↓ Skip to main content

Deep data analysis via physically constrained linear unmixing: universal framework, domain examples, and a community-wide platform

Overview of attention for article published in Advanced Structural and Chemical Imaging, April 2018
Altmetric Badge

Citations

dimensions_citation
50 Dimensions

Readers on

mendeley
55 Mendeley
Title
Deep data analysis via physically constrained linear unmixing: universal framework, domain examples, and a community-wide platform
Published in
Advanced Structural and Chemical Imaging, April 2018
DOI 10.1186/s40679-018-0055-8
Pubmed ID
Authors

R. Kannan, A. V. Ievlev, N. Laanait, M. A. Ziatdinov, R. K. Vasudevan, S. Jesse, S. V. Kalinin

Abstract

Many spectral responses in materials science, physics, and chemistry experiments can be characterized as resulting from the superposition of a number of more basic individual spectra. In this context, unmixing is defined as the problem of determining the individual spectra, given measurements of multiple spectra that are spatially resolved across samples, as well as the determination of the corresponding abundance maps indicating the local weighting of each individual spectrum. Matrix factorization is a popular linear unmixing technique that considers that the mixture model between the individual spectra and the spatial maps is linear. Here, we present a tutorial paper targeted at domain scientists to introduce linear unmixing techniques, to facilitate greater understanding of spectroscopic imaging data. We detail a matrix factorization framework that can incorporate different domain information through various parameters of the matrix factorization method. We demonstrate many domain-specific examples to explain the expressivity of the matrix factorization framework and show how the appropriate use of domain-specific constraints such as non-negativity and sum-to-one abundance result in physically meaningful spectral decompositions that are more readily interpretable. Our aim is not only to explain the off-the-shelf available tools, but to add additional constraints when ready-made algorithms are unavailable for the task. All examples use the scalable open source implementation from https://github.com/ramkikannan/nmflibrary that can run from small laptops to supercomputers, creating a user-wide platform for rapid dissemination and adoption across scientific disciplines.

Mendeley readers

Mendeley readers

The data shown below were compiled from readership statistics for 55 Mendeley readers of this research output. Click here to see the associated Mendeley record.

Geographical breakdown

Country Count As %
Unknown 55 100%

Demographic breakdown

Readers by professional status Count As %
Student > Ph. D. Student 19 35%
Researcher 12 22%
Professor > Associate Professor 4 7%
Student > Master 3 5%
Student > Postgraduate 3 5%
Other 4 7%
Unknown 10 18%
Readers by discipline Count As %
Materials Science 13 24%
Physics and Astronomy 9 16%
Computer Science 4 7%
Engineering 3 5%
Medicine and Dentistry 2 4%
Other 9 16%
Unknown 15 27%