Feature Parameter Candidate Generation for Health Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques fail to effectively evaluate and prepare feature parameters that account for the complexity and individuality of the human body, leading to inefficient modeling of health conditions due to the lack of a quantitative method for assessing feature parameter properties.
Innovation Solution
A feature parameter candidate generation apparatus that calculates normalization cardinality for each feature parameter, evaluates the uniformity of their frequency distribution, and selects combinations that satisfy a predetermined criterion to ensure well-balanced representation, allowing for the automatic selection of optimal feature parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If feature parameters are prepared exhaustively to cover variations due to complexity and individuality of the living body, then modeling accuracy and reliability are improved, but the efficiency of feature parameter preparation deteriorates due to lack of quantitative evaluation method
Solution Approach 1:
The invention changes the parameter of feature parameter selection from qualitative trial-and-error to quantitative evaluation using normalization cardinality. By calculating NC values and selecting feature parameters based on uniform frequency distribution of NC values, the system efficiently identifies optimal feature parameters without exhaustive preparation, thus improving both reliability and efficiency.
Solution Approach 2:
The invention replaces the mechanical trial-and-error process of feature parameter selection with an automated information-theoretic evaluation system. The normalization cardinality calculation and uniformity evaluation automatically identify suitable feature parameters, substituting manual trial-and-error with a systematic quantitative approach.
2Measurement precision
If feature parameters are selected based on trial and error using prior knowledge, then some modeling capability is achieved, but the process is inefficient and lacks quantitative evaluation
Solution Approach 1:
The invention replaces manual trial-and-error selection with automated quantitative evaluation using normalization cardinality. The system calculates NC values for candidate feature parameters and automatically selects those with uniform frequency distribution, eliminating time-consuming manual processes while providing precise quantitative evaluation.
Solution Approach 2:
The system performs self-evaluation of feature parameters through automatic calculation of normalization cardinality and uniformity assessment. The feature parameter selection process serves itself by using objective quantitative criteria rather than relying on external prior knowledge or manual judgment, thereby reducing time loss and improving precision.
Data Source
AI summary
A feature parameter candidate generation apparatus has a storage unit that stores the values of feature parameters extracted from each of samples, an index value calculation unit that calculates an index value, which is obtained by normalizing the number of the kinds of the values of feature parameters by the number of the samples, for each of the feature parameters, an evaluation object selection unit that selects combinations of feature parameters which are objects to be evaluated, an evaluation unit that evaluates whether the uniformity of a frequency distribution of index values of the individual feature parameters for combinations of feature parameters selected as the objects to be evaluated satisfies a predetermined criterion, and a candidate determination unit that determines, as feature parameter candidates to be given to the model generation device, a combination of feature parameters that is evaluated to satisfy the predetermined criterion.