Pulse Wave Fatigue Assessment Using Systolic Posterior Component Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing human fatigue assessment methods using pulse wave signals face challenges in accuracy due to influences from factors other than fatigue, and real-time analysis is difficult, especially with complex chaos analysis, which increases computational load. Additionally, previous methods lack clear supporting data for state determination, making the assessment of fatigue states arbitrary.
Innovation Solution
A human fatigue assessment device that measures pulse wave signals, extracts feature values from the systolic posterior component, and compares them to stored values to determine fatigue, using components like the c wave and d wave to reduce influence from factors other than fatigue, improving accuracy and enabling real-time analysis. The device also determines fatigue type as due to difficult work or monotonous work based on parasympathetic nerve activity and brain signal analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If chaos analysis is performed on the accelerated plethysmogram to reduce influence from factors other than fatigue, then measurement precision is improved, but device complexity and computational load increase making real-time analysis difficult
Solution Approach 1:
The patent extracts only the necessary feature values (peak values of a wave to e wave, and maximal Lyapunov exponent) from the pulse wave signal for fatigue assessment, rather than performing complete chaos analysis on the entire signal. This selective extraction reduces computational complexity while maintaining the ability to assess fatigue accurately by focusing on the most relevant parameters.
Solution Approach 2:
The patent segments the pulse wave signal into distinct waveform components (a wave, b wave, c wave, d wave, e wave) and analyzes each component separately to extract specific feature values. This segmentation allows for targeted analysis of fatigue-related characteristics without processing the entire signal, reducing overall computational load while preserving measurement precision.
2Ease of operation
If conventional pulse wave assessment methods are used, then ease of operation is maintained, but measurement precision deteriorates due to influence from factors other than fatigue
Solution Approach 1:
The patent introduces an automated analysis unit that acts as an intermediary between the simple pulse wave measurement and the complex fatigue assessment. This unit automatically performs feature extraction, chaos analysis, and fatigue determination based on extracted features, maintaining ease of operation for the user while achieving high measurement precision through sophisticated analysis algorithms.
3Ease of operation
If feature values from the entire pulse wave signal are used for assessment, then ease of operation is maintained, but measurement precision deteriorates due to confounding factors
Solution Approach 1:
The patent applies local quality by focusing analysis on specific portions of the pulse wave signal (systolic posterior component including c wave and d wave) rather than the entire signal. This localized approach isolates fatigue-related features from confounding factors present in other parts of the waveform, improving measurement precision while maintaining operational simplicity through automated regional analysis.
Data Source
Figure 1
Figure 2A~2B
Figure 3A~3B
AI summary
A human fatigue assessment device capable of performing highly accurate fatigue assessment is provided. The human fatigue assessment device (100) includes: a physiological signal measuring unit (101) which measures a pulse wave signal of a user; a feature value extracting unit (102) which extracts first feature values each of which is obtained from a systolic posterior component of the pulse wave signal measured by the physiological signal measuring unit (101); a storage unit (103) in which the first feature values extracted by the feature value extracting unit (102) are stored; and a fatigue determining unit (104) which determines whether or not the user is fatigued, using the first feature values extracted by the feature value extracting unit (102), in which the fatigue determining unit (104) compares a first feature value among the first feature values extracted by the feature value extracting unit (102) and at least one of the first feature values stored in the storage unit (103), to determine whether or not the user is fatigued.