Fig. 7From: Animal behaviour on the move: the use of auxiliary information and semi-supervision to improve behavioural inferences from Hidden Markov Models applied to GPS tracking datasets Increase in global accuracy and state-wise sensitivity, specificity and precision in complete dataset From left to right, increase in global accuracy (A), and state-wise sensitivity (B), specificity (C), and precision (D), of resting (yellow), foraging (dark red) and travelling (cyan) states without and with the maximum proportion of known states in the complete GPS datasetBack to article page