Model transfer method based on hyperspectral data

Abstract

The invention provides a model transfer method based on hyperspectral data. The method comprises the steps of using a primary instrument and a secondary instrument to perform spectral collection on a sample, and establishing a classified prediction model of the sample according to spectral data collected by the primary instrument after all the spectral data is subjected to preprocessing; selecting N groups of corresponding spectral data as a conversion data set, and building a spectral transfer relationship; conducting correction on spectral data collected by the secondary instrument according to the spectral transfer relationship; randomly selecting M spectral data from corrected spectral data of the secondary instrument as a training sample, and regarding the rest data as a testing sample; picking m dimensional data with highest accuracy from n dimensional spectral data to conduct waveband combination according to a forward selection algorithm; classifying the m dimensional data according to a machine learning method to determine the classification of the testing sample and calculating the accuracy of the testing data. By means of the model transfer method based on the hyperspectral data, high-accuracy classified prediction of the spectral data collected by different instruments can be achieved, and meanwhile the processing time of a data classification algorithm is shortened.

Description

technical field [0001] The invention relates to the technical field of hyperspectral data processing, in particular to a model transfer method based on hyperspectral data. Background technique [0002] Compared with traditional chemical analysis and identification, spectral detection technology has insurmountable advantages in rapidity, non-destructiveness and convenience. The classification prediction model of spectral data is the basis of spectral detection, and establishing an accurate and complete classification prediction model often requires a lot of time, manpower and material resources. However, due to the different structures and devices of the spectrometer, the environment during spectrum collection is different, and the data collected by different spectrometers are significantly different; even if the same instrument collects uniform samples at different times, the spectral data are not completely consistent. This makes the established model inapplicable, especia...

AI Technical Summary

Problems solved by technology

At the same time, considering the redundancy of spectral data storage, redundant information will not only reduce the speed of classification and prediction of spectral data, but also affect the classification accuracy after model transfer.

Images