Near infrared spectroscopy (NIRS) analysis technology, combined with chemometrics, can be effectively used in quick and nondestructive analysis of quality and category. In this paper, an effective drug identification method by using deep belief network (DBN) with dropout mecha-nism (dropout-DBN) to model NIRS is introduced, in which dropout is employed to overcome the overfitting problem coming from the small sample. This paper tests proposed method under datasets of different sizes with the example of near infrared diffuse reflectance spectroscopy of erythromycin ethylsuccinate drugs and other drugs, aluminum and nonaluminum packaged. Meanwhile, it gives experiments to compare the proposed method's performance with back propagation (BP) neural network, support vector machines (SVMs) and sparse denoising auto-encoder (SDAE). The results show that for both binary classification and multi-classification, dropout mechanism can improve the classification accuracy, and dropout-DBN can achieve best classification accuracy in almost all cases. SDAE is similar to dropout-DBN in the aspects of classification accuracy and algorithm stability, which are higher than that of BP neural network and SVM methods. In terms of training time, dropout-DBN model is superior to SDAE model, but inferior to BP neural network and SVM methods. Therefore, dropout-DBN can be used as a modeling tool with effective binary and multi-class classification performance on a spectrum sample set of small size.

Near Infrared spectroscopy (NIRS) has been widely used in the discrimination (classification) of pharmaceutical drugs. In real applications, however, the class imbalance of the drug samples, i.e., the number of one drug sample may be much larger than the number of the other drugs, deceases drastically the discrimination performance of the classification models. To address this class imbalance problem, a new computational method — the scaled convex hull (SCH)-based maximum margin classifier is proposed in this paper. By a suitable selection of the reduction factor of the SCHs generated by the two classes of drug samples, respectively, the maximal margin classifier between SCHs can be constructed which can obtain good classification performance. With an optimization of the parameters involved in the modeling by Cuckoo Search, a satisfied model is achieved for the classification of the drug. The experiments on spectra samples produced by a pharmaceutical company show that the proposed method is more effective and robust than the existing ones.