Method for estimating human emotions using deep psychological affect network and system therefor
AssigneeKorea Advanced Institute of Science and Technology
InventorsSungho Jo, Byung Hyung Kim
Life of this patent
Estimating the term…
Abstract
Disclosed are a method and a system for estimating human emotions using a deep psychological affect network for human emotion recognition. According to an embodiment of the present disclosure, a method for estimating emotion includes obtaining a physiological signal of a user, learning a network, which receives the obtained physiological signal, by using a temporal margin-based classification loss function considering a temporal margin, when the learning is in progress along a time axis, and estimating an emotion of the user through the learning of the network using the temporal margin-based classification loss function.
Claims17
A method for estimating emotion, the method comprising:
- obtaining a physiological signal of a user;
- learning a network, which receives the obtained physiological signal, by using a temporal margin-based classification loss function which is defined based on a temporal margin, when the learning is in progress along a time axis wherein the temporal margin is defined over time between two time points along the time axis;
- and
- estimating an emotion of the user through the learning of the network using the temporal margin-based classification loss function.
A method of estimating emotion, the method comprising:
- providing a temporal margin-based classification loss function which is defined based on a temporal margin, when learning is in progress along a time axis wherein the temporal margin is defined over time between two time points along the time axis;
- and
- estimating an emotion of a user through learning using the temporal margin-based classification loss function.
An emotion estimating system comprising:
- an obtainment unit configured to obtain a physiological signal of a user;
- a learning unit configured to learn a network, which receives the obtained physiological signal, by using a temporal margin-based classification loss function which is defined based on a temporal margin, when learning is in progress along a time axis wherein the temporal margin is defined over time between two time points along the time axis;
- and
- an estimation unit configured to estimate an emotion of the user through the learning of the network using the temporal margin-based classification loss function.
A method for estimating emotion, the method comprising:
- obtaining a physiological signal of a user;
- and
- estimating an emotion of the user corresponding to the physiological signal by using a temporal margin-based classification loss function which is defined based on a temporal margin, wherein the temporal margin is defined over time between two time points.
Dependencies are inferred from the claim text.