Figure 6From: Analysis of nanopore detector measurements using Machine-Learning methods, with application to single-molecule kinetic analysisExample classification results with and without spike analysis. Note that adding a spike feature significantly improves classification accuracy over a wide range of kernel parameters. The Y-axis, "Accuracy", is taken to be (SN+SP)/2 expressed as a percentage, to be consistent with the prior SN+SP based measure, so is not the conventional accuracy = (TP+TN)/(TP+TN+FP+FN). The X-axis is the kernel parameter σ.Back to article page