Deep Learning Enabled SERS Identification of Gaseous Molecules on Flexible Plasmonic MOF Nanowire Films

Abstract

Through the capture of a target molecule at the metal surface with a highly confined electromagnetic field induced by surface plasmon, surface enhanced Raman spectroscopy (SERS) emerges as a spectral analysis technology with high sensitivity. However, accurate SERS identification of a gaseous molecule with low density and high velocity is still a challenge due to its difficulty in capture. In this work, a flexible paper-based plasmonic metal−organic framework (MOF) film consisting of Ag

Neural Network Enables High Accuracy for Hepatitis B Surface Antigen Detection with a Plasmonic Platform

“…Then, we designed an MLP model to predict the possibility of HBsAg positive by analyzing the obtained spectra. MLP, a classical DL model, utilizes nonlinear transformation and parameter tuning of multiple neuron layers to learn and approximate complex nonlinear mapping relations, which have been widely used in spectrum analysis. − This fully connected MLP model comprised an input layer, an output layer, and two hidden layers with each hidden layer containing 1000 nodes (Figure a). 894 spectra collected from 149 human serum samples were split into training and test data sets.…”