Ambulation Detection via Orthogonal Motion Component Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for detecting ambulation motion, particularly in elderly or sick individuals who walk slowly, are inaccurate due to reliance on comparison of acceleration magnitudes to thresholds, which fail to account for slow movements effectively.

Innovation Solution

A processing apparatus that extracts orthogonal motion components from high-pass filtered accelerometer data, compares their direction to the gravity component, and classifies motion as ambulation using source-separation techniques like blind source separation and independent component analysis, allowing for accurate detection of slow ambulation without prior knowledge of the gravity vector.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If acceleration magnitude comparison to thresholds is used for ambulation detection, then the detection method is simple, but the detection accuracy deteriorates for slow walking

Engineering Contradiction:
Improvedetection method complexityVSAvoidambulation detection accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The accelerometer data is segmented into orthogonal motion components (vertical, anterior-posterior, medio-lateral) that represent different directions of movement. This segmentation allows the system to analyze specific motion patterns characteristic of ambulation rather than relying on overall acceleration magnitude, thereby improving detection accuracy for slow walking while maintaining computational simplicity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The invention transitions from analyzing acceleration magnitude (scalar) to analyzing motion components in multiple orthogonal dimensions (vector decomposition). By examining the directional characteristics of motion components relative to the gravity vector, the system can detect ambulation patterns more accurately, especially for slow walking where magnitude-based methods fail.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Measurement precision

If source-separation techniques are used to extract motion components, then the precision of motion component identification is improved, but the computational complexity increases

Engineering Contradiction:
Improvemotion component identification precisionVSAvoidsignal processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The invention extracts orthogonal motion components from the raw accelerometer signal using source-separation techniques. By separating the vertical, anterior-posterior, and medio-lateral motion components, the system can identify ambulation-specific patterns with high precision. The extraction focuses on isolating the relevant motion signals from the composite accelerometer data.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The invention transforms the accelerometer data by applying high-pass and low-pass filters to isolate different frequency components, then decomposes the signal into orthogonal motion components. This parameter transformation approach converts the raw acceleration signal into meaningful motion characteristics that can be accurately classified for ambulation detection.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If gravity component determination is performed to compare motion directions, then the accuracy of ambulation classification is improved, but the processing time increases

Engineering Contradiction:
Improveambulation classification accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The gravity component is determined in advance through low-pass filtering of the accelerometer data, establishing a reference direction before ambulation detection begins. This preliminary determination of the gravity vector allows for rapid comparison with motion components during actual ambulation detection, reducing real-time processing requirements while maintaining high classification accuracy.

Inventive Principle:
Principle #10Preliminary action

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

Enables reliable detection of slow ambulation motions, improving the interpretation of vital signs and enabling auto-calibration, with enhanced precision and accuracy in identifying motion components, even in non-clinical settings.

Implementation Method 1

obtaining accelerometer data indicative of a trunk motion of the subject

Methodology Applied
Scientific EffectAccelerometer: Accelerometer

Implementation Method 2

performing a high pass filter on the accelerometer data to obtain high-pass filtered accelerometer data

Methodology Applied
Scientific EffectHigh-pass filter: Filter (electronic)

Implementation Method 3

performing a low-pass filter on the accelerometer data to obtain low-pass filtered accelerometer data; determining a gravity component from the low-pass filtered accelerometer data

Methodology Applied
Scientific EffectLow-pass filter: Filter (electronic)

Data Source

PatentEP3442403B1Processing apparatus and method for determining an ambulation motion of a subject
Publication Date: 2019.10.09 KONINKLIJKE PHILIPS NV
  • EP3442403B1 patent drawingFigure 1~2
  • EP3442403B1 patent drawingFigure 3~4B
  • EP3442403B1 patent drawingFigure 5A~5F

AI summary

The present invention relates to a processing apparatus (10), system (1) and method (20) for determining an ambulation motion of a subject. Advantageously also a slow ambulation motion may be detected. The processing apparatus is configured to perform the steps of obtaining accelerometer data indicative of a trunk motion of the subject; extracting one or more orthogonal motion components from high-pass filtered accelerometer data; determining a gravity component from low-pass filtered accelerometer data; comparing a direction of at least one of said orthogonal motion components with a direction of the gravity component; and classifying a motion of the subject as ambulation if said motion component is orthogonal or parallel to said gravity component.