Igor Isaev

Increase of the Resistance to Noise in Data for Neural Network Solution of the Inverse Problem of Magnetotellurics with Group Determination of Parameters

When a multi-parameter inverse problem is solved with artificial neural networks, it is usually solved separately for each determined parameter (autonomous determination). In their preceding studies, the authors have demonstrated that joining parameters into groups with simultaneous determination of the values of all parameters within each group may in some cases improve the precision of solution of inverse problems. In this study, the observed effect has been investigated in respect to its resistance to noise in data. The study has been performed at the example of the inverse problem of magnetotellurics, which has a high dimensionality.

Training with noise as a method to increase noise resilience of neural network solution of inverse problems

Inverse problems constitute a special class of problems, which consist in reconstruction of parameters of an object by the data of indirect measurements, which are affected by these parameters. Many inverse problems are ill-posed (incorrect), i.e., characterized by nonuniqueness and/or instability of the solution. Improvement in the stability of the solution of inverse problems is a very topical problem; one of the ways to solve it is the use of artificial neural networks. In the present study, at the example of a model 5-parameter inverse problem it is demonstrated that adding noise to the training set when training neural networks allows one to improve resilience of the neural network solution to noise in input data, with various distribution and intensity of noise.

Study of Influence of Parameter Grouping on the Error of Neural Network Solution of the Inverse Problem of Electrical Prospecting

In the electrical prospecting inverse problem, the sought-for distribution of electrical conductivity in Earth stratum is described by dividing the studied section into blocks arranged in layers, with determination of electrical conductivity in the center of each block. This inverse problem can be solved separately for each block, or simultaneously for a group of blocks. In this study, the dependence of solution error on the number of blocks for simultaneous solution of the problem with a single neural network, and on the method of their choice, was investigated.

Comparative Analysis of Residual Minimization and Artificial Neural Networks as Methods of Solving Inverse Problems: Test on Model Data

This study compares perceptron type neural network and residual minimization for solving inverse problems, at the example of a model inverse problem. Stability of both methods against noise in data was investigated. The conclusion about limited applicability of residual as a criterion of the solution quality has been made.

Artificial Neural Networks for Diagnostics of Water-Ethanol Solutions by Raman Spectra

The present paper is devoted to an elaboration of a method of diagnosis of alcoholic beverages using artificial neural networks: the inverse problem of spectroscopy – determination of concentrations of ethanol, methanol, fusel oil, ethyl acetate in water-ethanol solutions – was solved using Raman spectra. We obtained the following accuracies of concentration determination: 0.25% vol. for ethanol, 0.19% vol. for fusel oil, 0.35% vol. for methanol, and 0.29% vol. for ethyl acetate. The obtained results demonstrate the prospects of using Raman spectroscopy in combination with modern data processing methods (artificial neural networks) for the elaboration of an express non-contact method of detection of harmful and dangerous impurities in alcoholic beverages, as well as for the detection of counterfeit and low-quality beverages.

Neural Network Recognition of the Type of Parameterization Scheme for Magnetotelluric Data

The inverse problem of magnetotelluric sounding is a highly non-linear ill-posed inverse problem with high dimension both at the input and at the output. One way to reduce the incorrectness is to narrow the scope of the problem. In our case, this can be implemented in the form of a complex algorithm, which first makes the choice of one of the narrower classes of geological sections and then performs the solution of the regression inverse problem within the selected class. In the present study, we investigate the effectiveness of the implementation of the first phase of this algorithm. The neural network solution of the problem of classification of magnetotelluric sounding data was considered. We estimate the maximum accuracy of classification, perform search for optimal parameters, and test the results for resilience to noise in the data.

Joint Application of Group Determination of Parameters and of Training with Noise Addition to Improve the Resilience of the Neural Network Solution of the Inverse Problem in Spectroscopy to Noise in Data

In most cases, inverse problems are ill-posed or ill-conditioned, which is the reason for high sensitivity of their solution to noise in the input data. Despite the fact that neural networks have the ability to work with noisy data, in the case of inverse problems, this is not enough, because the incorrectness of the problem “outweighs” the ability of the neural network. In previous studies, the authors have shown that separate use of methods of group determination of parameters and of noise addition during training of neural networks can improve the resilience of the solution to noise in the input data. This study is devoted to the investigation of joint application of these methods. The study is performed at the example of an inverse problem in laser Raman spectroscopy - determination of concentrations of ions in a solution of inorganic salts by Raman spectrum of the solution.

Monitoring of the excretion of fluorescent nanocomposites out of the body using artificial neural networks

In this study we propose a new approach to monitoring of the removal of luminescent nanocomposites and their components with urine using artificial neural networks. A complex multiparametric problem of optical imaging of synthesized nanocomposites - nanometer graphene oxides, covered by the poly(ethylene imine)–poly(ethylene glycol) copolymer and by the folic acid in a biomaterial is solved. The proposed method is applicable for optical imaging of any fluorescent nanoparticles used as imaging nanoagents in biological tissue.

Group Determination of Parameters and Training with Noise Addition: Joint Application to Improve the Resilience of the Neural Network Solution of a Model Inverse Problem to Noise in Data

Solution of inverse problems is usually sensitive to noise in the input data, as problems of this type are usually ill-posed or ill-conditioned. While neural networks have high noise resilience by themselves, this may be not enough in case of incorrect inverse problems. In their previous studies, the authors have demonstrated that the method of group determination of parameters, as well as noise addition during training of a neural network, can improve the resilience of the solution to noise in the input data. This study is devoted to the investigation of joint application of these methods. It has been performed on a model problem, for which the direct function is set explicitly as a polynomial.

A method for optical imaging and monitoring of the excretion of fluorescent nanocomposites from the body using artificial neural networks

In this study, a new approach to the implementation of optical imaging of fluorescent nanoparticles in a biological medium using artificial neural networks is proposed. The studies were carried out using new synthesized nanocomposites - nanometer graphene oxides, covered by the poly(ethylene imine)-poly(ethylene glycol) copolymer and by the folic acid. We present an example of a successful solution of the problem of monitoring the removal of nanocomposites based on nGO and their components with urine using fluorescent spectroscopy and artificial neural networks. However, the proposed method is applicable for optical imaging of any fluorescent nanoparticles used as theranostic agents in biological tissue.