%0 Journal Article
%T Classifying Vibration Modes Generated by The Michelson Interferometer Using Machine Learning Methods
%A Xin-Han Tsai
%A Anthony An-Chih Yeh
%A Chen-Hsin Lu
%A Shang-Yu Chou
%A Shih-Wei Wang
%A Chi-Wei Lee
%A Po-Han Lee
%J Journal of Modern Physics
%P 2169-2192
%@ 2153-120X
%D 2024
%I Scientific Research Publishing
%R 10.4236/jmp.2024.1512087
%X In this paper, we explore the classification of vibration modes generated by handwriting on an optical desk using deep learning architectures. Three deep learning models—Long Short-Term Memory (LSTM) networks with attention mechanism, Video Vision Transformer (ViViT), and Long-term Recurrent Convolutional Network (LRCN)—were evaluated to determine the most effective method for analyzing time series patterns generated by a Michelson interferometer. The interferometer was used to detect vibration modes created by handwriting, capturing time-series data from the diffraction patterns. Among these models, the LSTM-Attention network achieved the highest validation accuracy, reaching up to 92%, outperforming both ViViT and LRCN. These findings highlight the potential of deep learning in material science for detecting and classifying vibration patterns. The powerful performance of the LSTM-Attention model suggests that it could be applied to similar classification tasks in related fields.
%K Michelson Interferometer
%K Machine Learning
%K Vibration Modes
%K Long Short-Term Memory (LSTM)
%U http://www.scirp.org/journal/PaperInformation.aspx?PaperID=137287