Respiration Rate Detection Using Histogram Weighting for Motion Artifact Filtering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing devices are not reliable in determining the respiration rate of children due to their fast and irregular breathing patterns, as well as motion artifacts that interfere with sensor signals.

Innovation Solution

A method and apparatus that analyze breathing-related features from sensor signals, such as accelerometers or heart rate sensors, by forming histograms and applying weighting to emphasize the most frequent breath periods, thereby improving the accuracy of respiration rate measurement by considering multiple breathing rates and filtering out motion artifacts.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing devices use simple sensor signals to measure respiration rate, then the device complexity is low, but the measurement precision deteriorates for children due to fast and irregular breathing patterns

Engineering Contradiction:
Improverespiration rate measurement precisionVSAvoidsignal processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the breathing-related signal into multiple candidate breath periods by identifying zero-crossings and peaks/troughs. Each candidate breath period is analyzed separately to determine candidate respiration rates, allowing the system to handle irregular breathing patterns by processing individual breath events rather than assuming regular intervals

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transforms the raw sensor signal into multiple derived parameters including candidate breath periods, candidate respiration rates, and histogram distributions. By changing from a single raw signal to multiple processed parameters, the system can accurately capture fast and irregular breathing patterns characteristic of children's respiration

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If the device uses manual counting method as golden reference, then the measurement precision is high, but the productivity is low due to requiring full minute counting by trained clinician

Engineering Contradiction:
Improverespiration rate accuracyVSAvoidmeasurement speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces the mechanical manual counting method with an automated electronic signal processing system. The processing unit automatically identifies zero-crossings, peaks, and troughs in sensor signals to determine candidate breath periods and respiration rates, eliminating the need for trained clinicians to manually count breaths while maintaining measurement accuracy

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

Solution Approach 2:

The system performs self-service by automatically processing sensor signals to generate respiration rate measurements without requiring human intervention. The processing unit autonomously analyzes candidate breath periods, forms histograms, determines weighted average centers, and outputs final respiration rates, enabling rapid continuous measurements

Inventive Principle:
Principle #25Self-service

3Reliability

If the device processes all candidate breath periods equally, then the calculation is simple, but the reliability deteriorates due to motion artifacts interfering with sensor signals

Engineering Contradiction:
Improverespiration rate detection reliabilityVSAvoidsignal filtering complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent implements feedback by forming a histogram from candidate respiration rates and using the histogram distribution to identify and weight reliable measurements. The weighted average center calculation uses feedback from the histogram shape to determine which candidate rates are most representative, filtering out motion artifact contamination through statistical analysis of the rate distribution

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system changes from processing single candidate rates to analyzing the distribution of multiple candidate rates through histograms. By examining the statistical distribution and applying weighted averaging based on histogram characteristics, the system can distinguish true respiration rates from motion artifacts that appear as outliers in the distribution

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3376953B1Method and apparatus for determining a respiration rate of a subject
Publication Date: 2021.03.31 KONINKLIJKE PHILIPS NV
  • EP3376953B1 patent drawingFigure 1
  • EP3376953B1 patent drawingFigure 2
  • EP3376953B1 patent drawingFigure 3

AI summary

According to an aspect, there is provided a method of determining the respiration rate of a subject, the method comprising obtaining a signal from a sensor that is worn or carried by the subject; analyzing the signal to determine a plurality of values for a breathing-related feature; forming a histogram from the plurality of values for the breathing- related feature, the histogram comprising a plurality of groups, with each group having an associated count that is the number of occurrences of a value or values for the breathing-related feature corresponding to the group; applying a weighting to the count associated with each group to form weighted counts; and determining the respiration rate from a mean of the histogram with the weighted counts.