Jongkwan Choi

Dr. Jongkwan Choi

Industrial Engineering, Yonsei University, Seoul, Republic of Korea
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
4 March 2022 in IEEE Transactions on Semiconductor Manufacturing
Verified
Journal Article
Closed access
MLMin Yong Lee
Min Yong Lee
YCYeoung Je Choi
Yeoung Je Choi
GLGyeong Taek Lee
Gyeong Taek Lee
JCJongkwan Choi
Jongkwan Choi
CKChang Ouk Kim
Chang Ouk Kim
In semiconductor manufacturing processes, yield analysis aims to increase the yield by determining and managing the causes of low yield. The variable data collected from semiconductor manufacturing processes, in which hundreds of unit processes are implemented according to specific conditions and sequences, are interdependent, and the variables related to previous processes influence the variables in subsequent processes. Therefore, the order of processes should be considered when building a model that searches for the causes of low yield. However, there have been few studies in this area. This paper proposes a low-yield root cause search method considering the order of processes using a long short-term memory with attention mechanism (LSTM-AM) model. Specifically, the LSTM-AM model is applied to data classified according to the process structure of semiconductor products, and the causes of low yield are determined considering the order of processes by extracting attention weights. Experiments are conducted to verify the suitability of the proposed method using real yield data from a semiconductor company. The experimental results confirm that the proposed method outperforms the existing low yield root cause search methods in terms of low yield prediction.

23 June 2023 in Drones
Verified
Journal Article
Open access
PDF file
JCJongkwan Choi
Jongkwan Choi
HKHyeonmin Kim
Hyeonmin Kim
HHHa Jun Hwang
Ha Jun Hwang
YKYong-Duk Kim
Yong-Duk Kim
CKChang Ouk Kim
Chang Ouk Kim
Recently, research on unmanned aerial vehicles (UAVs) has increased significantly. UAVs do not require pilots for operation, and UAVs must possess autonomous flight capabilities to ensure that they can be controlled without a human pilot on the ground. Previous studies have mainly focused on rule-based methods, which require specialized personnel to create rules. Reinforcement learning has been applied to research on UAV autonomous flight; however, it does not include six-degree-of-freedom (6-DOF) environments and lacks realistic application, resulting in difficulties in performing complex tasks. This study proposes a method of efficient learning by connecting two different maneuvering methods using modular learning for autonomous UAV flights. The proposed method divides complex tasks into simpler tasks, learns them individually, and then connects them in order to achieve faster learning by transferring information from one module to another. Additionally, the curriculum learning concept was applied, and the difficulty level of individual tasks was gradually increased, which strengthened the learning stability. In conclusion, modular learning and curriculum learning methods were used to demonstrate that UAVs can effectively perform complex tasks in a realistic, 6-DOF environment.

24 August 2023 in Drones
Verified
Journal Article
Open access
PDF file
HHHa Jun Hwang
Ha Jun Hwang
JJJaeyeon Jang
Jaeyeon Jang
JCJongkwan Choi
Jongkwan Choi
JBJung Ho Bae
Jung Ho Bae
SKSung Ho Kim
Sung Ho Kim
CKChang Ouk Kim
Chang Ouk Kim
Despite the growing demand for unmanned aerial vehicles (UAVs), the use of conventional UAVs is limited, as most of them require being remotely operated by a person who is not within the vehicle’s field of view. Recently, many studies have introduced reinforcement learning (RL) to address hurdles for the autonomous flight of UAVs. However, most previous studies have assumed overly simplified environments, and thus, they cannot be applied to real-world UAV operation scenarios. To address the limitations of previous studies, we propose a stepwise soft actor–critic (SeSAC) algorithm for efficient learning in a continuous state and action space environment. SeSAC aims to overcome the inefficiency of learning caused by attempting challenging tasks from the beginning. Instead, it starts with easier missions and gradually increases the difficulty level during training, ultimately achieving the final goal. We also control a learning hyperparameter of the soft actor–critic algorithm and implement a positive buffer mechanism during training to enhance learning effectiveness. Our proposed algorithm was verified in a six-degree-of-freedom (DOF) flight environment with high-dimensional state and action spaces. The experimental results demonstrate that the proposed algorithm successfully completed missions in two challenging scenarios, one for disaster management and another for counter-terrorism missions, while surpassing the performance of other baseline approaches.

31 December 2024 in Drones
Verified
Journal Article
Open access
PDF file
HKHyeonmin Kim
Hyeonmin Kim
JCJongkwan Choi
Jongkwan Choi
HDHyungrok Do
Hyungrok Do
GLGyeong Taek Lee
Gyeong Taek Lee
The focus of unmanned aerial vehicle (UAV) path planning includes challenging tasks such as obstacle avoidance and efficient target reaching in complex environments. Building upon these fundamental challenges, an additional need exists for agents that can handle diverse missions like round-trip navigation without requiring retraining for each specific task. In our study, we present a path planning method using reinforcement learning (RL) for a fully controllable UAV agent. We combine goal-conditioned RL and curriculum learning to enable agents to progressively master increasingly complex missions, from single-target reaching to round-trip navigation. Our experimental results demonstrate that the trained agent successfully completed 95% of simple target-reaching tasks and 70% of complex round-trip missions. The agent maintained stable performance even with multiple subgoals, achieving over 75% success rate in three-subgoal missions, indicating strong potential for practical applications in UAV path planning.

12 January 2026 in IEEE Access
Verified
Journal Article
Open access
JCJongkwan Choi
Jongkwan Choi
YLYujin Lee
Yujin Lee
EYEunbin Yun
Eunbin Yun
GLGyeongtaek Lee
Gyeongtaek Lee
This paper proposes a regularization technique called sparse probabilistic split (SPS), which introduces controlled randomness into the node-splitting process of decision trees to mitigate overfitting and enhance generalization. Building on this technique, we propose two models: the sparse probabilistic tree (SPT) and the sparse probabilistic ensemble tree (SPET). SPT improves robustness in single-tree settings by probabilistically exploring diverse partition structures, while SPET extends this mechanism to ensemble learning, promoting model diversity and stability. SPT successfully handled the XOR dataset, a representative nonlinear classification problem that typically challenges traditional decision trees. In additional analyses comparing the number of trees, SPET showed greater stability and accuracy even with fewer trees, demonstrating its efficiency. On high-dimensional and class-imbalanced manufacturing datasets, SPET achieved the highest average F1 score and ROC AUC with competitive generalization gaps compared to widely-used ensemble models, demonstrating strong robustness to overfitting. SPET also maintained reliable performance across public benchmark datasets, indicating its adaptability to diverse data environments. These results suggest that SPS is a lightweight and effective regularization strategy for improving the generalization of tree-based models in practical applications.

13 June 2026 in Expert Systems
Verified
Journal Article
Closed access
PDF file
HLHyeong Gu Lim
Hyeong Gu Lim
JJJaeyeon Jang
Jaeyeon Jang
JCJongkwan Choi
Jongkwan Choi
KKKyeong Hui Kim
Kyeong Hui Kim
CKChang Ouk Kim
Chang Ouk Kim