Suhee Jo

Ms. Suhee Jo

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
25 January 2024 in IEEE Access
Verified
Journal Article
Open access
RKRyeonggu Kwon
Ryeonggu Kwon
GKGihwon Kwon
Gihwon Kwon
SPSohee Park
Sohee Park
JCJiyoung Chang
Jiyoung Chang
SJSuhee Jo
Suhee Jo
Reinforcement learning (RL) is rapidly used in safety-centric applications. However, many studies focus on generating optimal policy that achieves maximum rewards. While maximum rewards are beneficial, safety constraints and non-functional requirements must also be considered in safety-centric applications to avoid dangerous situations. For example, in the case of food delivery robots in restaurants, RL should be used not only to find optimal policy that response to all customer requests through maximum rewards but also to consider safety constraints such as collision avoidance and non-functional requirements such as battery saving. In this paper, we investigated the fulfillment of safety constraints and non-functional requirements of learning models generated through RL with quantitative model checking. We experimented with various time steps and learning rates required for RL, targeting restaurant delivery robots. The functional requirement of these robots is to process all customer order requests, and the non-functional requirements are the number of steps and battery consumption to complete the task. Safety constraints include the amount of collision and the probability of collision. Through these experiments, we made three important findings. First, learning models that obtain maximum rewards may have a low degree of achievement of non-functional requirements and safety constraints. Second, as safety constraints are met, the degree of achievement of non-functional requirements may be low. Third, even if the maximum reward is not obtained, sacrificing non-functional requirements can maximize the achievement of safety constraints. These results show that learning models generated through RL can trade off rewards to achieve safety constraints. In conclusion, our work can contribute to selecting suitable hyperparameters and optimal learning models during RL.

2 February 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SJSuhee Jo
Suhee Jo
RKRyeonggu Kwon
Ryeonggu Kwon
GKGihwon Kwon
Gihwon Kwon
GitHub serves as a platform for collaborative software development, where contributors engage, evolve projects, and shape the community. This study presents a novel approach to analyzing GitHub activity that departs from traditional methods. Using Discrete-Time Markov Chains and probabilistic Computation Tree Logic for model checking, we aim to uncover temporal dynamics, probabilities, and key factors influencing project behavior. By explicitly modeling state transitions, our approach provides transparency and explainability for sequential properties. The application of our method to five repositories demonstrates its feasibility and scalability and provides insights into the long-term probabilities of various activities. In particular, the analysis provides valuable perspectives for project managers to optimize team dynamics and resource allocation. The query specifications developed for model checking allow users to generate and execute queries for specific aspects, demonstrating scalability beyond the queries we present. In conclusion, our analysis provides an understanding of GitHub repository properties, branch management, and subscriber behavior. We anticipate its applicability to various open-source projects, revealing trends among contributors based on the unique characteristics of repositories.

31 August 2023 in The Journal of Korean Institute of Information Technology
Verified
Journal Article
Closed access
SJSuhee Jo
Suhee Jo
RKRyeonggu Kwon
Ryeonggu Kwon
GKGihwon Kwon
Gihwon Kwon
강화 학습은 의료, 자율 주행 자동차 등 다양한 분야에서 사용된다. 그러나 강화 학습은 에이전트의 의사 결정과정에 대해 이해하기 어렵고, 지도학습처럼 출력된 결과에 대한 정확성을 측정할 수 없다. 그렇기 때문에, 강화학습 시스템의 안전성을 평가하는 연구가 매우 필요하다. 따라서, 본 논문에서는 행동 주도 개발 기법과 위험원분석을 결합하여 강화 학습 모델의 안전성을 평가하는 방법을 제안한다. 자율 주행 시뮬레이션 환경에 대해 제안한 방법을 적용한 결과, 강화 학습 모델의 평균 보상이 유사하더라도 안전 제약 조건을 위반한 빈도의 편차가 나타나는 것을 관찰할 수 있었다. 안전성 평가로 도출된 결과는 다양한 측면에 걸친 분석과 반복적인 개선을 통해 모델의 안전성 향상에 기여할 수 있을 것으로 기대된다.

30 November 2022 in The Journal of Korean Institute of Information Technology
Verified
Journal Article
Closed access
SJSuhee Jo
Suhee Jo
SPSohee Park
Sohee Park
GKGihwon Kwon
Gihwon Kwon
최근 소프트웨어 개발은 빠른 개발과 배포를 추구하기 때문에 애자일 방법론을 주로 채택하여 소프트웨어 개발 프로젝트를 진행한다. 이런 애자일 기법을 교육하기 위해 교육용으로 경량화 된 스크럼 프로세스를 개발하여 2022년도 상반기에 학생들에게 배포하였지만 기대한 만큼의 결과를 도출하지는 못했다. 본 논문에서는 이런 문제의 원인에 대해 분석하고 이를 보완할 방법으로 학생 친화적인 교육용 스크럼 프레임워크를 제안한다. 학생들이 스크럼 방법론을 학습하고 나아가서는 실습환경까지 조성해 줄 수 있는 프레임워크는 크게 베이스 프로젝트, 툴 체인, 스크럼 가이드로 구성되어있다. 학생들이 스크럼 프로세스에 대해 잘 알지 못하더라도 이 프레임워크의 단계만 수행하면 자연스럽게 학습할 수 있을 것으로 기대된다.

2 January 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SJSuhee Jo
Suhee Jo
GKGihwon Kwon
Gihwon Kwon
Open-source software (OSS) projects rely on collaborative contributions, yet sustaining long-term engagement remains a challenge. This study examines how contributor activity frequency and network centrality impact sustained contributions in 672 GitHub repositories. Using k-core decomposition and model checking, we find that contributors with higher k-core values manage more pull requests. Additionally, they show greater resilience in continuing to contribute after pull request rejections, a behavior rarely seen in non-core contributors. Moreover, the likelihood of long-term engagement increases significantly when contributors’ pull requests are processed swiftly, with delayed or rejected pull requests resulting in higher disengagement, particularly among peripheral contributors. We also observe that as project networks grow more complex over time, core contributors become essential in maintaining project sustainability. These findings offer new insights into fostering core contributor retention and underscore the need for efficient governance and PR management practices in OSS projects.