Assessing Motor Performance with PCA

  1. Lookup NU author(s)
  2. Nils Hammerla
  3. Dr Thomas Ploetz
  4. Professor Peter Andras
  5. Professor Patrick Olivier
Author(s)Hammerla N, Ploetz T, Andras P, Olivier P
Publication type Conference Proceedings (inc. Abstract)
Conference NameInternational Workshop on Frontiers in Activity Recognition using Pervasive Sensing (in conjunction with Pervasive)
Conference LocationSan Francisco, California, USA
Year of Conference2011
Source Publication Date12-15 June 2011
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
Information about the motor performance, i.e. how well an activity is performed, is valuable information for a variety of novel applications in Activity Recognition (AR). Its as- sessment represents a significant challenge, as requirements depend on the specific application. We develop an approach to quantify one aspect that many domains share – the ef- ficiency of motion – that has implications for signals from body-worn or pervasive sensors, as it influences the inherent complexity of the recorded multi-variate time-series. Based on the energy distribution in PCA we infer a single, nor- malised metric that is intimately linked to signal complexity and allows comparison of (subject-specific) time-series. We evaluate the approach on artificially distorted signals and apply it to a simple kitchen task to show its applicability to real-life data streams.