Home Patent Forecast® Sectors Log In   Contact  
How it works Patent Forecast® Sectors Insights
Menu

Patent US10136852
Facense

Detecting An Allergic Reaction From Nasal Temperatures

Described herein are systems and methods for personalized detection of an allergic reaction of a user. In one embodiment, a system includes an inward-facing head-mounted thermal camera (CAM) and a computer. CAM takes thermal measurements of a region on the nose (THN) of a user. The computer generates feature values based on THN and utilizes a model to detect an allergic reaction of the user based on the feature values. The model is trained based on previous THN of the user taken during different days. Some embodiments may utilize additional thermal cameras that take thermal measurements of other regions on the face, which may be utilized by the computer to generate additional feature values that are used to detect the allergic reaction. In some cases, detection of the allergic reaction may occur following a rise in nasal temperature, even before the user becomes aware of the allergic reaction.

Much More than Average Length Specification


1 Independent Claims

  • Claim CLM-00001. 1. A system configured to detect allergic reaction, comprising: an inward-facing head-mounted thermal camera (CAM) configured to take thermal measurements of a region on the nose (THN) of a user; and a computer configured to: generate feature values based on THN, and utilize a machine learning-based model to detect an allergic reaction of the user based on the feature values; wherein the machine learning-based model was trained based on previous THN taken during different days.
  • Claim CLM-00013. 13. A method for performing a personalized detection of an allergic reaction, comprising: taking thermal measurements of a region on the nose (THN) of a user utilizing an inward-facing head-mounted thermal camera; generating feature values based on THN; and utilizing a machine learning-based model for detecting an allergic reaction of the user based on the feature values; wherein the machine learning-based model was trained based on previous THN taken during different days.


View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >



Patent Matrix® Search


USPTO Patent Document Number