Skip to main content
. Author manuscript; available in PMC: 2016 Aug 1.
Published in final edited form as: J Neural Eng. 2015 Jun 10;12(4):046018. doi: 10.1088/1741-2560/12/4/046018

Figure 2.

Figure 2

Analysis of the sensitivity of offline results to the number of particles used. Results were computed for each subject in the offline dataset using cross-validation with the particle filter classifier and the specified number of particles. Selection accuracies were then computed and averaged across all subjects. Optimal classifier performance was achieved when using at least 10,000 particles.