Оцінювання валідності діагностування пошкоджень біотканин за допомогою цифрової колориметрії з використанням нейромережі

Abstract

In this paper, we designed and analyzed the expert system of diagnostic adoption of sup-port solutions in the study of surface damage biological tissues by means of digital colorimetry using a neural network to process the results. The researchers tested the possibility of using neural network architecture based on multilayer perceptron with one hidden layer; multilayer perceptron with two hidden layers, probabilistic neural networks and network with radial basis function. After learning neural network based on test sequences we have studied performance results and errors in their work. We have developed specialized software for administration personal data of patients in forensic examination of biological tissues of human skin and combination of data in common database with digital photos injuries. The researchers analyzed the operating parameters of a diagnostic test to assess the diagnostic accuracy of surface damage biological tissues based on advanced of digital colorimetry method.