Daily datasets were split into 12 h, 6 h and 3 h subsets in order to investigate the impact of data length on estimated displacement.
The datasets were split into training set used during learning and the test set used during evaluation.
Before applying the framework, the two used datasets were split in four subsets of data (Table 7).
The modeling datasets were split into training and validation subsets.
Datasets were split to obtain the test set/training set accuracy estimate.
Each of the datasets was split into a reference and validation set (Table 1) to allow for cross validation of the accuracy of DGV.
Each of the three list-mode datasets was split into 60 noise realizations each containing the same number of list-mode events, which were spread out regularly over the entire scan time.
(B ) The datasets were split into <5 and ≥5 copies to ensure that the observed difference was not an artefact of the arbitrary two-copy cut-off used in Figure 4B.
Last, the datasets were splitted into training set and testing set.
When the dataset was split into two groups, we found no significant correlation between the preference scores of the students and locals.
