Skip to content
View kimdoeon's full-sized avatar
πŸ˜„
πŸ˜„
  • AI convergence, Soongsil Univ
  • Korea, Seoul

Organizations

@coding-study-19

Block or report kimdoeon

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
kimdoeon/README.md

Hi there! I'm doeon kim :)

πŸ‘‹ I'm doeon, a Master's student in the Graduate school of AI at Soongsil University, co-advised by Prof. Sungshin Kim (SmartAILab) and Prof. Seongheum Kim (VIP Lab). My research focuses on WiFi CSI sensing πŸ” and multimodal deep learning for EMF prediction πŸ“‘. Moving forward, I aim to extend my work toward wireless sensing for human perception.

πŸ“ͺ Contact


πŸ† Awards

  • 26 LPCVC - 2nd Place (link)
    • Issued by: Qualcomm and ECV workshop at CVPR, 6.2026
    • AI Generated Images Detection
  • SW-Centered University Joint AI Competition - Chairman’s Award (link)
    • Issued by: Ministry of Science and ICT, 11.2023
    • Developed an AI model for building area segmentation in satellite images
  • SW/DT SeSAC Competition - excellence award
    • Issued by: Soongsil Univ, 10. 2022
    • Developed a rule-based model for recommending music based on image sentiment analysis

πŸ“š Publications

  • Estimation of Electromagnetic Field Strength:Experiments Using Vision Transformers, IEEE Access, 2025
  • 5G ν™˜κ²½μ—μ„œ μ „μžκΈ°μž₯ μ˜ˆμΈ‘μ„ μœ„ν•œ ViT 기반 λ©€ν‹°λͺ¨λ‹¬ 물리 데이터 κ²°ν•© 연ꡬ, λŒ€ν•œμ „μžκ³΅ν•™νšŒ(CEIC) 좔계 ν•™μˆ λŒ€νšŒ, 2025
    Multimodal Physical Data Fusion using ViT for 5G Electromagnetic Field Estimation, CEIC Fall Conference, 2025
  • 이쒅 νŠΉμ§• 맡을 μ΄μš©ν•œ ꡐ차 μ–΄ν…μ…˜ 기반 μ†Œν˜• 객체 κ²€μΆœ 기법, ν•œκ΅­μ§€λŠ₯μ‹œμŠ€ν…œν•™νšŒ(KIIS) μΆ”κ³„ν•™μˆ λŒ€νšŒ, 2024
    Small Object Detection Method Based on Cross Attention of Heterogeneous Feature Maps, Korean Institute of Intelligent Systems(KIIS) Fall Conference, 2024

πŸ“‚ Projects and 🧩 Activities

  • πŸ“‚ShowMyWorld in Korean (02.2025-04.2025)

    • Scene Text-to-Scene Text Translation (English/Korean Signboard Image Translation)
    • Responsible for translation accuracy and contextual meaning preservation using translation models
  • πŸ“‚EMF(Electromagnetic Field) Prediction (05.2024-07.2025)

    • Vision Transformer-Based EMF Prediction in 5G Networks
    • Applied transformer models (ViT, SegFormer, Swinformer, HRFormer, Mask2Former)
  • πŸ“‚Watchlist filtering (05.2024-02.2025)

    • Developed a BERT-based model to measure name similarity for watchlisted individuals
    • Utilized Semantic Textual Similarity(STS) BERT with Cosine Similarity
  • 🧩SW DONGHANG Hackathon University Mentor (23.11.2024-24.11.2024)

    • Hosted by Korea Foundation for the Advancement of Science and Creativity(KOSAC)
    • Mentored students in a hackathon project as an AI major, providing guidance on AI projects.
  • 🧩SKT FLY AI Challenger 4κΈ° (12.2023-02.2024)

    • Hosted by SK telecom
    • Developed an AI-based artwork description application for museums utilizing ChatGPT and generative AI.

πŸ’ͺ Skills


πŸ“œ Certification

Β Β Β AI-900 (Microsoft Azure AI Fundamentals)

Pinned Loading

  1. Satellite-Image-Building-Segmentation Satellite-Image-Building-Segmentation Public

    Jupyter Notebook 6