| Fast Multiscale Algorithms for Information Representation and Fusion |
Oct 2012 |
11 pages |
| Authors:
Devasis Bassu; APPLIED COMMUNICATION SCIENCES PISCATAWAY NJ
|
 | In the ninth quarter of the work effort, we focused on a) conducting experiments on real-world data sets using the developed algorithms, b) design/implementation of the Multiscale Heat-Kernel Coordinates (MHKC) algorithms and c) packaging for releasing the software as open source. This report documents algorithm designs for the MHKC algorithms. The project is currently on track - in the upcoming quarter, we will continue applying the developed algorithms to various ... |
|
| A Block Coordinate Descent Method for Multi-Convex Optimization with Applications to Nonnegative Tensor Factorization and Completion |
Aug 2012 |
25 pages |
| Authors:
Yangyang Xu; Wotao Yin; RICE UNIV HOUSTON TX DEPT OF COMPUTATIONAL AND APPLIED MATHEMATICS
|
| This paper considers block multi-convex optimization, where the feasible set and objective function are generally non-convex but convex in each block of variables. We review some of its interesting examples and propose a generalized block coordinate descent method. Under certain conditions, we show that any limit point satisfies the Nash equilibrium conditions. Furthermore, we establish its global convergence and estimate its asymptotic convergence rate by assuming a property based on ... |
|
| Learning Circulant Sensing Kernels |
Aug 2012 |
20 pages |
| Authors:
Yangyang Xu; Wotao Yin; Stanley Osher; RICE UNIV HOUSTON TX DEPT OF COMPUTATIONAL AND APPLIED MATHEMATICS
|
| In signal acquisition, Toeplitz and circulant matrices are widely used as sensing operators. They correspond to discrete convolutions and are easily or even naturally realized in various applications. For compressive sensing, recent work has used random Toeplitz and circulant sensing matrices and proved their efficiency in theory, by computer simulations, as well as through physical optical experiments. Motivated by recent work, we propose models to learn a circulant sensing matrix/operator ... |
|
| On the Extraction of Spread-Spectrum Hidden Data in Digital Media |
Jun 2012 |
6 pages |
| Authors:
MING LI; Michel Kulhandjian; Dimitris A Pados; Stella N Batalama; Michael J Medley; John D Matyjas; STATE UNIV OF NEW YORK AT BUFFALO DEPT OF ELECTRICAL ENGINEERING
|
| This paper considers the problem of blindly extracting data embedded over a wide band in a spectrum (transform) domain of a digital medium (image, audio, video). We first develop a multi-signature iterative generalized least-squares (MIGLS) core procedure to seek unknown data hidden in hosts via multi-signature direct-sequence spread-spectrum embedding. Neither the original host nor the embedding signatures are assumed available. Then, cross-correlation enhanced M-IGLS (CCM- IGLS), a procedure described herein ... |
|
| Jensen-Bregman LogDet Divergence for Efficient Similarity Computations on Positive Definite Tensors |
02 May 2012 |
31 pages |
| Authors:
Anoop Cherian; Suvrit Sra; Arindam Banerjee; Nikos Papanikolopoulos; MINNESOTA UNIV MINNEAPOLIS DEPT OF COMPUTER SCIENCE AND ENGINEERING
|
| Covariance matrices provide an easy platform for fusing multiple features compactly and as a result have found immense success in several computer vision applications including activity recognition, visual surveillance, and diffusion tensor imaging. An important task in all of these applications is to compute the distance between covariance matrices using a (dis)similarity function, for which the natural choice is the Riemannian metric corresponding to the manifold inhabited by these matrices. ... |
|
| Exact Low-Rank Matrix Completion from Sparsely Corrupted Entries via Adaptive Outlier Pursuit |
02 May 2012 |
13 pages |
| Authors:
Ming Yan; Yi Yang; Stanley Osher; CALIFORNIA UNIV LOS ANGELES DEPT OF MATHEMATICS
|
| Recovering a low-rank matrix from some of its linear measurements is a popular problem in many areas of science and engineering. One special case of it is the matrix completion problem, where we need to reconstruct a low-rank matrix from incomplete samples of its entries. A lot of efficient algorithms have been proposed to solve this problem and they perform well when Gaussian noise with a small variance is added ... |
|
| Real-time Probabilistic Covariance Tracking with Efficient Model Update |
May 2012 |
16 pages |
| Authors:
Yi Wu; Jian Cheng; Jinqiao Wang; Hanqing Lu; Jun Wang; Haibin Ling; Erik Blasch; Li Bai; AIR FORCE RESEARCH LAB WRIGHT-PATTERSON AFB OH
|
| The recently proposed covariance region descriptor has been proven robust and versatile for a modest computational cost. The covariance matrix enables efficient fusion of different types of features, where the spatial and statistical properties as well as their correlation are characterized. The similarity between two covariance descriptors is measured on Riemannian manifolds. Based on the same metric, but with a probabilistic framework, we propose a novel tracking approach on Riemannian ... |
|
| Local Principal Component Pursuit for Nonlinear Datasets |
May 2012 |
5 pages |
| Authors:
Brendt Wohlberg; Rick Chartrand; James Theiler; LOS ALAMOS NATIONAL LAB NM
|
| A robust version of Principal Component Analysis (PCA) can be constructed via a decomposition of a data matrix into low-rank and sparse components, the former representing a low-dimensional linear model of the data, and the latter representing sparse deviations from the low-dimensional subspace. This decomposition has been shown to be highly effective, but the underlying model is not appropriate when the data are not modeled well by a single low-dimensional ... |
|
| Discovering Structure via Matrix Rank Minimization |
25 Apr 2012 |
8 pages |
| Authors:
Stephen A Vavasis; Henry Wolkowicz; WATERLOO UNIV (ONTARIO)
|
| During this three-year project, Vavasis and Wolkowicz, together with students, postdocs, and colleagues, made a number of advances in the convex optimization and its application to data mining and sensor localization. In this report we highlight some of these accomplishments. |
|
| Using QR Factorization for Real-Time Anomaly Detection in Hyperspectral Images |
22 Mar 2012 |
59 pages |
| Authors:
Kelly R Bush; AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OH GRADUATE SCHOOL OF ENGINEERING AND MANAGEMENT
|
| Anomaly detection has been used successfully on hyperspectral images for over a decade. However, there is an ever increasing need for real-time anomaly detectors. Historically, anomaly detection methods have focused on analysis after the entire image has been collected. As useful as post-collection anomaly detection is, there is a great advantage to detecting an anomaly as it is being collected. This research is focused on speeding up the process of ... |
|
| Matrix Representation of Iterative Approximate Byzantine Consensus in Directed Graphs |
08 Mar 2012 |
18 pages |
| Authors:
Nitin Vaidya; ILLINOIS UNIV AT URBANA DEPT OF ELECTRICAL AND COMPUTER ENGINEERING
|
| This paper presents a proof of correctness of an iterative approximate Byzantine consensus (IABC) algorithm for directed graphs. The iterative algorithm allows fault- free nodes to reach approximate consensus despite the presence of up to f Byzantine faults. Necessary conditions on the underlying network graph for the existence of a correct IABC algorithm were shown in our recent work [15, 16]. [15] also analyzed a specific IABC algorithm and showed ... |
|
| Matrix Determination of Reflectance of Hidden Object via Indirect Photography |
Mar 2012 |
69 pages |
| Authors:
Simon S Ferrel; AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OH GRADUATE SCHOOL OF ENGINEERING AND MANAGEMENT
|
| Indirect photography is a recently demonstrated technique that expands on the principles of dual photography and allows for the imaging of hidden objects. A camera and light source are collocated with neither having line-of-sight access to the hidden object. Light from the source, a laser, is reflected off a visible non-specular surface onto the hidden object, where it is reflected back to the initial non-specular surface and collected by the ... |
|
| Determining Optimal Evacuation Decision Policies for Disasters |
Mar 2012 |
81 pages |
| Authors:
Jason C Crews; NAVAL POSTGRADUATE SCHOOL MONTEREY CA DEPT OF OPERATIONS RESEARCH
|
| Decision making in the face of uncertainty is a difficult task, and this is exacerbated when the decision is irreversible, it involves a near-term deadline, and/or the cost of a bad decision is high. Deciding whether to stay or evacuate from an impending natural disaster is difficult for all of these reasons. This thesis explores the evacuation decision as a Markov decision problem. We develop a generic disaster model to ... |
|
| Toward an Integrated Framwork for Data-Efficient Parametric Adaptive Detection |
27 Feb 2012 |
47 pages |
| Authors:
Hongbin Li; STEVENS INST OF TECHNOLOGY HOBOKEN NJ
|
| The conjugate-gradient (CG) algorithm is investigated for reduced-rank STAP detection. A family of CG matched filter (CG-MF) is developed by using the k-th iteration of the CG in solving the Wiener-Hopf equation. The performance the CG-MF detectors is examined for two cases. The first involves an arbitrary covariance matrix. It is shown that each CG-MF detector 1) yields the highest output SINR and smallest MSE among all linear solutions in ... |
|
| Signal Designs via Combinatorial Designs |
24 Feb 2012 |
9 pages |
| Authors:
K T Arasu; WRIGHT STATE UNIV DAYTON OH DEPT OF MATHEMATICS AND STATISTICS
|
| This report describes progress to date on designing signals using combinatorial designs. We shall regard signal design problems as The Correlation Problem . The Correlation Problem is to design sequences with specified lengths with entries chosen from a specified finite set so that all non-trivial periodic autocorrelations lie in a prescribed restrictive set. Mathematical tools from algebraic number theory, representation theory and group theory are employed to investigate the theory ... |
|
| Random Matrices, Combinatorics, Numerical Linear Algebra and Complex Networks |
16 Feb 2012 |
13 pages |
| Authors:
Van H Vu; RUTGERS - THE STATE UNIV PISCATAWAY NJ
|
| Understanding large, random, matrices is important in many areas of interest to AFORS. These includes the probabilistic analysis of problems in numerical linear algebra, the efficiency of the simplex method in linear programming, the key parameters in statistical sampling, the expansion of complex networks such as the Internet graph, to mention a few. We have developed new methods with combinatorial flavor, combining tools from combinatorics, probability and high dimensional geometry ... |
|
| The Masked Sample Covariance Estimator: An Analysis via the Matrix Laplace Transform |
Feb 2012 |
23 pages |
| Authors:
Richard Y Chen; Alex Gittens; Joel A Tropp; CALIFORNIA INST OF TECH PASADENA DEPT OF COMPUTING AND MATHEMATICAL SCIENCES
|
| Covariance estimation becomes challenging in the regime where the number p of vari- ables outstrips the number n of samples available to construct the estimate. One way to circumvent this problem is to assume that the covariance matrix is nearly sparse and to focus on estimating only the signi cant entries. To analyze this approach, Levina and Vershynin (2011) introduce a formalism called masked covariance estimation, where each entry of ... |
|
| Matrix Concentration Inequalities via the Method of Exchangeable Pairs |
27 Jan 2012 |
30 pages |
| Authors:
Lester Mackey; Michael I Jordan; Richard Y Chen; Brendan Farrell; Joel A Tropp; CALIFORNIA INST OF TECH PASADENA DEPT OF COMPUTING AND MATHEMATICAL SCIENCES
|
| This paper derives exponential concentration inequalities and polynomial moment inequalities for the spectral norm of a random matrix. The analysis requires a matrix extension of the scalar concentration theory developed by Sourav Chatterjee using Stein's method of exchangeable pairs. When applied to a sum of independent random matrices, this approach yields matrix generalizations of the classical inequalities due to Hoe ding, Bernstein, Khintchine, and Rosenthal. The same technique delivers bounds ... |
|
| Joining of Components of Complex Structures for Improved Dynamic Response |
28 Oct 2011 |
40 pages |
| Authors:
Sung-Kwon Hong; Bogdan I Epureanu; Matthew P Castanier; ARMY TANK AUTOMOTIVE RESEARCH DEVELOPMENT AND ENGINEERING CENTER WARREN MI
|
| The goal of this work is to provide a method for choosing joining (e.g., bolt) locations for attaching structural reinforcements onto complex structures. The joining locations affect structural performance criteria such as the frequency response and the static compliance of the modified structure. One approach to finding improved/ optimal joining locations is to place the joints such that the total amount of energy input into the structure (from external forces) ... |
|
| Next-Generation Parametric Reduced-Order Models |
24 Oct 2011 |
57 pages |
| Authors:
Sung-Kwon Hong; Bogdan I Epureanu; Matthew P Castanier; ARMY TANK AUTOMOTIVE RESEARCH DEVELOPMENT AND ENGINEERING CENTER WARREN MI
|
| Novel parametric reduced-order models are proposed for fast reanalysis to predict the dynamic response of complex structures, which suffered thickness variations caused by design changes or damage in one or more substructures. Parametric reduced-order models developed previously have two important challenges to overcome to improve accuracy and performance: (a) the transformation matrix is not mathematically stable, (b) the Taylor series parameterization techniques do not capture thickness variations of the structure ... |
|
| Eigengaps for Hub-Dominant Matrices |
Sep 2011 |
17 pages |
| Authors:
Lixin Shen; Bruce W Suter; AIR FORCE RESEARCH LAB ROME NY INFORMATION DIRECTORATE
|
| Hub-dominant matrices are natural extensions of hub matrices. In this article we study eigengaps of the Gram matrix associated with a hub-dominant matrix. A class of hub-dominant matrices is then constructed by using equiangular tight frames. |
|
| Calculating Path-Dependent Travel Time Prediction Variance and Covariance for a Global Tomographic P-Velocity Model |
Sep 2011 |
11 pages |
| Authors:
Jim R Hipp; Andre V Encarnacao; Chris J Young; Sandy Ballard; Marcus C Chang; W S Phillips; Mike L Begnaud; LOS ALAMOS NATIONAL LAB NM
|
| Several studies have shown that global 3D models of the compression wave speed in the Earth's mantle can provide superior first P travel time predictions at both regional and teleseismic distances. However, given the variable data quality and uneven data sampling associated with this type of model, it is essential that there be a means to calculate high-quality estimates of the path-dependent variance and covariance associated with the predicted travel ... |
|
| Green's Symmetries In Finite Digraphs |
15 AUG 2011 |
11 pages |
| Authors:
Allen D. Parks; NAVAL SURFACE WARFARE CENTER DAHLGREN VA ELECTROMAGNETIC AND SENSOR SYSTEMS DIV
|
| The semigroup D(sub V) of digraphs on a set V of n labeled vertices is defined. It is shown that D(sub V) is faithfully represented by the semigroup B(sub n) of n x n Boolean matrices and that the Green's L, R, H, and D equivalence classifications of digraphs in D(sub V) follow directly from the Green's classifications already established for Bn. The new results found from this are: (i) ... |
|
| Tail Bounds for All Eigenvalues of a Sum of Random Matrices |
21 Jul 2011 |
24 pages |
| Authors:
Alex Gittens; Joel A Tropp; CALIFORNIA INST OF TECH PASADENA DEPT OF COMPUTING AND MATHEMATICAL SCIENCES
|
| The field of nonasymptotic random matrix theory has traditionally focused on the problem of bounding the extreme eigenvalues of a random matrix. In some circumstances, however, we may also be interested in studying the behavior of the interior eigenvalues. In this case, classical tools do not readily apply. Indeed, the interior eigenvalues are determined by the minmax of a random process, which is very challenging to control. This paper demonstrates ... |
|
| The Restricted Isometry Property for Time-Frequency Structured Random Matrices |
16 Jun 2011 |
26 pages |
| Authors:
Goetz E Pfander; Holger Rauhut; Joel A Tropp; CALIFORNIA INST OF TECH PASADENA DEPT OF COMPUTING AND MATHEMATICAL SCIENCES
|
| We establish the restricted isometry property for finite dimensional Gabor systems, that is, for families of time{frequency shifts of a randomly chosen window function. We show that the s-th order restricted isometry constant of the associated n n2 Gabor synthesis matrix is small provided s less or equal to cn2/3 / log2 n. This improves on previous estimates that exhibit quadratic scaling of n in s. Our proof develops bounds ... |
|
| Parametric Rao Tests for Multichannel Adaptive Detection in Partially Homogeneous Environment |
11 MAR 2011 |
12 pages |
| Authors:
Pu Wang; Hongbin Li; Braham Himed; STEVENS INST OF TECH HOBOKEN NJ DEPT OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE
|
| This paper considers the problem of detecting a multichannel signal in partially homogeneous environments, where the disturbances in both test signal and training signals share the same covariance matrix up to an unknown power scaling factor. Two different parametric Rao tests, referred to as the normalized parametric Rao (NPRao) test and the scale-invariant parametric Rao (SI-PRao) test, respectively, are developed by modeling the disturbance as a multichannel autoregressive (AR)process. The ... |
|
| User-Friendly Tail Bounds for Matrix Martingales |
16 Jan 2011 |
15 pages |
| Authors:
Joel A Tropp; CALIFORNIA INST OF TECH PASADENA
|
| This report presents probability inequalities for sums of adapted sequences of random self-adjoint matrices. The results frame simple, easily verifiable hypotheses on the summands, and they yield strong conclusions about the large-deviation behavior of the maximum eigenvalue of the sum. The methods also specialize to sums of independent random matrices. |
|
| Factorizations and Representations of Binary Polynomial Recurrences by Matrix Methods |
Jan 2011 |
13 pages |
| Authors:
Emrah Kilic; Pantelimon Stanica; NAVAL POSTGRADUATE SCHOOL MONTEREY CA DEPT OF APPLIED MATHEMATICS
|
| In this paper, the authors derive factorizations and representations of a polynomial analogue of an arbitrary binary sequence by matrix methods. It generalizes various results on Fibonacci, Lucas, Chebyshev, and Morgan-Voyce polynomials. |
|
| A Matrix Approach for General Higher Order Linear Recurrences |
Jan 2011 |
18 pages |
| Authors:
Emrah Kilic; Pantelimon Stanica; NAVAL POSTGRADUATE SCHOOL MONTEREY CA DEPT OF APPLIED MATHEMATICS
|
| We consider k sequences of generalized order-k linear recurrences with arbitrary initial conditions and coefficients, and we give their generalized Binet formulas and generating functions. We also obtain a new matrix method to derive explicit formulas for the sums of terms of the k sequences. Further some relationships between determinants of certain Hessenberg matrices and the terms of these sequences are obtained. |
|
| The Spectrum of Generalized Petersen Graphs |
05 Sep 2010 |
11 pages |
| Authors:
Ralucca Gera; Pantelimon Stanica; NAVAL POSTGRADUATE SCHOOL MONTEREY CA DEPT OF APPLIED MATHEMATICS
|
| In this paper, we completely describe the spectrum of the generalized Petersen graph P(n, k), thus adding to the classes of graphs whose spectrum is completely known. |
|
| Generating Matrices of C-nomial Coefficients and Their Spectra |
20 Apr 2010 |
14 pages |
| Authors:
Emrah Kilic; Pantelimon Stanica; NAVAL POSTGRADUATE SCHOOL MONTEREY CA DEPT OF APPLIED MATHEMATICS
|
| In this paper, we consider a generalization of binomial coefficients, called C-nomial coefficients, dependent upon a sequence {un}n, with indices in arithmetic progressions. We obtain a general recurrence relation and a generating matrix, and point out some new relationships between these coefficients and the generalized Pascal matrices. Further, we obtain generating functions, combinatorial representations, and many new interesting identities and properties of these coefficients. |
|
| The Lehmer Matrix and Its Recursive Analogue |
Jan 2010 |
14 pages |
| Authors:
Emrah Kilic; Pantelimon Stanica; NAVAL POSTGRADUATE SCHOOL MONTEREY CA DEPT OF APPLIED MATHEMATICS
|
| This paper considers the Lehmer matrix and its recursive analogue. The determinant of Lehmer matrix is derived explicitly by both its LU and Cholesky factorizations. We further define a generalized Lehmer matrix with (i; j) entries gij = min {ui+1, uj+1} / max {ui+1, uj+1} where un is the nth term of a binary sequence {un}. We derive both the LU and Cholesky factorizations of this analogous matrix and we ... |
|
| Balance and Ensemble Kalman Filter Localization Techniques |
2010 |
38 pages |
| Authors:
Steven J. Greybush; Eugenia Kalnay; Takemasa Miyoshi; Kayo Ide; Brian R. Hunt; MARYLAND UNIV COLLEGE PARK
|
| In Ensemble Kalman Filter data assimilation, localization modifies the error covariance matrices to suppress the influence of distant observations, removing spurious long distance correlations. In addition to allowing efficient parallel implementation, this takes advantage of the atmosphere's lower dimensionality in local regions. There are two primary methods for localization. In B-localization, the background error covariance matrix elements are reduced by a Schur product so that correlations between grid points that ... |
|
| Multipath Diversity and Coding Gains of Cyclic-Prefixed Single Carrier Systems |
Apr 2009 |
5 pages |
| Authors:
Mounir Ghogho; Victor P Gil-Jimenez; Ananthram Swami; LEEDS UNIV (UNITED KINGDOM)
|
| The multipath diversity and coding gain metrics for cyclic-prefixed single-carrier (SC-CP) systems, which characterize the bit error rate (BER) at high SNR, have not been carefully studied in the literature. We first show that, unlike OFDM, the diversity and coding gains for SC-CP are data realization-dependent. Then, we show that there is a signal-to-noise ratio (SNR) threshold beyond which the dominant diversity order starts deviating from the maximum diversity order ... |
|
| Rational Canonical Form of Polyphase Matrices with Applications to Designing Paraunitary Filter Banks |
Apr 2009 |
5 pages |
| Authors:
Peter Vouras; Trac Tran; Michael Ching; NAVAL RESEARCH LAB WASHINGTON DC
|
| In this paper we consider the rational canonical form of arbitrary polyphase matrices and use it to derive a simple implementation of paraunitary filter banks (PUFBs) based on a cascade of elementary building blocks. Furthermore, this decomposition is shown to be easily extendable to include a large class of perfect reconstruction filter banks (PRFBs) and can be especially useful for deriving the initial condition of PUFB design algorithms. |
|
| Factorizations and Representations of Second Order Linear Recurrences with Indices in Arithmetic Progressions |
Jan 2009 |
14 pages |
| Authors:
E Kilic; P Stanica; NAVAL POSTGRADUATE SCHOOL MONTEREY CA DEPT OF APPLIED MATHEMATICS
|
| In this paper we consider second order recurrences {Vk} and {Un} We give second order linear recurrences for the sequences {V +/- kn} and {U +/-kn}. Using these recurrence relations, we derive relationships between the determinants of certain matrices and these sequences. Further, as generalizations of the earlier results, we give representations and trigonometric factorizations of these sequences by matrix methods and methods relying on Chebyshev polynomials of the first ... |
|
| Spectral Properties of Some Combinatorial Matrices |
30 Nov 2008 |
13 pages |
| Authors:
Emrah Kilic; Gabriela N Stanica; Pantelimon Stanica; NAVAL POSTGRADUATE SCHOOL MONTEREY CA DEPT OF APPLIED MATHEMATICS
|
| In this paper we investigate the spectra and related questions for various combinatorial matrices, generalizing work by Carlitz, Cooper and Kennedy. |
|
| Wafer-Fused Orientation-Patterned GaAs |
13 FEB 2008 |
9 pages |
| Authors:
Jin Li; David B. Fenner; Krongtip Termkoa; Mark G. Allen; Peter F. Moulton; Candace Lynch; David F. Bliss; William D. Goodhue; MASSACHUSETTS UNIV LOWELL
|
| The fabrication of thick orientation-patterned GaAs (OP-GaAs) films is reported using a two-step process where an OP-GaAs template with the desired crystal domain pattern was prepared by wafer fusion bonding and then a thick film was grown over the template by low pressure hydride vapor phase epitaxy (HVPE). The OP template was fabricated using molecular beam epitaxy (MBE) followed by thermocompression wafer fusion, substrate removal, and lithographic patterning. On-axis (100) ... |
|
| Computing the Observed Information Matrix for Dynamic Mixture Models |
25 SEP 2006 |
87 pages |
| Authors:
Michael J. Walsh; NAVAL UNDERSEA WARFARE CENTER DIV NEWPORT RI
|
| The observed information matrix for an important class of finite mixture models, called dynamic mixture models, is derived in this report. Dynamic mixture models are useful probability models for random data originating from a number of distinct moving sources. The multiple-target tracking problem is one application of these models. For these models, the inverse of the observed information matrix is a consistent estimate of the error-covariance matrix for the mixture ... |
|
| Polarimetric SAR Image Classification Employing Subaperture Polarimetric Analysis |
25 JUL 2005 |
4 pages |
| Authors:
T. L. Ainsworth; J. S. Lee; NAVAL RESEARCH LAB WASHINGTON DC REMOTE SENSING DIV
|
| Polarimetric SAR image classification remains an important research area. Various methods continue to be developed for specific applications. High-resolution polarimetric SAR systems and advances in computational and data storage capabilities have revived interest in novel polarimetric analysis techniques. Accordingly, subaperture analysis of polarimetric SAR data has received renewed attention. A central assumption of SAR image formation is that individual radar scatterers are stationary; they have no structure and provide a ... |
|
| Investigation on Constrained Matrix Factorization for Hyperspectral Image Analysis |
25 JUL 2005 |
4 pages |
| Authors:
Qian Du; Ivica Kopriva; Harold Szu; MISSISSIPPI STATE UNIV MISSISSIPPI STATE DEPT OF ELECTRICAL AND COMPUTER ENGINEERING
|
| Matrix factorization is applied to unsupervised linear unmixing for hyperspectral imagery. The algorithm, called nonnegative matrix factorization, is used. It imposes a constraint on the non-negativity of the amplitudes of the recovered endmember spectral signatures as well as their fractional abundances. This ensures the recovery of physically meaningful endmembers and their abundances. This algorithm is further modified to include the sum-to-one constraint such that the sum of the fractional abundances ... |
|
| Problems in Mathematical Statistics |
10 MAR 2005 |
9 pages |
| Authors:
N. R. Chaganty; OLD DOMINION UNIV RESEARCH FOUNDATION NORFOLK VA
|
| The primary goal of this project was to develop new statistical methods to meet the challenges of the evolving data analysis problems that the army encounters. These statistical methods also have numerous applications in biology, medicine and related sciences. Our research is focused on the following three important problems: (I) study mathematical details of the quasi-least squares method that we have developed for analyzing longitudinal and clustered data, (2) develop ... |
|
| Adaptive Radar Detection of Extended Gaussian Targets |
20 DEC 2004 |
20 pages |
| Authors:
Giuseppe Ricci; Louis L. Scharf; LECCE UNIV (ITALY)
|
| We have addressed the derivation and the analysis of an adaptive decision scheme to detect possible extended targets modeled as Gaussian vectors known to belong to a given subspace; noise returns from the cells under test are modeled as independent and identically-distributed Gaussian vectors with one and the same covariance matrix; a set of secondary data free of signal components is also available; secondary data are Gaussian-distributed and share the ... |
|
| Atomic Spectral Methods for Molecular Electronic Structure Calculations: Atomic-Pair Representations of Aggregate Hamiltonian Matrices (Postprint) |
15 NOV 2004 |
21 pages |
| Authors:
P. W> Langhoff; R. J. Hinde; J. D. Mills; J. A. Boatz; AIR FORCE RESEARCH LAB WRIGHT-PATTERSON AFB OH PROPULSION DIRECTORATE
|
| New methods which avoid the repeated constructions of aggregate Hamiltonian matrices over antisymmetric basis states generally required in conventional calculations of adiabatic potential energy surfaces are reported for ab initio studies of the structures, spectra, and chemical reactions of molecules and other forms of matter. A representational basis in the form of an outer spectral product of atomic eigenstates, employed in the absence of overall electron antisymmetry, is shown to ... |
|
| Role of P13 Kinase Signaling Pathways in Polarity Determination of Human Mammary Epithelial Cells Grown in Three-Dimensional Extracellular Matrix |
SEP 2004 |
23 pages |
| Authors:
Hong Liu; CALIFORNIA UNIV BERKELEY LAWRENCE BERKELEY LAB
|
| Loss of tissue polarity and increased proliferation are the characteristic alterations of the breast tumor phenotype. To investigate these processes, we have used a three-dimensional (3D) culture system in which malignant human breast cells can be reverted to a normal phenotype. Exposure to inhibitors of phosphatidylinositol 3-kinase (PI3K) leads to decreased proliferation and restored tissue polarity. We show that Akt and Rac1 act as downstream effectors of PI3K and function ... |
|
| Restoration of Wavelet-Compressed Images and Motion Imagery |
JAN 2004 |
68 pages |
| Authors:
Mark A. Robertson; AIR FORCE RESEARCH LAB ROME NY INFORMATION DIRECTORATE
|
| This technical report investigates the characteristics of compression noise in images and motion imagery compressed by scalar quantization of the data's two- or three-dimensional wavelet transform coefficients. Such quantization noise is both experimentally and theoretically shown to be spatially varying in the pixel domain, with statistical correlations between the errors at the pixel locations. A quantization noise covariance matrix is presented that can find use in general restoration scenarios where ... |
|
| Short-Data-Record Adaptive Receivers for Rapidly Changing Communications Environments |
01 SEP 2003 |
112 pages |
| Authors:
Stella N. Batalama; Dimitris A. Pados; STATE UNIV OF NEW YORK AT BUFFALO AMHERST
|
| We defined and pursued a novel line of research that lies in a multidisciplinary intersection of Estimation Theory, Communications Theory, and Mean-Square optimum linear filtering. Consider an arbitrary input signal vector space and a given information bearing signal vector to be protected or recovered in the presence of multiuser or other forms of heavy interference. Based strictly on statistical conditional optimization principles, we developed an iterative algorithm that starts from ... |
|
| A Computational Model for Sound Field Absorption by Acoustic Arrays (revision 6) |
24 JUL 2001 |
20 pages |
| Authors:
H. T. Banks; D. G. Cole; K. M. Furati; K. Ito; G. A. Pinter; NORTH CAROLINA STATE UNIV AT RALEIGH CENTER FOR RESEARCH IN SCIENTIFIC COMPUTATION
|
| In this paper, the authors discuss the sound absorption property of arrays of micro-acoustic actuators at a control surface. They use the wave equation over the half plane for the velocity potential with a boundary dissipation by a proportional pressure feedback law along the half plane boundary. The feedback gain over the array is described by a distributed shape function. They develop a computational method based on the Fourier transform ... |
|
| On the Boundary Over Distance Preconditioner for Radial Basis Function Interpolation |
JUL 2001 |
8 pages |
| Authors:
C. T. Mouat; R. K. Beatson; CANTERBURY UNIV CHRISTCHURCH (NEW ZEALAND) DEPT OF MATHEMATICS AND STATISTICS
|
| In this paper we consider the boundary over distance preconditioner for radial basis function interpolation problems. We give both theoretical and numerical results indicating that it performs extremely well. |
|
| Generalised Gauss-Markov Regression |
JUL 2001 |
8 pages |
| Authors:
Alistair B. Forbes; Peter M. Harris; Ian M. Smith; NATIONAL PHYSICAL LAB TEDDINGTON (UNITED KINGDOM)
|
| Experimental data analysis is an key activity in metrology, the science of measurement. It involves developing a mathematical model of the physical system in terms of mathematical equations involving parameters that describe all the relevant aspects of the system. The model specifies how the system is expected to respond to input data and the nature of the uncertainties in the inputs. Given measurement data, estimates of the model parameters are ... |
|
Reports by Keyword(s)
MATRICES(MATHEMATICS)
