Multi-component background learning automates signal detection for spectroscopic data  

作　　者：Sebastian E.Ament Helge S.Stein Dan Guevarra Lan Zhou Joel A.Haber David A.Boyd Mitsutaro Umehara John M.Gregoire Carla P.Gomes 

机构地区：[1]Department of Computer Science,Cornell University,Ithaca,NY 14850,USA [2]Joint Center for Artificial Photosynthesis,California Institute of Technology,Pasadena,CA 91125,USA [3]Future Mobility Research Department,Toyota Research Institute of North America,Ann Arbor,MI 48105,USA

出　　处：《npj Computational Materials》2019年第1期484-490,共7页计算材料学（英文）

基　　金：The development of the MCBL algorithm,inkjet printing synthesis,and Raman measurements were supported by a an Accelerated Materials Design and Discovery grant from the Toyota Research Institute;Initial design of the algorithm and data procurement were supported by the NSF Expedition award for Computational Sustainability CCF-1522054 and by Army Research Office(ARO)award W911-NF-14-1-0498;The implementation of the algorithm for automated,unsupervised operation was supported by MURI/AFOSR grant FA9550;Compute infrastructure was provided by NSF award CNS-0832782 and by ARO DURIP award W911NF-17-1-0187;The sputter deposition and XRD measurements were supported through the Office of Science of the U.S.Department of Energy under Award No.DE-SC0004993.

摘　　要：Automated experimentation has yielded data acquisition rates that supersede human processing capabilities.Artificial Intelligence offers new possibilities for automating data interpretation to generate large,high-quality datasets.Background subtraction is a long-standing challenge,particularly in settings where multiple sources of the background signal coexist,and automatic extraction of signals of interest from measured signals accelerates data interpretation.Herein,we present an unsupervised probabilistic learning approach that analyzes large data collections to identify multiple background sources and establish the probability that any given data point contains a signal of interest.The approach is demonstrated on X-ray diffraction and Raman spectroscopy data and is suitable to any type of data where the signal of interest is a positive addition to the background signals.While the model can incorporate prior knowledge,it does not require knowledge of the signals since the shapes of the background signals,the noise levels,and the signal of interest are simultaneously learned via a probabilistic matrix factorization framework.Automated identification of interpretable signals by unsupervised probabilistic learning avoids the injection of human bias and expedites signal extraction in large datasets,a transformative capability with many applications in the physical sciences and beyond.

关 键 词：SIGNAL COMPONENT SPECTROSCOPIC 

分 类 号：TN9[电子电信—信息与通信工程]