Adaptive Movement Evaluation Algorithm for Sensor Noise
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing movement evaluation systems face reliability issues due to sensor artefacts and quality issues, such as drift and noise in acceleration and air pressure measurements, which can lead to inaccurate fall detection and mobility assessment.
Innovation Solution
A computer-implemented method that adjusts the configuration of the movement evaluation algorithm based on the quality of the measurement signal, including determining decision thresholds and feature weightings, to mitigate the effects of artefacts and noise, ensuring reliable evaluation of movement regardless of signal quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If standard movement evaluation algorithms are used with sensor data, then fall detection and mobility assessment can be performed, but the reliability is reduced due to sensor artefacts and quality issues such as drift and noise
Solution Approach 1:
The patent changes parameters of the movement evaluation algorithm based on the quality measure of the sensor signal. When signal quality deteriorates (e.g., drift or noise increases), the algorithm adjusts parameters such as decision thresholds and feature weightings to maintain reliable fall detection and mobility assessment despite the degraded measurement precision
Solution Approach 2:
The system implements a feedback mechanism where the quality measure of the sensor signal is continuously evaluated and used to dynamically adjust the configuration of the movement evaluation algorithm. This closed-loop approach ensures that the algorithm adapts to changing signal quality conditions, maintaining reliability even when measurement precision varies
2Measurement precision
If sensor quality and calibration are controlled, then measurement accuracy improves, but device complexity and manufacturing constraints increase
Solution Approach 1:
The movement evaluation algorithm performs self-adjustment by automatically modifying its parameters based on the quality measure of the incoming sensor signal. This self-service mechanism eliminates the need for external calibration procedures or complex quality control systems, allowing the algorithm to adapt to different sensor qualities without increasing device complexity
Solution Approach 2:
The system transitions from a static algorithm with fixed parameters to a dynamic algorithm that continuously adapts its configuration based on real-time signal quality assessment. This dynamic approach allows the system to work effectively with varying sensor qualities without requiring multiple dedicated calibration modes or complex control mechanisms
Data Source
AI summary
According to an aspect, there is provided a computer-implemented method for evaluating movement of a subject. The method comprises obtaining a first signal from a first sensor; processing the first signal to determine a value of a quality measure for the first signal; and determining a configuration for a movement evaluation algorithm. The configuration of the movement evaluation algorithm is dependent on the determined value of the quality measure for the first signal such that either or both of a decision threshold of the movement evaluation algorithm is determined based on the determined value of the quality measure; and one or more weightings used in the movement evaluation algorithm for the one or more first features that are to be derived from a signal from the first sensor are determined based on the determined value of the quality measure. A corresponding apparatus and computer program product are also provided.