CNN based Raman Spectroscopy Algorithm That is Robust to Noise and Spectral Shift

Abstract

Raman spectroscopy is an equipment that is widely used for classifying chemicals in chemical defense operations. However, the classification performance of Raman spectrum may deteriorate due to dark current noise, background noise, spectral shift by vibration of equipment, spectral shift by pressure change, etc. In this paper, we compare the classification accuracy of various machine learning algorithms including k-nearest neighbor, decision tree, linear discriminant analysis, linear support vector machine, nonlinear support vector machine, and convolutional neural network under noisy and spectral shifted conditions. Experimental results show that convolutional neural network maintains a high classification accuracy of over 95 % despite noise and spectral shift. This implies that convolutional neural network can be an ideal classification algorithm in a real combat situation where there is a lot of noise and spectral shift.

Fast Detection and Classification of Microplastics below 10 μm Using CNN with Raman Spectroscopy

“…Using MATLAB R2023a software from MathWorks, the obtained Raman signals were subjected to baseline correction and normalization. Algorithms discussed by Park et al 29 were used to enhance the capabilities of machine learning (ML) against noise and spectrum shifts. However, to maximize ML performance against noise, the α value was set from 0 to 5, and the β value was set to 50.…”