An evaluation of the predictive power of component vector angles for seated spinal posture monitoring.

Lucy E. Dunne, Pauline Walsh, Barry Smyth, Brian Caulfield

Research output: Contribution to journalArticlepeer-review

Abstract

This work is part of a larger project developing wearable posture monitors for the work environment. We seek to evaluate the predictive power of individual spinal segment vector angles, towards the selection of the optimum angles for posture monitoring. A marker-based optoelectronic motion capture system was used to monitor seated posture for 9 healthy subjects during a range of motion flexion-extension exercise. Machine learning techniques were used to evaluate the prediction accuracy of the component vector angles recorded, and the range of motion for each vector angle was calculated for each subject. The overall flexion vector angle, which encompasses the entire spinal length between the C7 and L4 vertebrae, was determined to be the best predictor angle, due to its predictive accuracy and simplicity, and its relatively larger range of motion in all subjects.

PubMed: MeSH publication types

  • Journal Article
  • Research Support, Non-U.S. Gov't

Fingerprint Dive into the research topics of 'An evaluation of the predictive power of component vector angles for seated spinal posture monitoring.'. Together they form a unique fingerprint.

Cite this