Respiratory Signal Extraction from 3-Axis Acceleration

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing respiratory monitoring systems for ambulatory patients are cumbersome, require controlled sensor attachment and orientation, and suffer from estimation errors and computational complexity, limiting their robustness and applicability.

Innovation Solution

A processor that isolates a gravity vector from a 3-axis acceleration signal, performs a coordinate transformation to a transformed 3-axis coordinate system, and analyzes the remaining two axes to derive a 1-dimensional respiratory signal, simplifying processing and increasing robustness by projecting into a 2D plane, which is then used for respiratory rate determination and sleep disordered breathing event detection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional respiratory monitoring sensors (thorax impedance plethysmography, respiration band) are used, then measurement precision is improved, but device complexity and ease of operation deteriorate due to obtrusive design and controlled attachment requirements

Engineering Contradiction:
Improverespiratory signal accuracyVSAvoidsensor attachment convenience
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces traditional mechanical respiratory monitoring systems (impedance plethysmography, respiration bands) with an accelerometer-based system that measures chest wall acceleration. This substitution eliminates the need for obtrusive sensors and controlled attachment, allowing free placement on the chest while maintaining respiratory monitoring capability through acceleration signal analysis

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The accelerometer serves multiple functions: it measures respiratory motion, determines gravity vector for coordinate transformation, and provides data for both respiratory rate and sleep disordered breathing event detection. This multi-functionality simplifies the overall system while maintaining measurement precision

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Measurement precision

If prior knowledge about sensor orientation is required for respiratory rate determination, then measurement precision is improved, but adaptability deteriorates due to controlled attachment location and orientation requirements

Engineering Contradiction:
Improverespiratory rate accuracyVSAvoidsensor placement freedom
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary coordinate transformation to align the accelerometer's coordinate system with the gravity vector before processing respiratory signals. This preliminary alignment action eliminates the need for controlled sensor orientation during placement, as the software automatically adapts to any initial orientation by referencing the gravity vector

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The coordinate system dynamically adapts to the sensor's actual orientation by using the gravity vector as a reference. This dynamic adjustment allows the system to maintain measurement precision regardless of how the sensor is placed on the patient's chest

Inventive Principle:
Principle #15Dynamics

3Measurement precision

If 3D acceleration analysis is performed to derive respiratory signal, then measurement precision is improved, but computational complexity increases

Engineering Contradiction:
Improverespiratory signal accuracyVSAvoidprocessing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts and removes the gravity vector component from the 3-axis acceleration signal before processing. By separating the gravity component (which is constant or slowly varying) from the respiratory signal components, the system reduces computational complexity in subsequent processing steps while maintaining accuracy

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The processing is segmented into distinct stages: gravity vector isolation, coordinate transformation, and respiratory signal extraction from the remaining two axes. This segmentation allows each stage to be optimized independently, reducing overall computational complexity

Inventive Principle:
Principle #1Segmentation

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The solution enables reliable respiratory monitoring without requiring specific sensor attachment or orientation, reduces computational complexity, and enhances the accuracy of respiratory rate estimation and sleep disordered breathing event detection.

Implementation Method 1

an accelerometer for generating a 3-axis acceleration signal

Methodology Applied
Scientific EffectAccelerometer: Accelerometer

Data Source

PatentEP4216812B1A processor and method for determining a respiratory signal
Publication Date: 2025.11.26 KONINKLIJKE PHILIPS NV
  • EP4216812B1 patent drawingFigure 1
  • EP4216812B1 patent drawingFigure 2
  • EP4216812B1 patent drawingFigure 3

AI summary

A processor and method for deriving a respiratory signal is based on processing a 3-axis acceleration signal. A gravity vector is isolated from the 3-axis acceleration signal and a coordinate transformation is performed into a transformed 3-axis coordinate system in which the isolated average gravity vector is aligned with a first axis of the transformed 3-axis coordinate system. Analysis is then performed only of the components for the remaining two axes of the transformed 3-axis coordinate system, thereby to derive a 1 dimensional respiratory signal. A respiration rate may for example be obtained from the 1 dimensional respiratory signal using frequency analysis, or sleep disordered breathing events may be identified.