skip to main content
DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Source identification by non-negative matrix factorization combined with semi-supervised clustering

Abstract

Machine-learning methods and apparatus are provided to solve blind source separation problems with an unknown number of sources and having a signal propagation model with features such as wave-like propagation, medium-dependent velocity, attenuation, diffusion, and/or advection, between sources and sensors. In exemplary embodiments, multiple trials of non-negative matrix factorization are performed for a fixed number of sources, with selection criteria applied to determine successful trials. A semi-supervised clustering procedure is applied to trial results, and the clustering results are evaluated for robustness using measures for reconstruction quality and cluster separation. The number of sources is determined by comparing these measures for different trial numbers of sources. Source locations and parameters of the signal propagation model can also be determined. Disclosed methods are applicable to a wide range of spatial problems including chemical dispersal, pressure transients, and electromagnetic signals, and also to non-spatial problems such as cancer mutation.

Inventors:
; ; ; ;
Issue Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1735270
Patent Number(s):
10776718
Application Number:
15/690,176
Assignee:
Triad National Security, LLC (Los Alamos, NM)
Patent Classifications (CPCs):
G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING
DOE Contract Number:  
AC52-06NA25396
Resource Type:
Patent
Resource Relation:
Patent File Date: 08/29/2017
Country of Publication:
United States
Language:
English

Citation Formats

Alexandrov, Boian S., Alexandrov, Ludmil B., Iliev, Filip L., Stanev, Valentin G., and Vesselinov, Velimir V.. Source identification by non-negative matrix factorization combined with semi-supervised clustering. United States: N. p., 2020. Web.
Alexandrov, Boian S., Alexandrov, Ludmil B., Iliev, Filip L., Stanev, Valentin G., & Vesselinov, Velimir V.. Source identification by non-negative matrix factorization combined with semi-supervised clustering. United States.
Alexandrov, Boian S., Alexandrov, Ludmil B., Iliev, Filip L., Stanev, Valentin G., and Vesselinov, Velimir V.. Tue . "Source identification by non-negative matrix factorization combined with semi-supervised clustering". United States. https://www.osti.gov/servlets/purl/1735270.
@article{osti_1735270,
title = {Source identification by non-negative matrix factorization combined with semi-supervised clustering},
author = {Alexandrov, Boian S. and Alexandrov, Ludmil B. and Iliev, Filip L. and Stanev, Valentin G. and Vesselinov, Velimir V.},
abstractNote = {Machine-learning methods and apparatus are provided to solve blind source separation problems with an unknown number of sources and having a signal propagation model with features such as wave-like propagation, medium-dependent velocity, attenuation, diffusion, and/or advection, between sources and sensors. In exemplary embodiments, multiple trials of non-negative matrix factorization are performed for a fixed number of sources, with selection criteria applied to determine successful trials. A semi-supervised clustering procedure is applied to trial results, and the clustering results are evaluated for robustness using measures for reconstruction quality and cluster separation. The number of sources is determined by comparing these measures for different trial numbers of sources. Source locations and parameters of the signal propagation model can also be determined. Disclosed methods are applicable to a wide range of spatial problems including chemical dispersal, pressure transients, and electromagnetic signals, and also to non-spatial problems such as cancer mutation.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2020},
month = {9}
}

Patent:

Save / Share:

Works referenced in this record:

A blind source separation technique using second-order statistics
journal, January 1997


A Machine Learning Approach for Locating Acoustic Emission
journal, October 2010


Combining multiple clusterings by soft correspondence
patent, June 2012


Clock-like mutational processes in human somatic cells
journal, November 2015


Mutational signatures associated with tobacco smoking in human cancer
journal, November 2016


Learning the parts of objects by non-negative matrix factorization
journal, October 1999


Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture
journal, July 1991


Reference-free time-based localization for an asynchronous target
journal, January 2012


Algorithm AS 136: A K-Means Clustering Algorithm
journal, January 1979


ToQ.jl: A high-level programming language for D-Wave machines based on Julia
conference, September 2016


An Approach to Bayesian Sensitivity Analysis
journal, November 1996


Fully Scalable Methods for Distributed Tensor Factorization
journal, January 2017


Shifted factor analysis?Part II: Algorithms
journal, January 2003


Shifted factor analysis?Part I: Models and properties
journal, January 2003


Statistical source identification of metals in groundwater exposed to industrial contamination
journal, May 2007


Multivariate statistical and GIS-based approach to identify heavy metal sources in soils
journal, October 2001


On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming
journal, April 2005


Understanding the origins of human cancer
journal, December 2015


Artificial intelligence for management and control of pollution minimization and mitigation processes
journal, March 2003


Machine Learning Approach for Contamination Source Identification in Water Distribution Systems
conference, July 2012


Silhouettes: A graphical aid to the interpretation and validation of cluster analysis
journal, November 1987


Blind source separation for groundwater pressure analysis based on nonnegative matrix factorization
journal, September 2014


Probabilistic sensitivity analysis of complex models: a Bayesian approach
journal, August 2004


Characterization of guanidiniocarbonyl pyrroles in water by pH-dependent UV Raman spectroscopy and component analysis
journal, January 2008


Dynamical Model of Drug Accumulation in Bacteria: Sensitivity Analysis and Experimentally Testable Predictions
journal, November 2016


Using Bayesian statistics in the estimation of heat source in radiation
journal, January 2005


Denoising acoustic signals using constrained non-negative matrix factorization
patent, September 2011


A mutational signature in gastric cancer suggests therapeutic strategies
journal, October 2015


Mutational signatures: the patterns of somatic mutations hidden in cancer genomes
journal, February 2014


Three-dimensional numerical inversion of pneumatic cross-hole tests in unsaturated fractured tuff: 1. Methodology and borehole effects
journal, December 2001


F lexi F a CT: Scalable Flexible Factorization of Coupled Tensors on Hadoop
conference, April 2014


Robust Multilinear Tensor Rank Estimation Using Higher Order Singular Value Decomposition and Information Criteria
journal, March 2017


Applicability of statistical learning algorithms in groundwater quality modeling: GROUNDWATER MODELING BY LEARNING MACHINES
journal, May 2005


A new structure identification scheme for ANFIS and its application for the simulation of virtual air pollution monitoring stations in urban areas
journal, May 2015


Broadly targeted CD8+ T cell responses restricted by major histocompatibility complex E
journal, January 2016


Second-order optimization based adaptive PARAFAC decomposition of three-way tensors
journal, April 2017


Identification of Pumping Influences in Long-Term Water Level Fluctuations
journal, April 2011


Document clustering based on non-negative matrix factorization
conference, January 2003

  • Xu, Wei; Liu, Xin; Gong, Yihong
  • Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval - SIGIR '03
  • https://doi.org/10.1145/860435.860485

Acoustic source localization in mixed field using spherical microphone arrays
journal, June 2014


Deciphering Signatures of Mutational Processes Operative in Human Cancer
journal, January 2013


Automatic Relevance Determination in Nonnegative Matrix Factorization with the /spl beta/-Divergence
journal, July 2013


Algorithm quasi‐optimal (AQ) learning
journal, March 2010

  • Cervone, Guido; Franzese, Pasquale; Keesee, Allen P. K.
  • Wiley Interdisciplinary Reviews: Computational Statistics, Vol. 2, Issue 2
  • https://doi.org/10.1002/wics.78