- AI-driven Automated Attack Response Strategy Generation System
- Development of Value-Added Resource Conversion Technology for Waste Plastic Pyrolysis Products
- Development of Wearable Neuromorphic Heterogeneous Integration Platform for SPAD-fNIRS-Based Pain Signal Quantification
- Identification of Novel Disease Markers Using Depression Patient-Derived iPSCs
- Development of Sustainable and Highly Functional Polymer Synthesis and Application Technologies for Future Mobility Regulatory Compliance
- AI-driven Discovery of Targeted Protein Degraders — CRBN-based Molecular Glue Degraders
- Ultra-Low-Latency Storage-Driven I/O Subsystem for Large Language Models
- Intelligent E-Skin Foundry Platform
- Korea Sustainable Hybrid Intensification for Fractionation Technology (K-SHIFT)
- kaist_prj10
- ARC-H2: Autonomous Robotics-driven Catalysts for Hydrogen with High Durability
- PFAS-free Research Initiative for Macromolecular Energy materials (PRIME)
- Center for Divertor Science and Innovation in Fusion Energy (D-SINE)
- Quantum teleportation with quantum dot photons of different colors using a system of PIC and ASIC
- Development of AI-Based Super-Gap Core Technology for Next-Generation Eco-Friendly Free-Form Displays
- Net-zero Seawater Refinery; An AI-Based Integrated Refinery Platform for Carbon Capture and Resource Recovery from Seawater
- Transcendent Material Innovation of Phase Transition Artificial Muscles for Soft Robotics
- Development of an AX-based Intelligent Disaster Prevention Platform for Ultra-Safe SMR Construction Against Extreme External Hazards
- nEAR-LINK Initiative: In-Ear Affective BCI-AI Research Network
- Center of AI-BASE (Brain Architecture, Simulation & Engineering)
- Spin-based Neuromorphic/Quantum Hardware Platform
- Green Carbon Capture via AI-assisted Chloroplast DNA Editing
- Digital Health Technologies for Prediction and Intervention in Neurodegenerative Diseases
- Development of AI-Biofoundry Integrated Platform for Rapid On-Site Detection of Polycarbonate Microplastics and BPA Upcycling
Development of Wearable Neuromorphic Heterogeneous Integration Platform for SPAD-fNIRS-Based Pain Signal Quantification
KEYWORDKeyword
OBJECTIVE Objective
We aim to achieve phased objectives in an interconnected manner, centering on the three core capabilities of the SPAD-fNIRS-based pain quantification platform: 'memristor neuromorphic signal processing', 'flexible/3D heterogeneous integration packaging', and 'SPAD-fNIRS sensing platform'. These include developing hardware-friendly pain indexing algorithms, optimizing highly reliable vertical interconnection packaging processes, implementing integrated on-chip unit optodes, and conducting in-vivo validation. Ultimately, by developing a wearable hardware prototype at Technology Readiness Level (TRL) 5 for the integrated system—capable of real-time, low-power computation near the sensor—we intend to resolve diagnostic uncertainties in clinical and chronic disease management environments while drastically enhancing the industrial applicability of high-precision wearable biosensing and its scalability to brain function monitoring.
INTRODUCTION Director's Message
Hello.
I am Professor Kyung Min Kim, the Principal Investigator of the project, "Development of a Wearable Neuromorphic Pain Quantification Platform based on SPAD-fNIRS."
This research aims to overcome the limitations of conventional pain assessment, which has heavily relied on patients' subjective reports, and to implement a next-generation biosensing platform that objectively quantifies
pain based on physiological signals.
By organically combining KAIST's neuromorphic semiconductor and flexible
3D packaging technologies with KIST's high-precision optical sensing
capabilities, we will successfully deliver a wearable hardware prototype that
operates in real-time with ultra-low power consumption.
We will do our utmost to secure core source technologies in the fields of
digital healthcare and brain function monitoring through this collaborative
research framework.
Thank you.
IMPACT Impact
Through the demonstration of heterogeneous integration packaging for core source technologies and the technology transfer of the integrated platform, this research will accelerate the biomedical industrial application of wearable edge AI technology and contribute to creating a high-value-added new market in the digital healthcare device industry
Furthermore, by securing core patents, we intend to promote technology diffusion into the fields of brain function monitoring and rehabilitation therapy. We also aim to realize social value as a compassionate biotechnology by overcoming the limitations of subjective pain assessment in clinical settings, thereby improving diagnostic objectivity and the quality of medical services for communication-impaired patient groups (such as infants, the elderly, and critically ill patients).
TALENT Ideal Talent
The postdoctoral researcher to be recruited for this project must understand KAIST's memristor/packaging technology and KIST's sensing platform, possessing the integration capabilities to seamlessly bridge the collaborative research between the two institutions at a practical level. As they are required to split their time and spend more than half of the total project period on dispatch between both institutions, strong communication skills and a collaborative attitude to lead joint experiments and data analysis are essential. In terms of values, we aim to nurture a researcher with a proactive growth mindset who seeks to self-improve beyond merely performing assigned tasks, along with a strong sense of responsibility to personally complete a pain-measurement technology that offers practical help to clinical settings.