Thermal sensor position detecting device
AssigneeChild Mind Institute, Inc.
InventorCurtis P. White
Life of this patent
Estimating the term…
Abstract
Devices and methods for determining the position of a device relative to a person using the device, or the position of a part of a user's body relative to the user. One or more thermal sensor may be used to determine the relative position of the device or part of the user's body.
Claims20
A device capable of collecting data used to determine an angular position of the device relative to a user of the device, comprising:
- a first sensor configured to detect temperature at a surface of the user's body;
- a non-transitory computer memory;
- one or more processors coupled to the memory;
- computer software stored in the memory and executable by the one or more processors, said computer software comprising instructions for:
- receiving from the first sensor first data corresponding to a first temperature detected when the first sensor is pointed toward the user's body;
- receiving from the first sensor second data corresponding to a second temperature detected when the first sensor is not pointed toward the user's body;
- combining said first data and said second data to produce a combined data set;
- generating a neural network weight from the combined data set using a machine learning algorithm;
- generating a neural network function using the neural network weight, wherein the neural network function is configured to receive as input data corresponding to temperature and output a probability of whether the input data matches the first data;
- receiving from the first sensor third data corresponding to a third temperature;
- inputting the third data to the neural network function to generate a value indicating the extent to which the third data matches the first data.
A method for determining an angular position of a first device relative to a user of the first device, said first device having one or more sensors configured to sense temperature at the surface of the user's body, comprising:
- receiving from a first sensor first data corresponding to a first temperature detected when the first sensor is pointed toward a part of the user;
- receiving from the first sensor second data corresponding to a second temperature detected when the first sensor is not pointed toward said part of the user;
- producing a combined data set by combining said first data and said second data;
- generating a neural network weight from the combined data set using a machine learning algorithm;
- generating a neural network function using the neural network weight, wherein the neural network function is configured to receive as input data corresponding to temperature and output a probability of whether the input data matches the first data;
- receiving from the first sensor third data corresponding to a third temperature;
- inputting the third data to the neural network function to generate a value indicating the extent to which the third data matches the first data.
Dependencies are inferred from the claim text.