Neural Network Classification Method for Solution of the Problem of Monitoring Theremoval of the Theranostics Nanocomposites from an Organism
In this study artificial neural networks were used for elaboration of the new method of monitoring of excreted nanocomposites-drug carriers and their components in human urine by their fluorescence spectra. The problem of classification of nanocomposites consisting of fluorescence carbon dots covered by copolymers and ligands of folic acid in urine was solved. A set of different architectures of neural networks and 4 alternative procedures of the selection of significant input features: by cross-correlation, cross-entropy, standard deviation and by analysis of weights of a neural network were used. The best solution of the problem of classification of nanocomposites and their components in urine provides the perceptron with 8 neurons in a single hidden layer, trained on a set of significant input features selected using cross-correlation. The percentage of correct recognition averaged over all five classes, is 72.3%.
KeywordsArtificial neural network Inverse problem Fluorescent spectroscopy Carbon nanocomposite Drug carrier
The following parts of this study were supported by the following foundations: (i) elaboration of optical visualization of nanocomposites using ANN (O.E.S.,I.V.I.,T.A.D.) have been performed at the expense of the grant of Russian Science Foundation (project no. 17-12-01481); (ii) the test of nanocomposites properties (S.A.B., K.A.L.) were supported by the grant of the Russian Foundation for Basic Research no. 15-29-01290 ofi_m.
- 5.Prabhakar, N., Näreoja, T., von Haartman, E., Karaman, D., Burikov, S., Dolenko, T., Deguchi, T., Mamaeva, V., Hänninen, P., Vlasov, I., Shenderova, O., Rosenholm, J.: Functionalization of graphene oxide nanostructures improves photoluminescence and facilitates their use as optical probes in preclinical imaging. Nanoscale 7, 10410–10420 (2015)CrossRefGoogle Scholar