Nonlinear Data Mapping for Physical Condition Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating physical conditions, such as stress and fatigue, face challenges in precision due to data concentration around the median, leading to poor estimation for individuals with high or low stress levels.
Innovation Solution
An information processing method that maps correct answer data onto a nonlinear space and generates an estimation model using state data as an explanatory variable and mapped correct answer data as a response variable.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a model is generated by learning using data that is concentrated around the median, then the learning process is simple and efficient, but the precision of stress estimation for people who are highly stressed or who are stressed little deteriorates
Solution Approach 1:
The patent applies dimensionality change by transforming the concentrated data distribution into a dispersed one through mapping to a nonlinear space. This allows the model to learn from data that appears concentrated in the original space but becomes well-distributed in the transformed space, thereby improving estimation precision for extreme values while maintaining learning efficiency.
Solution Approach 2:
The patent changes the parameter space by applying a nonlinear transformation to the data. This transformation modifies the distribution characteristics of the data, converting a concentrated distribution around the median into a more dispersed distribution that includes extreme values, thus improving the model's ability to estimate stress for people with high or low stress levels.
2Ease of manufacture
If data about typical people is used for learning, then the data collection process is easier and less complex, but the estimation accuracy for extreme physical conditions deteriorates
Solution Approach 1:
The patent uses dimensionality change to transform the data space, allowing the model to effectively utilize data from typical people while still achieving accurate estimation for extreme physical conditions. The nonlinear transformation maps the data from the original space to a transformed space where typical and extreme values are appropriately distributed.
Solution Approach 2:
The patent introduces a transformation function as an intermediary between the data collection process and the model learning process. This intermediary transforms the raw data from typical people into a transformed data space where the model can learn effective patterns that generalize to extreme physical conditions as well.
Data Source
AI summary
An information processing device 100 of the present invention includes: a transforming unit 121 that maps correct answer data included in learning data onto a nonlinear space, the learning data including state data representing a state of a predetermined person, and the correct answer data representing the physical condition of the predetermined person at the time of acquisition of the state data; and a generating unit 122 that generates an estimation model to be used for estimating the physical condition of a target person by learning using the state data as an explanatory variable, and the mapped correct answer data as a response variable.