DeepAI AI Chat
Log In Sign Up

Decoding the shift-invariant data: applications for band-excitation scanning probe microscopy

by   Yongtao Liu, et al.

A shift-invariant variational autoencoder (shift-VAE) is developed as an unsupervised method for the analysis of spectral data in the presence of shifts along the parameter axis, disentangling the physically-relevant shifts from other latent variables. Using synthetic data sets, we show that the shift-VAE latent variables closely match the ground truth parameters. The shift VAE is extended towards the analysis of band-excitation piezoresponse force microscopy (BE-PFM) data, disentangling the resonance frequency shifts from the peak shape parameters in a model-free unsupervised manner. The extensions of this approach towards denoising of data and model-free dimensionality reduction in imaging and spectroscopic data are further demonstrated. This approach is universal and can also be extended to analysis of X-ray diffraction, photoluminescence, Raman spectra, and other data sets.


page 9

page 11

page 12

page 13


Disentangling Physical Parameters for Anomalous Sound Detection Under Domain Shifts

To develop a sound-monitoring system for machines, a method for detectin...

An adaptive dimension reduction algorithm for latent variables of variational autoencoder

Constructed by the neural network, variational autoencoder has the overf...

Learning to regularize with a variational autoencoder for hydrologic inverse analysis

Inverse problems often involve matching observational data using a physi...

6GCVAE: Gated Convolutional Variational Autoencoder for IPv6 Target Generation

IPv6 scanning has always been a challenge for researchers in the field o...

3D Nanoscale Mapping of Short-Range Order in GeSn Alloys

GeSn on Si has attracted much research interest due to its tunable direc...