Nondestructive Evaluation of Solid Pharmaceutical Products Using Wavelet Transformations and Multispectral Data

Abstract

Abstract The nondestructive analysis of a solid pharmaceutical product (SPP) is essential to evaluating the quality without destroying the product. This analysis may be performed using various signal processing techniques on multispectral data. Based on this analysis, the SPPs may be classified as defective or nondefective. In this research, we have used multispectral data and applied wavelet transformations in conjunction with various machine learning techniques for the classification. The SPPs (categorized as defective) are exposed to three different environmental factors (humidity, temperature, and moisture) over different time periods, and the variations in multispectral data are analyzed to judge the effects of these factors on the classification of the SPPs. The results show that the spectra extracted from only the ultraviolet (UV) wavelength range are more suitable for the classification of defective and nondefective SPPs. Furthermore, results also describe that the K-nearest neighbors classifier or ensemble of classifiers is a more appropriate classifier.