Driver Heartbeat Interval Detection for Rapid Abnormality Signs

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing driver abnormality detection methods face challenges in achieving both high responsiveness and reliability, particularly in detecting short-term changes in driving ability due to conditions like epilepsy or heart attacks, as they are either noise-sensitive or require lengthy data acquisition, leading to unstable results.

Innovation Solution

A method and device that estimate heartbeat intervals, standardize time-series data, and calculate probabilities to detect abnormalities within a predetermined range centered at zero, allowing for quick and reliable detection of driver abnormalities using a processor and heartbeat detection device, even in short time frames.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If heart rate variability analysis using frequency region methods (VLF band or ULF band) is used, then reliability of abnormality detection is improved, but responsiveness deteriorates because longer data acquisition is required

Engineering Contradiction:
Improvereliability of abnormality detectionVSAvoiddata acquisition time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent changes the analysis parameters from frequency region (VLF/ULF bands requiring long data) to time region analysis of heartbeat intervals. By analyzing the distribution of heartbeat interval differences in the time domain and comparing against reference values, the system achieves reliable detection without requiring extended data acquisition periods, thus resolving the contradiction between reliability and responsiveness.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If non-linear analysis of heart rate variability is used, then reliability of detection is improved, but responsiveness deteriorates when long time scales are required for stable results

Engineering Contradiction:
Improvedetection reliabilityVSAvoiddetection speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent transitions from non-linear analysis methods requiring long time scales to a time-region analysis of heartbeat interval distributions. By calculating the distribution of interval differences and comparing against pre-established reference ranges, the system achieves both high detection reliability and rapid responsiveness, eliminating the trade-off between these two parameters.

Inventive Principle:
Principle #35Parameter changes

3Reliability

If driving behavior monitoring is used for abnormality detection, then detection can be performed, but responsiveness deteriorates because monitoring must continue for several minutes to detect changes

Engineering Contradiction:
Improveabnormality detection capabilityVSAvoidmonitoring time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces mechanical/behavioral monitoring (which requires observing driving patterns over several minutes) with a physiological measurement system that analyzes heartbeat intervals. This substitution enables detection of driver abnormalities in real-time or near real-time by measuring autonomic nervous system responses, dramatically reducing the monitoring time required while maintaining or improving detection reliability.

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

Data Source

PatentEP4437941A1Driver abnormality sign detection device
Publication Date: 2024.10.02 MAZDA MOTOR CORP
  • EP4437941A1 patent drawingFigure 1
  • EP4437941A1 patent drawingFigure 2
  • EP4437941A1 patent drawingFigure 3

AI summary

Driver abnormality sign detection method and device are provided that are capable of detecting an abnormality sign of a driver while realizing both of high responsiveness and high reliability.A driver abnormality sign detection method includes a step B of estimating a heartbeat interval BI of a driver based on heartbeats detected by a driver camera, a step C of acquiring time-series data of the heartbeat interval of the driver in a predetermined time period, a step D of standardizing the time-series data of the heartbeat interval, a step E of calculating a probability PA that the standardized heartbeat interval falls within a predetermined range (A region), which has zero as a center, in the time-series data of the standardized heartbeat interval CG-Blz, and a step F of determining that a sign of an abnormality of the driver is detected in a case where the probability PA is greater than a predetermined abnormality sign threshold value TA.