Supervised Dictionary Learning With Regularization for Near-Infrared Spectroscopy Classification

Near-infrared spectroscopy (NIRS) has been widely used in many fields due to its advantages with fast analysis speed, non-destructive testing, and on-site detection. However, NIRS has some shortcomings, such as low signal-to-noise ratio, weak absorption intensity, and overlapping peaks. The research of near-infrared spectral modeling method becomes the core of analyzing NIRS. In order to improve the accuracy of prediction model for NIRS, this paper proposes a novel sparse classification mechanism by designing appropriate regularization factors. The existing supervised dictionary learning methods have been proposed for classification aim and increasing its accuracy, the proposed method addresses some defects existing in this area through designing the representation-constrained term and the coefficients incoherence term, and the added two terms can get the reconstruction error of coding coefficients and correlations between similar samples by sharing dictionary under more stable control. Then, based on the proposed model, a supervised class-specific dictionary learning algorithm is developed by choosing appropriate samples with class labels. Finally, a classification scheme integrating the novel sparse model is designed to exploit such discriminative information. The proposed method is evaluated by conducting experiments on drug and tobacco leaves NIRS datasets. The experimental results show that the proposed sparse classification mechanism is promising for classifying NIRS and may be an alternative method to the traditional ones.