Method and apparatus for removing noise from data
A method for removing noise from spectral data recorded using a spectrometer. The method includes normalising spectral data to generate normalised spectral data and applying a machine learning model to the normalised spectral data. The machine learning model is trained to remove noise from spectral data using normalised training data, wherein the spectral data is normalised based on a different scaling to the normalisation of the training data.
1 . A method for removing noise from spectral data recorded using a spectrometer, the method comprising normalising spectral data to generate normalised spectral data and applying a machine learning model to the normalised spectral data, the machine learning model trained to remove noise from spectral data using normalised training data, wherein the spectral data is normalised based on a different scaling to the normalisation of the training data.
2 . A method according to claim 1 , wherein the normalisation is a rescaling and the different scaling a scaling of the spectral data to a different range to the scaling of the training data.
3 . A method according to claim 1 , wherein the normalisation is a mean value normalisation.
4 . A method according to claim 1 , wherein the normalisation is a standardisation normalisation.
5 . A method according to claim 1 , comprising receiving a selection of the different scaling to apply to the spectral data from a user.
6 . A method according to claim 1 , comprising generating the spectral data by carrying out spectroscopy on a sample.
7 . A method according to claim 1 , comprising outputting processed spectral data generated by applying the machine learning model to the spectral data.
8 . A method according to claim 1 , wherein the method is computer-implemented.
9 . Apparatus comprising a hardware-based processor configured to carry out the method of claim 1 .
10 . Apparatus according to claim 9 , comprising a spectrometer.
11 . Apparatus according to claim 9 , comprising an interface configured to receive an input from a user of the different scaling to apply to the spectral data.
12 . Apparatus according to claim 9 comprising an output device configured to output normalised values of the spectral data and/or one or more components determined as present in a sample.
13 . A non-transitory computer readable storage medium having instructions stored thereon which, when executed by a processor, cause the processor to carry out the method of claim 1 .