18205472. ESTIMATING GAIT EVENT TIMES & GROUND CONTACT TIME AT WRIST simplified abstract (Apple Inc.)

ESTIMATING GAIT EVENT TIMES & GROUND CONTACT TIME AT WRIST

Organization Name

Apple Inc.

Inventor(s)

Allison L. Gilmore of Redwood City CA (US)

Adeeti V. Ullal of Emerald Hills CA (US)

Alexander G. Bruno of Cupertino CA (US)

Eugene Song of San Jose CA (US)

Gabriel A. Blanco of San Francisco CA (US)

James J. Dunne of San Francisco CA (US)

João Antunes of Campbell CA (US)

Karthik Jayaraman Raghuram of Foster City CA (US)

Po An Lin of San Jose CA (US)

Richard A. Fineman of Campbell CA (US)

William R. Powers, Iii of San Francisco CA (US)

Asif Khalak of Belmont CA (US)

ESTIMATING GAIT EVENT TIMES & GROUND CONTACT TIME AT WRIST - A simplified explanation of the abstract

This abstract first appeared for US patent application 18205472 titled 'ESTIMATING GAIT EVENT TIMES & GROUND CONTACT TIME AT WRIST

Simplified Explanation

The abstract describes a patent application for estimating gait time events and GCT (Ground Contact Time) using a wrist-worn device. The method involves obtaining sensor data related to acceleration and rotation rate from the device and using a machine learning model to predict gait event times based on this data.

• The patent application focuses on estimating gait time events and GCT using a wrist-worn device.
• The method involves obtaining sensor data related to acceleration and rotation rate from the device.
• A machine learning model is used to predict at least one gait event time based on the sensor data.
• The acceleration and rotation rate serve as input to the machine learning model.

Potential Applications

• Fitness tracking devices that can provide accurate gait analysis and performance metrics.
• Rehabilitation devices that can monitor and analyze gait patterns for patients recovering from injuries or surgeries.
• Sports training devices that can provide real-time feedback on gait performance and help improve technique.

Problems Solved

• Accurately estimating gait time events and GCT using a wrist-worn device.
• Overcoming the limitations of existing methods that may require specialized equipment or be less portable.
• Providing a convenient and accessible solution for monitoring and analyzing gait patterns.

Benefits

• Improved accuracy in estimating gait time events and GCT.
• Increased convenience and portability with a wrist-worn device.
• Potential for real-time feedback and analysis, leading to better gait performance and technique.

Original Abstract Submitted

Enclosed are embodiments for estimating gait time events and GCT using a wrist-worn device. In some embodiments, a method comprises: obtaining, with at least one processor of a wrist-worn device, sensor data indicative of acceleration and rotation rate; and predicting, with the at least one processor, at least one gait event time based on a machine learning (ML) model with the acceleration and rotation rate as input to the ML model.