FUNCTIONAL THRESHOLD POWER PREDICTION USING MACHINE LEARNING

Organization Name

apple inc.

Inventor(s)

Julia K. Nichols of Alameda CA (US)

James P. Ochs of San Francisco CA (US)

Gregory Darnell of Palo Alto CA (US)

You Ren of Seattle WA (US)

Agni Kumar of Milton GA (US)

En-Tzu Yang of Cupertino CA (US)

Eshika Manchanda of Cupertino CA (US)

Britni O. Chau of Cupertino CA (US)

Riley Roberts of Cupertino CA (US)

FUNCTIONAL THRESHOLD POWER PREDICTION USING MACHINE LEARNING - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240374164 titled 'FUNCTIONAL THRESHOLD POWER PREDICTION USING MACHINE LEARNING

The subject technology provides a framework for generating physiological predictions for a user of an electronic device. The physiological predictions may include user-specific predictions of functional threshold power (FTP) that may occur if the user engages in a future activity, such as a future workout. The FTP predictions may be generated by a machine learning model that utilizes user-specific and user-agnostic physiological measures such as VO2 max to generate multiple FTP estimates according to different physiological approaches in calculating the FTP estimates and arbitrating between the FTP estimates to make the prediction with the best FTP estimate.

Machine learning model used to generate physiological predictions
User-specific and user-agnostic physiological measures utilized
Predictions include user-specific FTP estimates for future activities
Multiple FTP estimates generated based on different physiological approaches
Best FTP estimate selected through arbitration process

Potential Applications: - Personalized fitness training programs - Health monitoring and optimization - Performance enhancement in sports and athletics

Problems Solved: - Lack of personalized physiological predictions for users - Difficulty in optimizing workouts and activities based on individual physiology

Benefits: - Improved performance outcomes - Enhanced user experience and engagement - Tailored fitness and health recommendations

Commercial Applications: Title: Personalized Fitness Prediction Technology This technology can be used in fitness apps, wearable devices, and online training platforms to offer personalized workout recommendations and performance predictions. It can also be integrated into sports training programs and health monitoring systems for enhanced results and user satisfaction.

Prior Art: Prior research in the field of personalized fitness training and physiological predictions may provide insights into similar technologies and approaches.

Frequently Updated Research: Ongoing studies in machine learning algorithms for physiological data analysis and personalized health predictions may contribute to the advancement of this technology.

Questions about Personalized Fitness Prediction Technology: 1. How does this technology improve user engagement and motivation in fitness activities? 2. What are the potential privacy concerns associated with collecting and analyzing user-specific physiological data for predictions?

Original Abstract Submitted

the subject technology provides a framework for generating physiological predictions for a user of an electronic device. the physiological predictions may include user-specific predictions of functional threshold power (ftp) that may occur if the user engages in a future activity, such as a future workout. the ftp predictions may be generated by a machine learning model that utilizes user-specific and user-agnostic physiological measures such as vo2 max to generate multiple ftp estimates according to different physiological approaches in calculating the ftp estimates and arbitrating between the ftp estimates to make the prediction with the best ftp estimate.