Wearable Oxygen Uptake Prediction via Machine Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for accurately estimating oxygen uptake (VO2) and its maximum (VO2Max) require expensive equipment and physically demanding exercise protocols, making them costly and inefficient for widespread use, especially in wearable devices with memory constraints.

Innovation Solution

A machine learning-based method that uses a wearable device to predict oxygen uptake in proportion to VO2Max (% VO2Max) during walking or running sessions, employing user profile data, heart rate, speed, and step frequency signals, with a combination of machine learning approaches like multilayer perceptron, extra trees regressor, and linear regressor, and includes light filtering and post-processing to handle anomalies and noise.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If direct measurement methods are used to accurately estimate VO2 and VO2Max, then measurement precision is improved, but device cost and complexity increase significantly

Engineering Contradiction:

ImproveVO2 measurement accuracyVSAvoidequipment complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces direct mechanical/physical measurement systems (gas exchange analysis equipment) with a machine learning-based computational system that processes physiological signals (heart rate, speed, step frequency) to estimate VO2 and VO2Max indirectly, thereby reducing device complexity while maintaining reasonable measurement accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces machine learning models as intermediary components that translate easily measurable parameters (heart rate, speed, step frequency) into estimates of VO2 and VO2Max, serving as a bridge between simple sensor measurements and complex physiological metrics without requiring direct measurement of gas exchange

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If exhaustive exercise protocols are used to reach VO2Max, then measurement precision is improved, but user physical burden increases

Engineering Contradiction:

ImproveVO2Max measurement accuracyVSAvoidexercise protocol ease

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent applies partial action by using submaximal exercise protocols instead of requiring users to reach true VO2Max through exhaustive exercise. The machine learning model is trained on data from maximal tests but can accurately estimate VO2Max from submaximal performance, reducing user burden while maintaining measurement precision

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The patent performs preliminary action by pre-training machine learning models using data from exhaustive exercise protocols. This allows the system to learn the relationship between exercise parameters and VO2Max in advance, so that during actual use, users only need to perform light exercise while the pre-trained model provides accurate estimates

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If reference equipment is used for direct gas exchange measurement, then measurement precision is improved, but cost increases

Engineering Contradiction:

ImproveVO2 measurement accuracyVSAvoidsystem cost

Core Design Contradiction:

Measurement precisionVSEase of manufacture

Solution Approach 1:

The patent replaces expensive, complex reference equipment with inexpensive wearable sensors and computational algorithms. The system uses low-cost components (heart rate sensor, speed sensor, step frequency detector) combined with machine learning to achieve accurate VO2 estimation, dramatically reducing system cost while maintaining reasonable precision

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

4Device complexity

If machine learning models are used to estimate % VO2Max, then device complexity is reduced, but measurement precision may deteriorate

Engineering Contradiction:

Improvesystem simplicityVSAvoidVO2 prediction accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent changes parameters by selecting and optimizing specific input features (heart rate, speed, step frequency) and adjusting machine learning model parameters through training on labeled datasets. This allows the system to achieve high prediction accuracy despite using simple, low-complexity computational approaches

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20230191195A1Computer implemented method and wearable electronic system for predicting the oxygen uptake during an exercise, and, non-transitory computer readable storage medium

Publication Date: 2023.06.22 SAMSUNG ELECTRONICSA AMAZONIA LTDA

AI summary

A computer implemented method for predicting the oxygen uptake (% VO2Max) during an exercise of a user in proportion to the user's maximum oxygen uptake through a wearable device. The method comprising obtaining information from a user profile, capturing at least three temporal input data from a user during an exercise, using the information from a user profile and the at least three temporal input data to extract features to compose features vectors, identifying the exercise being performed by the user based on the feature vectors, selecting a predictor model to compute predictions for the % VO2Max from the user based on the exercise being performed, and predicting the % VO2Max from the user based on the selected predictor model.