Abstract
The article describes the use of neural network algorithms for setting the modes of investigation of photonic crystal films by tapping mode of atomic force microscopy. The photonic crystal thin films and monolayers obtained from colloidal suspensions by methods of sedimentation, centrifugation, vertical deposition, electrophoresis, and Langmuir-Blodgett are studied in this work. Study of films growth kinetics revealed that many factors were critical for reproducible deposition of the structure. To obtain high-quality images of samples, it is very important to get rid of artifacts and correctly configure the scanning parameters. To solve these problems it was proposed to use neural network algorithms. They allow to choose individual settings for each sample. We got acceptable results using a multilayer perceptron with one hidden layer.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call