Pushkarova Y. Solving tasks of qualitative chemical analysis with the use of artificial neural networks

The object of the research is an identification and clustering of objects based on multiresponse experimental data in qualitative chemical analysis. The purpose of the research is the exploring the applicability of artificial neural networks, developing recommendations for optimizing the parameters, architecture and procedures for using of artificial neural networks for reliable solving tasks of qualitative chemical analysis. Methods of investigation and equipment: algorithms of artificial neural networks, preliminary analysis of data sets, parametric and non-parametric methods of statistics and chemometrics. Theoretical and practical results: the urgent scientific problem of adapting artificial neural networks for the reliable identification and discrimination of objects in qualitative chemical analysis has been solved. The scientific novelty: first the recommendations for the choice of optimal parameters and architecture of artificial neural networks for reliable solving tasks of qualitative chemical analysis have been developed. The realization: the act of implementing the results of dissertation in the educational process chemistry department is received. The sphere (area) of employment: qualitative chemical analysis, authenticity of foodstuff, food raw material and environmental objects.