Stress Estimation Model Clustering for Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing stress estimation devices face instability in estimation accuracy, particularly when dealing with unknown data.
Innovation Solution
A learning device and method that sorts observation feature values based on attributes and environments, selects relevant stress estimation feature values, and trains a stress estimation model for each cluster to improve estimation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single stress estimation model is used for all data, then the device complexity is low, but the estimation accuracy for unknown data is unstable
Solution Approach 1:
The patent divides the stress estimation model into multiple cluster-specific models based on sorting observation feature values by attributes and environment. Each model is trained on specific clusters of data, allowing the system to select the appropriate model based on the input data's characteristics, thereby improving estimation accuracy while managing complexity through modular organization
Solution Approach 2:
The system dynamically selects which stress estimation model to use based on the attributes and environment of the input data. This dynamic model selection allows the system to adapt to different data characteristics and maintain high estimation accuracy across various conditions without requiring a single complex universal model
2Reliability
If multiple stress estimation models are trained for different clusters, then the estimation accuracy is stable, but the device complexity increases
Solution Approach 1:
The patent performs preliminary sorting of observation feature values by attributes and environment before training the models. This preliminary organization of data into clusters allows the system to prepare multiple specialized models in advance, each optimized for specific data patterns, thereby ensuring stable estimation accuracy when the models are deployed
Solution Approach 2:
Each stress estimation model is specialized for a specific cluster of data with particular attributes and environmental conditions. This local optimization ensures that each model has high accuracy for its designated cluster, and the system maintains reliability by selecting the appropriate local model based on the input data's characteristics
3Measurement precision
If observation feature values are sorted by attributes and environment, then the feature value selection becomes more accurate, but the processing time increases
Solution Approach 1:
The patent segments the observation feature values into distinct clusters based on attributes and environment before selecting stress estimation feature values. This segmentation allows for more accurate feature selection within each cluster, as the system can identify the most relevant features for each specific context rather than using a generic feature set for all data
Data Source
AI summary
An information processing device 1X mainly includes first and sorting means 14X and 15X, a feature value selection means 16X, and a learning means 17X. The first sorting means 14X performs a first sorting for sorting observation feature values of a target person based on attribute and/or environment of the target person. The second sorting means 15X performs a second sorting for sorting the observed feature values based on an observation target of the observed feature values and/or an activity state of the target person. The feature value selection means 16X selects stress estimation feature values for stress estimation from the observed feature values sorted based on the first sorting and the second sorting. The learning means 17X trains a stress estimation model based on the stress estimation feature values and corresponding correct stress values for each cluster of the observed feature values sorted by the first sorting.