Spectroscopic Quantification Boundary Screening for False Positive Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing spectroscopic quantification methods suffer from false positive identifications due to incorrect sample types or improper measurement conditions, leading to inaccurate determinations of component concentrations.
Innovation Solution
Implementing a single class support vector machine (SC-SVM) technique to analyze spectroscopic measurements, determining confidence metrics and decision boundaries to verify if an unknown sample corresponds to the intended material type, thereby reducing false positive identifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If traditional spectroscopic quantification methods are used, then measurement speed is improved, but false positive identification increases
Solution Approach 1:
The patent applies preliminary action by performing sample verification against a decision boundary before conducting the actual quantification measurement. The SC-SVM model pre-establishes a decision boundary that separates valid samples from invalid ones, allowing the system to quickly filter out incorrect samples before they can cause false positive identifications. This preliminary classification step prevents wasted measurement time on invalid samples while maintaining high identification accuracy.
2Productivity
If spectroscopic measurements are performed on all samples, then productivity is improved, but measurement accuracy deteriorates due to false positives
Solution Approach 1:
The patent applies the taking out principle by extracting and removing invalid samples from the measurement process through the SC-SVM decision boundary evaluation. The system identifies and excludes samples that fall outside the decision boundary (indicating incorrect sample types or improper measurement conditions) before they can contaminate the quantification results. This extraction of invalid samples maintains high measurement precision while preserving productivity by avoiding rework of erroneous measurements.
3Reliability
If a single class support vector machine is implemented, then identification reliability is improved, but device complexity increases
Solution Approach 1:
The patent applies parameter changes by utilizing the decision boundary parameter established by the SC-SVM model to transform a complex classification problem into a simple distance calculation. Instead of implementing a complex multi-class classification system, the patent changes the approach to using a single decision boundary parameter that separates valid from invalid samples. This parameter transformation maintains high identification reliability while significantly reducing computational complexity and model complexity.
Data Source
AI summary
A device may receive information identifying results of a spectroscopic measurement performed on an unknown sample. The device may determine a decision boundary for a quantification model based on a configurable parameter, such that a first plurality of training set samples of the quantification model is within the decision boundary and a second plurality of training set samples of the quantification model is not within the decision boundary. The device may determine a distance metric for the spectroscopic measurement performed on the unknown sample relative to the decision boundary. The device may determine a plurality of distance metrics for the second plurality of training set samples of the quantification model relative to the decision boundary. The device may provide information indicating whether the spectroscopic measurement performed on the unknown sample corresponds to the quantification model.