SERSNET: SURFACE-ENHANCED RAMAN SPECTROSCOPY BASED BIOMOLECULE DETECTION USING DEEP NEURAL NETWORK
Loading...
Date
2021-11-30
Authors
Park, Seongyong
Lee, Jaeseok
Khan, Shujaat
Wahab, Abdul
Kim, Minseok
Journal Title
Journal ISSN
Volume Title
Publisher
MDPI AG
Abstract
Surface-Enhanced Raman Spectroscopy (SERS)-based biomolecule detection has been
a challenge due to large variations in signal intensity, spectral profile, and nonlinearity. Recent
advances in machine learning offer great opportunities to address these issues. However, welldocumented procedures for model development and evaluation, as well as benchmark datasets,
are lacking. Towards this end, we provide the SERS spectral benchmark dataset of Rhodamine 6G
(R6G) for a molecule detection task and evaluate the classification performance of several machine
learning models. We also perform a comparative study to find the best combination between the
preprocessing methods and the machine learning models. Our best model, coined as the SERSNet,
robustly identifies R6G molecule with excellent independent test performance. In particular, SERSNet
shows 95.9% balanced accuracy for the cross-batch testing task.
Keywords: Surface Enhanced Raman Spectroscopy; molecule detection; machine learning; deep
learning
Description
Keywords
Surface Enhanced Raman Spectroscopy, molecule detection, machine learning, deep learning, Type of access: Open Access
Citation
Park, S., Lee, J., Khan, S., Wahab, A., & Kim, M. (2021). SERSNet: Surface-Enhanced Raman Spectroscopy Based Biomolecule Detection Using Deep Neural Network. In Biosensors (Vol. 11, Issue 12, p. 490). MDPI AG. https://doi.org/10.3390/bios11120490