Figure 3

Evaluation of different methods on a toy accelerometer set-up. From top to bottom: Predictions from a (a) Van der Pol oscillator (\(\mathcal{P}(t)\)), (b) Gaussian Process (\(\mathcal{D}(t)\)) and (c) hybrid model combining both approaches according to the delta model (\(\mathcal{H}(t) = \mathcal{P}(t) + \mathcal{D}(t)\)). Training data is shown in blue, test data in red. The predictions are shown in yellow. The yellow shaded areas in Figure (b) and (c) depict the 95% confidence interval of the predictions. We can observe that the Van der Pol oscillator cannot capture the local effects of the data, while the Gaussian Process falls short when training data is scarce. The hybrid model combines the best of both worlds and performs well under all data scenarios