Wrist Device Algorithm Calibrates Arm Motion Using Torso Reference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional exercise devices face inaccuracies in determining physiological parameters due to the varying motion patterns of sensors attached to different body locations, such as arms and torsos, leading to inconsistent and less accurate results.
Innovation Solution
A wrist device equipped with two algorithms processes acceleration data from both arm and torso motions, using torso data for calibration to correct arm data estimates, thereby improving the accuracy of physiological parameter calculations like speed and energy expenditure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single dedicated algorithm is used for processing acceleration data based on sensor attachment location, then the device complexity is reduced, but the measurement precision deteriorates due to varying motion patterns at different body locations
Solution Approach 1:
The patent implements a universal processing system that can handle acceleration data from multiple sensor attachment locations (arm, torso, foot) using a single multi-functional algorithm. This algorithm automatically adapts to different motion patterns based on the detected attachment location, eliminating the need for multiple dedicated algorithms while maintaining high measurement precision across all locations.
Solution Approach 2:
The processing algorithm is designed to be dynamic and adaptive, automatically adjusting its processing parameters based on the detected motion pattern and sensor attachment location. This allows the single algorithm to optimize its performance for each specific attachment location, resolving the contradiction between simplicity and precision.
2Device complexity
If the sensor attachment location is fixed to a single location with a dedicated algorithm, then the device complexity is minimized, but the adaptability deteriorates when users wear the device at different locations
Solution Approach 1:
The patent creates a universal algorithm that can process acceleration data from any attachment location (arm, torso, foot, or other body parts). The algorithm includes automatic detection capabilities that identify the attachment location and adjust processing parameters accordingly, providing full adaptability without requiring multiple dedicated algorithms or complex configuration settings.
Solution Approach 2:
The processing system automatically detects the sensor attachment location and configures itself without user intervention. The algorithm analyzes the acceleration data patterns to determine which body location the sensor is attached to and automatically selects the appropriate processing mode, making the system self-adapting and eliminating the need for manual configuration.
3Measurement precision
If different algorithms are used for different attachment locations, then the measurement precision is improved, but the device complexity increases due to multiple algorithms and selection mechanisms
Solution Approach 1:
The patent merges multiple location-specific algorithms into a single integrated processing algorithm. This unified algorithm incorporates the processing logic for all attachment locations (arm, torso, foot) within one computational framework, maintaining the precision benefits of location-specific processing while eliminating the complexity of managing multiple separate algorithms.
Solution Approach 2:
The algorithm dynamically adjusts its processing parameters based on the detected attachment location, effectively transforming a single static algorithm into a dynamic multi-functional processor. This allows the system to achieve the precision of multiple dedicated algorithms while maintaining the simplicity of a single algorithm structure.
Data Source
Figure 1A~2
Figure 3~4
Figure 5
AI summary
An apparatus for measuring a physiological parameter of a user is disclosed. The apparatus comprises at least one processor and at least one memory comprising a computer program code comprising program instructions of a first algorithm modelling acquisition of the physiological parameter from motion of a user's arm and program instructions of a second algorithm modelling acquisition of the physiological parameter from motion of the user's torso. The at least one memory and the computer program code are configured, with the at least one processor, to cause the apparatus to: acquire torso acceleration data representing motion of the torso of the user; process the torso acceleration data with the second algorithm; and acquire, from the acceleration data processed with the second algorithm, reference parameters for the first algorithm.