Method and wearable device for detecting and verbalizing nonverbal communication
AssigneesThe Regents of the University of California, Chongqing University
InventorsJun Chen, Jin Yang, Zhihao Zhou
Life of this patent
Estimating the term…
Abstract
A triboelectric sensor device with a substantially cylindrical nonconductive core, and a conductive fiber substantially helically disposed around the conductive core and in an axial direction thereof. Example implementations also include a method of extracting communication from body position, by transforming one or more training body position inputs by a principal component analysis, generating training input to a support vector machine (SVM) based on a target body position, and generating one or more SVM classification outputs associated with the target body position.
Claims42
A triboelectric sensor device comprising:
- a substantially cylindrical nonconductive core;
- and
- a conductive fiber substantially helically disposed around the nonconductive core and in an axial direction thereof, wherein the conductive fiber comprises:
- a substantially cylindrical conductive core;
- and
- a nonconductive fiber substantially helically disposed around the conductive core in an axial direction thereof.
A method of manufacturing a deformable sensor array for body position detection, the method comprising:
- twisting a textile fiber around a substantially cylindrical conductive core to form a conductive fiber;
- twisting the conductive fiber around a substantially cylindrical nonconductive core to form a sensor fiber;
- disposing the sensor fiber within a nonconductive sleeve;
- mixing a curing agent with a base monomer to form a nonconductive sleeve material;
- and
- fabricating the nonconductive sleeve from the nonconductive sleeve material,
- wherein the fabricating the nonconductive sleeve comprises degasifying the nonconductive sleeve material in a vacuum.
A method of extracting communication from body position, the method comprising:
- transforming one or more training body position inputs by a principal component analysis, wherein the training body position inputs comprise at least hand gestures associated with sign language expressions;
- generating training inputs to a support vector machine (SVM) based on a target body position;
- and
- generating one or more SVM classification outputs associated with the target body position.
A method of detecting body position by a deformable sensor array, the method comprising:
- deforming a sensor fiber in an axial direction thereof;
- increasing friction contact within the sensor fiber;
- generating a triboelectric voltage at a conductive fiber of the sensor fiber;
- obtaining a body position input based on the triboelectric voltage;
- transforming the body position input based on a principal component analysis;
- classifying body position by a trained SVM to an expression;
- and
- generating a verbal communication based on the classified body position.
Dependencies are inferred from the claim text.