Fig. 3From: 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 Confusion matrices of auxiliary data only models Confusion matrices showing the mean and standard deviation in the number of reference behaviours against model predictions for iterations of the auxiliary data only models with no supervision (left) and with the highest amount of supervision (75%, right). Top row shows all positions while the bottom row shows positions with a classification probability over 0.9Back to article page