Modeling and Understanding Human Routine Behavior

To test whether the empirical data behaves as good as the synthetic data we calculated the KS and KS W statistics between the empirical data and its best fit and compared these

Unlike [12] and other predictability studies [4–7, 10] where human mobility is considered as a whole, here we propose a strategy to separate a person’s mobility into two

‘Needs’ define the requirements (physical or non-physical) that must be fulfilled to achieve desired satisfaction. ‘Actions’ are the set of interactions with the urban

For artificial agent supervision, the comparison between correct re- sponses and error detection based on permutation analysis revealed one significant cluster in a

The method we propose is based on the combination of simulation logs analysis (objective part) and answers to a behavior questionnaire (subjective part). The simulation data

We calculate three mass features - (difference area, Distance of Action and Center variance on x axis)- from the MHI image of the video to separate the ten actions into two

Commanders of high performing teams have in shift 4 a stronger inhibition that a New Message is followed by a Show Information or that a Show Information is fol- lowed by a

The robot co-worker must: i) recognise human actions, and specifically their gestures, using a sort of gesture sensor ; ii) represent all the allowed sequences of operations, and