Login / Signup

Integrating Wearable Sensors and Video to Determine Microlocation-Specific Physiologic and Motion Biometrics-Method Development for Competitive Climbing.

Miyuki BreenTaylor ReedHannah M BreenCharles T OsborneMichael S Breen
Published in: Sensors (Basel, Switzerland) (2022)
Competitive indoor climbing has increased in popularity at the youth, collegiate, and Olympic levels. A critical aspect for improving performance is characterizing the physiologic response to different climbing strategies (e.g., work/rest patterns, pacing) and techniques (e.g., body position and movement) relative to location on climbing wall with spatially varying characteristics (e.g., wall inclinations, position of foot/hand holds). However, this response is not well understood due to the limited capabilities of climbing-specific measurement and assessment tools. In this study, we developed a novel method to examine time-resolved sensor-based measurements of multiple personal biometrics at different microlocations (finely spaced positions; MLs) along a climbing route. For the ML-specific biometric system (MLBS), we integrated continuous data from wearable biometric sensors and smartphone-based video during climbing, with a customized visualization and analysis system to determine three physiologic parameters (heart rate, breathing rate, ventilation rate) and one body movement parameter (hip acceleration), which are automatically time-matched to the corresponding video frame to determine ML-specific biometrics. Key features include: (1) biometric sensors that are seamlessly embedded in the fabric of an athletic compression shirt, and do not interfere with climbing performance, (2) climbing video, and (3) an interactive graphical user interface to rapidly visualize and analyze the time-matched biometrics and climbing video, determine timing sequence between the biometrics at key events, and calculate summary statistics. To demonstrate the capabilities of MLBS, we examined the relationship between changes in ML-specific climbing characteristics and changes in the physiologic parameters. Our study demonstrates the ability of MLBS to determine multiple time-resolved biometrics at different MLs, in support of developing and assessing different climbing strategies and training methods to help improve performance.
Keyphrases
  • physical activity
  • heart rate
  • body composition
  • young adults
  • machine learning
  • electronic health record
  • intensive care unit
  • mass spectrometry
  • mental health
  • deep learning
  • particulate matter