The extraction of relevant wavelengths from a large dataset of Near Infrared Spectroscopy (NIRS) is a significant challenge in vibrational spectroscopy research. Nonetheless, this process allows the improvement in the chemical interpretability by emphasizing the chemical entities related to the chemical parameters of samples. With the complexity in the dataset, it may be possible that irrelevant wavelengths are still included in the multivariate calibration. This yields the computational process to become unnecessary complex and decreases the accuracy and robustness of the model. In multivariate analysis, Partial Least Square Regression (PLSR) is a method commonly used to build a predictive model from NIR spectral data. However, in the PLSR method and common commercial chemometrics software, there is no standard wavelength selection procedure applied to screen the irrelevant wavelengths. In this study, a new robust wavelength selection procedure called the modified VIP-MCUVE (mod-VIP-MCUVE) using Filter-Wrapper method and input scaling strategy is introduced. The proposed method combines the modified Variable Importance in Projection (VIP) and modified Monte Carlo Uninformative Variable Elimination (MCUVE) to calculate the scale matrix of the input variable. The modified VIP uses the orthogonal components of Partial Least Square (PLS) in investigating the informative variable in the model by applying the amount of variation both in X and y{SSX,SSY}, simultaneously. The modified MCUVE uses a robust reliability coefficient and a robust tolerance interval in the selection procedure. To evaluate the superiority of the proposed method, the classical VIP, MCUVE, and autoscaling procedure in classical PLSR were also included in the evaluation. Using artificial data with Monte Carlo simulation and NIR spectral data of oil palm (Elaeis guineensis Jacq.) fruit mesocarp, the study shows that the proposed method offers advantages to improve model interpretability, to be computationally extensive, and to produce better model accuracy.
In practice, the collected spectra are very often composes of complex overtone and many overlapping peaks which may lead to misinterpretation because of its significant nonlinear characteristics. Using linear solution might not be appropriate. In addition, with a high-dimension of dataset due to large number of observations and data points the classical multiple regressions will neglect to fit. These complexities commonly will impact to multicollinearity problem, furthermore the risk of contamination of multiple outliers and high leverage points also increases. To address these problems, a new method called Kernel Partial Diagnostic Robust Potential (KPDRGP) is introduced. The method allows the nonlinear solution which maps nonlinearly the original input
X
matrix into higher dimensional feature mapping with corresponds to the Reproducing Kernel Hilbert Spaces (RKHS). In dimensional reduction, the method replaces the dot products calculation of elements in the mapped data to a nonlinear function in the original input space. To prevent the contamination of the multiple outlier and high leverage points the robust procedure using Diagnostic Robust Generalized Potentials (DRGP) algorithm was used. The results verified that using the simulation and real data, the proposed KPDRGP method was superior to the methods in the class of non-kernel and some other robust methods with kernel solution.