐fidelity surrogate for numerical simulations, the proposed prediction tool provides high prediction accuracy and calculation speed, offering an excellent complement to conventional scaling laws and enhancing the understanding of Hall effect ion source performance characteristics.
- 25 December 2024
- Published by Wiley in Advanced Intelligent Systems
- Vol. 7 (3)
Open AccessPredicting Performance of Hall Effect Ion Source Using Machine Learning
Accurate performance prediction methods are essential for the development of high‐efficiency Hall effect ion sources, which are employed in industries ranging from material surface treatment to spacecraft electric propulsion (known as Hall thrusters). Traditional methods rely on simplified scaling laws and computationally intensive numerical simulations. Herein, a robust machine learning model is introduced that uses a neural network ensemble to predict the performance of Hall effect ion sources based on design parameters such as discharge channel dimensions and magnetic field structure. The neural networks are trained using 18 000 data points generated from numerical simulations with input powers ranging from sub‐kW‐ to kW‐class. The accuracy of the developed machine learning model is demonstrated using untrained 700 W‐ and 1 kW‐class Hall effect ion sources, producing results with deviations of less than 10% compared to the experimentally measured thrust and discharge current, thus surpassing the accuracy of conventional scaling laws. As a high‐fidelity surrogate for numerical simulations, the proposed prediction tool provides high prediction accuracy and calculation speed, offering an excellent complement to conventional scaling laws and enhancing the understanding of Hall effect ion source performance characteristics.
- Open Access
- 16 June 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (12) , 5569
Coupling Denoising to Detection for SAR Imagery
Detecting objects in synthetic aperture radar (SAR) imagery has received much attention in recent years since SAR can operate in all-weather and day-and-night conditions. Due to the prosperity and development of convolutional neural networks (CNNs), many previous methodologies have been proposed for SAR object detection. In spite of the advance, existing detection networks still have limitations in boosting detection performance because of inherently noisy characteristics in SAR imagery; hence, separate preprocessing step such as denoising (despeckling) is required before utilizing the SAR images for deep learning. However, inappropriate denoising techniques might cause detailed information loss and even proper denoising methods does not always guarantee performance improvement. In this paper, we therefore propose a novel object detection framework that combines unsupervised denoising network into traditional two-stage detection network and leverages a strategy for fusing region proposals extracted from both raw SAR image and synthetically denoised SAR image. Extensive experiments validate the effectiveness of our framework on our own object detection datasets constructed with remote sensing images from TerraSAR-X and COSMO-SkyMed satellites. Extensive experiments validate the effectiveness of our framework on our own object detection datasets constructed with remote sensing images from TerraSAR-X and COSMO-SkyMed satellites. The proposed framework shows better performances when we compared the model with using only noisy SAR images and only denoised SAR images after despeckling under multiple backbone networks.
- 16 June 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (12) , 5569
Open AccessCoupling Denoising to Detection for SAR Imagery
Detecting objects in synthetic aperture radar (SAR) imagery has received much attention in recent years since SAR can operate in all-weather and day-and-night conditions. Due to the prosperity and development of convolutional neural networks (CNNs), many previous methodologies have been proposed for SAR object detection. In spite of the advance, existing detection networks still have limitations in boosting detection performance because of inherently noisy characteristics in SAR imagery; hence, separate preprocessing step such as denoising (despeckling) is required before utilizing the SAR images for deep learning. However, inappropriate denoising techniques might cause detailed information loss and even proper denoising methods does not always guarantee performance improvement. In this paper, we therefore propose a novel object detection framework that combines unsupervised denoising network into traditional two-stage detection network and leverages a strategy for fusing region proposals extracted from both raw SAR image and synthetically denoised SAR image. Extensive experiments validate the effectiveness of our framework on our own object detection datasets constructed with remote sensing images from TerraSAR-X and COSMO-SkyMed satellites. Extensive experiments validate the effectiveness of our framework on our own object detection datasets constructed with remote sensing images from TerraSAR-X and COSMO-SkyMed satellites. The proposed framework shows better performances when we compared the model with using only noisy SAR images and only denoised SAR images after despeckling under multiple backbone networks.
- Open Access
- 24 August 2020
- Published by MDPI AG in Remote Sensing
- Vol. 12 (17) , 2734
Hierarchical Multi-Label Object Detection Framework for Remote Sensing Images
Detecting objects such as aircraft and ships is a fundamental research area in remote sensing analytics. Owing to the prosperity and development of CNNs, many previous methodologies have been proposed for object detection within remote sensing images. Despite the advance, using the object detection datasets with a more complex structure, i.e., datasets with hierarchically multi-labeled objects, is limited to the existing detection models. Especially in remote sensing images, since objects are obtained from bird’s-eye view, the objects are captured with restricted visual features and not always guaranteed to be labeled up to fine categories. We propose a hierarchical multi-label object detection framework applicable to hierarchically partial-annotated datasets. In the framework, an object detection pipeline called Decoupled Hierarchical Classification Refinement (DHCR) fuses the results of two networks: (1) an object detection network with multiple classifiers, and (2) a hierarchical sibling classification network for supporting hierarchical multi-label classification. Our framework additionally introduces a region proposal method for efficient detection on vain areas of the remote sensing images, called clustering-guided cropping strategy. Thorough experiments validate the effectiveness of our framework on our own object detection datasets constructed with remote sensing images from WorldView-3 and SkySat satellites. Under our proposed framework, DHCR-based detections significantly improve the performance of respective baseline models and we achieve state-of-the-art results on the datasets.
- 24 August 2020
- Published by MDPI AG in Remote Sensing
- Vol. 12 (17) , 2734
Open AccessHierarchical Multi-Label Object Detection Framework for Remote Sensing Images
Detecting objects such as aircraft and ships is a fundamental research area in remote sensing analytics. Owing to the prosperity and development of CNNs, many previous methodologies have been proposed for object detection within remote sensing images. Despite the advance, using the object detection datasets with a more complex structure, i.e., datasets with hierarchically multi-labeled objects, is limited to the existing detection models. Especially in remote sensing images, since objects are obtained from bird’s-eye view, the objects are captured with restricted visual features and not always guaranteed to be labeled up to fine categories. We propose a hierarchical multi-label object detection framework applicable to hierarchically partial-annotated datasets. In the framework, an object detection pipeline called Decoupled Hierarchical Classification Refinement (DHCR) fuses the results of two networks: (1) an object detection network with multiple classifiers, and (2) a hierarchical sibling classification network for supporting hierarchical multi-label classification. Our framework additionally introduces a region proposal method for efficient detection on vain areas of the remote sensing images, called clustering-guided cropping strategy. Thorough experiments validate the effectiveness of our framework on our own object detection datasets constructed with remote sensing images from WorldView-3 and SkySat satellites. Under our proposed framework, DHCR-based detections significantly improve the performance of respective baseline models and we achieve state-of-the-art results on the datasets.
- 1 August 2018
- Published by Elsevier in Pattern Recognition Letters
- Vol. 111, 94-100
Hierarchical prescription pattern analysis with symptom labels
- 1 August 2018
- Published by Elsevier in Pattern Recognition Letters
- Vol. 111, 94-100
Hierarchical prescription pattern analysis with symptom labels