Hyeoncheol Kim

ORCID: 0000-0003-0555-8591
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Geological and Geochemical Analysis
  • Education and Learning Interventions
  • Online Learning and Analytics
  • Geochemistry and Geologic Mapping
  • Educational Systems and Policies
  • Educational Research and Pedagogy
  • High-pressure geophysics and materials
  • Topic Modeling
  • earthquake and tectonic studies
  • Intelligent Tutoring Systems and Adaptive Learning
  • Educational Technology and Assessment
  • Teaching and Learning Programming
  • Neural Networks and Applications
  • Geology and Paleoclimatology Research
  • Explainable Artificial Intelligence (XAI)
  • Geological and Geophysical Studies
  • Paleontology and Stratigraphy of Fossils
  • Geological Studies and Exploration
  • Technology and Data Analysis
  • Innovative Teaching and Learning Methods
  • Machine Learning and Data Classification
  • Machine Learning in Bioinformatics
  • Mobile Learning in Education
  • Natural Language Processing Techniques
  • Advanced Graph Neural Networks

Korea University
2009-2024

Seoul National University
1997-2023

Jeonbuk National University
2022

Korea Institute of Geoscience and Mineral Resources
2008-2021

Sungkyunkwan University
2014

Chinese Academy of Sciences
2007

Korea Basic Science Institute
2002-2003

University of Florida
2002

Samsung (South Korea)
2001

Korea Institute of Ocean Science and Technology
2000

Advancements in artificial intelligence (AI) have stimulated the development of educational AI tools (EAIT). EAITs intelligently assist teachers formulating better pedagogical decisions or actions for their students. However, are hardly integrating EAITs, and little is known about perceptions EAITs. This study seeks to identify human factors that encourage restrict teachers' acceptance We propose a revised technology model incorporating beliefs perceived trust Survey data were collected from...

10.1080/10447318.2022.2049145 article EN International Journal of Human-Computer Interaction 2022-04-19

With the rapid technological change of society with Artificial Intelligence, elementary schools' goal should be to prepare next generations according competencies. We propose an AI curriculum cultivate students' literacy answer question ‘why and what teach’ on AI. The proposed focuses achieving based three competencies: Knowledge, Skill, Attitude. anticipate that will equip students core competencies for future

10.1609/aaai.v35i17.17833 article EN Proceedings of the AAAI Conference on Artificial Intelligence 2021-05-18

In recent years, the development of adaptive models to tailor instructional content learners by measuring their cognitive load has become a topic active research. Brain fog, also known as confusion, is common cause poor performance, and real-time detection confusion challenging important task for applications in online education driver fatigue detection. this study, we propose deep learning method recognition based on electroencephalography (EEG) signals using long short-term memory network...

10.3390/bioengineering10030361 article EN cc-by Bioengineering 2023-03-15

Autistic students often face challenges in social interaction, which can hinder their educational and personal development. This study introduces Echo-Teddy, a Large Language Model (LLM)-based robot designed to support autistic developing communication skills. Unlike previous chatbot-based solutions, Echo-Teddy leverages advanced LLM capabilities provide more natural adaptive interactions. The research addresses two key questions: (1) What are the design principles initial prototype...

10.48550/arxiv.2502.04029 preprint EN arXiv (Cornell University) 2025-02-06

U‐Pb zircon ages of tuffs and sandstones the Daedong Supergroup (Bansong Nampo groups) in Korean Peninsula were determined using a sensitive high‐resolution ion microprobe (SHRIMP) order to constrain their age sedimentation unravel discrete geologic events as recorded detrital zircons. The four tuffaceous samples from Bansong Group imply that formed at ca. 187–172 Ma association with Early‐Middle Jurassic orogeny. These data are marked contrast paleomagnetic arguments suggesting groups...

10.1086/519776 article EN The Journal of Geology 2007-07-26

10.1007/s11277-016-3346-1 article EN Wireless Personal Communications 2016-05-02

Research on converting 2D raster drawings into 3D vector data has a long history in the field of pattern recognition. Prior to achievement machine learning, existing studies were based heuristics and rules. In recent years, there have been several employing deep but great effort was required secure large amount for learning. this study, overcome these limitations, we used 3DPlanNet Ensemble methods incorporating rule-based heuristic learn with only small (30 floor plan images)....

10.3390/electronics10222729 article EN Electronics 2021-11-09
Coming Soon ...