Back

Humans postural sways: non-Gauss, variability, and aging aspects of a data set mining

Chuiko, G. P.; Darnapuk, Y. S.; Dvornik, O. V.; Krainyk, Y. M.; Yaremchuk, O. M.

2021-04-21 bioinformatics
10.1101/2021.04.20.440576 bioRxiv
Show abstract

This report presents the results of data mining of a sample with two focus-groups. They have the same sizes: seven people into each one, random-wise picked up from the same data set. The trials of groups were idem. The postural swings, that is, the move of the center-of-pressure (COP), were recorded. Maple, a computer math system, has allowed us to apply the Principal Components Analysis, Statistical analysis, Kernel Density Estimations (KDE) for the probabilities. Poincare and Recurrence Plots were other tools for modern data mining. The non-Gauss features of the real distributions are not that to be neglect. They exist not only as outliers but as sharp kurtosis and skewness. Still, they are so far not enow to grave doubts to the Fractional Brownian model. We found some subtle aging hallmarks for focus-groups. First, the trend of variability descriptors to be bi-modal is sheerer for the older group. Second, the coefficients of correlations of the short-time variability index with other descriptors are clear age-related. 2012 ACM Subject ClassificationApplied computing [->] Life and medical sciences [->] Health informatics

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.