Person identification utilizing vibration response of human fingers
ID:62 View Protection:ATTENDEE Updated Time:2022-10-30 17:08:37 Hits:422 Oral Presentation

Start Time:Pending(Asia/Shanghai)

Duration:Pending

Session:No Session »

Video No Permission

Tips: Only the registered participant can access the file. Please sign in first.

Abstract
This research suggests a new biometric identification approach in future personal devices that uses the frequency response of human body, especially fingers for personal identification. A series of experimental vibration modal analysis were conducted to measure frequency response functions (FRFs) of fingers of actual individuals. In addition, the major components of a finger such as phalanges, joints and skin were modeled in a biodynamic lumped system, and corresponding analytical FRFs were calculated for analytical modal analysis of finger for the comparison with the measured FRFs. In the identification process, an effective feature extraction method based on the correlation coefficient between frequency bins of measured FRFs was applied to extract the most effective set of frequency bins among all FRF spectrum. Extracted features were utilized to train support vector machine in the classification of the individuals. The classification results showed 99% accuracy at maximum in a controlled experimental setup, which verifies the feasibility of vibrational response as a new biometric identification of individuals.
Keywords
Frequency Response Function,Human Body Vibration,Biometric Authentication,Biodynamics,Feature Extraction,Support Vector Machine,Machine Learning
Speaker
Yong-Hwa Park
Professor KAIST

Yong-Hwa Park received BS, MS, and PhD in Mechanical Engineering from KAIST in 1991, 1993, and 1999, respectively. In 2000-2003, he joined to Aerospace Department in University of Colorado at Boulder as a research associate. In 2003-2016, he worked for Samsung Electronics in Visual Display Division and Samsung Advanced Institute of Technology (SAIT) as a Research Master in the field of vibrating micro-opto-electro-mechanical systems with applications to 3D imaging, health sensors and display systems. From 2016, he joined to KAIST as an associate professor of NOVIC+ (Noise & Vibration Control Plus) at the department of Mechanical Engineering devoting to researches on vibration, acoustics, vision sensors and AI-based recognitions for human-machine interactions. His research fields include structural vibration; system identification; event detection and condition monitoring from vibration and acoustic signatures utilizing AI; blood pressure and health monitoring sensors; and 3D/lidar sensors for vibration measurements. He has been working for SPIE Photonics West as a conference chair of MOEMS and miniaturized systems since 2013. He is a board member of KSME, KSNVE, KSPE, and SPIE. He works for KSME as an associated editor.

Submission Author
Hyewon Yoo KAIST
Jae Woong Bae KAIST
Jae-Hak Jeong KAIST
Yong-Hwa Park KAIST
Submit Comment
Verify Code Change Another
All Comments
Important Date
  • Conference Date

    Nov 01

    2022

    to

    Nov 03

    2022

  • Oct 30 2022

    Draft paper submission deadline

  • Nov 09 2022

    Registration deadline

Sponsored By
Qingdao University of Technology