Skip to main content
Fig. 6 | Journal of NeuroEngineering and Rehabilitation

Fig. 6

From: Semi-automated approaches to optimize deep brain stimulation parameters in Parkinson’s disease

Fig. 6

Probit Gaussian process fits. Rigidity response to frequency model after BayesOpt compared to preference model. The BayesOpt model was created after 12 iterations of the algorithm. The participants were asked which setting they preferred (the current or previous frequency setting). This was used to obtain their preference model. The average expected preference an input has over the entire input space is shown as the solid blue line, and the 95% confidence interval is shown as the shaded blue region

Back to article page