Figure 8From: Robust Peak Recognition in Intracranial Pressure Signals Effect of the source data used to train the peak recognition models on the average recognition accuracy (Eq. 21) evaluated on the large dataset D. The reference library T 1 is made of randomly chosen ICP pulses. The second training set, weighted sampling T 2 , is made of an equal number of randomly selected pulses from the large dataset D and challenging pulses randomly extracted from the challenging dataset D'. Both datasets contain 3000 pulsesBack to article page