Research

Identity Recognition via Bioacoustics

We are establishing technologies to obtain biomechanical and biomaterial characteristics of the human body tissues for biometric identity authentication. By transmitting mechanical and electrical signals inside the fingers and hands, we demonstrate identity recognition systems that analyze the anatomical and biomechanical characteristics of individual person with the help of deep learning. This biometric identity recognition technology holds immense potential for human computer interaction, mobile transactions, access control, and robotics.

Photoacoustics for Healthcare and Biomedical Engineering

We use photoacoustics, the formation of sound waves following light absorption in a target material, to acquire human body information. We built photoacoustic sensing and imaging systems that can monitor blood glucose under the skin without taking out blood from a fingertip. Our research interest include photoacoustic design optimization, microscopic imaging system, and machine learning for glucose level prediction from spectral data.

Design for Mechanobiology of the Cells and Tissues

We built systems to stretch cells and tissues with the underlying substrate. Using the system, we studied mechanical signaling pathways that regulate cell cycle, proliferation, cellular mitotic alignment, and stem cell differentiation. We established methods to measure the contraction forces of cells by using molecular tensor sensors, hydrogel-based tissue culture substrates, and polymer-based micro-pillar arrays. These methods were employed to evaluate the functionality of stem-cell-derived cardiomyocytes, cadherin-mediated mechanical cell-cell interactions, and exploratory lamellipodia activities

Implantable and Wearable Platforms with Machine Learning

We develop implantable and wearable platforms, for applications in physiological monitoring, with expertise in a mechanically transformative platform. This mechanically reconfigurable platform can tune its mechanical modulus on demand and fully reversibly, for the usability in both standalone and wearables. The proposed platform can tune its mechanical modulus, with application demonstrations as monitoring of human activity signals and further extended to pressure sensors and implantable neural probes. We further expanded this research to parallel signal processing of a wireless pressure-sensing platform integrated with a machine-learning-based cognitive system.

Contact Us

 

Cheongpa-ro 47-gil 100, Yongsan-gu, Seoul, 04310, Republic of Korea

Renaissance Plaza, Room 314

TEL: +82-2-710-9827

E-mail: jysim at sookmyung.ac.kr

© 2020 Intelligent Biomedical System Lab