Noise-Adjusted Principal Component Analysis for Buried Radioactive Target Detection and Classification

被引:19
作者
Du, Qian [1 ]
Wei, Wei [1 ]
May, Daniel [1 ]
Younan, Nicolas H. [1 ]
机构
[1] Mississippi State Univ, Dept Elect & Comp Engn, Mississippi State, MS 39762 USA
关键词
Buried target detection; classification; Gammaray spectral analysis; noise-adjusted principal component analysis; principal component analysis;
D O I
10.1109/TNS.2010.2084105
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
We present a noise-adjusted principal component analysis (NAPCA)-based approach to the detection and classification of buried radioactive targets with short sensor dwell time. The data used in the experiments is the gamma spectroscopy collected by a Sodium Iodide (NAI) scintillation detector. Spectral transformation methods are first applied to the data, followed by NAPCA. Then kappa-nearest neighbor (kappa NN) clustering is applied to the NAPCA-transformed feature subspace to achieve detection or classification. This method is evaluated using a database of 240 spectral measurements consisting of background (construction sand), benign material measurements (uranium ore), and target measurements (depleted uranium) at various depths. Compared to other widely used algorithms for depleted uranium, the proposed technique can provide better performance.
引用
收藏
页码:3760 / 3767
页数:8
相关论文
共 12 条
[1]   Discriminating nuclear threats from benign sources in gamma-ray spectra using a spectral comparison ratio method [J].
Anderson, K. K. ;
Jarman, K. D. ;
Mann, M. L. ;
Pfund, D. M. ;
Runkle, R. C. .
JOURNAL OF RADIOANALYTICAL AND NUCLEAR CHEMISTRY, 2008, 276 (03) :713-718
[2]   NEAREST NEIGHBOR PATTERN CLASSIFICATION [J].
COVER, TM ;
HART, PE .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1967, 13 (01) :21-+
[3]   The use of energy windowing to discriminate SNM from NORM in radiation portal monitors [J].
Ely, James ;
Kouzes, Richard ;
Schweppe, John ;
Siciliano, Edward ;
Strachan, Denis ;
Weier, Dennis .
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 2006, 560 (02) :373-387
[4]   A TRANSFORMATION FOR ORDERING MULTISPECTRAL DATA IN TERMS OF IMAGE QUALITY WITH IMPLICATIONS FOR NOISE REMOVAL [J].
GREEN, AA ;
BERMAN, M ;
SWITZER, P ;
CRAIG, MD .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1988, 26 (01) :65-74
[5]  
Haslip D. S., 2000, TM2000049 DREO
[6]   The role of spectroscopy versus detection for border security [J].
Kouzes, R. T. ;
Ely, J. H. .
JOURNAL OF RADIOANALYTICAL AND NUCLEAR CHEMISTRY, 2008, 276 (03) :719-723
[7]   ENHANCEMENT OF HIGH SPECTRAL RESOLUTION REMOTE-SENSING DATA BY A NOISE-ADJUSTED PRINCIPAL COMPONENTS TRANSFORM [J].
LEE, JB ;
WOODYATT, S ;
BERMAN, M .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1990, 28 (03) :295-304
[8]   Examination of count-starved gamma spectra using the method of spectral comparison ratios [J].
Pfund, David Michael ;
Runkle, Robert C. ;
Anderson, Kevin K. ;
Jarman, Kenneth D. .
IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 2007, 54 (04) :1232-1238
[9]   Reliably estimating the noise in AVIRIS hyperspectral images [J].
Roger, RE ;
Arnold, JF .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1996, 17 (10) :1951-1962
[10]   Analysis of spectroscopic radiation portal monitor data using principal components analysis [J].
Runkle, Robert C. ;
Tardiff, Mark F. ;
Anderson, Kevin K. ;
Carlson, Deborah K. ;
Smith, L. Eric .
IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 2006, 53 (03) :1418-1423