Waveform analytical method and waveform analytical device
AssigneeShimadzu Corporation
InventorShinji Kanazawa
Life of this patent
Estimating the term…
Abstract
A waveform analytical device 4 which analyzes a target waveform which is a chromatogram or an optical spectrum includes a waveform division unit 54 configured to divide the target waveform into a plurality of partial waveforms, a determination unit 55 configured to determine whether each of the plurality of partial waveforms of the target waveform is a peak portion using a learned model created by machine learning using a plurality of sets of a plurality of partial waveforms created by dividing a reference waveform having a peak portion whose position is known, and a classification unit 56 configured to classify the target waveform into a peak region where the peak portion continues and a non-peak region other than the peak region based on a determination result from the determination unit.
Claims16
A waveform analytical method for analyzing a target waveform which is a chromatogram or an optical spectrum, the method comprising:
- creating, by machine learning using sets of partial waveforms created by dividing a reference waveform including a single nonoverlapping peak and overlapping peaks having peaks overlapping each other, positions of the single nonoverlapping peak and the overlapping peaks being known, a learned model which specifies a peak portion included in an input waveform;
- dividing the target waveform into partial waveforms;
- determining whether each of the partial waveforms of the target waveform is a peak portion using the learned model;
- classifying the target waveform into a peak region where the peak portion continues and a non-peak region other than the peak region based on a result of the determining,
- determining whether a peak included in the peak region where the peak portion continues is a single nonoverlapping peak or overlapping peaks;
- classifying the peak region further into a single nonoverlapping peak region and an overlapping peak region;
- and
- identifying a component contained in a sample corresponding to a peak in the target waveform, based on the peak region and the non-peak region classified.
A waveform analytical device which analyzes a target waveform which is a chromatogram or an optical spectrum, the waveform analytical device comprising:
- a waveform division unit configured to divide the target waveform into partial waveforms;
- a determination unit configured to determine whether each of the partial waveforms of the target waveform is a peak portion using a learned model created by machine learning using sets of a plurality of partial waveforms created by dividing a reference waveform including a single nonoverlapping peak and overlapping peaks having peaks overlapping each other, positions of the single nonoverlapping peak and the overlapping peaks being known known;
- and
- a classification unit configured to
- classify the target waveform into a peak region where the peak portion continues and a non-peak region other than the peak region based on a determination result from the determination unit, and
- identify a component contained in a sample corresponding to a peak in the target waveform, based on the peak region and the non-peak region classified,
- wherein
- the determination unit is further configured to determine whether a peak included in the peak region where the peak portion continues is a single nonoverlapping peak or an overlapping peak, and
- the classification unit is further configured to classify the peak region further into a single nonoverlapping peak region and an overlapping peak region.
Dependencies are inferred from the claim text.