Training a neural network for determining correlations between lighting effects and biological states

Patent metadata

Field	Value
Publication number	US-11468662-B2
Application number	US-201916664546-A
Country	US
Kind code	B2
Filing date	Oct 25, 2019
Priority date	Apr 27, 2017
Publication date	Oct 11, 2022
Grant date	Oct 11, 2022

Abstract

Method includes recording biomarker information being indicative of at least one biological state of user remaining in lighting control environment over time frame, biomarker information being generated by at least one physiological sensor remaining with user in lighting control environment over time frame; recording light control settings for at least one light remaining in lighting control environment with user and with physiological sensor generating biomarker information over time frame; and training a neural network to determine correlations between biological state of user remaining in lighting control environment over time frame and lighting effects caused by at least one light remaining in lighting control environment with user over time frame, based on recordings of biomarker information and recordings of light control settings, and utilizing the correlations for controlling the at least one light. Computer readable medium for executing method.

First claim

We claim:

1. A method, comprising:
recording biomarker information being indicative of at least one biological state of a user remaining in a lighting control environment over a time frame, the biomarker information being generated by at least one physiological sensor remaining with the user in the lighting control environment over the time frame;
recording light control settings for at least one light remaining in the lighting control environment with the user and with the at least one physiological sensor generating the biomarker information over the time frame; and
training a neural network to determine correlations between the at least one biological state of the user remaining in the lighting control environment over the time frame and lighting effects caused by the at least one light remaining in the lighting control environment with the user over the time frame, based on the recordings of the biomarker information and the recordings of the light control settings, and utilizing the correlations for controlling the at least one light.

2. A non-transitory computer readable medium having stored thereon processor-executable software instructions that, when executed by a processor, cause the processor to generate control signals for determining correlations between at least one biological state of a user and lighting effects caused by at least one light in a lighting control environment, by executing the steps comprising:
recording biomarker information being indicative of the at least one biological state of a user remaining in a lighting control environment over a time frame, the biomarker information being generated by at least one physiological sensor remaining with the user in the lighting control environment over the time frame;
recording light control settings for at least one light remaining in the lighting control environment with the user and with the at least one physiological sensor generating the biomarker information over the time frame; and
training a neural network to determine correlations between the at least one biological state of the user remaining in the lighting control environment over the time frame and lighting effects caused by the at least one light remaining in the lighting control environment with the user over the time frame, based on the recordings of the biomarker information and the recordings of the light control settings, and utilizing the correlations for controlling the at least one light.

3. The method of claim 1 , wherein the neural network adapts the light control settings for the at least one light in the lighting control environment based on the biomarker information generated by the at least one physiological sensor remaining with the user in the lighting control environment.

4. The method of claim 1 , wherein the neural network adapts the light control settings for the at least one light in the lighting control environment based on feedback on the lighting effects caused by the light control settings being recorded for the at least one light remaining in the lighting control environment over the time frame.

5. The method of claim 1 , wherein determining the correlations includes classifying the lighting effects based on a measurable effect on the user.

6. The method of claim 1 , wherein determining the correlations includes classifying the lighting effects based on a measurable productivity effect or health effect on the user.

7. The method of claim 5 , wherein classifying the lighting effects includes storing the light control settings as being correlated with the lighting effects in a light fixture library.

8. The method of claim 1 , wherein recording the light control settings includes causing the at least one light to generate light varying over the time frame through a range of color, intensity, spectrum, direction, shape, or distance.

9. The non-transitory computer readable medium of claim 2 , wherein the neural network adapts the light control settings for the at least one light in the lighting control environment based on the biomarker information generated by the at least one physiological sensor remaining with the user in the lighting control environment.

10. The non-transitory computer readable medium of claim 2 , wherein the neural network adapts the light control settings for the at least one light in the lighting control environment based on feedback on the lighting effects caused by the light control settings being recorded for the at least one light remaining in the lighting control environment over the time frame.

11. The non-transitory computer readable medium of claim 2 , wherein determining the correlations includes classifying the lighting effects based on a measurable effect on the user.

12. The non-transitory computer readable medium of claim 2 , wherein determining the correlations includes classifying the lighting effects based on a measurable productivity effect or health effect on the user.

13. The non-transitory computer readable medium of claim 11 , wherein classifying the lighting effects includes storing the light control settings as being correlated with the lighting effects in a light fixture library.

14. The non-transitory computer readable medium of claim 2 , wherein recording the light control settings includes causing the at least one light to generate light varying over the time frame through a range of color, intensity, spectrum, direction, shape, or distance.

15. The method of claim 1 , wherein the at least one physiological sensor includes a wearable sensor.

16. The method of claim 1 , wherein the biomarker information is generated by the at least one physiological sensor as including another physiological sensor.

17. The non-transitory computer readable medium of claim 2 , wherein the at least one physiological sensor includes a wearable sensor.

18. The non-transitory computer readable medium of claim 2 , wherein the biomarker information is generated by the at least one physiological sensor as including another physiological sensor.

Assignees

• Korrus Inc

Inventors

• Harrison Benjamin James
• Koparkar Shruti
• Reynoso Mark
• Pickard Paul
• Petluri Raghuram L V
• Vick Gary
• Villegas Andrew

Classifications

• G06F30/13 Primary

  Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads · CPC title

• H04N23/80

  Camera processing pipelines; Components thereof · CPC title

• H04N23/90

  Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G06T15/08

  Volume rendering · CPC title