CaltechAUTHORS
  A Caltech Library Service

Imitation Refinement for X-ray Diffraction Signal Processing

Bai, Junwen and Lai, Zihang and Yang, Runzhe and Xue, Yexiang and Gregoire, John and Gomes, Carla (2019) Imitation Refinement for X-ray Diffraction Signal Processing. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE , Piscataway, NJ, pp. 3337-3341. ISBN 978-1-5386-4658-8. https://resolver.caltech.edu/CaltechAUTHORS:20190425-082002655

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190425-082002655

Abstract

Many real-world tasks involve identifying signals from data satisfying background or prior knowledge. In domains like materials discovery, due to the flaws and biases in raw experimental data, the identification of X-ray diffraction (XRD) signals often requires significant (manual) expert work to find refined signals that are similar to the ideal theoretical ones. Automatically refining the raw XRD signals utilizing simulated theoretical data is thus desirable. We propose imitation refinement, a novel approach to refine imperfect input signals, guided by a pre-trained classifier incorporating prior knowledge from simulated theoretical data, such that the refined signals imitate the ideal ones. The classifier is trained on the ideal simulated data to classify signals and learns an embedding space where each class is represented by a prototype. The refiner learns to refine the imperfect signals with small modifications, such that their embeddings are closer to the corresponding prototypes. We show that the refiner can be trained in both supervised and unsupervised fashions. We further illustrate the effectiveness of the proposed approach both qualitatively and quantitatively in an X-ray diffraction signal refinement task in materials discovery.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/ICASSP.2019.8683723DOIArticle
ORCID:
AuthorORCID
Gregoire, John0000-0002-2863-5265
Additional Information:© 2019 IEEE. Work supported by an NSF Expedition award for Computational Sustainability (CCF-1522054), NSF Computing Research Infrastructure (CNS-1059284), NSF Inspire (1344201), a MURI/AFOSR grant (FA9550), and a grant from the Toyota Research Institute.
Funders:
Funding AgencyGrant Number
NSFCCF-1522054
NSFCNS-1059284
NSFIIS-1344201
Air Force Office of Scientific Research (AFOSR)FA9550
Toyota Research InstituteUNSPECIFIED
Subject Keywords:refinement, classification, X-ray diffraction signals, embeddings, neural nets
Record Number:CaltechAUTHORS:20190425-082002655
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190425-082002655
Official Citation:J. Bai, Z. Lai, R. Yang, Y. Xue, J. Gregoire and C. Gomes, "Imitation Refinement for X-ray Diffraction Signal Processing," ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom, 2019, pp. 3337-3341. doi: 10.1109/ICASSP.2019.8683723
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94960
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:25 Apr 2019 16:01
Last Modified:03 Oct 2019 21:09

Repository Staff Only: item control page