Sieun Kim

Ms. Sieun Kim


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
16 January 2026 in Electronics
Verified
Journal Article
Open access
PDF file
SJSihwa Jin
Sihwa Jin
DPDo Yeon Park
Do Yeon Park
SKSieun Kim
Sieun Kim
JLJinho Lee
Jinho Lee
IJInwhee Joe
Inwhee Joe
This study proposes a reinforcement learning-based link selection method for Low Earth Orbit satellite networks, aiming to reduce handover frequency while extending link duration under highly dynamic orbital environments. The proposed approach relies solely on basic satellite positional information, namely latitude, longitude, and altitude, to construct compact state representations without requiring complex sensing or prediction mechanisms. Using relative satellite and terminal geometry, each state is represented as a vector consisting of azimuth, elevation, range, and direction difference. To validate the feasibility of policy learning under realistic conditions, a total of 871,105 orbit based data samples were generated through simulations of 300 LEO satellite orbits. The reinforcement learning environment was implemented using the OpenAI Gym framework, in which an agent selects an optimal communication target from a prefiltered set of candidate satellites at each time step. Three reinforcement learning algorithms, namely SARSA, Q-Learning, and Deep Q-Network, were evaluated under identical experimental conditions. Performance was assessed in terms of smoothed total reward per episode, average handover count, and average link duration. The results show that the Deep Q-Network-based approach achieves approximately 77.4% fewer handovers than SARSA and 49.9% fewer than Q-Learning, while providing the longest average link duration. These findings demonstrate that effective handover control can be achieved using lightweight state information and indicate the potential of deep reinforcement learning for future LEO satellite communication systems.

29 August 2025
Verified
Book Chapter
Closed access
PDF file
ZWZhan Wang
Zhan Wang
JLJongwon Lee
Jongwon Lee
SKSieun Kim
Sieun Kim
IJInwhee Joe
Inwhee Joe
SKSieun Kim
Sieun Kim
DSDongyeop Sung
Dongyeop Sung


16 March 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
PYPark Yougyung
Park Yougyung
SKSieun Kim
Sieun Kim
IJInwhee Joe
Inwhee Joe
As artificial intelligence (AI) systems are increasingly deployed in real-world applications, concerns regarding the unauthorized use of copyrighted images during model training have become more pronounced. In particular, both generative and discriminative models may implicitly internalize distinctive visual patterns from copyrighted data, leading to potential ethical and legal risks even after data removal. In this study, we propose a practical copyright protection framework, termed the Predictable-Image Solution (PIS), which aims to disrupt the learning of copyrighted visual features during the training process. PIS leverages Layer-wise Relevance Propagation (LRP) to identify image regions that contribute positively to a model’s prediction and selectively modifies these regions using non-copyrighted visual substitutes, such as textures or benign image patterns. By targeting semantically influential regions rather than applying global perturbations, the proposed approach effectively interferes with feature extraction while preserving the perceptual quality and overall visual structure of the original image. Extensive experiments conducted on multiple pre-trained image classification models demonstrate that PIS consistently degrades classification performance on protected images, while maintaining high visual similarity as measured by perceptual metrics. These results indicate that PIS offers an effective, model-agnostic, and visually unobtrusive solution for mitigating unauthorized exploitation of copyrighted images in practical AI training scenarios.

1 April 2026 in IEEE Access
Verified
Journal Article
Open access
SKSieun Kim
Sieun Kim
IJInwhee Joe
Inwhee Joe
Explainable artificial intelligence (XAI) remains underexplored in quantum machine learning (QML) due to limited quantum computational resources and the lack of practical interpretability techniques. In this study, we implement the Local Interpretable Model-Agnostic Explanations (LIME) algorithm within the CUDA-Q framework and propose an interpretable QML analysis method using GPU-accelerated quantum simulation. All experiments are conducted on a GPU-based simulator rather than real quantum hardware, enabling stable large-scale sampling required by LIME and ensuring reproducible results. We design a binary classification model based on a single-qubit variational circuit composed of parameterized RY and RX rotations, and the model is trained with gradient-based optimization. The performance is evaluated on the MNIST, KMNIST, Fashion-MNIST, and CIFAR-10 datasets using training and test accuracy as metrics. By applying LIME, the classification outcomes of the quantum model are visualized and interpreted in a human-understandable form, demonstrating that meaningful interpretability can be achieved even under limited qubit counts and constrained computational environments. Furthermore, we analyze the trade-off between simulator performance and model accuracy, confirming that GPU-based CUDA-Q simulation provides a scalable and practical research environment for QML. This work offers a concrete pathway toward transparent and interpretable quantum machine learning.