Abstract

Spectral features in Raman spectra of organic molecules can be attributed to certain functional groups. A library of 1222 Raman spectra was used to train an artificial neural network (ANN) for predicting the presence of 13 functional groups. Sensitivity analysis was applied to the ANN models to determine a sensitivity factor or feature spectrum for each functional group. The feature spectra could then be used to predict the presence of specific groups based on Bayes' theorem. Once a model is constructed for each functional group, it can be applied directly to measured spectra of structurally unknown molecules and provide real-time predictions. Prediction accuracies of greater than 90% were obtained for aromatic, alkene, aldehyde, ketone, ester, nitro, and nitrile linkages. Accuracies for alcohols and amines were in the 80% range.

High-sensitivity and specificity of laser-induced autofluorescence spectra for detection of colorectal cancer with an artificial neural network

L. C. Kwek, Sheng Fu, T. C. Chia, C. H. Diong, C. L. Tang, and S. M. Krishnan
Appl. Opt. 44(19) 4004-4008 (2005)

Multiplex coherent anti-Stokes Raman scattering (MCARS) for chemically sensitive, label-free flow cytometry

Charles H. Camp Jr., Siva Yegnanarayanan, Ali A. Eftekhar, Hamsa Sridhar, and Ali Adibi
Opt. Express 17(25) 22879-22889 (2009)

Analysis of the sensitivity of optical waveguide chemical sensors for TM modes by the group-index method

De-Kui Qing and Ichirou Yamaguchi
J. Opt. Soc. Am. B 16(9) 1359-1369 (1999)

Position-resolved Raman spectra from a laser-trapped single airborne chemical droplet

Aimable Kalume, Eric Zhu, Chuji Wang, Joshua Santarpia, and Yong-Le Pan
Opt. Lett. 42(24) 5113-5116 (2017)

Use of Raman spectroscopy to screen diabetes mellitus with machine learning tools

Edgar Guevara, Juan Carlos Torres-Galván, Miguel G. Ramírez-Elías, Claudia Luevano-Contreras, and Francisco Javier González
Biomed. Opt. Express 9(10) 4998-5010 (2018)