View source for 18099187. SYSTEM AND METHOD FOR LEARNING RELATIONSHIPS BETWEEN PHYSIOLOGICAL SIGNALS AND PSYCHOLOGICAL STATE TO PREDICT INDIVIDUAL BEHAVIOR simplified abstract (TOYOTA RESEARCH INSTITUTE, INC.)

=SYSTEM AND METHOD FOR LEARNING RELATIONSHIPS BETWEEN PHYSIOLOGICAL SIGNALS AND PSYCHOLOGICAL STATE TO PREDICT INDIVIDUAL BEHAVIOR=


==Organization Name==

[[:Category:TOYOTA RESEARCH INSTITUTE, INC.|TOYOTA RESEARCH INSTITUTE, INC.]]


[[Category:TOYOTA RESEARCH INSTITUTE, INC.]]

==Inventor(s)==

[[:Category:Shabnam Hakimi of San Francisco CA (US)|Shabnam Hakimi of San Francisco CA (US)]][[Category:Shabnam Hakimi of San Francisco CA (US)]]

[[:Category:Charlene Wu of San Francisco CA (US)|Charlene Wu of San Francisco CA (US)]][[Category:Charlene Wu of San Francisco CA (US)]]

[[:Category:Yanxia Zhang of Foster City CA (US)|Yanxia Zhang of Foster City CA (US)]][[Category:Yanxia Zhang of Foster City CA (US)]]

==SYSTEM AND METHOD FOR LEARNING RELATIONSHIPS BETWEEN PHYSIOLOGICAL SIGNALS AND PSYCHOLOGICAL STATE TO PREDICT INDIVIDUAL BEHAVIOR - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18099187 titled 'SYSTEM AND METHOD FOR LEARNING RELATIONSHIPS BETWEEN PHYSIOLOGICAL SIGNALS AND PSYCHOLOGICAL STATE TO PREDICT INDIVIDUAL BEHAVIOR

The abstract describes a method for predicting learned behavior based on physiological data from different modalities, grouping the data by similar behaviors, learning a shared latent space, and utilizing a behavior prediction engine to predict future behavior.

* Physiological data from various modalities is received.
* The data is grouped based on similar behaviors.
* A shared latent space is learned by a transfer function learner.
* Embeddings from different modalities are grouped in the latent space according to similar behaviors.
* A behavior prediction engine uses the trained transfer function learner to predict an individual's future behavior based on physiological data and a user-specified prediction model.

Potential Applications:
- Personalized healthcare monitoring
- Behavioral analysis in psychology
- Predictive maintenance in industrial settings

Problems Solved:
- Predicting future behavior based on physiological data
- Grouping data from different modalities to enhance prediction accuracy

Benefits:
- Improved accuracy in predicting learned behavior
- Personalized behavior prediction for individuals
- Enhanced understanding of behavior patterns

Commercial Applications:
Predictive analytics software for healthcare providers to monitor patient behavior and predict health outcomes.

Questions about the technology:
1. How does the shared latent space improve behavior prediction accuracy?
2. What are the potential limitations of this method in real-world applications?


==Original Abstract Submitted==

A method for learned behavior prediction is described. The method includes receiving physiological data from a plurality of different modalities. The method also includes grouping the received physiological data by corresponding, similar behaviors. The method further includes learning, by a transfer function learner, a shared latent space, in which embeddings from the different modalities are grouped according to the similar behaviors. The method also includes utilizing, by a behavior prediction engine, a trained, transfer function learner to predict an individual's future behavior based on an input of physiological data and a user-specified prediction model.



[[Category:A61B5/0205]]
[[Category:A61B5/00]]
[[Category:CPC_A61B5/0205]]