Rapid material identification via low-resolution Raman spectroscopy and deep convolutional neural network

Abstract

Raman spectroscopy is a vital technique being able to detect and identify molecular information with advantages of being fast and non-invasive. This technique also enables numbers of potential applications, including forensic drugs detector, explosive detection, and biomedical analysis. In this work, we investigated the identification performance of a custom-made low-resolution Raman system equipped with machine learning capability to classify various types of materials. Here, a relatively broadband laser diode with center wavelength of 808 nm was used for Raman excitation. An off-axis parabolic mirror with through hole was used in place of a beamspiltter for sample excitation, as well as collection, and collimation of scattered light from long working distance of 50 mm. The signal was filtered and delivered to a cooled spectrometer via an optical fiber for spectra measurements. Raman spectra of test samples were on the range of 100-2000 cm−1 with 7.65 cm−1 data steps. For spectral analysis, a convolutional neural network (CNN) was implemented as classification algorithm with feature extraction from multiple layers together with error-back propagation, which displayed the performance in term of accuracy. It was found that with only three sets of convolution layers up to 96.7% testing performance can be achieved even with low spectral resolution input.

Recent Progresses in Machine Learning Assisted Raman Spectroscopy

“…[89,90] The convergence of computing techniques and materials research, [91] and some AI algorithms, such as ML and deep learning techniques, can aid in identifying materials and comprehending material behaviors and properties more efficiently. [92] In a study by Boonsit et al, [93] CNN can identify materials with an accuracy of up to 96.7%, even with low-resolution Raman spectra. Pan et al [94] proposed an algorithmic model for multi-label classification based on deep learning to recognize complex mixture materials.…”

A Label-Free Marker Based Breast Cancer Detection using Hybrid Deep Learning Models and Raman Spectroscopy

“…Raffiee et al, employed a 1D-CNN to identify microbial load by differentiating Raman spectra of Chinese hamster ovary cells from 12 kinds of microbes, achieving 95 -100 % of accuracy [23]. To quickly identify components, Kalasuwan et al, built a 1D-CNN for low-resolution Raman spectra recorded from BaSO4, NaNO3, Ba(NO3)2, Pb(NO3)2, CH4N2O, and KNO3 with an accuracy of 96.7 % [24]. This model is composed of 4 conv-blocks for the extraction of features and 1 output layer for the classification of the spectrogram.…”

Deep Learning for Raman Spectroscopy: A Review

“…This model is composed of three parts: an initial convolutional layer with the kernel size of 7 (followed by a batch normalization layer and a ReLU layer), eight residual blocks with the kernel size of 3 and a fully-connected layer at the end. To identify materials rapidly, Boonsit et al, implemented a 1D CNN as well for low-resolution Raman spectra collected from NaNO 3 , BaSO 4 , Ba(NO 3 ) 2 , KNO 3 , Pb(NO 3 ) 2 , and CH 4 N 2 O, and the accuracy of which was found to be 96.7% [7]. This model consists of four convolutional blocks (each contains a convolutional layer, a ReLU layer, and a maxpooling layer) for feature extraction and one output layer for spectral classification.…”

“…Therefore, enhancement techniques, such as coherent anti-Stokes Raman spectroscopy (CARS) [3] and surface-enhanced Raman spectroscopy (SERS) [4], were invented. Nowadays, Raman spectroscopy has already widely spread into different research fields, for example, forensic analysis [5], pharmaceutical product design [6], material identification [7], disease diagnosis [8], etc. Most of the presented and similar studies employ the unlabelled version of Raman spectroscopy.…”

“…This kind of representation learning is called deep learning and it can solve various artificial-intelligence tasks [19] (pp. [1][2][3][4][5][6][7][8][9][10][11][12]. With the rapid development of computer science, deep learning has changed numerous traditional research fields, including photonics [20], chemistry [21], and biology [22].…”