Figure 7

The influence of different features on the performance of classification when using the 100 ms ROW, MV with 5 samples, and SVM classifier. The case of: A) Proprioceptive versus rest; B) VF versus Proprioceptive versus rest. The "power-based" (MAV, VAR, WL, DFT) features and their combinations (MULTI1, MULTI2, MULTI3, MULTI4) are significantly better than the other tested (p < 0.05, Kruskal Wallis test). Among the best features there is not significant difference.