Device and a computer-implemented method for determining a behavior of a target user
A device for determining a behavior of a target user, the device including a sensing unit configured to face at least one eye area of a target user, the sensing unit being configured to acquire a plurality of target signals representative of a variation of at least one characteristic of the at least one eye area of the target user, the sensing unit including at least one sensor, and the at least one sensor being oriented towards the eye area. The device also includes a controller configured to provide a machine learning algorithm, provide a plurality of objective target data related to the acquired target signals as an input to the machine learning algorithm, and determine a behavior of the target user as an output of the machine learning algorithm.
1 . A device for determining a behavior of a target user, comprising:
a sensing unit configured to face at least one eye area of a target user, the sensing unit being configured to acquire a plurality of target signals representative of a variation of at least one characteristic of said at least one eye area of said target user,
the sensing unit comprising at least one sensor, the at least one sensor being a non-imaging sensor, and
the at least one sensor being oriented towards said at least one eye area;
a light stimuli source configured to stimulate at least one eye, said behavior being a change in visual comfort of the target user, said variation of said at least one characteristic being caused by a light stimulus provided to said at least one eye area, and said change in the visual comfort of the target user being glare; and
a controller configured to:
provide a machine learning algorithm,
stimulate at least one eye with said light stimuli source,
provide a plurality of objective target data related to the acquired target signals as an input to said machine learning algorithm,
determine a behavior of said target user as an output of the machine learning algorithm, and
determine at least one filter for a transparent support to improve or to maintain the visual comfort and/or visual performance of said target user based on said behavior.
2 . The device according to claim 1 , wherein the at least one sensor is placed around said at least one eye area.
3 . The device according to claim 1 , wherein the at least one sensor is associated to at least one light source.
4 . A computer-implemented method for determining a behavior of a target user, the method comprising:
providing a machine learning algorithm;
stimulating at least one eye with a light stimuli source;
acquiring a plurality of target signals representative of a variation of at least one characteristic of at least one eye area of a target user by using a sensing unit facing said at least one eye area of a target user, the sensing unit comprising at least one sensor, the at least one sensor being a non-imaging sensor, said behavior being a change in visual comfort of the target user, said variation of said at least one characteristic being caused by a light stimulus provided to said at least one eye area, and said change in the visual comfort of the target user being glare;
providing a plurality of objective target data related to the acquired target signals as an input to said machine learning algorithm;
determining a behavior of said target user as an output of the machine learning algorithm; and
determining at least one filter for a transparent support to improve or to maintain the visual comfort and/or visual performance of said target user based on said behavior.
5 . The computer-implemented method according to claim 4 , wherein said machine learning algorithm is based on a plurality of initial data related to a set of initial users, said initial data comprising a plurality of acquired learning signals representative of a variation of at least one characteristic of at least one eye area for each initial user of the set.
6 . The computer-implemented method according to claim 5 , wherein said plurality of initial data related to a set of initial users comprises subjective and objective data, said subjective data comprising perception of the initial users of the set to a behavior caused by said variation of at least one characteristic of at least one eye area for each initial user of the set.
7 . The computer-implemented method according to claim 5 , further comprising:
providing to the machine learning algorithm said plurality of initial data related to a set of initial users; and
training said machine learning algorithm with regard to said plurality of initial data.
8 . The computer-implemented method according to claim 4 , further comprising:
determining subjective data related to said target user, said subjective data comprising perception of the target user to said behavior; and
providing said subjective data related to said target user as an input of said machine learning algorithm.
9 . The computer-implemented method according to claim 4 , wherein said behavior is a change in visual comfort of the target user, said variation of said at least one characteristic being caused by a light stimulus provided to said at least one eye area.
10 . The computer-implemented method according to claim 9 , further comprising determining a plurality of glare classes to classify initial users with respect to light sensitivity, said determining a behavior comprising determining a glare class among the plurality of glare classes corresponding to the behavior of said target user.
11 . The computer-implemented method according to claim 4 , wherein said behavior is a movement of at least one eye of the target user or a dimension of at least one pupil of the target user.
12 . The method according to claim 4 , wherein said at least one characteristic comprising at least one among a position of at least one eyelid, a position of a pupil, a size of the pupil and a muscle contraction in said at least one eye area.