Graph learning
EEG graph learning and compact decoding
Graph contrastive learning and compact temporal models were developed for EEG emotion recognition and motor-imagery decoding.
EEG research leadNEUROAI LAB / KWANGWOON UNIVERSITY
Dae Hyeon Kim
김대현
Graph learning, multimodal AI
and biosignal analysis
Integrated M.S.-Ph.D. student at NeuroAI Lab, Kwangwoon University. I study EEG emotion recognition and motor-imagery decoding, speech-text fusion and contactless physiological sensing.
Advisor: Young-Seok Choi
Expected graduation: February 2027
6
SCIE published / accepted
7
International conference papers
8
Government-funded projects
4
Technical work packages led
01 / RESEARCH
Research focus
01
Graph representations and structure
Sample and electrode relationships in EEG. Semi-supervised contrastive learning and graph sparsity for classification with limited labels.
02
Multimodal learning and domain adaptation
Fusion of biosignals, speech and text. Emotion recognition under missing inputs and subject or session changes.
03
Efficient models and clinical dialogue
Compact models for motor-imagery EEG and embedded pulse inference. Retrieval, record generation and evidence verification for clinical dialogue systems.
02 / PROJECTS
Selected projects
Multimodal learning
Multimodal emotion recognition
Built an older-adult speech dataset and evaluated graph-based fusion of speech and text for emotion recognition.
Technical work-package lead
KIST internship
Focused-ultrasound registration and control
Registered imaging and tracking coordinates and implemented position control for focused-ultrasound field measurement.
3D Slicer module and device-control developer
Undergraduate internship
Blood pressure estimation from two-channel BCG
Estimated blood pressure from two chair BCG channels using a CNN, BiGRU and temporal attention.
Co-developer of blood-pressure estimation and real-time processing
AI Champion 2026
NeuroSync
Combined Korean LLMs with evidence verification to turn intake conversations into structured clinician handoff records.
Method design and core implementation
AI Champion 2026
NeuroTruth
Connected wearable craving estimates and rule-based risk decisions to app notifications and conversational support.
Technical lead and project manager03 / PUBLICATIONS
Selected publications
-
2026
-
2026
-
2026
-
2026
-
2025
-
2024
04 / EXPERIENCE
Education & experience
-
2022.03 – Present
Integrated M.S.–Ph.D. / Graduate research assistant
NeuroAI Lab, Kwangwoon University. Advisor: Young-Seok Choi. Expected February 2027. GPA 4.50/4.50.
-
2022.01 – 2022.02
Research intern, NeuroAI Lab
EEG entropy and connectivity-based graph learning; co-first author of the subsequent MBE paper.
-
2021.01 – 2021.02
Research intern, KIST
Bionics Research Center. CT/MRI registration, tracking, focused-ultrasound measurement and robotic control.
-
2020.09 – 2021.06
Undergraduate research intern, BCML
Kwangwoon University. ECG, PPG and BCG acquisition, blood-pressure estimation and industry-linked software development.
-
2016.03 – 2022.02
B.S. in Computer Engineering
Kwangwoon University. GPA 3.86/4.50.
05 / SERVICE
Awards & academic service
Recognition
- AI Champion 2026 main round in the regular and Korean-AI tracks
- KOSOMBE 2024 Best Poster Award
- One technology transfer, KRW 20 million
- Full-tuition RA scholarship for six semesters; three undergraduate merit scholarships
Reviewing & teaching
- Reviewer for npj Artificial Intelligence, Scientific Reports and Cluster Computing
- IEEE Graduate Student Member; SPS and EMBS
- Teaching assistant: Signals & Systems and Digital Signal Processing
- KW-VIP mentoring and research tutorials for 21 undergraduates