Recently, we have proposed to use complementary complexity measures discovered by boosting-like ensemble learning for the enhancement of quantitative indicators dealing with necessarily short physiological time series. We have confirmed robustness of such multi-complexity measures for heart rate variability analysis with the emphasis on detection of emerging and intermittent cardiac abnormalities. Here we demonstrate that such ensemble-based approach could be also effective in discovering universal meta-indicators for early detection and convenient monitoring of neurological abnormalities using gait time series.

This content is only available via PDF.
You do not currently have access to this content.