Skip to main content
Fig. 11 | Journal of NeuroEngineering and Rehabilitation

Fig. 11

From: Classification complexity in myoelectric pattern recognition

Fig. 11

Classification accuracy for the best sets compared to the reference sets. Boxplot of average classification accuracy over all movements when using the best sets representing SI with modified Mahalanobis as distance definition, NNS with k = 120 and the reference sets. The value of k is found in the legend. The middle line of the box is the median, the marker is the mean, and the box extends to the 25th and the 75th percentiles for the bottom and the top, respectively. The different insets compare sets different number of feature algorithms. The result is derived from the IM data set. Classifiers were used in the conventional “single” topology, apart from LDA, which was used in “single” and OVO

Back to article page