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

Title: A statistical approach to combining multisource information in one-class classifiers

Journal Article · · Statistical Analysis and Data Mining
DOI:https://doi.org/10.1002/sam.11342· OSTI ID:1399493

A new method is introduced for combining information from multiple sources to support one‐class classification. The contributing sources may represent measurements taken by different sensors of the same physical entity, repeated measurements by a single sensor, or numerous features computed from a single measured image or signal. The approach utilizes the theory of statistical hypothesis testing, and applies Fisher's technique for combining p ‐values, modified to handle nonindependent sources. Classifier outputs take the form of fused p ‐values, which may be used to gauge the consistency of unknown entities with one or more class hypotheses. The approach enables rigorous assessment of classification uncertainties, and allows for traceability of classifier decisions back to the constituent sources, both of which are important for high‐consequence decision support. Application of the technique is illustrated in two challenge problems, one for skin segmentation and the other for terrain labeling. The method is seen to be particularly effective for relatively small training samples.

Research Organization:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA); SNL Laboratory Directed Research and Development (LDRD) program
Grant/Contract Number:
AC04-94AL85000
OSTI ID:
1399493
Alternate ID(s):
OSTI ID: 1400859
Report Number(s):
SAND2017-2026J; 651299
Journal Information:
Statistical Analysis and Data Mining, Vol. 10, Issue 4; ISSN 1932-1864
Publisher:
WileyCopyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 9 works
Citation information provided by
Web of Science

References (45)

The Optics of Human Skin journal July 1981
Log-polar wavelet energy signatures for rotation and scale invariant texture classification journal May 2003
Polarimetric SAR interferometry journal January 1998
Learning Hierarchical Features for Scene Labeling journal August 2013
Multiple classifiers applied to multisource remote sensing data journal January 2002
Asymptotic Optimality of Fisher's Method of Combining Independent Tests II journal March 1973
A review of novelty detection journal June 2014
A Functional Data—Analytic Approach to Signal Discrimination journal February 2001
Expert guided natural language processing using one-class classification journal June 2015
A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting journal August 1997
SLIC Superpixels Compared to State-of-the-Art Superpixel Methods journal November 2012
An Empirical Comparison of Expert-Derived and Data-Derived Classification Trees journal January 1996
Combining dependent P-values journal November 2002
Bagging predictors journal August 1996
From colour to tissue histology: Physics-based interpretation of images of pigmented skin lesions journal December 2003
Methods of combining multiple classifiers and their applications to handwriting recognition journal January 1992
One-class classification based authentication of peanut oils by fatty acid profiles journal January 2015
An overview of text-independent speaker recognition: From features to supervectors journal January 2010
The FERET evaluation methodology for face-recognition algorithms conference January 1997
Active and dynamic information fusion for facial expression understanding from image sequences journal May 2005
Growing a multi-class classifier with a reject option journal July 2008
General Four-Component Scattering Power Decomposition With Unitary Transformation of Coherency Matrix journal May 2013
Classification and Extraction of Spatial Features in Urban Areas Using High-Resolution Multispectral Imagery journal April 2007
Some bivariate uniform distributions journal January 1980
Robust Real-Time Unusual Event Detection using Multiple Fixed-Location Monitors journal March 2008
A survey on feature selection methods journal January 2014
A systematic comparison of methods for combining p-values from independent tests journal October 2004
Soft computing methods applied to combination of one-class classifiers journal January 2012
The strength of weak learnability journal June 1990
Estimating the Support of a High-Dimensional Distribution journal July 2001
Evolving feature selection journal November 2005
Wavelet packet feature extraction for vibration monitoring journal June 2000
Distribution of Fisher's combination statistic when the tests are dependent journal January 2010
Combining probability from independent tests: the weighted Z-method is superior to Fisher's approach: Combining probabilities from many tests journal August 2005
ECG Beats Classification Using Mixture of Features journal January 2014
Statistical pattern recognition: a review journal January 2000
Support-vector networks journal September 1995
A Fast Learning Algorithm for Deep Belief Nets journal July 2006
Combination of multiple classifiers using local accuracy estimates journal April 1997
A New Coherency Formalism for Change Detection and Phenomenology in SAR Imagery: A Field Approach journal July 2009
On the Combination of Independent Test Statistics journal June 1967
Effective dimension reduction methods for tumor classification using gene expression data journal March 2003
400: A Method for Combining Non-Independent, One-Sided Tests of Significance journal December 1975
A Review of Anomaly based Intrusion Detection Systems journal August 2011
Arcing classifier (with discussion and a rejoinder by the author) journal June 1998