Application of iterative distance correlation and PLS for wavelength interval selection in near infrared spectroscopy

Wavelength selection is a fundamental and critical step in near infrared spectral analysis, which can improve the prediction performance and enhance the interpretability of the model. Motivated by the appealing properties of the distance correlation, a novel wavelength interval selection algorithm, named iterative distance correlation combined with PLS regression (IDC-PLS), is developed. To obtain all the possible wavelength intervals, our method mainly consists of two steps. First, an effective iterative procedure based on distance correlation is used to screen wavelength interval variables. Then, build a series of PLS models by recursive using all the wavelength intervals but one interval until the optimal wavelength intervals obtain, which correspond the lowest root mean square error of prediction. The IDC-PLS integrates the advantages of distance correlation with PLS method, which is an efficient strategy to enhance the performance of PLS in wavelengths selection. The performance of IDC-PLS was tested on three real NIR datasets. The results demonstrate that IDC-PLS can improve prediction performance and efficiently select strongly correlated wavelength intervals related to the response. The proposed method may be a good wavelength interval selection strategy due to its simplicity and efficiency.

Automated summary

Wavelength selection is crucial in near infrared spectral analysis and can enhance prediction performance and interpretability of the model. This study proposes a novel algorithm called iterative distance correlation combined with PLS regression (IDC-PLS) that incorporates the advantages of distance correlation and PLS. The method involves an iterative procedure based on distance correlation to screen wavelength interval variables and the construction of PLS models using all possible wavelength intervals. The results demonstrate that IDC-PLS can improve prediction performance and efficiently select strongly correlated wavelength intervals.