Fatigue Estimation via Activity-State Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fatigue level estimation methods face challenges in accurately estimating fatigue levels due to fluctuations in biological data caused by the autonomic nervous system and activity states, making it difficult to obtain reproducible data.
Innovation Solution
A fatigue level estimation apparatus and method that extracts biological data during a specific activity state, calculates feature values from this data, and uses machine learning models to estimate fatigue levels, ensuring data stability and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If biological data is obtained from a subject in various activity states, then the quantity of available data increases, but the reliability of fatigue level estimation deteriorates due to fluctuations caused by autonomic nervous system and activity state variations
Solution Approach 1:
The patent segments the biological data based on activity states detected by the activity state detection unit. By dividing the data into distinct segments corresponding to different activity states (e.g., resting, exercising, sleeping), the system can selectively process only the segments that meet the predetermined criteria for reliable fatigue estimation, thus resolving the contradiction between data quantity and reliability.
Solution Approach 2:
The patent changes the parameter of data selection by introducing activity state as a filtering criterion. The biological data extraction unit uses the activity state detection results to determine whether to extract or discard specific data segments. This parameter change allows the system to maintain high reliability by selecting only data from appropriate activity states while still utilizing available biological data.
2Ease of operation
If biological data is obtained without considering activity state, then the ease of data collection improves, but the measurement precision of fatigue level deteriorates due to confounding variables
Solution Approach 1:
The patent introduces an intermediary component - the activity state detection unit - that mediates between the biological data collection and the fatigue level estimation. This intermediary detects the activity state and provides guidance to the biological data extraction unit on which data to select. This approach maintains ease of operation by automatically handling the selection process without requiring manual intervention, while simultaneously improving measurement precision by filtering out data from inappropriate activity states.
3Productivity
If all biological data is used for fatigue level estimation, then the productivity of the estimation process improves, but the manufacturing precision of the estimation result deteriorates due to inclusion of irrelevant data components
Solution Approach 1:
The patent applies preliminary action by performing activity state detection and data selection before the fatigue level estimation process. The biological data extraction unit pre-processes the biological data by filtering it based on activity state criteria before the estimation algorithm is applied. This preliminary filtering action ensures that only relevant data is used in the estimation process, improving precision without significantly impacting productivity since the filtering is automated and integrated into the data pipeline.
Data Source
AI summary
A fatigue level estimation apparatus includes: a biological data extraction unit that extracts biological data obtained when a subject is in a specific activity state, from biological data obtained from the subject; a feature value calculation unit that calculates a feature value of the biological data, based on the extracted biological data obtained when the subject is in a specific activity state; and a fatigue level estimation unit that estimates a fatigue level indicating a level of fatigue of the subject, based on the calculated feature value.