arXiv subjects

Soobin Jeon

Publications and source records attributed to Soobin Jeon.

4 recordsLinked to original sources

arXiv2025

Implementation of a Skin Lesion Detection System for Managing Children with Atopic Dermatitis Based on Ensemble Learning

The amendments made to the Data 3 Act and impact of COVID-19 have fostered the growth of digital healthcare market and promoted the use of medical data in artificial intelligence in South Korea. Atopic dermatitis, a chronic inflammatory skin disease, is diagnosed via subjective evaluations without using objective diagnostic methods, thereby increasing the risk of misdiagnosis. It is also similar to psoriasis in appearance, further complicating its accurate diagnosis. Existing studies on skin diseases have used high-quality dermoscopic image datasets, but such high-quality images cannot be obtained in actual clinical settings. Moreover, existing systems must ensure accuracy and fast response times. To this end, an ensemble learning-based skin lesion detection system (ENSEL) was proposed herein. ENSEL enhanced diagnostic accuracy by integrating various deep learning models via an ensemble approach. Its performance was verified by conducting skin lesion detection experiments using images of skin lesions taken by actual users. Its accuracy and response time were measured using randomly sampled skin disease images. Results revealed that ENSEL achieved high recall in most images and less than 1s s processing speed. This study contributes to the objective diagnosis of skin lesions and promotes the advancement of digital healthcare.

cs.CV↗

arXiv2024

Communication Constellation Design of Minimum Number of Satellites with Continuous Coverage and Inter-Satellite Link

The recent advancement in research on distributed space systems that operate a large number of satellites as a single system urges the need for the investigation of satellite constellations. Communication constellations can be used to construct global or regional communication networks using inter-satellite and ground-to-satellite links. This study examines two challenges of communication constellations: continuous coverage and inter-satellite link connectivity. The bounded Voronoi diagram and APC decomposition are presented as continuous coverage analysis methods. For continuity analysis of the inter-satellite link, the relative motion between adjacent orbital planes is used to derive analytic solutions. The Walker-Delta constellation and common ground-track constellation design methods are introduced as examples to verify the analysis methods. The common ground-track constellations are classified into quasi-symmetric and optimal constellations. The optimal common ground-track constellation is optimized using the BILP algorithm. The simulation results compare the performance of the communication constellations according to various design methods.

physics.space-ph↗

arXiv2024

Adaptive Smooth Control via Nonsingular Fast Terminal Sliding Mode for Distributed Space Telescope Demonstration Mission by CubeSat Formation Flying

This paper presents a nonsingular fast terminal sliding mode-based adaptive smooth control methodology for a distributed space telescope demonstration mission. The distributed space telescope has a flexible focal length that corresponds to the relative position in the formation flying concept. The limited specification of a CubeSat generally restricts the performance of actuators, most critically the degrees of freedom of controlled motion. This investigation leads to the development of an adaptive smooth control methodology via nonsingular fast terminal sliding modes. The adaptive smooth control algorithm that was developed for a single-input single-output system is adopted and extended to the relative orbit and attitude control systems of the distributed space telescope. The software simulation is conducted under a real mission, which means the real CubeSat structures, hardware specifications, and operational constraints. The proposed algorithm possesses only seven parameters that can be easily adjusted considering their physical meanings. Furthermore, the pre-designated error bounds are analytically derived, which enhances the applicability of the algorithm to real missions. The simulation compares the efficiency of the adaptive smooth nonsingular fast terminal sliding mode controller with the linear quadratic regulator and proportional derivative algorithms. The results verify that the adaptive smooth nonsingular fast terminal sliding mode control algorithm shows better control performance in the perspective of the alignment time and the fuel consumption for the distributed space telescope demonstration mission.

eess.SY↗

arXiv2024

Mathemyths: Leveraging Large Language Models to Teach Mathematical Language through Child-AI Co-Creative Storytelling

Mathematical language is a cornerstone of a child's mathematical development, and children can effectively acquire this language through storytelling with a knowledgeable and engaging partner. In this study, we leverage the recent advances in large language models to conduct free-form, creative conversations with children. Consequently, we developed Mathemyths, a joint storytelling agent that takes turns co-creating stories with children while integrating mathematical terms into the evolving narrative. This paper details our development process, illustrating how prompt-engineering can optimize LLMs for educational contexts. Through a user study involving 35 children aged 4-8 years, our results suggest that when children interacted with Mathemyths, their learning of mathematical language was comparable to those who co-created stories with a human partner. However, we observed differences in how children engaged with co-creation partners of different natures. Overall, we believe that LLM applications, like Mathemyths, offer children a unique conversational experience pertaining to focused learning objectives.

cs.HC↗