7th International Conference on Body Area Networks

Research Article

A Data-driven Functional PCA Filter for Compensating the Effect of Sensor Position Changes in Motion Data

Download351 downloads
  • @INPROCEEDINGS{10.4108/icst.bodynets.2012.250004,
        author={Roya Haratian and Chris Phillips and Tijana Timotijevic},
        title={A Data-driven Functional PCA Filter for Compensating the Effect of Sensor Position Changes in Motion Data},
        proceedings={7th International Conference on Body Area Networks},
        publisher={ICST},
        proceedings_a={BODYNETS},
        year={2012},
        month={11},
        keywords={motion capturing measurement variability functional principal component analysis},
        doi={10.4108/icst.bodynets.2012.250004}
    }
    
  • Roya Haratian
    Chris Phillips
    Tijana Timotijevic
    Year: 2012
    A Data-driven Functional PCA Filter for Compensating the Effect of Sensor Position Changes in Motion Data
    BODYNETS
    ICST
    DOI: 10.4108/icst.bodynets.2012.250004
Roya Haratian,*, Chris Phillips1, Tijana Timotijevic1
  • 1: Queen Mary University of London London, UK
*Contact email: roya.haratian@gmail.com

Abstract

Human body motion is typically captured by body area sensor networks. Accurate sensor placement with respect to anatomical landmarks is one of the main concerns in reliability of the motion capturing systems. Changes in position of sensors cause increased variability in motion data. Our goal is to isolate the characteristic features that represent the principle motion pattern. By using functional Principal Component Analysis (f-PCA) we compensate for the variation in data due to inadvertent movement of sensor placement. F-PCA is an effective tool for the study of human motion modeling by identifying hidden combinations and relationships between variables. The collected data from our experiment show differences between similar actions within different sessions of marker wearing. After applying f-PCA to the data, we show how the uncertainties due to sensor position changes can be compensated for.