Investigation of medicine quality by Raman spectroscopy and machine learning methods
Igor S. Golyak, 1
Igor L. Fufurin, 1
Dmitriy R. Anfimov, 1,
Anastasiya V. Scherbakova, 1
Andrey Morozov, 1
Abstract
In this work, the possibility of using machine learning in the spectral analysis of medicine quality is considered. A Raman spectrometer with a wavelength of 785 nm and a power of 120 mW was used. Aspirin from several manufacturers acted as test substances (target group). Pure aspirin was used for quality control (control group). 100 spectra were taken for each type of aspirin. A shallow neural network was used as a machine learning method. A 1-D convolutional neural network for the classification of aspirin quality allows to get AUC score more than 99%.
Speaker
Igor Golyak
Bauman Moscow State University
Russia
Discussion
Ask question