IDENTIFICATION OF EMOTIONAL STATES USING PHYSIOLOGICAL RESPONSES

• US 20080221401A1
• Filed: 10/26/2007
• Published: 09/11/2008
• Est. Priority Date: 10/27/2006
• Status: Active Grant

• Current Assignee: Adidas AG
• Original Assignee: Adidas AG
• Inventors: Derchak, P. Alexander, Myers, Lance Jonathan
• Granted Patent: US 9,833,184 B2
• Time in Patent Office: Days
• US Class Current: 600/301
• CPC Class Codes: A61B 5/16 Devices for psychotechnics using teaching or educational appliances G09B1/00 - G09B7/00; Testing reaction times ; Devices for evaluating the psychological state
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: A61B 5/6805 Vests
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G06F 2203/011 Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns
• CPC Class Codes: G06F 2203/014 Force feedback applied to GUI
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

The invention provides a method for automatically identifying emotional states of a person in real-time based on physiological responses by exposing a person to a stimulus, measuring the person'"'"'s physiological response to the stimulus, and comparing the measured physiological response to a known baseline physiological. The deviation of the measured physiological response from the baseline physiological response is determinative of the emotional state.

Claims

1. A method for automatically identifying a likely emotional state in real-time comprising:

exposing a person to a stimulus;

measuring the person'"'"'s physiological responses to the stimulus;

comparing the measured physiological responses to baseline physiological responses; and

identifying a likely emotional state in dependence on the pattern of deviations of the measured physiological responses from the baseline physiological responses.

2. The method of claim 1, wherein the baseline physiological responses are measured in the person when exposed to a neutral stimulus.

3. The method of claim 1, wherein the measured physiological responses comprise one or more respiratory responses.

4. The method of claim 3, wherein the measured respiratory responses comprise a measure of breath to breath variability.

5. The method of claim 4, wherein the measure of breath to breath variability comprises a sample entropy.

6. The method of claim 4, wherein the measured respiratory responses comprise a respiratory rate, a minute ventilation rate, a tidal volume, a tidal volume instability, an inspiratory flow rate, an expiratory flow rate, an inspiratory pause, and expiratory pause, a presence of cough, and presence of apnea or hypopnea, or a combination thereof.

7. The method of claim 1, wherein the measured physiological responses further comprise a cardiac response, a posture/activity response, a temperature response, a galvanic skin response, an EEG response, an EOG response, an EMG response, and a vocal response, or a combination thereof.

8. The method of claim 7, wherein the cardiac responses comprise an ECG response, an RSA response, a heart rate response, and a heart rate variability response, or a combination thereof.

9. The method of claim 1, wherein the emotional state comprises neutrality or indifference, fear, anxiety, excitement, happiness, sadness, attentiveness, anticipation, boredom, anger, pleasure, or calmness, or a combination thereof.

10. The method of claim 1, wherein the emotional state comprises a measure of the degree to which the person is engaged with, concentrated on, or focused on the stimulus.

11. The method of claim 1, wherein the baseline physiological responses are measured in the person when exposed to a stimulus known as likely to elicit a selected emotional state, and wherein the emotional state of the person is subsequently identified as likely to be the selected emotional state when the measured physiological responses significantly similar to the baseline physiological responses.

12. The method of claim 11 wherein two sets of responses are significantly similar when the likelihood that the similarity is due to chance is less than a selected threshold.

13. A monitoring system for automatically identifying an emotional state of a person in real-time, comprising:

a processor;

a computer readable memory operatively coupled to the processor and configured with instructions for causing the processor to perform the method of claim 1; and

a physiological monitoring device operatively coupled to the processor for measuring the person'"'"'s physiological response, the device being configured and arranged for monitoring an ambulatory subject.

14. The monitoring system of claim 13, wherein the processor correlates the time of exposure to the stimulus and the type of stimulus with the measured physiological response.

15. A method for automatically identifying an emotional state of a person in real-time, comprising:

exposing a person to a stimulus;

measuring the person'"'"'s physiological responses to the stimulus;

classifying the measured responses into one or more classes by means of a classifier trained to recognize patterns of physiological responses occurring in a plurality of emotional states; and

identifying a likely emotional state in dependence on the classes into which the measured responses have been classified.

16. The method of claim 15 wherein a pattern of measured physiological responses comprises deviations of the measured responses from baseline physiological responses, the baseline physiological responses characteristic of an emotional state.

17. The method of claim 15, wherein classifier training further comprises:

measuring physiological responses one or more emotional states determining feature vectors that characterize the emotional states; and

grouping the determined feature vectors into groups that characterize the emotional states, the grouping comprising use of a learning algorithm.

18. The method of claim 17, further comprising scaling the determined feature vectors, or applying dimension-reduction analysis to the determined feature vectors, or both scaling and applying dimension-reduction analysis to the determined feature vectors.

19. The method of claim 17, wherein the learning algorithm comprises a kernel machine algorithm.

20. The method of claim 17, wherein classifying further comprises:

extracting the determined feature vectors from the measured physiological responses, the determined feature vectors being those determined during classifier training; and

applying the trained classifier to the extracted feature vectors.

21. The method of claim 20 further comprising scaling the extracted feature vectors, or applying dimension-reduction analysis to the extracted feature vectors, or both scaling and applying dimension-reduction analysis to the extracted feature vectors.