Optimization through use of conductive threads and biometric data

Patent metadata

Field	Value
Publication number	US-10180688-B2
Application number	US-201615180619-A
Country	US
Kind code	B2
Filing date	Jun 13, 2016
Priority date	Jun 13, 2016
Publication date	Jan 15, 2019
Grant date	Jan 15, 2019

Abstract

In a method, a computer receives biometric data from sensors. The computer compares the biometric data to predefined levels of biometric data. The computer determines a score based on the biometric data. The computer compares the score to previously stored scores. The computer sends a score to conductive threads if the score is not acceptable.

First claim

What is claimed is:

1. A method of optimizing a garment being worn by a user, the garment comprising: a plurality of conductive threads forming a fabric, the fabric comprising a plurality of sensors, the method comprising the steps of:
a computer receiving biometric data from the sensors in the garment;
the computer comparing the biometric data received from the sensors to predefined levels of biometric data associated with the user;
the computer determining a comfort score of the garment for the user based on the biometric data, the determining further comprising:
a long short term memory network in communication with the computer receiving a particle defined as the garment being worn by the user and at least one feature of the garment as feature vectors of the garment;
the long short term memory network measuring a quality of each particle in multiple intervals of time by: normalizing feature vectors; converging the feature vectors; applying sigmoid functions to the convergence of the feature vectors; applying memory weights to the convergence of the feature vectors; updating the memory weights to store a state of the particle at an interval of time; and outputting a measure of comfort of the garment relative to the user as a comfort score to the computer;

the computer comparing the comfort score of the garment to previously stored comfort scores; and
if the comfort score is not acceptable for the garment currently being worn by the user, the computer sending a signal to the conductive threads of the garment while being worn by the user to alter a feature of the garment selected from the group consisting of: texture, shape and size.

2. The method of claim 1 , wherein, if the comfort score is acceptable, storing the comfort score of the garment associated with the user in a repository.

3. The method of claim 1 , wherein the garment is worn next to the skin of the user.

4. The method of claim 1 , further comprising the step of receiving biometric data of the user from a mobile device.

5. The method of claim 1 , wherein the conductive threads are made of shape memory materials and alter the shape based on stimuli.

6. The method of claim 5 , wherein the shape memory materials are selected from the group consisting of: shape memory alloys and shape memory polymers.

7. The method of claim 1 , wherein the long short term memory network comprises the computer.

8. A computer program product for optimizing a garment being worn by a user, the garment comprising: a plurality of conductive threads forming a fabric, the fabric comprising a plurality of sensors, a computer comprising at least one processor, one or more memories, one or more computer readable storage media, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by the computer to perform a method comprising:
receiving, by the computer, biometric data from the sensors in the garment;
comparing, by the computer, the biometric data received from the sensors to predefined levels of biometric data associated with the user;
determining, by the computer, a comfort score of the garment for the user based on the biometric data, the determining further comprising:
receiving, by a long short term memory network in communication with the computer, a particle defined as the garment being worn by the user and at least one feature of the garment as feature vectors of the garment;
measuring, by the long short term memory network, a quality of each particle in multiple intervals of time by: normalizing feature vectors; converging the feature vectors; applying sigmoid functions to the convergence of the feature vectors; applying memory weights to the convergence of the feature vectors; updating the memory weights to store a state of the particle at an interval of time; and outputting a measure of comfort of the garment relative to the user as a comfort score to the computer;

comparing, by the computer, the comfort score of the garment to previously stored comfort scores; and
if the comfort score is not acceptable for the garment currently being worn by the user, sending, by the computer, a signal to the conductive threads of the garment while being worn by the user to alter a feature of the garment selected from the group consisting of: texture, shape and size.

9. The computer program product of claim 8 , wherein, if the comfort score is acceptable, storing the comfort score of the garment associated with the user in a repository.

10. The computer program product of claim 8 , wherein the garment is worn next to the skin of the user.

11. The computer program product of claim 8 , further comprising the program instructions of receiving, by the computer, the biometric data of the user from a mobile device.

12. The computer program product of claim 8 , wherein the conductive threads are made of shape memory materials and alter the shape based on stimuli.

13. The computer program product of claim 12 , wherein the shape memory materials are selected from the group consisting of: shape memory alloys and shape memory polymers.

14. The computer program product of claim 8 , wherein the long short term memory network comprises the computer.

15. A computer system for optimizing a garment being worn by a user, the garment comprising: a plurality of conductive threads forming a fabric, the fabric comprising a plurality of sensors, the computer system comprising a computer comprising at least one processor, one or more memories, one or more computer readable storage media having program instructions executable by the computer to perform the program instructions comprising:
receiving, by the computer, biometric data from the sensors in the garment;
comparing, by the computer, the biometric data received from the sensors to predefined levels of biometric data associated with the user;
determining, by the computer, a comfort score of the garment for the user based on the biometric data, the determining further comprising:
receiving, by a long short term memory network in communication with the computer, a particle defined as the garment being worn by the user and at least one feature of the garment as feature vectors of the garment;
measuring, by the long short term memory network, a quality of each particle in multiple intervals of time by: normalizing feature vectors; converging the feature vectors; applying sigmoid functions to the convergence of the feature vectors; applying memory weights to the convergence of the feature vectors; updating the memory weights to store a state of the particle at an interval of time; and outputting a measure of comfort of the garment relative to the user as a comfort score to the computer;

comparing, by the computer, the comfort score of the garment to previously stored comfort scores; and
if the comfort score is not acceptable for the garment currently being worn by the user, sending, by the computer, a signal to the conductive threads of the garment while being worn by the user to alter a feature of the garment selected from the group consisting of: texture, shape and size.

16. The computer system of claim 15 , wherein, if the comfort score is acceptable, storing the comfort score of the garment associated with the user in a repository.

17. The computer system of claim 15 , wherein the garment is worn next to the skin of the user.

18. The computer system of claim 15 , further comprising the program instructions of receiving, by the computer, the biometric data of the user from a mob

Assignees

• IBM

Inventors

• Baughman Aaron K
• Joseph Arun
• O'Connell Brian M
• Pandey Diwesh

Classifications

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title

• A61B5/01

  Measuring temperature of body parts {; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue} (clinical contact thermometers G01K13/20) · CPC title

• A61B5/0537

  Measuring body composition by impedance, e.g. tissue hydration or fat content · CPC title

• A61B5/6804 Primary

  Garments; Clothes · CPC title