Fig. 3.

The distribution of distance definitions and classifiers data using simultaneous movements (SM set). Plot matrix where the insets shows classification accuracy plotted against the SI for the simultaneous movements data set. One marker represents the average over all movements for one subject and one feature. The classifiers are grouped in rows and the distance definitions for SI are group in columns. Classifiers were configured using “all movements as individual” (AMI) or “mixed outputs” (MIX). Classifiers were used in the conventional “single” topology, apart from LDA, which was used in “single” and OVO. All correlations were found statistically significant at p < 0.01. Classifiers and distance definitions are stated at the left side and the bottom of the plot matrix respectively. The highest correlating distance definition for every classifier is marked by a thicker frame around the plot