Application of jitter augmentation in classification of Raman scattering from glucose liquid with several machine learning models
Abstract
The utilisation of machine learning technology for invasive diabetes diagnosis has emerged as a prominent research area in the medical field in recent years. The study employs Raman spectroscopy of a glucose fluid sample to ascertain glucose levels. We produce glucose-liquid samples with 14 varying ratios of glucose to pure water to replicate the 14 glucose concentrations found in human blood and acquire the corresponding Raman spectra. With the optimistic result of the previous study, we also design the jittering augmentation approach to enhance the dataset and the dataset size was increased by a factor of 100. We employ a 1-D Convolutional Neural Network to ascertain glucose levels in samples. The result proves the positive effect of jitter augmentation for improving the performance of the deep learning model as well as high accuracy of these models in classification of Raman scattering.
References
[2] J. Xu, Q. He, Z. Xiong, et al. (2021), “Raman spectroscopy as a versatile tool for investigating thermochemical processing of coal, biomass, and wastes: Recent advances and future perspectives”, Energy & Fuels, 35(4), pp.2870-2913, DOI: 10.1021/acs. energyfuels.0c03975.
[3] J. Shao, M. Lin, Y. Li, et al. (2012), “In vivo blood glucose quantification using Raman spectroscopy”, PLOS ONE, 7(10), DOI: 10.1371/journal.pone.0048127.
[4] I. Rehan, S. Khan, R. Ullah (2024), “Raman spectroscopy assisted support vector machine: A steadfast tool for noninvasive classification of urinary glucose of diabetes mellitus”, Physica Scripta, 99(2), DOI: 10.1088/1402-4896/ad1da8.
[5] L.A. Duc, N.T. Tung, T.T. Oanh, et al. (2023), “Noninvasive in vivo type 2 diabetes mellitus diagnosis using Raman spectroscopy in combination with machine learning”, Mobile Networks and Applications, DOI: 10.1007/s11036- 023-02220-9.
[6] J. Smulko, M.S. Wróbel, I. Barman (2015), Noise in Biological Raman Spectroscopy, Book Noise in Biological Raman Spectroscopy, pp.1-6.
[7] N.G. Viveros, P.G. Gil, J.C. Ramos, et al. (2021), “On the estimation of sugars concentrations using Raman spectroscopy and artificial neural networks”, Food Chemistry, 352, DOI: 10.1016/j.foodchem.2021.129375.
[8] T.N. Quang, T.T. Nguyen, H.P.T. Viet (2024), “Machine learning approach for early detection of diabetes using Raman spectroscopy”, Mobile Networks and Applications, 29, pp.294-305, DOI: 10.1007/s11036-024- 02340-w.
[9] M. Shokrekhodaei, D.P. Cistola, R.C. Roberts, et al. (2021), “Non-invasive glucose monitoring using optical sensor and machine learning techniques for diabetes applications”, Ieee Access: Practical Innovations, Open Solutions, 9, pp.73029-73045, DOI: 10.1109/ access.2021.3079182.
[10] A. Gavrilov, A. Jordache, M. Vasdani, et al. (2018), “Preventing model overfitting and underfitting in convolutional neural networks”, International Journal of Software Science and Computational Intelligence, 10(4), pp.19-28, DOI: 10.4018/IJSSCI.2018100102.
[11] P. Esling, C. Agon (2012), “Time-series data mining”, ACM Computing Surveys (CSUR), 45(1), DOI: 10.1145/2379776.2379788.
[12] G. Iglesias, E. Talavera, A.G. Prieto, et al. (2023), “Data augmentation techniques in time series domain: A survey and taxonomy”, Neural Computing and Applications, 35(14), pp.10123-10145, DOI: 10.1007/s00521-022- 08122-y.
[13] C.H. Chen, P.H. Lin, J.G. Hsieh, et al. (2020), “Robust multi-class classification using linearly scored categorical cross-entropy”, 2020 International Joint Conference on Neural Networks (IJCNN), DOI: 10.1109/ IJCNN48605.2020.9207212.
