Composition analysis
First Claim
1. A method of analysing a sample, comprising the steps of training a neural network to correct for measurement drift of a given analytical instrument, said training being carried out using a first set of data obtained by said instrument from samples of known compositions at an initial instant of time and a second set of data obtained by said instrument from samples of the same known compositions at a subsequent instant of time, then using said neural network to transform data, obtained by said instrument from a sample of unknown composition at said subsequent instant of time, to an estimate of the data which would have been obtained by said instrument from said sample of unknown composition at said initial instant of time, and analysing the transformed data to analyse said sample of unknown composition.
1 Assignment
0 Petitions
Accused Products
Abstract
A method and apparatus for analysing a sample, in which a neural network is trained to correct for measurement drift of a given analytical instrument (e.g., a mass spectrometer). The training is carried out using first and second sets of data obtained by the instrument from samples of known compositions at initial and subsequent instants of time, respectively. The trained neural network is used to transform data, obtained by the instrument from a sample of unknown composition at said subsequent instant of time, to an estimate of the data which would have been obtained by the instrument from that sample at the initial instant of time. The transformed dasta is then analysed to analyse the sample of unknown composition.
47 Citations
20 Claims
- 1. A method of analysing a sample, comprising the steps of training a neural network to correct for measurement drift of a given analytical instrument, said training being carried out using a first set of data obtained by said instrument from samples of known compositions at an initial instant of time and a second set of data obtained by said instrument from samples of the same known compositions at a subsequent instant of time, then using said neural network to transform data, obtained by said instrument from a sample of unknown composition at said subsequent instant of time, to an estimate of the data which would have been obtained by said instrument from said sample of unknown composition at said initial instant of time, and analysing the transformed data to analyse said sample of unknown composition.
- 16. An apparatus for analysing a sample, comprising a neural network arranged to be trained to correct for measurement drift of a given analytical instrument, using first and second sets of data obtained by said instrument from samples of known compositions at initial and subsequent time instants respectively, said neural network further being arranged to transform data, obtained by said instrument from a sample of unknown composition at said subsequent instant of time, to an estimate of the data which would have been obtained by said instrument from said sample of unknown composition at said initial instant of time, and means for analysing the transformed data to analyse said sample of unknown composition.
Specification