MGMRES: A generalization of GMRES for solving large sparse nonsymmetric linear systems
Young, D.M.; Chen, J.Y.
1994-12-31
The authors are concerned with the solution of the linear system (1): Au = b, where A is a real square nonsingular matrix which is large, sparse and non-symmetric. They consider the use of Krylov subspace methods. They first choose an initial approximation u{sup (0)} to the solution {bar u} = A{sup {minus}1}B of (1). They also choose an auxiliary matrix Z which is nonsingular. For n = 1,2,{hor_ellipsis} they determine u{sup (n)} such that u{sup (n)} {minus} u{sup (0)}{epsilon}K{sub n}(r{sup (0)},A) where K{sub n}(r{sup (0)},A) is the (Krylov) subspace spanned by the Krylov vectors r{sup (0)}, Ar{sup (0)}, {hor_ellipsis}, A{sup n{minus}1}r{sup 0} and where r{sup (0)} = b{minus}Au{sup (0)}. If ZA is SPD they also require that (u{sup (n)}{minus}{bar u}, ZA(u{sup (n)}{minus}{bar u})) be minimized. If, on the other hand, ZA is not SPD, then they require that the Galerkin condition, (Zr{sup n}, v) = 0, be satisfied for all v{epsilon}K{sub n}(r{sup (0)}, A) where r{sup n} = b{minus}Au{sup (n)}. In this paper the authors consider a generalization of GMRES. This generalized method, which they refer to as `MGMRES`, is very similar to GMRES except that they let Z = A{sup T}Y where Y is a nonsingular matrix which is symmetric by not necessarily SPD.
Iterative solution of general sparse linear systems on clusters of workstations
Lo, Gen-Ching; Saad, Y.
1996-12-31
Solving sparse irregularly structured linear systems on parallel platforms poses several challenges. First, sparsity makes it difficult to exploit data locality, whether in a distributed or shared memory environment. A second, perhaps more serious challenge, is to find efficient ways to precondition the system. Preconditioning techniques which have a large degree of parallelism, such as multicolor SSOR, often have a slower rate of convergence than their sequential counterparts. Finally, a number of other computational kernels such as inner products could ruin any gains gained from parallel speed-ups, and this is especially true on workstation clusters where start-up times may be high. In this paper we discuss these issues and report on our experience with PSPARSLIB, an on-going project for building a library of parallel iterative sparse matrix solvers.
Sparse linear programming subprogram
Hanson, R.J.; Hiebert, K.L.
1981-12-01
This report describes a subprogram, SPLP(), for solving linear programming problems. The package of subprogram units comprising SPLP() is written in Fortran 77. The subprogram SPLP() is intended for problems involving at most a few thousand constraints and variables. The subprograms are written to take advantage of sparsity in the constraint matrix. A very general problem statement is accepted by SPLP(). It allows upper, lower, or no bounds on the variables. Both the primal and dual solutions are returned as output parameters. The package has many optional features. Among them is the ability to save partial results and then use them to continue the computation at a later time.
Approximate inverse preconditioners for general sparse matrices
Chow, E.; Saad, Y.
1994-12-31
Preconditioned Krylov subspace methods are often very efficient in solving sparse linear matrices that arise from the discretization of elliptic partial differential equations. However, for general sparse indifinite matrices, the usual ILU preconditioners fail, often because of the fact that the resulting factors L and U give rise to unstable forward and backward sweeps. In such cases, alternative preconditioners based on approximate inverses may be attractive. We are currently developing a number of such preconditioners based on iterating on each column to get the approximate inverse. For this approach to be efficient, the iteration must be done in sparse mode, i.e., we must use sparse-matrix by sparse-vector type operatoins. We will discuss a few options and compare their performance on standard problems from the Harwell-Boeing collection.
Inpainting with sparse linear combinations of exemplars
Wohlberg, Brendt
2008-01-01
We introduce a new exemplar-based inpainting algorithm based on representing the region to be inpainted as a sparse linear combination of blocks extracted from similar parts of the image being inpainted. This method is conceptually simple, being computed by functional minimization, and avoids the complexity of correctly ordering the filling in of missing regions of other exemplar-based methods. Initial performance comparisons on small inpainting regions indicate that this method provides similar or better performance than other recent methods.
Sparse brain network using penalized linear regression
NASA Astrophysics Data System (ADS)
Lee, Hyekyoung; Lee, Dong Soo; Kang, Hyejin; Kim, Boong-Nyun; Chung, Moo K.
2011-03-01
Sparse partial correlation is a useful connectivity measure for brain networks when it is difficult to compute the exact partial correlation in the small-n large-p setting. In this paper, we formulate the problem of estimating partial correlation as a sparse linear regression with a l1-norm penalty. The method is applied to brain network consisting of parcellated regions of interest (ROIs), which are obtained from FDG-PET images of the autism spectrum disorder (ASD) children and the pediatric control (PedCon) subjects. To validate the results, we check their reproducibilities of the obtained brain networks by the leave-one-out cross validation and compare the clustered structures derived from the brain networks of ASD and PedCon.
Iterative algorithms for large sparse linear systems on parallel computers
NASA Technical Reports Server (NTRS)
Adams, L. M.
1982-01-01
Algorithms for assembling in parallel the sparse system of linear equations that result from finite difference or finite element discretizations of elliptic partial differential equations, such as those that arise in structural engineering are developed. Parallel linear stationary iterative algorithms and parallel preconditioned conjugate gradient algorithms are developed for solving these systems. In addition, a model for comparing parallel algorithms on array architectures is developed and results of this model for the algorithms are given.
Pilipchuk, L. A.; Pilipchuk, A. S.
2015-11-30
In this paper we propose the theory of decomposition, methods, technologies, applications and implementation in Wol-fram Mathematica for the constructing the solutions of the sparse linear systems. One of the applications is the Sensor Location Problem for the symmetric graph in the case when split ratios of some arc flows can be zeros. The objective of that application is to minimize the number of sensors that are assigned to the nodes. We obtain a sparse system of linear algebraic equations and research its matrix rank. Sparse systems of these types appear in generalized network flow programming problems in the form of restrictions and can be characterized as systems with a large sparse sub-matrix representing the embedded network structure.
Reconstruction Techniques for Sparse Multistatic Linear Array Microwave Imaging
Sheen, David M.; Hall, Thomas E.
2014-06-09
Sequentially-switched linear arrays are an enabling technology for a number of near-field microwave imaging applications. Electronically sequencing along the array axis followed by mechanical scanning along an orthogonal axis allows dense sampling of a two-dimensional aperture in near real-time. In this paper, a sparse multi-static array technique will be described along with associated Fourier-Transform-based and back-projection-based image reconstruction algorithms. Simulated and measured imaging results are presented that show the effectiveness of the sparse array technique along with the merits and weaknesses of each image reconstruction approach.
Scalable Library for the Parallel Solution of Sparse Linear Systems
Jones, Mark; Plassmann, Paul E.
1993-07-14
BlockSolve is a scalable parallel software library for the solution of large sparse, symmetric systems of linear equations. It runs on a variety of parallel architectures and can easily be ported to others. BlockSovle is primarily intended for the solution of sparse linear systems that arise from physical problems having multiple degrees of freedom at each node point. For example, when the finite element method is used to solve practical problems in structural engineering, each node will typically have anywhere from 3-6 degrees of freedom associated with it. BlockSolve is written to take advantage of problems of this nature; however, it is still reasonably efficient for problems that have only one degree of freedom associated with each node, such as the three-dimensional Poisson problem. It does not require that the matrices have any particular structure other than being sparse and symmetric. BlockSolve is intended to be used within real application codes. It is designed to work best in the context of our experience which indicated that most application codes solve the same linear systems with several different right-hand sides and/or linear systems with the same structure, but different matrix values multiple times.
Reconstruction techniques for sparse multistatic linear array microwave imaging
NASA Astrophysics Data System (ADS)
Sheen, David M.; Hall, Thomas E.
2014-06-01
Sequentially-switched linear arrays are an enabling technology for a number of near-field microwave imaging applications. Electronically sequencing along the array axis followed by mechanical scanning along an orthogonal axis allows dense sampling of a two-dimensional aperture in near real-time. The Pacific Northwest National Laboratory (PNNL) has developed this technology for several applications including concealed weapon detection, groundpenetrating radar, and non-destructive inspection and evaluation. These techniques form three-dimensional images by scanning a diverging beam swept frequency transceiver over a two-dimensional aperture and mathematically focusing or reconstructing the data into three-dimensional images. Recently, a sparse multi-static array technology has been developed that reduces the number of antennas required to densely sample the linear array axis of the spatial aperture. This allows a significant reduction in cost and complexity of the linear-array-based imaging system. The sparse array has been specifically designed to be compatible with Fourier-Transform-based image reconstruction techniques; however, there are limitations to the use of these techniques, especially for extreme near-field operation. In the extreme near-field of the array, back-projection techniques have been developed that account for the exact location of each transmitter and receiver in the linear array and the 3-D image location. In this paper, the sparse array technique will be described along with associated Fourier-Transform-based and back-projection-based image reconstruction algorithms. Simulated imaging results are presented that show the effectiveness of the sparse array technique along with the merits and weaknesses of each image reconstruction approach.
A multi-level method for sparse linear systems
Shapira, Y.
1997-09-01
A multi-level method for the solution of sparse linear systems is introduced. The definition of the method is based on data from the coefficient matrix alone. An upper bound for the condition number is available for certain symmetric positive definite (SPD) problems. Numerical experiments confirm the analysis and illustrate the efficiency of the method for diffusion problems with discontinuous coefficients with discontinuities which are not aligned with the coarse meshes.
Solution of large, sparse systems of linear equations in massively parallel applications
Jones, M.T.; Plassmann, P.E.
1992-01-01
We present a general-purpose parallel iterative solver for large, sparse systems of linear equations. This solver is used in two applications, a piezoelectric crystal vibration problem and a superconductor model, that could be solved only on the largest available massively parallel machine. Results obtained on the Intel DELTA show computational rates of up to 3.25 gigaflops for these applications.
Predicting cognitive data from medical images using sparse linear regression.
Kandel, Benjamin M; Wolk, David A; Gee, James C; Avants, Brian
2013-01-01
We present a new framework for predicting cognitive or other continuous-variable data from medical images. Current methods of probing the connection between medical images and other clinical data typically use voxel-based mass univariate approaches. These approaches do not take into account the multivariate, network-based interactions between the various areas of the brain and do not give readily interpretable metrics that describe how strongly cognitive function is related to neuroanatomical structure. On the other hand, high-dimensional machine learning techniques do not typically provide a direct method for discovering which parts of the brain are used for making predictions. We present a framework, based on recent work in sparse linear regression, that addresses both drawbacks of mass univariate approaches, while preserving the direct spatial interpretability that they provide. In addition, we present a novel optimization algorithm that adapts the conjugate gradient method for sparse regression on medical imaging data. This algorithm produces coefficients that are more interpretable than existing sparse regression techniques.
Learning a Nonnegative Sparse Graph for Linear Regression.
Fang, Xiaozhao; Xu, Yong; Li, Xuelong; Lai, Zhihui; Wong, Wai Keung
2015-09-01
Previous graph-based semisupervised learning (G-SSL) methods have the following drawbacks: 1) they usually predefine the graph structure and then use it to perform label prediction, which cannot guarantee an overall optimum and 2) they only focus on the label prediction or the graph structure construction but are not competent in handling new samples. To this end, a novel nonnegative sparse graph (NNSG) learning method was first proposed. Then, both the label prediction and projection learning were integrated into linear regression. Finally, the linear regression and graph structure learning were unified within the same framework to overcome these two drawbacks. Therefore, a novel method, named learning a NNSG for linear regression was presented, in which the linear regression and graph learning were simultaneously performed to guarantee an overall optimum. In the learning process, the label information can be accurately propagated via the graph structure so that the linear regression can learn a discriminative projection to better fit sample labels and accurately classify new samples. An effective algorithm was designed to solve the corresponding optimization problem with fast convergence. Furthermore, NNSG provides a unified perceptiveness for a number of graph-based learning methods and linear regression methods. The experimental results showed that NNSG can obtain very high classification accuracy and greatly outperforms conventional G-SSL methods, especially some conventional graph construction methods.
Kernelized Elastic Net Regularization: Generalization Bounds, and Sparse Recovery.
Feng, Yunlong; Lv, Shao-Gao; Hang, Hanyuan; Suykens, Johan A K
2016-03-01
Kernelized elastic net regularization (KENReg) is a kernelization of the well-known elastic net regularization (Zou & Hastie, 2005). The kernel in KENReg is not required to be a Mercer kernel since it learns from a kernelized dictionary in the coefficient space. Feng, Yang, Zhao, Lv, and Suykens (2014) showed that KENReg has some nice properties including stability, sparseness, and generalization. In this letter, we continue our study on KENReg by conducting a refined learning theory analysis. This letter makes the following three main contributions. First, we present refined error analysis on the generalization performance of KENReg. The main difficulty of analyzing the generalization error of KENReg lies in characterizing the population version of its empirical target function. We overcome this by introducing a weighted Banach space associated with the elastic net regularization. We are then able to conduct elaborated learning theory analysis and obtain fast convergence rates under proper complexity and regularity assumptions. Second, we study the sparse recovery problem in KENReg with fixed design and show that the kernelization may improve the sparse recovery ability compared to the classical elastic net regularization. Finally, we discuss the interplay among different properties of KENReg that include sparseness, stability, and generalization. We show that the stability of KENReg leads to generalization, and its sparseness confidence can be derived from generalization. Moreover, KENReg is stable and can be simultaneously sparse, which makes it attractive theoretically and practically.
Saravanan, Chandra; Shao, Yihan; Baer, Roi; Ross, Philip N; Head-Gordon, Martin
2003-04-15
A sparse matrix multiplication scheme with multiatom blocks is reported, a tool that can be very useful for developing linear-scaling methods with atom-centered basis functions. Compared to conventional element-by-element sparse matrix multiplication schemes, efficiency is gained by the use of the highly optimized basic linear algebra subroutines (BLAS). However, some sparsity is lost in the multiatom blocking scheme because these matrix blocks will in general contain negligible elements. As a result, an optimal block size that minimizes the CPU time by balancing these two effects is recovered. In calculations on linear alkanes, polyglycines, estane polymers, and water clusters the optimal block size is found to be between 40 and 100 basis functions, where about 55-75% of the machine peak performance was achieved on an IBM RS6000 workstation. In these calculations, the blocked sparse matrix multiplications can be 10 times faster than a standard element-by-element sparse matrix package.
Generalized Linear Covariance Analysis
NASA Technical Reports Server (NTRS)
Carpenter, James R.; Markley, F. Landis
2014-01-01
This talk presents a comprehensive approach to filter modeling for generalized covariance analysis of both batch least-squares and sequential estimators. We review and extend in two directions the results of prior work that allowed for partitioning of the state space into solve-for'' and consider'' parameters, accounted for differences between the formal values and the true values of the measurement noise, process noise, and textita priori solve-for and consider covariances, and explicitly partitioned the errors into subspaces containing only the influence of the measurement noise, process noise, and solve-for and consider covariances. In this work, we explicitly add sensitivity analysis to this prior work, and relax an implicit assumption that the batch estimator's epoch time occurs prior to the definitive span. We also apply the method to an integrated orbit and attitude problem, in which gyro and accelerometer errors, though not estimated, influence the orbit determination performance. We illustrate our results using two graphical presentations, which we call the variance sandpile'' and the sensitivity mosaic,'' and we compare the linear covariance results to confidence intervals associated with ensemble statistics from a Monte Carlo analysis.
A linear geospatial streamflow modeling system for data sparse environments
Asante, Kwabena O.; Arlan, Guleid A.; Pervez, Md Shahriar; Rowland, James
2008-01-01
In many river basins around the world, inaccessibility of flow data is a major obstacle to water resource studies and operational monitoring. This paper describes a geospatial streamflow modeling system which is parameterized with global terrain, soils and land cover data and run operationally with satellite‐derived precipitation and evapotranspiration datasets. Simple linear methods transfer water through the subsurface, overland and river flow phases, and the resulting flows are expressed in terms of standard deviations from mean annual flow. In sample applications, the modeling system was used to simulate flow variations in the Congo, Niger, Nile, Zambezi, Orange and Lake Chad basins between 1998 and 2005, and the resulting flows were compared with mean monthly values from the open‐access Global River Discharge Database. While the uncalibrated model cannot predict the absolute magnitude of flow, it can quantify flow anomalies in terms of relative departures from mean flow. Most of the severe flood events identified in the flow anomalies were independently verified by the Dartmouth Flood Observatory (DFO) and the Emergency Disaster Database (EM‐DAT). Despite its limitations, the modeling system is valuable for rapid characterization of the relative magnitude of flood hazards and seasonal flow changes in data sparse settings.
Benzi, Michele; Evans, Thomas M.; Hamilton, Steven P.; ...
2017-03-05
Here, we consider hybrid deterministic-stochastic iterative algorithms for the solution of large, sparse linear systems. Starting from a convergent splitting of the coefficient matrix, we analyze various types of Monte Carlo acceleration schemes applied to the original preconditioned Richardson (stationary) iteration. We expect that these methods will have considerable potential for resiliency to faults when implemented on massively parallel machines. We also establish sufficient conditions for the convergence of the hybrid schemes, and we investigate different types of preconditioners including sparse approximate inverses. Numerical experiments on linear systems arising from the discretization of partial differential equations are presented.
Quantization of general linear electrodynamics
Rivera, Sergio; Schuller, Frederic P.
2011-03-15
General linear electrodynamics allow for an arbitrary linear constitutive relation between the field strength 2-form and induction 2-form density if crucial hyperbolicity and energy conditions are satisfied, which render the theory predictive and physically interpretable. Taking into account the higher-order polynomial dispersion relation and associated causal structure of general linear electrodynamics, we carefully develop its Hamiltonian formulation from first principles. Canonical quantization of the resulting constrained system then results in a quantum vacuum which is sensitive to the constitutive tensor of the classical theory. As an application we calculate the Casimir effect in a birefringent linear optical medium.
Orthogonal Procrustes Analysis for Dictionary Learning in Sparse Linear Representation
Grossi, Giuliano; Lin, Jianyi
2017-01-01
In the sparse representation model, the design of overcomplete dictionaries plays a key role for the effectiveness and applicability in different domains. Recent research has produced several dictionary learning approaches, being proven that dictionaries learnt by data examples significantly outperform structured ones, e.g. wavelet transforms. In this context, learning consists in adapting the dictionary atoms to a set of training signals in order to promote a sparse representation that minimizes the reconstruction error. Finding the best fitting dictionary remains a very difficult task, leaving the question still open. A well-established heuristic method for tackling this problem is an iterative alternating scheme, adopted for instance in the well-known K-SVD algorithm. Essentially, it consists in repeating two stages; the former promotes sparse coding of the training set and the latter adapts the dictionary to reduce the error. In this paper we present R-SVD, a new method that, while maintaining the alternating scheme, adopts the Orthogonal Procrustes analysis to update the dictionary atoms suitably arranged into groups. Comparative experiments on synthetic data prove the effectiveness of R-SVD with respect to well known dictionary learning algorithms such as K-SVD, ILS-DLA and the online method OSDL. Moreover, experiments on natural data such as ECG compression, EEG sparse representation, and image modeling confirm R-SVD’s robustness and wide applicability. PMID:28103283
Mahrous, Hesham; Ward, Rabab
2016-01-01
This paper proposes a compressive sensing (CS) method for multi-channel electroencephalogram (EEG) signals in Wireless Body Area Network (WBAN) applications, where the battery life of sensors is limited. For the single EEG channel case, known as the single measurement vector (SMV) problem, the Block Sparse Bayesian Learning-BO (BSBL-BO) method has been shown to yield good results. This method exploits the block sparsity and the intra-correlation (i.e., the linear dependency) within the measurement vector of a single channel. For the multichannel case, known as the multi-measurement vector (MMV) problem, the Spatio-Temporal Sparse Bayesian Learning (STSBL-EM) method has been proposed. This method learns the joint correlation structure in the multichannel signals by whitening the model in the temporal and the spatial domains. Our proposed method represents the multi-channels signal data as a vector that is constructed in a specific way, so that it has a better block sparsity structure than the conventional representation obtained by stacking the measurement vectors of the different channels. To reconstruct the multichannel EEG signals, we modify the parameters of the BSBL-BO algorithm, so that it can exploit not only the linear but also the non-linear dependency structures in a vector. The modified BSBL-BO is then applied on the vector with the better sparsity structure. The proposed method is shown to significantly outperform existing SMV and also MMV methods. It also shows significant lower compression errors even at high compression ratios such as 10:1 on three different datasets. PMID:26861335
Amesos2 and Belos: Direct and Iterative Solvers for Large Sparse Linear Systems
Bavier, Eric; Hoemmen, Mark; Rajamanickam, Sivasankaran; ...
2012-01-01
Solvers for large sparse linear systems come in two categories: direct and iterative. Amesos2, a package in the Trilinos software project, provides direct methods, and Belos, another Trilinos package, provides iterative methods. Amesos2 offers a common interface to many different sparse matrix factorization codes, and can handle any implementation of sparse matrices and vectors, via an easy-to-extend C++ traits interface. It can also factor matrices whose entries have arbitrary “Scalar” type, enabling extended-precision and mixed-precision algorithms. Belos includes many different iterative methods for solving large sparse linear systems and least-squares problems. Unlike competing iterative solver libraries, Belos completely decouples themore » algorithms from the implementations of the underlying linear algebra objects. This lets Belos exploit the latest hardware without changes to the code. Belos favors algorithms that solve higher-level problems, such as multiple simultaneous linear systems and sequences of related linear systems, faster than standard algorithms. The package also supports extended-precision and mixed-precision algorithms. Together, Amesos2 and Belos form a complete suite of sparse linear solvers.« less
Gene Golub; Kwok Ko
2009-03-30
The solutions of sparse eigenvalue problems and linear systems constitute one of the key computational kernels in the discretization of partial differential equations for the modeling of linear accelerators. The computational challenges faced by existing techniques for solving those sparse eigenvalue problems and linear systems call for continuing research to improve on the algorithms so that ever increasing problem size as required by the physics application can be tackled. Under the support of this award, the filter algorithm for solving large sparse eigenvalue problems was developed at Stanford to address the computational difficulties in the previous methods with the goal to enable accelerator simulations on then the world largest unclassified supercomputer at NERSC for this class of problems. Specifically, a new method, the Hemitian skew-Hemitian splitting method, was proposed and researched as an improved method for solving linear systems with non-Hermitian positive definite and semidefinite matrices.
A novel method to design sparse linear arrays for ultrasonic phased array.
Yang, Ping; Chen, Bin; Shi, Ke-Ren
2006-12-22
In ultrasonic phased array testing, a sparse array can increase the resolution by enlarging the aperture without adding system complexity. Designing a sparse array involves choosing the best or a better configuration from a large number of candidate arrays. We firstly designed sparse arrays by using a genetic algorithm, but found that the arrays have poor performance and poor consistency. So, a method based on the Minimum Redundancy Linear Array was then adopted. Some elements are determined by the minimum-redundancy array firstly in order to ensure spatial resolution and then a genetic algorithm is used to optimize the remaining elements. Sparse arrays designed by this method have much better performance and consistency compared to the arrays designed only by a genetic algorithm. Both simulation and experiment confirm the effectiveness.
Feature Modeling in Underwater Environments Using Sparse Linear Combinations
2010-01-01
waters . Optics Express, 16(13), 2008. 2, 3 [9] J. Jaflfe. Monte carlo modeling of underwate-image forma- tion: Validity of the linear and small-angle... turbid water , etc), we would like to determine if these two images contain the same (or similar) object(s). One approach is as follows: 1. Detect...nearest neighbor methods on extracted feature descriptors This methodology works well for clean, out-of- water images, however, when imaging underwater
Sparse non-negative generalized PCA with applications to metabolomics
Allen, Genevera I.; Maletić-Savatić, Mirjana
2011-01-01
Motivation: Nuclear magnetic resonance (NMR) spectroscopy has been used to study mixtures of metabolites in biological samples. This technology produces a spectrum for each sample depicting the chemical shifts at which an unknown number of latent metabolites resonate. The interpretation of this data with common multivariate exploratory methods such as principal components analysis (PCA) is limited due to high-dimensionality, non-negativity of the underlying spectra and dependencies at adjacent chemical shifts. Results: We develop a novel modification of PCA that is appropriate for analysis of NMR data, entitled Sparse Non-Negative Generalized PCA. This method yields interpretable principal components and loading vectors that select important features and directly account for both the non-negativity of the underlying spectra and dependencies at adjacent chemical shifts. Through the reanalysis of experimental NMR data on five purified neural cell types, we demonstrate the utility of our methods for dimension reduction, pattern recognition, sample exploration and feature selection. Our methods lead to the identification of novel metabolites that reflect the differences between these cell types. Availability: www.stat.rice.edu/~gallen/software.html Contact: gallen@rice.edu Supplementary Information: Supplementary data are available at Bioinformatics online. PMID:21930672
SuperLU{_}DIST: A scalable distributed-memory sparse direct solver for unsymmetric linear systems
Li, Xiaoye S.; Demmel, James W.
2002-03-27
In this paper, we present the main algorithmic features in the software package SuperLU{_}DIST, a distributed-memory sparse direct solver for large sets of linear equations. We give in detail our parallelization strategies, with focus on scalability issues, and demonstrate the parallel performance and scalability on current machines. The solver is based on sparse Gaussian elimination, with an innovative static pivoting strategy proposed earlier by the authors. The main advantage of static pivoting over classical partial pivoting is that it permits a priori determination of data structures and communication pattern for sparse Gaussian elimination, which makes it more scalable on distributed memory machines. Based on this a priori knowledge, we designed highly parallel and scalable algorithms for both LU decomposition and triangular solve and we show that they are suitable for large-scale distributed memory machines.
BIRD: A general interface for sparse distributed memory simulators
NASA Technical Reports Server (NTRS)
Rogers, David
1990-01-01
Kanerva's sparse distributed memory (SDM) has now been implemented for at least six different computers, including SUN3 workstations, the Apple Macintosh, and the Connection Machine. A common interface for input of commands would both aid testing of programs on a broad range of computer architectures and assist users in transferring results from research environments to applications. A common interface also allows secondary programs to generate command sequences for a sparse distributed memory, which may then be executed on the appropriate hardware. The BIRD program is an attempt to create such an interface. Simplifying access to different simulators should assist developers in finding appropriate uses for SDM.
The impact of improved sparse linear solvers on industrial engineering applications
Heroux, M.; Baddourah, M.; Poole, E.L.; Yang, Chao Wu
1996-12-31
There are usually many factors that ultimately determine the quality of computer simulation for engineering applications. Some of the most important are the quality of the analytical model and approximation scheme, the accuracy of the input data and the capability of the computing resources. However, in many engineering applications the characteristics of the sparse linear solver are the key factors in determining how complex a problem a given application code can solve. Therefore, the advent of a dramatically improved solver often brings with it dramatic improvements in our ability to do accurate and cost effective computer simulations. In this presentation we discuss the current status of sparse iterative and direct solvers in several key industrial CFD and structures codes, and show the impact that recent advances in linear solvers have made on both our ability to perform challenging simulations and the cost of those simulations. We also present some of the current challenges we have and the constraints we face in trying to improve these solvers. Finally, we discuss future requirements for sparse linear solvers on high performance architectures and try to indicate the opportunities that exist if we can develop even more improvements in linear solver capabilities.
Improving the energy efficiency of sparse linear system solvers on multicore and manycore systems.
Anzt, H; Quintana-Ortí, E S
2014-06-28
While most recent breakthroughs in scientific research rely on complex simulations carried out in large-scale supercomputers, the power draft and energy spent for this purpose is increasingly becoming a limiting factor to this trend. In this paper, we provide an overview of the current status in energy-efficient scientific computing by reviewing different technologies used to monitor power draft as well as power- and energy-saving mechanisms available in commodity hardware. For the particular domain of sparse linear algebra, we analyse the energy efficiency of a broad collection of hardware architectures and investigate how algorithmic and implementation modifications can improve the energy performance of sparse linear system solvers, without negatively impacting their performance.
Evaluation of generalized degrees of freedom for sparse estimation by replica method
NASA Astrophysics Data System (ADS)
Sakata, A.
2016-12-01
We develop a method to evaluate the generalized degrees of freedom (GDF) for linear regression with sparse regularization. The GDF is a key factor in model selection, and thus its evaluation is useful in many modelling applications. An analytical expression for the GDF is derived using the replica method in the large-system-size limit with random Gaussian predictors. The resulting formula has a universal form that is independent of the type of regularization, providing us with a simple interpretation. Within the framework of replica symmetric (RS) analysis, GDF has a physical meaning as the effective fraction of non-zero components. The validity of our method in the RS phase is supported by the consistency of our results with previous mathematical results. The analytical results in the RS phase are calculated numerically using the belief propagation algorithm.
Generalized linear mixed models for meta-analysis.
Platt, R W; Leroux, B G; Breslow, N
1999-03-30
We examine two strategies for meta-analysis of a series of 2 x 2 tables with the odds ratio modelled as a linear combination of study level covariates and random effects representing between-study variation. Penalized quasi-likelihood (PQL), an approximate inference technique for generalized linear mixed models, and a linear model fitted by weighted least squares to the observed log-odds ratios are used to estimate regression coefficients and dispersion parameters. Simulation results demonstrate that both methods perform adequate approximate inference under many conditions, but that neither method works well in the presence of highly sparse data. Under certain conditions with small cell frequencies the PQL method provides better inference.
NASA Astrophysics Data System (ADS)
Deglint, Jason; Kazemzadeh, Farnoud; Wong, Alexander; Clausi, David A.
2015-09-01
One method to acquire multispectral images is to sequentially capture a series of images where each image contains information from a different bandwidth of light. Another method is to use a series of beamsplitters and dichroic filters to guide different bandwidths of light onto different cameras. However, these methods are very time consuming and expensive and perform poorly in dynamic scenes or when observing transient phenomena. An alternative strategy to capturing multispectral data is to infer this data using sparse spectral reflectance measurements captured using an imaging device with overlapping bandpass filters, such as a consumer digital camera using a Bayer filter pattern. Currently the only method of inferring dense reflectance spectra is the Wiener adaptive filter, which makes Gaussian assumptions about the data. However, these assumptions may not always hold true for all data. We propose a new technique to infer dense reflectance spectra from sparse spectral measurements through the use of a non-linear regression model. The non-linear regression model used in this technique is the random forest model, which is an ensemble of decision trees and trained via the spectral characterization of the optical imaging system and spectral data pair generation. This model is then evaluated by spectrally characterizing different patches on the Macbeth color chart, as well as by reconstructing inferred multispectral images. Results show that the proposed technique can produce inferred dense reflectance spectra that correlate well with the true dense reflectance spectra, which illustrates the merits of the technique.
Grouping in sparse random-dot patterns: linear and nonlinear mechanisms
NASA Astrophysics Data System (ADS)
Kashi, Ramanujan S.; Papathomas, Thomas V.; Gorea, Andrei
1997-06-01
This study reports on experiments conducted with human observers to investigate the properties of linear and non- linear, perceptual grouping mechanisms by using reverse- polarity sparse random-dot patterns. The stimuli were generated by spatially superimposing a sparse set of randomly distributed square elements onto a copy of the original set that was expanded or rotated about the center of the screen. In the control experiment both the original and transformed sets contained elements of identical luminance contrast with the background. The main experiments involved a reverse- contrast random-dot pattern, in which the transformed set consisted of elements of equal contrast magnitude but opposite polarity to that of the original set. At least two competing global percepts are possible: 'forward grouping' in which perceived grouping agrees with the physical transformation; or 'reverse grouping' in a direction orthogonal to that of the 'forward grouping.' The two-alternative forced-choice (2AFC) task was to report the direction of the global grouping. For the control experiment, the observers reported forward grouping both at the fovea and eccentricities of up to 4 degrees; as expected, no reverse grouping was observed. With the reverse-polarity stimulus, reverse grouping was observed at high eccentricities and low contrasts, but forward grouping dominated under foveal viewing. In another experiment, the influence of chromatic mechanisms was studied by using opposite-contrast red elements on a yellow background. In this experiment reverse grouping was not observed, which indicates that color mechanisms veto reverse grouping. Reverse grouping can be hypothesized to be the result of processing by linear oriented spatial mechanisms, in analogy with reverse-phi motion. Forward grouping, on the other hand, can be explained by non-linear preprocessing (such s squaring or full-wave rectification).
Many-core graph analytics using accelerated sparse linear algebra routines
NASA Astrophysics Data System (ADS)
Kozacik, Stephen; Paolini, Aaron L.; Fox, Paul; Kelmelis, Eric
2016-05-01
Graph analytics is a key component in identifying emerging trends and threats in many real-world applications. Largescale graph analytics frameworks provide a convenient and highly-scalable platform for developing algorithms to analyze large datasets. Although conceptually scalable, these techniques exhibit poor performance on modern computational hardware. Another model of graph computation has emerged that promises improved performance and scalability by using abstract linear algebra operations as the basis for graph analysis as laid out by the GraphBLAS standard. By using sparse linear algebra as the basis, existing highly efficient algorithms can be adapted to perform computations on the graph. This approach, however, is often less intuitive to graph analytics experts, who are accustomed to vertex-centric APIs such as Giraph, GraphX, and Tinkerpop. We are developing an implementation of the high-level operations supported by these APIs in terms of linear algebra operations. This implementation is be backed by many-core implementations of the fundamental GraphBLAS operations required, and offers the advantages of both the intuitive programming model of a vertex-centric API and the performance of a sparse linear algebra implementation. This technology can reduce the number of nodes required, as well as the run-time for a graph analysis problem, enabling customers to perform more complex analysis with less hardware at lower cost. All of this can be accomplished without the requirement for the customer to make any changes to their analytics code, thanks to the compatibility with existing graph APIs.
LANZ: Software solving the large sparse symmetric generalized eigenproblem
NASA Technical Reports Server (NTRS)
Jones, Mark T.; Patrick, Merrell L.
1990-01-01
A package, LANZ, for solving the large symmetric generalized eigenproblem is described. The package was tested on four different architectures: Convex 200, CRAY Y-MP, Sun-3, and Sun-4. The package uses a Lanczos' method and is based on recent research into solving the generalized eigenproblem.
Application of the Cramer rule in the solution of sparse systems of linear algebraic equations
NASA Astrophysics Data System (ADS)
Mittal, R. C.; Al-Kurdi, Ahmad
2001-11-01
In this work, the solution of a sparse system of linear algebraic equations is obtained by using the Cramer rule. The determinants are computed with the help of the numerical structure approach defined in Suchkov (Graphs of Gearing Machines, Leningrad, Quebec, 1983) in which only the non-zero elements are used. Cramer rule produces the solution directly without creating fill-in problem encountered in other direct methods. Moreover, the solution can be expressed exactly if all the entries, including the right-hand side, are integers and if all products do not exceed the size of the largest integer that can be represented in the arithmetic of the computer used. The usefulness of Suchkov numerical structure approach is shown by applying on seven examples. Obtained results are also compared with digraph approach described in Mittal and Kurdi (J. Comput. Math., to appear). It is shown that the performance of the numerical structure approach is better than that of digraph approach.
Li, Yanming; Zhu, Ji
2015-01-01
Summary We propose a multivariate sparse group lasso variable selection and estimation method for data with high-dimensional predictors as well as high-dimensional response variables. The method is carried out through a penalized multivariate multiple linear regression model with an arbitrary group structure for the regression coefficient matrix. It suits many biology studies well in detecting associations between multiple traits and multiple predictors, with each trait and each predictor embedded in some biological functioning groups such as genes, pathways or brain regions. The method is able to effectively remove unimportant groups as well as unimportant individual coefficients within important groups, particularly for large p small n problems, and is flexible in handling various complex group structures such as overlapping or nested or multilevel hierarchical structures. The method is evaluated through extensive simulations with comparisons to the conventional lasso and group lasso methods, and is applied to an eQTL association study. PMID:25732839
Bagging linear sparse Bayesian learning models for variable selection in cancer diagnosis.
Lu, Chuan; Devos, Andy; Suykens, Johan A K; Arús, Carles; Van Huffel, Sabine
2007-05-01
This paper investigates variable selection (VS) and classification for biomedical datasets with a small sample size and a very high input dimension. The sequential sparse Bayesian learning methods with linear bases are used as the basic VS algorithm. Selected variables are fed to the kernel-based probabilistic classifiers: Bayesian least squares support vector machines (BayLS-SVMs) and relevance vector machines (RVMs). We employ the bagging techniques for both VS and model building in order to improve the reliability of the selected variables and the predictive performance. This modeling strategy is applied to real-life medical classification problems, including two binary cancer diagnosis problems based on microarray data and a brain tumor multiclass classification problem using spectra acquired via magnetic resonance spectroscopy. The work is experimentally compared to other VS methods. It is shown that the use of bagging can improve the reliability and stability of both VS and model prediction.
Semi-Parametric Generalized Linear Models.
1985-08-01
is nonsingular, upper triangular, and of full rank r. It is known (Dongarra et al., 1979) that G-1 FT is the Moore - Penrose inverse of L . Therefore... GENERALIZED LINEAR pq Mathematics Research Center University of Wisconsin-Madison 610 Walnut Street Madison, Wisconsin 53705 TI C August 1985 E T NOV 7 8...North Carolina 27709 -. -.. . - -.-. g / 6 O5’o UNIVERSITY OF WISCONSIN-MADISON MATHD4ATICS RESEARCH CENTER SD4I-PARAMETRIC GENERALIZED LINEAR MODELS
Comparison of l₁-Norm SVR and Sparse Coding Algorithms for Linear Regression.
Zhang, Qingtian; Hu, Xiaolin; Zhang, Bo
2015-08-01
Support vector regression (SVR) is a popular function estimation technique based on Vapnik's concept of support vector machine. Among many variants, the l1-norm SVR is known to be good at selecting useful features when the features are redundant. Sparse coding (SC) is a technique widely used in many areas and a number of efficient algorithms are available. Both l1-norm SVR and SC can be used for linear regression. In this brief, the close connection between the l1-norm SVR and SC is revealed and some typical algorithms are compared for linear regression. The results show that the SC algorithms outperform the Newton linear programming algorithm, an efficient l1-norm SVR algorithm, in efficiency. The algorithms are then used to design the radial basis function (RBF) neural networks. Experiments on some benchmark data sets demonstrate the high efficiency of the SC algorithms. In particular, one of the SC algorithms, the orthogonal matching pursuit is two orders of magnitude faster than a well-known RBF network designing algorithm, the orthogonal least squares algorithm.
Parallel Sparse Linear System and Eigenvalue Problem Solvers: From Multicore to Petascale Computing
2015-06-01
addressed designing: (1) Tools for sparse matrix primtives such as sparse matrix‐ vector multiplication (and sparse matrix‐multivector...of the Harwell Subroutine Library (HSL), while our symmetric reordering is based on the Fiedler vector of the corresponding...and extended through this grant) for obtaining the Fiedler vector rather than the multilevel eigensolver used in MC73 which
LANZ - SOFTWARE FOR SOLVING THE LARGE SPARSE SYMMETRIC GENERALIZED EIGENPROBLEM
NASA Technical Reports Server (NTRS)
Jones, M. T.
1994-01-01
LANZ is a sophisticated algorithm based on the simple Lanczos method for solving the generalized eigenvalue problem. LANZ uses a technique called dynamic shifting to improve the efficiency and reliability of the basic Lanczos algorithm. The program has been successfully used to solve problems such as: 1) finding the vibration frequencies and mode shape vectors of a structure, and 2) finding the smallest load at which a structure will buckle. Several methods exist for solving the large symmetric generalized eigenvalue problem. LANZ offers an alternative to the popular sub-space iteration approach. The program includes a new algorithm for solving the tri-diagonal matrices that arise when using the Lanczos method. Procedurally, LANZ starts with the user's initial shift, then executes the Lanczos algorithm until: 1) the desired number of eigenvalues is found; 2) no storage space is left; or 3) LANZ determines that a new shift is needed. When a new shift is needed, the program selects it based on accumulated information. At each iteration, LANZ examines the converged and unconverged eigenvalues along with the inertia counts to ensure that no eigenvalues have been missed. LANZ is written in FORTRAN 77 and C language. It was originally designed to run on computers that support vector processing such as the CRAY Y-MP and is therefore optimized for vector machines. Makefiles are included for the Sun3, Sun4, Cray Y-MP, and CONVEX 220. When implemented on a Sun4 computer, LANZ required 670K of main memory. The standard distribution medium for this program is a .25 inch streaming magnetic cartridge tape in Unix tar format. It is also available on a 3.5 inch diskette in UNIX tar format. LANZ was developed in 1989. Sun3 and Sun4 are trademarks of Sun Microsystems, Inc. Cray Y-MP is a trademark of Cray Research, Inc. CONVEX 220 is a trademark of Convex Computer Corporation.
Fang, Jun; Zhang, Lizao; Li, Hohgbin
2016-04-20
We consider the problem of recovering twodimensional (2-D) block-sparse signals with unknown cluster patterns. Two-dimensional block-sparse patterns arise naturally in many practical applications such as foreground detection and inverse synthetic aperture radar imaging. To exploit the underlying block-sparse structure, we propose a 2-D pattern-coupled hierarchical Gaussian prior model. The proposed pattern-coupled hierarchical Gaussian prior model imposes a soft coupling mechanism among neighboring coefficients through their shared hyperparameters. This coupling mechanism enables effective and automatic learning of the underlying irregular cluster patterns, without requiring any a priori knowledge of the block partition of sparse signals. We develop a computationally efficient Bayesian inference method which integrates the generalized approximate message passing (GAMP) technique with the proposed prior model. Simulation results show that the proposed method offers competitive recovery performance for a range of 2-D sparse signal recovery and image processing applications over existing method, meanwhile achieving a significant reduction in computational complexity.
Fahmy, Ahmed S.; Gabr, Refaat E.; Heberlein, Keith; Hu, Xiaoping P.
2006-01-01
Image reconstruction from nonuniformly sampled spatial frequency domain data is an important problem that arises in computed imaging. Current reconstruction techniques suffer from limitations in their model and implementation. In this paper, we present a new reconstruction method that is based on solving a system of linear equations using an efficient iterative approach. Image pixel intensities are related to the measured frequency domain data through a set of linear equations. Although the system matrix is too dense and large to solve by direct inversion in practice, a simple orthogonal transformation to the rows of this matrix is applied to convert the matrix into a sparse one up to a certain chosen level of energy preservation. The transformed system is subsequently solved using the conjugate gradient method. This method is applied to reconstruct images of a numerical phantom as well as magnetic resonance images from experimental spiral imaging data. The results support the theory and demonstrate that the computational load of this method is similar to that of standard gridding, illustrating its practical utility. PMID:23165034
NASA Technical Reports Server (NTRS)
Kincaid, D. R.; Young, D. M.
1984-01-01
Adapting and designing mathematical software to achieve optimum performance on the CYBER 205 is discussed. Comments and observations are made in light of recent work done on modifying the ITPACK software package and on writing new software for vector supercomputers. The goal was to develop very efficient vector algorithms and software for solving large sparse linear systems using iterative methods.
BlockSolve v1.1: Scalable library software for the parallel solution of sparse linear systems
Jones, M.T.; Plassmann, P.E.
1993-03-01
BlockSolve is a software library for solving large, sparse systems of linear equations on massively parallel computers. The matrices must be symmetric, but may have an arbitrary sparsity structure. BlockSolve is a portable package that is compatible with several different message-passing pardigms. This report gives detailed instructions on the use of BlockSolve in applications programs.
BlockSolve v1. 1: Scalable library software for the parallel solution of sparse linear systems
Jones, M.T.; Plassmann, P.E.
1993-03-01
BlockSolve is a software library for solving large, sparse systems of linear equations on massively parallel computers. The matrices must be symmetric, but may have an arbitrary sparsity structure. BlockSolve is a portable package that is compatible with several different message-passing pardigms. This report gives detailed instructions on the use of BlockSolve in applications programs.
Pratapa, Phanisri P.; Suryanarayana, Phanish; Pask, John E.
2015-12-01
We employ Anderson extrapolation to accelerate the classical Jacobi iterative method for large, sparse linear systems. Specifically, we utilize extrapolation at periodic intervals within the Jacobi iteration to develop the Alternating Anderson–Jacobi (AAJ) method. We verify the accuracy and efficacy of AAJ in a range of test cases, including nonsymmetric systems of equations. We demonstrate that AAJ possesses a favorable scaling with system size that is accompanied by a small prefactor, even in the absence of a preconditioner. In particular, we show that AAJ is able to accelerate the classical Jacobi iteration by over four orders of magnitude, with speed-upsmore » that increase as the system gets larger. Moreover, we find that AAJ significantly outperforms the Generalized Minimal Residual (GMRES) method in the range of problems considered here, with the relative performance again improving with size of the system. As a result, the proposed method represents a simple yet efficient technique that is particularly attractive for large-scale parallel solutions of linear systems of equations.« less
Pratapa, Phanisri P.; Suryanarayana, Phanish; Pask, John E.
2015-12-01
We employ Anderson extrapolation to accelerate the classical Jacobi iterative method for large, sparse linear systems. Specifically, we utilize extrapolation at periodic intervals within the Jacobi iteration to develop the Alternating Anderson–Jacobi (AAJ) method. We verify the accuracy and efficacy of AAJ in a range of test cases, including nonsymmetric systems of equations. We demonstrate that AAJ possesses a favorable scaling with system size that is accompanied by a small prefactor, even in the absence of a preconditioner. In particular, we show that AAJ is able to accelerate the classical Jacobi iteration by over four orders of magnitude, with speed-ups that increase as the system gets larger. Moreover, we find that AAJ significantly outperforms the Generalized Minimal Residual (GMRES) method in the range of problems considered here, with the relative performance again improving with size of the system. As a result, the proposed method represents a simple yet efficient technique that is particularly attractive for large-scale parallel solutions of linear systems of equations.
Evaluation of parallel direct sparse linear solvers in electromagnetic geophysical problems
NASA Astrophysics Data System (ADS)
Puzyrev, Vladimir; Koric, Seid; Wilkin, Scott
2016-04-01
High performance computing is absolutely necessary for large-scale geophysical simulations. In order to obtain a realistic image of a geologically complex area, industrial surveys collect vast amounts of data making the computational cost extremely high for the subsequent simulations. A major computational bottleneck of modeling and inversion algorithms is solving the large sparse systems of linear ill-conditioned equations in complex domains with multiple right hand sides. Recently, parallel direct solvers have been successfully applied to multi-source seismic and electromagnetic problems. These methods are robust and exhibit good performance, but often require large amounts of memory and have limited scalability. In this paper, we evaluate modern direct solvers on large-scale modeling examples that previously were considered unachievable with these methods. Performance and scalability tests utilizing up to 65,536 cores on the Blue Waters supercomputer clearly illustrate the robustness, efficiency and competitiveness of direct solvers compared to iterative techniques. Wide use of direct methods utilizing modern parallel architectures will allow modeling tools to accurately support multi-source surveys and 3D data acquisition geometries, thus promoting a more efficient use of the electromagnetic methods in geophysics.
Linear and nonlinear generalized Fourier transforms.
Pelloni, Beatrice
2006-12-15
This article presents an overview of a transform method for solving linear and integrable nonlinear partial differential equations. This new transform method, proposed by Fokas, yields a generalization and unification of various fundamental mathematical techniques and, in particular, it yields an extension of the Fourier transform method.
Extended Generalized Linear Latent and Mixed Model
ERIC Educational Resources Information Center
Segawa, Eisuke; Emery, Sherry; Curry, Susan J.
2008-01-01
The generalized linear latent and mixed modeling (GLLAMM framework) includes many models such as hierarchical and structural equation models. However, GLLAMM cannot currently accommodate some models because it does not allow some parameters to be random. GLLAMM is extended to overcome the limitation by adding a submodel that specifies a…
NASA Astrophysics Data System (ADS)
Pinski, Peter; Riplinger, Christoph; Valeev, Edward F.; Neese, Frank
2015-07-01
In this work, a systematic infrastructure is described that formalizes concepts implicit in previous work and greatly simplifies computer implementation of reduced-scaling electronic structure methods. The key concept is sparse representation of tensors using chains of sparse maps between two index sets. Sparse map representation can be viewed as a generalization of compressed sparse row, a common representation of a sparse matrix, to tensor data. By combining few elementary operations on sparse maps (inversion, chaining, intersection, etc.), complex algorithms can be developed, illustrated here by a linear-scaling transformation of three-center Coulomb integrals based on our compact code library that implements sparse maps and operations on them. The sparsity of the three-center integrals arises from spatial locality of the basis functions and domain density fitting approximation. A novel feature of our approach is the use of differential overlap integrals computed in linear-scaling fashion for screening products of basis functions. Finally, a robust linear scaling domain based local pair natural orbital second-order Möller-Plesset (DLPNO-MP2) method is described based on the sparse map infrastructure that only depends on a minimal number of cutoff parameters that can be systematically tightened to approach 100% of the canonical MP2 correlation energy. With default truncation thresholds, DLPNO-MP2 recovers more than 99.9% of the canonical resolution of the identity MP2 (RI-MP2) energy while still showing a very early crossover with respect to the computational effort. Based on extensive benchmark calculations, relative energies are reproduced with an error of typically <0.2 kcal/mol. The efficiency of the local MP2 (LMP2) method can be drastically improved by carrying out the LMP2 iterations in a basis of pair natural orbitals. While the present work focuses on local electron correlation, it is of much broader applicability to computation with sparse tensors in
Pinski, Peter; Riplinger, Christoph; Neese, Frank E-mail: frank.neese@cec.mpg.de; Valeev, Edward F. E-mail: frank.neese@cec.mpg.de
2015-07-21
In this work, a systematic infrastructure is described that formalizes concepts implicit in previous work and greatly simplifies computer implementation of reduced-scaling electronic structure methods. The key concept is sparse representation of tensors using chains of sparse maps between two index sets. Sparse map representation can be viewed as a generalization of compressed sparse row, a common representation of a sparse matrix, to tensor data. By combining few elementary operations on sparse maps (inversion, chaining, intersection, etc.), complex algorithms can be developed, illustrated here by a linear-scaling transformation of three-center Coulomb integrals based on our compact code library that implements sparse maps and operations on them. The sparsity of the three-center integrals arises from spatial locality of the basis functions and domain density fitting approximation. A novel feature of our approach is the use of differential overlap integrals computed in linear-scaling fashion for screening products of basis functions. Finally, a robust linear scaling domain based local pair natural orbital second-order Möller-Plesset (DLPNO-MP2) method is described based on the sparse map infrastructure that only depends on a minimal number of cutoff parameters that can be systematically tightened to approach 100% of the canonical MP2 correlation energy. With default truncation thresholds, DLPNO-MP2 recovers more than 99.9% of the canonical resolution of the identity MP2 (RI-MP2) energy while still showing a very early crossover with respect to the computational effort. Based on extensive benchmark calculations, relative energies are reproduced with an error of typically <0.2 kcal/mol. The efficiency of the local MP2 (LMP2) method can be drastically improved by carrying out the LMP2 iterations in a basis of pair natural orbitals. While the present work focuses on local electron correlation, it is of much broader applicability to computation with sparse tensors in
Pinski, Peter; Riplinger, Christoph; Valeev, Edward F; Neese, Frank
2015-07-21
In this work, a systematic infrastructure is described that formalizes concepts implicit in previous work and greatly simplifies computer implementation of reduced-scaling electronic structure methods. The key concept is sparse representation of tensors using chains of sparse maps between two index sets. Sparse map representation can be viewed as a generalization of compressed sparse row, a common representation of a sparse matrix, to tensor data. By combining few elementary operations on sparse maps (inversion, chaining, intersection, etc.), complex algorithms can be developed, illustrated here by a linear-scaling transformation of three-center Coulomb integrals based on our compact code library that implements sparse maps and operations on them. The sparsity of the three-center integrals arises from spatial locality of the basis functions and domain density fitting approximation. A novel feature of our approach is the use of differential overlap integrals computed in linear-scaling fashion for screening products of basis functions. Finally, a robust linear scaling domain based local pair natural orbital second-order Möller-Plesset (DLPNO-MP2) method is described based on the sparse map infrastructure that only depends on a minimal number of cutoff parameters that can be systematically tightened to approach 100% of the canonical MP2 correlation energy. With default truncation thresholds, DLPNO-MP2 recovers more than 99.9% of the canonical resolution of the identity MP2 (RI-MP2) energy while still showing a very early crossover with respect to the computational effort. Based on extensive benchmark calculations, relative energies are reproduced with an error of typically <0.2 kcal/mol. The efficiency of the local MP2 (LMP2) method can be drastically improved by carrying out the LMP2 iterations in a basis of pair natural orbitals. While the present work focuses on local electron correlation, it is of much broader applicability to computation with sparse tensors in
Interpretable exemplar-based shape classification using constrained sparse linear models
NASA Astrophysics Data System (ADS)
Sigurdsson, Gunnar A.; Yang, Zhen; Tran, Trac D.; Prince, Jerry L.
2015-03-01
Many types of diseases manifest themselves as observable changes in the shape of the affected organs. Using shape classification, we can look for signs of disease and discover relationships between diseases. We formulate the problem of shape classification in a holistic framework that utilizes a lossless scalar field representation and a non-parametric classification based on sparse recovery. This framework generalizes over certain classes of unseen shapes while using the full information of the shape, bypassing feature extraction. The output of the method is the class whose combination of exemplars most closely approximates the shape, and furthermore, the algorithm returns the most similar exemplars along with their similarity to the shape, which makes the result simple to interpret. Our results show that the method offers accurate classification between three cerebellar diseases and controls in a database of cerebellar ataxia patients. For reproducible comparison, promising results are presented on publicly available 2D datasets, including the ETH-80 dataset where the method achieves 88.4% classification accuracy.
Fisher, Charles K.; Mehta, Pankaj
2014-01-01
Human associated microbial communities exert tremendous influence over human health and disease. With modern metagenomic sequencing methods it is now possible to follow the relative abundance of microbes in a community over time. These microbial communities exhibit rich ecological dynamics and an important goal of microbial ecology is to infer the ecological interactions between species directly from sequence data. Any algorithm for inferring ecological interactions must overcome three major obstacles: 1) a correlation between the abundances of two species does not imply that those species are interacting, 2) the sum constraint on the relative abundances obtained from metagenomic studies makes it difficult to infer the parameters in timeseries models, and 3) errors due to experimental uncertainty, or mis-assignment of sequencing reads into operational taxonomic units, bias inferences of species interactions due to a statistical problem called “errors-in-variables”. Here we introduce an approach, Learning Interactions from MIcrobial Time Series (LIMITS), that overcomes these obstacles. LIMITS uses sparse linear regression with boostrap aggregation to infer a discrete-time Lotka-Volterra model for microbial dynamics. We tested LIMITS on synthetic data and showed that it could reliably infer the topology of the inter-species ecological interactions. We then used LIMITS to characterize the species interactions in the gut microbiomes of two individuals and found that the interaction networks varied significantly between individuals. Furthermore, we found that the interaction networks of the two individuals are dominated by distinct “keystone species”, Bacteroides fragilis and Bacteroided stercosis, that have a disproportionate influence on the structure of the gut microbiome even though they are only found in moderate abundance. Based on our results, we hypothesize that the abundances of certain keystone species may be responsible for individuality in the human
Rosenblum, Michael; Liu, Han; Yen, En-Hsu
2014-01-01
We propose new, optimal methods for analyzing randomized trials, when it is suspected that treatment effects may differ in two predefined subpopulations. Such subpopulations could be defined by a biomarker or risk factor measured at baseline. The goal is to simultaneously learn which subpopulations benefit from an experimental treatment, while providing strong control of the familywise Type I error rate. We formalize this as a multiple testing problem and show it is computationally infeasible to solve using existing techniques. Our solution involves a novel approach, in which we first transform the original multiple testing problem into a large, sparse linear program. We then solve this problem using advanced optimization techniques. This general method can solve a variety of multiple testing problems and decision theory problems related to optimal trial design, for which no solution was previously available. In particular, we construct new multiple testing procedures that satisfy minimax and Bayes optimality criteria. For a given optimality criterion, our new approach yields the optimal tradeoff between power to detect an effect in the overall population versus power to detect effects in subpopulations. We demonstrate our approach in examples motivated by two randomized trials of new treatments for HIV.
Alternative approach to general coupled linear optics
Wolski, Andrzej
2005-11-29
The Twiss parameters provide a convenient description of beam optics in uncoupled linear beamlines. For coupled beamlines, a variety of approaches are possible for describing the linear optics; here, we propose an approach and notation that naturally generalizes the familiar Twiss parameters to the coupled case in three degrees of freedom. Our approach is based on an eigensystem analysis of the matrix of second-order beam moments, or alternatively (in the case of a storage ring) on an eigensystem analysis of the linear single-turn map. The lattice functions that emerge from this approach have an interpretation that is conceptually very simple: in particular, the lattice functions directly relate the beam distribution in phase space to the invariant emittances. To emphasize the physical significance of the coupled lattice functions, we develop the theory from first principles, using only the assumption of linear symplectic transport. We also give some examples of the application of this approach, demonstrating its advantages of conceptual and notational simplicity.
Systematic sparse matrix error control for linear scaling electronic structure calculations.
Rubensson, Emanuel H; Sałek, Paweł
2005-11-30
Efficient truncation criteria used in multiatom blocked sparse matrix operations for ab initio calculations are proposed. As system size increases, so does the need to stay on top of errors and still achieve high performance. A variant of a blocked sparse matrix algebra to achieve strict error control with good performance is proposed. The presented idea is that the condition to drop a certain submatrix should depend not only on the magnitude of that particular submatrix, but also on which other submatrices that are dropped. The decision to remove a certain submatrix is based on the contribution the removal would cause to the error in the chosen norm. We study the effect of an accumulated truncation error in iterative algorithms like trace correcting density matrix purification. One way to reduce the initial exponential growth of this error is presented. The presented error control for a sparse blocked matrix toolbox allows for achieving optimal performance by performing only necessary operations needed to maintain the requested level of accuracy.
NASA Astrophysics Data System (ADS)
Singh, Vimal; Tewfik, Ahmed H.
2011-03-01
Cardiac minimal invasive surgeries such as catheter based radio frequency ablation of atrial fibrillation requires high-precision tracking of inner cardiac surfaces in order to ascertain constant electrode-surface contact. Majority of cardiac motion tracking systems are either limited to outer surface or track limited slices/sectors of inner surface in echocardiography data which are unrealizable in MIS due to the varying resolution of ultrasound with depth and speckle effect. In this paper, a system for high accuracy real-time 3D tracking of both cardiac surfaces using sparse samples of outer-surface only is presented. This paper presents a novel approach to model cardiac inner surface deformations as simple functions of outer surface deformations in the spherical harmonic domain using multiple maximal-likelihood linear regressors. Tracking system uses subspace clustering to identify potential deformation spaces for outer surfaces and trains ML linear regressors using pre-operative MRI/CT scan based training set. During tracking, sparse-samples from outer surfaces are used to identify the active outer surface deformation space and reconstruct outer surfaces in real-time under least squares formulation. Inner surface is reconstructed using tracked outer surface with trained ML linear regressors. High-precision tracking and robustness of the proposed system are demonstrated through results obtained on a real patient dataset with tracking root mean square error <= (0.23 +/- 0.04)mm and <= (0.30 +/- 0.07)mm for outer & inner surfaces respectively.
Han, Lei; Zhang, Yu; Wan, Xiu-Feng; Zhang, Tong
2016-01-01
Recent statistical evidence has shown that a regression model by incorporating the interactions among the original covariates/features can significantly improve the interpretability for biological data. One major challenge is the exponentially expanded feature space when adding high-order feature interactions to the model. To tackle the huge dimensionality, hierarchical sparse models (HSM) are developed by enforcing sparsity under heredity structures in the interactions among the covariates. However, existing methods only consider pairwise interactions, making the discovery of important high-order interactions a non-trivial open problem. In this paper, we propose a generalized hierarchical sparse model (GHSM) as a generalization of the HSM models to tackle arbitrary-order interactions. The GHSM applies the ℓ1 penalty to all the model coefficients under a constraint that given any covariate, if none of its associated kth-order interactions contribute to the regression model, then neither do its associated higher-order interactions. The resulting objective function is non-convex with a challenge lying in the coupled variables appearing in the arbitrary-order hierarchical constraints and we devise an efficient optimization algorithm to directly solve it. Specifically, we decouple the variables in the constraints via both the general iterative shrinkage and thresholding (GIST) and the alternating direction method of multipliers (ADMM) methods into three subproblems, each of which is proved to admit an efficiently analytical solution. We evaluate the GHSM method in both synthetic problem and the antigenic sites identification problem for the influenza virus data, where we expand the feature space up to the 5th-order interactions. Empirical results demonstrate the effectiveness and efficiency of the proposed methods and the learned high-order interactions have meaningful synergistic covariate patterns in the influenza virus antigenicity.
NASA Astrophysics Data System (ADS)
Wu, Bo; Zhu, Yong; Huang, Xin; Li, Jiayi
2016-10-01
Sparse representation classification (SRC) is becoming a promising tool for hyperspectral image (HSI) classification, where the Euclidean spectral distance (ESD) is widely used to reflect the fidelity between the original and reconstructed signals. In this paper, a generalized model is proposed to extend SRC by characterizing the spectral fidelity with flexible similarity measures. To validate the flexibility, several typical similarity measures-the spectral angle similarity (SAS), spectral information divergence (SID), the structural similarity index measure (SSIM), and the ESD-are included in the generalized model. Furthermore, a general solution based on a gradient descent technique is used to solve the nonlinear optimization problem formulated by the flexible similarity measures. To test the generalized model, two actual HSIs were used, and the experimental results confirm the ability of the proposed model to accommodate the various spectral similarity measures. Performance comparisons with the ESD, SAS, SID, and SSIM criteria were also conducted, and the results consistently show the advantages of the generalized model for HSI classification in terms of overall accuracy and kappa coefficient.
Song, Dong; Robinson, Brian S; Hampson, Robert E; Marmarelis, Vasilis Z; Deadwyler, Sam A; Berger, Theodore W
2015-01-01
In order to build hippocampal prostheses for restoring memory functions, we build multi-input, multi-output (MIMO) nonlinear dynamical models of the human hippocampus. Spike trains are recorded from the hippocampal CA3 and CA1 regions of epileptic patients performing a memory-dependent delayed match-to-sample task. Using CA3 and CA1 spike trains as inputs and outputs respectively, second-order sparse generalized Laguerre-Volterra models are estimated with group lasso and local coordinate descent methods to capture the nonlinear dynamics underlying the spike train transformations. These models can accurately predict the CA1 spike trains based on the ongoing CA3 spike trains and thus will serve as the computational basis of the hippocampal memory prosthesis.
Permutation inference for the general linear model
Winkler, Anderson M.; Ridgway, Gerard R.; Webster, Matthew A.; Smith, Stephen M.; Nichols, Thomas E.
2014-01-01
Permutation methods can provide exact control of false positives and allow the use of non-standard statistics, making only weak assumptions about the data. With the availability of fast and inexpensive computing, their main limitation would be some lack of flexibility to work with arbitrary experimental designs. In this paper we report on results on approximate permutation methods that are more flexible with respect to the experimental design and nuisance variables, and conduct detailed simulations to identify the best method for settings that are typical for imaging research scenarios. We present a generic framework for permutation inference for complex general linear models (glms) when the errors are exchangeable and/or have a symmetric distribution, and show that, even in the presence of nuisance effects, these permutation inferences are powerful while providing excellent control of false positives in a wide range of common and relevant imaging research scenarios. We also demonstrate how the inference on glm parameters, originally intended for independent data, can be used in certain special but useful cases in which independence is violated. Detailed examples of common neuroimaging applications are provided, as well as a complete algorithm – the “randomise” algorithm – for permutation inference with the glm. PMID:24530839
Evaluating the double Poisson generalized linear model.
Zou, Yaotian; Geedipally, Srinivas Reddy; Lord, Dominique
2013-10-01
The objectives of this study are to: (1) examine the applicability of the double Poisson (DP) generalized linear model (GLM) for analyzing motor vehicle crash data characterized by over- and under-dispersion and (2) compare the performance of the DP GLM with the Conway-Maxwell-Poisson (COM-Poisson) GLM in terms of goodness-of-fit and theoretical soundness. The DP distribution has seldom been investigated and applied since its first introduction two decades ago. The hurdle for applying the DP is related to its normalizing constant (or multiplicative constant) which is not available in closed form. This study proposed a new method to approximate the normalizing constant of the DP with high accuracy and reliability. The DP GLM and COM-Poisson GLM were developed using two observed over-dispersed datasets and one observed under-dispersed dataset. The modeling results indicate that the DP GLM with its normalizing constant approximated by the new method can handle crash data characterized by over- and under-dispersion. Its performance is comparable to the COM-Poisson GLM in terms of goodness-of-fit (GOF), although COM-Poisson GLM provides a slightly better fit. For the over-dispersed data, the DP GLM performs similar to the NB GLM. Considering the fact that the DP GLM can be easily estimated with inexpensive computation and that it is simpler to interpret coefficients, it offers a flexible and efficient alternative for researchers to model count data.
NASA Astrophysics Data System (ADS)
Hashemi, Nezhad Z.; Karami, A.
2015-10-01
Hyperspectral images (HSI) have high spectral and low spatial resolutions. However, multispectral images (MSI) usually have low spectral and high spatial resolutions. In various applications HSI with high spectral and spatial resolutions are required. In this paper, a new method for spatial resolution enhancement of HSI using high resolution MSI based on sparse coding and linear spectral unmixing (SCLSU) is introduced. In the proposed method (SCLSU), high spectral resolution features of HSI and high spatial resolution features of MSI are fused. In this case, the sparse representation of some high resolution MSI and linear spectral unmixing (LSU) model of HSI and MSI is simultaneously used in order to construct high resolution HSI (HRHSI). The fusion process of HSI and MSI is formulated as an ill-posed inverse problem. It is solved by the Split Augmented Lagrangian Shrinkage Algorithm (SALSA) and an orthogonal matching pursuit (OMP) algorithm. Finally, the proposed algorithm is applied to the Hyperion and ALI datasets. Compared with the other state-of-the-art algorithms such as Coupled Nonnegative Matrix Factorization (CNMF) and local spectral unmixing, the SCLSU has significantly increased the spatial resolution and in addition the spectral content of HSI is well maintained.
Approximate Orthogonal Sparse Embedding for Dimensionality Reduction.
Lai, Zhihui; Wong, Wai Keung; Xu, Yong; Yang, Jian; Zhang, David
2016-04-01
Locally linear embedding (LLE) is one of the most well-known manifold learning methods. As the representative linear extension of LLE, orthogonal neighborhood preserving projection (ONPP) has attracted widespread attention in the field of dimensionality reduction. In this paper, a unified sparse learning framework is proposed by introducing the sparsity or L1-norm learning, which further extends the LLE-based methods to sparse cases. Theoretical connections between the ONPP and the proposed sparse linear embedding are discovered. The optimal sparse embeddings derived from the proposed framework can be computed by iterating the modified elastic net and singular value decomposition. We also show that the proposed model can be viewed as a general model for sparse linear and nonlinear (kernel) subspace learning. Based on this general model, sparse kernel embedding is also proposed for nonlinear sparse feature extraction. Extensive experiments on five databases demonstrate that the proposed sparse learning framework performs better than the existing subspace learning algorithm, particularly in the cases of small sample sizes.
NASA Astrophysics Data System (ADS)
Mohammadi-Ghazi, Reza; Büyüköztürk, Oral
2016-04-01
Singularity expansion method (SEM) is a system identification approach with applications in solving inverse scattering problems, electromagnetic interaction problems, remote sensing, and radars. In this approach, the response of a system is represented in terms of its complex poles; therefore, this method not only extracts the fundamental frequencies of the system from the signal, but also provides sufficient information about system's damping if its transient response is analyzed. There are various techniques in SEM among which the generalized pencil-of-function (GPOF) is the computationally most stable and the least sensitive one to noise. However, SEM methods, including GPOF, suffer from imposition of spurious poles on the expansion of signals due to the lack of apriori information about the number of true poles. In this study we address this problem by proposing sparse generalized pencil-of-function (SGPOF). The proposed method excludes the spurious poles through sparsity-based regularization with ℓ1-norm. This study is backed by numerical examples as well as an application example which employs the proposed technique for structural health monitoring (SHM) and compares the results with other signal processing methods.
Jones, M.T.; Plassmann, P.E.
1995-12-01
BlockSolve95 is a software library for solving large, sparse systems of linear equations on massively parallel computers or networks of workstations. The matrices must be symmetric in structure; however, the matrix nonzero values may be either symmetric or nonsymmetric. The nonzeros must be real valued. BlockSolve95 uses a message-passing paradigm and achieves portability through the use of the MPI message-passing standard. Emphasis has been placed on achieving both good professor performance through the use of higher-level BLAS and scalability through the use of advanced algorithms. This report gives detailed instructions on the use of BlockSolve95 and descriptions of a number of program examples that can be used as templates for application programs.
Liang, Yujie; Ying, Rendong; Lu, Zhenqi; Liu, Peilin
2014-01-01
In the design phase of sensor arrays during array signal processing, the estimation performance and system cost are largely determined by array aperture size. In this article, we address the problem of joint direction-of-arrival (DOA) estimation with distributed sparse linear arrays (SLAs) and propose an off-grid synchronous approach based on distributed compressed sensing to obtain larger array aperture. We focus on the complex source distribution in the practical applications and classify the sources into common and innovation parts according to whether a signal of source can impinge on all the SLAs or a specific one. For each SLA, we construct a corresponding virtual uniform linear array (ULA) to create the relationship of random linear map between the signals respectively observed by these two arrays. The signal ensembles including the common/innovation sources for different SLAs are abstracted as a joint spatial sparsity model. And we use the minimization of concatenated atomic norm via semidefinite programming to solve the problem of joint DOA estimation. Joint calculation of the signals observed by all the SLAs exploits their redundancy caused by the common sources and decreases the requirement of array size. The numerical results illustrate the advantages of the proposed approach. PMID:25420150
NASA Astrophysics Data System (ADS)
Ma, Sangback
In this paper we compare various parallel preconditioners such as Point-SSOR (Symmetric Successive OverRelaxation), ILU(0) (Incomplete LU) in the Wavefront ordering, ILU(0) in the Multi-color ordering, Multi-Color Block SOR (Successive OverRelaxation), SPAI (SParse Approximate Inverse) and pARMS (Parallel Algebraic Recursive Multilevel Solver) for solving large sparse linear systems arising from two-dimensional PDE (Partial Differential Equation)s on structured grids. Point-SSOR is well-known, and ILU(0) is one of the most popular preconditioner, but it is inherently serial. ILU(0) in the Wavefront ordering maximizes the parallelism in the natural order, but the lengths of the wave-fronts are often nonuniform. ILU(0) in the Multi-color ordering is a simple way of achieving a parallelism of the order N, where N is the order of the matrix, but its convergence rate often deteriorates as compared to that of natural ordering. We have chosen the Multi-Color Block SOR preconditioner combined with direct sparse matrix solver, since for the Laplacian matrix the SOR method is known to have a nondeteriorating rate of convergence when used with the Multi-Color ordering. By using block version we expect to minimize the interprocessor communications. SPAI computes the sparse approximate inverse directly by least squares method. Finally, ARMS is a preconditioner recursively exploiting the concept of independent sets and pARMS is the parallel version of ARMS. Experiments were conducted for the Finite Difference and Finite Element discretizations of five two-dimensional PDEs with large meshsizes up to a million on an IBM p595 machine with distributed memory. Our matrices are real positive, i. e., their real parts of the eigenvalues are positive. We have used GMRES(m) as our outer iterative method, so that the convergence of GMRES(m) for our test matrices are mathematically guaranteed. Interprocessor communications were done using MPI (Message Passing Interface) primitives. The
An automatic multigrid method for the solution of sparse linear systems
NASA Technical Reports Server (NTRS)
Shapira, Yair; Israeli, Moshe; Sidi, Avram
1993-01-01
An automatic version of the multigrid method for the solution of linear systems arising from the discretization of elliptic PDE's is presented. This version is based on the structure of the algebraic system solely, and does not use the original partial differential operator. Numerical experiments show that for the Poisson equation the rate of convergence of our method is equal to that of classical multigrid methods. Moreover, the method is robust in the sense that its high rate of convergence is conserved for other classes of problems: non-symmetric, hyperbolic (even with closed characteristics) and problems on non-uniform grids. No double discretization or special treatment of sub-domains (e.g. boundaries) is needed. When supplemented with a vector extrapolation method, high rates of convergence are achieved also for anisotropic and discontinuous problems and also for indefinite Helmholtz equations. A new double discretization strategy is proposed for finite and spectral element schemes and is found better than known strategies.
Collective synchronization as a method of learning and generalization from sparse data
NASA Astrophysics Data System (ADS)
Miyano, Takaya; Tsutsui, Takako
2008-02-01
We propose a method for extracting general features from multivariate data using a network of phase oscillators subject to an analogue of the Kuramoto model for collective synchronization. In this method, the natural frequencies of the oscillators are extended to vector quantities to which multivariate data are assigned. The common frequency vectors of the groups of partially synchronized oscillators are interpreted to be the template vectors representing the general features of the data set. We show that the proposed method becomes equivalent to the self-organizing map algorithm devised by Kohonen when the governing equations are linearized about their solutions of partial synchronization. As a case study to test the utility of our method, we applied it to care-needs-certification data in the Japanese public long-term care insurance program, and found major general patterns in the health status of the elderly needing nursing care.
Multiple Sparse Representations Classification
Plenge, Esben; Klein, Stefan S.; Niessen, Wiro J.; Meijering, Erik
2015-01-01
Sparse representations classification (SRC) is a powerful technique for pixelwise classification of images and it is increasingly being used for a wide variety of image analysis tasks. The method uses sparse representation and learned redundant dictionaries to classify image pixels. In this empirical study we propose to further leverage the redundancy of the learned dictionaries to achieve a more accurate classifier. In conventional SRC, each image pixel is associated with a small patch surrounding it. Using these patches, a dictionary is trained for each class in a supervised fashion. Commonly, redundant/overcomplete dictionaries are trained and image patches are sparsely represented by a linear combination of only a few of the dictionary elements. Given a set of trained dictionaries, a new patch is sparse coded using each of them, and subsequently assigned to the class whose dictionary yields the minimum residual energy. We propose a generalization of this scheme. The method, which we call multiple sparse representations classification (mSRC), is based on the observation that an overcomplete, class specific dictionary is capable of generating multiple accurate and independent estimates of a patch belonging to the class. So instead of finding a single sparse representation of a patch for each dictionary, we find multiple, and the corresponding residual energies provides an enhanced statistic which is used to improve classification. We demonstrate the efficacy of mSRC for three example applications: pixelwise classification of texture images, lumen segmentation in carotid artery magnetic resonance imaging (MRI), and bifurcation point detection in carotid artery MRI. We compare our method with conventional SRC, K-nearest neighbor, and support vector machine classifiers. The results show that mSRC outperforms SRC and the other reference methods. In addition, we present an extensive evaluation of the effect of the main mSRC parameters: patch size, dictionary size, and
ERIC Educational Resources Information Center
Cheong, Yuk Fai; Kamata, Akihito
2013-01-01
In this article, we discuss and illustrate two centering and anchoring options available in differential item functioning (DIF) detection studies based on the hierarchical generalized linear and generalized linear mixed modeling frameworks. We compared and contrasted the assumptions of the two options, and examined the properties of their DIF…
NASA Astrophysics Data System (ADS)
Hine, N. D. M.; Haynes, P. D.; Mostofi, A. A.; Payne, M. C.
2010-09-01
We present calculations of formation energies of defects in an ionic solid (Al2O3) extrapolated to the dilute limit, corresponding to a simulation cell of infinite size. The large-scale calculations required for this extrapolation are enabled by developments in the approach to parallel sparse matrix algebra operations, which are central to linear-scaling density-functional theory calculations. The computational cost of manipulating sparse matrices, whose sizes are determined by the large number of basis functions present, is greatly improved with this new approach. We present details of the sparse algebra scheme implemented in the ONETEP code using hierarchical sparsity patterns, and demonstrate its use in calculations on a wide range of systems, involving thousands of atoms on hundreds to thousands of parallel processes.
Hine, N D M; Haynes, P D; Mostofi, A A; Payne, M C
2010-09-21
We present calculations of formation energies of defects in an ionic solid (Al(2)O(3)) extrapolated to the dilute limit, corresponding to a simulation cell of infinite size. The large-scale calculations required for this extrapolation are enabled by developments in the approach to parallel sparse matrix algebra operations, which are central to linear-scaling density-functional theory calculations. The computational cost of manipulating sparse matrices, whose sizes are determined by the large number of basis functions present, is greatly improved with this new approach. We present details of the sparse algebra scheme implemented in the ONETEP code using hierarchical sparsity patterns, and demonstrate its use in calculations on a wide range of systems, involving thousands of atoms on hundreds to thousands of parallel processes.
Analysis, tuning and comparison of two general sparse solvers for distributed memory computers
Amestoy, P.R.; Duff, I.S.; L'Excellent, J.-Y.; Li, X.S.
2000-06-30
We describe the work performed in the context of a Franco-Berkeley funded project between NERSC-LBNL located in Berkeley (USA) and CERFACS-ENSEEIHT located in Toulouse (France). We discuss both the tuning and performance analysis of two distributed memory sparse solvers (superlu from Berkeley and mumps from Toulouse) on the 512 processor Cray T3E from NERSC (Lawrence Berkeley National Laboratory). This project gave us the opportunity to improve the algorithms and add new features to the codes. We then quite extensively analyze and compare the two approaches on a set of large problems from real applications. We further explain the main differences in the behavior of the approaches on artificial regular grid problems. As a conclusion to this activity report, we mention a set of parallel sparse solvers on which this type of study should be extended.
From linear to generalized linear mixed models: A case study in repeated measures
Technology Transfer Automated Retrieval System (TEKTRAN)
Compared to traditional linear mixed models, generalized linear mixed models (GLMMs) can offer better correspondence between response variables and explanatory models, yielding more efficient estimates and tests in the analysis of data from designed experiments. Using proportion data from a designed...
Generalized perceptual linear prediction features for animal vocalization analysis.
Clemins, Patrick J; Johnson, Michael T
2006-07-01
A new feature extraction model, generalized perceptual linear prediction (gPLP), is developed to calculate a set of perceptually relevant features for digital signal analysis of animal vocalizations. The gPLP model is a generalized adaptation of the perceptual linear prediction model, popular in human speech processing, which incorporates perceptual information such as frequency warping and equal loudness normalization into the feature extraction process. Since such perceptual information is available for a number of animal species, this new approach integrates that information into a generalized model to extract perceptually relevant features for a particular species. To illustrate, qualitative and quantitative comparisons are made between the species-specific model, generalized perceptual linear prediction (gPLP), and the original PLP model using a set of vocalizations collected from captive African elephants (Loxodonta africana) and wild beluga whales (Delphinapterus leucas). The models that incorporate perceptional information outperform the original human-based models in both visualization and classification tasks.
A Bayesian approach for inducing sparsity in generalized linear models with multi-category response
2015-01-01
Background The dimension and complexity of high-throughput gene expression data create many challenges for downstream analysis. Several approaches exist to reduce the number of variables with respect to small sample sizes. In this study, we utilized the Generalized Double Pareto (GDP) prior to induce sparsity in a Bayesian Generalized Linear Model (GLM) setting. The approach was evaluated using a publicly available microarray dataset containing 99 samples corresponding to four different prostate cancer subtypes. Results A hierarchical Sparse Bayesian GLM using GDP prior (SBGG) was developed to take into account the progressive nature of the response variable. We obtained an average overall classification accuracy between 82.5% and 94%, which was higher than Support Vector Machine, Random Forest or a Sparse Bayesian GLM using double exponential priors. Additionally, SBGG outperforms the other 3 methods in correctly identifying pre-metastatic stages of cancer progression, which can prove extremely valuable for therapeutic and diagnostic purposes. Importantly, using Geneset Cohesion Analysis Tool, we found that the top 100 genes produced by SBGG had an average functional cohesion p-value of 2.0E-4 compared to 0.007 to 0.131 produced by the other methods. Conclusions Using GDP in a Bayesian GLM model applied to cancer progression data results in better subclass prediction. In particular, the method identifies pre-metastatic stages of prostate cancer with substantially better accuracy and produces more functionally relevant gene sets. PMID:26423345
A general non-linear multilevel structural equation mixture model
Kelava, Augustin; Brandt, Holger
2014-01-01
In the past 2 decades latent variable modeling has become a standard tool in the social sciences. In the same time period, traditional linear structural equation models have been extended to include non-linear interaction and quadratic effects (e.g., Klein and Moosbrugger, 2000), and multilevel modeling (Rabe-Hesketh et al., 2004). We present a general non-linear multilevel structural equation mixture model (GNM-SEMM) that combines recent semiparametric non-linear structural equation models (Kelava and Nagengast, 2012; Kelava et al., 2014) with multilevel structural equation mixture models (Muthén and Asparouhov, 2009) for clustered and non-normally distributed data. The proposed approach allows for semiparametric relationships at the within and at the between levels. We present examples from the educational science to illustrate different submodels from the general framework. PMID:25101022
Generalized Linear Multi-Frequency Imaging in VLBI
NASA Astrophysics Data System (ADS)
Likhachev, S.; Ladygin, V.; Guirin, I.
2004-07-01
In VLBI, generalized Linear Multi-Frequency Imaging (MFI) consists of multi-frequency synthesis (MFS) and multi-frequency analysis (MFA) of the VLBI data obtained from observations on various frequencies. A set of linear deconvolution MFI algorithms is described. The algorithms make it possible to obtain high quality images interpolated on any given frequency inside any given bandwidth, and to derive reliable estimates of spectral indexes for radio sources with continuum spectrum.
Linear equations in general purpose codes for stiff ODEs
Shampine, L. F.
1980-02-01
It is noted that it is possible to improve significantly the handling of linear problems in a general-purpose code with very little trouble to the user or change to the code. In such situations analytical evaluation of the Jacobian is a lot cheaper than numerical differencing. A slight change in the point at which the Jacobian is evaluated results in a more accurate Jacobian in linear problems. (RWR)
A Matrix Approach for General Higher Order Linear Recurrences
2011-01-01
properties of linear recurrences (such as the well-known Fibonacci and Pell sequences ). In [2], Er defined k linear recurring sequences of order at...the nth term of the ith generalized order-k Fibonacci sequence . Communicated by Lee See Keong. Received: March 26, 2009; Revised: August 28, 2009...6], the author gave the generalized order-k Fibonacci and Pell (F-P) sequence as follows: For m ≥ 0, n > 0 and 1 ≤ i ≤ k uin = 2 muin−1 + u i n−2
Solution of generalized shifted linear systems with complex symmetric matrices
NASA Astrophysics Data System (ADS)
Sogabe, Tomohiro; Hoshi, Takeo; Zhang, Shao-Liang; Fujiwara, Takeo
2012-07-01
We develop the shifted COCG method [R. Takayama, T. Hoshi, T. Sogabe, S.-L. Zhang, T. Fujiwara, Linear algebraic calculation of Green's function for large-scale electronic structure theory, Phys. Rev. B 73 (165108) (2006) 1-9] and the shifted WQMR method [T. Sogabe, T. Hoshi, S.-L. Zhang, T. Fujiwara, On a weighted quasi-residual minimization strategy of the QMR method for solving complex symmetric shifted linear systems, Electron. Trans. Numer. Anal. 31 (2008) 126-140] for solving generalized shifted linear systems with complex symmetric matrices that arise from the electronic structure theory. The complex symmetric Lanczos process with a suitable bilinear form plays an important role in the development of the methods. The numerical examples indicate that the methods are highly attractive when the inner linear systems can efficiently be solved.
Beam envelope calculations in general linear coupled lattices
Chung, Moses; Qin, Hong; Groening, Lars; Xiao, Chen; Davidson, Ronald C.
2015-01-15
The envelope equations and Twiss parameters (β and α) provide important bases for uncoupled linear beam dynamics. For sophisticated beam manipulations, however, coupling elements between two transverse planes are intentionally introduced. The recently developed generalized Courant-Snyder theory offers an effective way of describing the linear beam dynamics in such coupled systems with a remarkably similar mathematical structure to the original Courant-Snyder theory. In this work, we present numerical solutions to the symmetrized matrix envelope equation for β which removes the gauge freedom in the matrix envelope equation for w. Furthermore, we construct the transfer and beam matrices in terms of the generalized Twiss parameters, which enables calculation of the beam envelopes in arbitrary linear coupled systems.
Confidence Intervals for Assessing Heterogeneity in Generalized Linear Mixed Models
ERIC Educational Resources Information Center
Wagler, Amy E.
2014-01-01
Generalized linear mixed models are frequently applied to data with clustered categorical outcomes. The effect of clustering on the response is often difficult to practically assess partly because it is reported on a scale on which comparisons with regression parameters are difficult to make. This article proposes confidence intervals for…
NASA Astrophysics Data System (ADS)
Prabhakar, Sunil Kumar; Rajaguru, Harikumar
2015-12-01
The most common and frequently occurring neurological disorder is epilepsy and the main method useful for the diagnosis of epilepsy is electroencephalogram (EEG) signal analysis. Due to the length of EEG recordings, EEG signal analysis method is quite time-consuming when it is processed manually by an expert. This paper proposes the application of Linear Graph Embedding (LGE) concept as a dimensionality reduction technique for processing the epileptic encephalographic signals and then it is classified using Sparse Representation Classifiers (SRC). SRC is used to analyze the classification of epilepsy risk levels from EEG signals and the parameters such as Sensitivity, Specificity, Time Delay, Quality Value, Performance Index and Accuracy are analyzed.
Credibility analysis of risk classes by generalized linear model
NASA Astrophysics Data System (ADS)
Erdemir, Ovgucan Karadag; Sucu, Meral
2016-06-01
In this paper generalized linear model (GLM) and credibility theory which are frequently used in nonlife insurance pricing are combined for reliability analysis. Using full credibility standard, GLM is associated with limited fluctuation credibility approach. Comparison criteria such as asymptotic variance and credibility probability are used to analyze the credibility of risk classes. An application is performed by using one-year claim frequency data of a Turkish insurance company and results of credible risk classes are interpreted.
A general theory of linear cosmological perturbations: bimetric theories
NASA Astrophysics Data System (ADS)
Lagos, Macarena; Ferreira, Pedro G.
2017-01-01
We implement the method developed in [1] to construct the most general parametrised action for linear cosmological perturbations of bimetric theories of gravity. Specifically, we consider perturbations around a homogeneous and isotropic background, and identify the complete form of the action invariant under diffeomorphism transformations, as well as the number of free parameters characterising this cosmological class of theories. We discuss, in detail, the case without derivative interactions, and compare our results with those found in massive bigravity.
Residuals analysis of the generalized linear models for longitudinal data.
Chang, Y C
2000-05-30
The generalized estimation equation (GEE) method, one of the generalized linear models for longitudinal data, has been used widely in medical research. However, the related sensitivity analysis problem has not been explored intensively. One of the possible reasons for this was due to the correlated structure within the same subject. We showed that the conventional residuals plots for model diagnosis in longitudinal data could mislead a researcher into trusting the fitted model. A non-parametric method, named the Wald-Wolfowitz run test, was proposed to check the residuals plots both quantitatively and graphically. The rationale proposedin this paper is well illustrated with two real clinical studies in Taiwan.
Linear spin-2 fields in most general backgrounds
NASA Astrophysics Data System (ADS)
Bernard, Laura; Deffayet, Cédric; Schmidt-May, Angnis; von Strauss, Mikael
2016-04-01
We derive the full perturbative equations of motion for the most general background solutions in ghost-free bimetric theory in its metric formulation. Clever field redefinitions at the level of fluctuations enable us to circumvent the problem of varying a square-root matrix appearing in the theory. This greatly simplifies the expressions for the linear variation of the bimetric interaction terms. We show that these field redefinitions exist and are uniquely invertible if and only if the variation of the square-root matrix itself has a unique solution, which is a requirement for the linearized theory to be well defined. As an application of our results we examine the constraint structure of ghost-free bimetric theory at the level of linear equations of motion for the first time. We identify a scalar combination of equations which is responsible for the absence of the Boulware-Deser ghost mode in the theory. The bimetric scalar constraint is in general not manifestly covariant in its nature. However, in the massive gravity limit the constraint assumes a covariant form when one of the interaction parameters is set to zero. For that case our analysis provides an alternative and almost trivial proof of the absence of the Boulware-Deser ghost. Our findings generalize previous results in the metric formulation of massive gravity and also agree with studies of its vielbein version.
NASA Astrophysics Data System (ADS)
Riplinger, Christoph; Pinski, Peter; Becker, Ute; Valeev, Edward F.; Neese, Frank
2016-01-01
Domain based local pair natural orbital coupled cluster theory with single-, double-, and perturbative triple excitations (DLPNO-CCSD(T)) is a highly efficient local correlation method. It is known to be accurate and robust and can be used in a black box fashion in order to obtain coupled cluster quality total energies for large molecules with several hundred atoms. While previous implementations showed near linear scaling up to a few hundred atoms, several nonlinear scaling steps limited the applicability of the method for very large systems. In this work, these limitations are overcome and a linear scaling DLPNO-CCSD(T) method for closed shell systems is reported. The new implementation is based on the concept of sparse maps that was introduced in Part I of this series [P. Pinski, C. Riplinger, E. F. Valeev, and F. Neese, J. Chem. Phys. 143, 034108 (2015)]. Using the sparse map infrastructure, all essential computational steps (integral transformation and storage, initial guess, pair natural orbital construction, amplitude iterations, triples correction) are achieved in a linear scaling fashion. In addition, a number of additional algorithmic improvements are reported that lead to significant speedups of the method. The new, linear-scaling DLPNO-CCSD(T) implementation typically is 7 times faster than the previous implementation and consumes 4 times less disk space for large three-dimensional systems. For linear systems, the performance gains and memory savings are substantially larger. Calculations with more than 20 000 basis functions and 1000 atoms are reported in this work. In all cases, the time required for the coupled cluster step is comparable to or lower than for the preceding Hartree-Fock calculation, even if this is carried out with the efficient resolution-of-the-identity and chain-of-spheres approximations. The new implementation even reduces the error in absolute correlation energies by about a factor of two, compared to the already accurate previous
Riplinger, Christoph; Pinski, Peter; Becker, Ute; Valeev, Edward F; Neese, Frank
2016-01-14
Domain based local pair natural orbital coupled cluster theory with single-, double-, and perturbative triple excitations (DLPNO-CCSD(T)) is a highly efficient local correlation method. It is known to be accurate and robust and can be used in a black box fashion in order to obtain coupled cluster quality total energies for large molecules with several hundred atoms. While previous implementations showed near linear scaling up to a few hundred atoms, several nonlinear scaling steps limited the applicability of the method for very large systems. In this work, these limitations are overcome and a linear scaling DLPNO-CCSD(T) method for closed shell systems is reported. The new implementation is based on the concept of sparse maps that was introduced in Part I of this series [P. Pinski, C. Riplinger, E. F. Valeev, and F. Neese, J. Chem. Phys. 143, 034108 (2015)]. Using the sparse map infrastructure, all essential computational steps (integral transformation and storage, initial guess, pair natural orbital construction, amplitude iterations, triples correction) are achieved in a linear scaling fashion. In addition, a number of additional algorithmic improvements are reported that lead to significant speedups of the method. The new, linear-scaling DLPNO-CCSD(T) implementation typically is 7 times faster than the previous implementation and consumes 4 times less disk space for large three-dimensional systems. For linear systems, the performance gains and memory savings are substantially larger. Calculations with more than 20 000 basis functions and 1000 atoms are reported in this work. In all cases, the time required for the coupled cluster step is comparable to or lower than for the preceding Hartree-Fock calculation, even if this is carried out with the efficient resolution-of-the-identity and chain-of-spheres approximations. The new implementation even reduces the error in absolute correlation energies by about a factor of two, compared to the already accurate
Riplinger, Christoph; Pinski, Peter; Becker, Ute; Neese, Frank E-mail: evaleev@vt.edu; Valeev, Edward F. E-mail: evaleev@vt.edu
2016-01-14
Domain based local pair natural orbital coupled cluster theory with single-, double-, and perturbative triple excitations (DLPNO-CCSD(T)) is a highly efficient local correlation method. It is known to be accurate and robust and can be used in a black box fashion in order to obtain coupled cluster quality total energies for large molecules with several hundred atoms. While previous implementations showed near linear scaling up to a few hundred atoms, several nonlinear scaling steps limited the applicability of the method for very large systems. In this work, these limitations are overcome and a linear scaling DLPNO-CCSD(T) method for closed shell systems is reported. The new implementation is based on the concept of sparse maps that was introduced in Part I of this series [P. Pinski, C. Riplinger, E. F. Valeev, and F. Neese, J. Chem. Phys. 143, 034108 (2015)]. Using the sparse map infrastructure, all essential computational steps (integral transformation and storage, initial guess, pair natural orbital construction, amplitude iterations, triples correction) are achieved in a linear scaling fashion. In addition, a number of additional algorithmic improvements are reported that lead to significant speedups of the method. The new, linear-scaling DLPNO-CCSD(T) implementation typically is 7 times faster than the previous implementation and consumes 4 times less disk space for large three-dimensional systems. For linear systems, the performance gains and memory savings are substantially larger. Calculations with more than 20 000 basis functions and 1000 atoms are reported in this work. In all cases, the time required for the coupled cluster step is comparable to or lower than for the preceding Hartree-Fock calculation, even if this is carried out with the efficient resolution-of-the-identity and chain-of-spheres approximations. The new implementation even reduces the error in absolute correlation energies by about a factor of two, compared to the already accurate
Comparative Study of Algorithms for Automated Generalization of Linear Objects
NASA Astrophysics Data System (ADS)
Azimjon, S.; Gupta, P. K.; Sukhmani, R. S. G. S.
2014-11-01
Automated generalization, rooted from conventional cartography, has become an increasing concern in both geographic information system (GIS) and mapping fields. All geographic phenomenon and the processes are bound to the scale, as it is impossible for human being to observe the Earth and the processes in it without decreasing its scale. To get optimal results, cartographers and map-making agencies develop set of rules and constraints, however these rules are under consideration and topic for many researches up until recent days. Reducing map generating time and giving objectivity is possible by developing automated map generalization algorithms (McMaster and Shea, 1988). Modification of the scale traditionally is a manual process, which requires knowledge of the expert cartographer, and it depends on the experience of the user, which makes the process very subjective as every user may generate different map with same requirements. However, automating generalization based on the cartographic rules and constrains can give consistent result. Also, developing automated system for map generation is the demand of this rapid changing world. The research that we have conveyed considers only generalization of the roads, as it is one of the indispensable parts of a map. Dehradun city, Uttarakhand state of India was selected as a study area. The study carried out comparative study of the generalization software sets, operations and algorithms available currently, also considers advantages and drawbacks of the existing software used worldwide. Research concludes with the development of road network generalization tool and with the final generalized road map of the study area, which explores the use of open source python programming language and attempts to compare different road network generalization algorithms. Thus, the paper discusses the alternative solutions for automated generalization of linear objects using GIS-technologies. Research made on automated of road network
Parametrizing linear generalized Langevin dynamics from explicit molecular dynamics simulations
NASA Astrophysics Data System (ADS)
Gottwald, Fabian; Karsten, Sven; Ivanov, Sergei D.; Kühn, Oliver
2015-06-01
Fundamental understanding of complex dynamics in many-particle systems on the atomistic level is of utmost importance. Often the systems of interest are of macroscopic size but can be partitioned into a few important degrees of freedom which are treated most accurately and others which constitute a thermal bath. Particular attention in this respect attracts the linear generalized Langevin equation, which can be rigorously derived by means of a linear projection technique. Within this framework, a complicated interaction with the bath can be reduced to a single memory kernel. This memory kernel in turn is parametrized for a particular system studied, usually by means of time-domain methods based on explicit molecular dynamics data. Here, we discuss that this task is more naturally achieved in frequency domain and develop a Fourier-based parametrization method that outperforms its time-domain analogues. Very surprisingly, the widely used rigid bond method turns out to be inappropriate in general. Importantly, we show that the rigid bond approach leads to a systematic overestimation of relaxation times, unless the system under study consists of a harmonic bath bi-linearly coupled to the relevant degrees of freedom.
Extracting Embedded Generalized Networks from Linear Programming Problems.
1984-09-01
E EXTRACTING EMBEDDED GENERALIZED NETWORKS FROM LINEAR PROGRAMMING PROBLEMS by Gerald G. Brown * . ___Richard D. McBride * R. Kevin Wood LcL7...authorized. EA Gerald ’Brown Richar-rD. McBride 46;val Postgrduate School University of Southern California Monterey, California 93943 Los Angeles...REOT UBE . OV S.SF- PERFOING’ CAORG soN UER. 7. AUTNOR(a) S. CONTRACT ON GRANT NUME111() Gerald G. Brown Richard D. McBride S. PERFORMING ORGANIZATION
Generalization of continuous-variable quantum cloning with linear optics
Zhai Zehui; Guo Juan; Gao Jiangrui
2006-05-15
We propose an asymmetric quantum cloning scheme. Based on the proposal and experiment by Andersen et al. [Phys. Rev. Lett. 94, 240503 (2005)], we generalize it to two asymmetric cases: quantum cloning with asymmetry between output clones and between quadrature variables. These optical implementations also employ linear elements and homodyne detection only. Finally, we also compare the utility of symmetric and asymmetric cloning in an analysis of a squeezed-state quantum key distribution protocol and find that the asymmetric one is more advantageous.
Generalized space and linear momentum operators in quantum mechanics
Costa, Bruno G. da
2014-06-15
We propose a modification of a recently introduced generalized translation operator, by including a q-exponential factor, which implies in the definition of a Hermitian deformed linear momentum operator p{sup ^}{sub q}, and its canonically conjugate deformed position operator x{sup ^}{sub q}. A canonical transformation leads the Hamiltonian of a position-dependent mass particle to another Hamiltonian of a particle with constant mass in a conservative force field of a deformed phase space. The equation of motion for the classical phase space may be expressed in terms of the generalized dual q-derivative. A position-dependent mass confined in an infinite square potential well is shown as an instance. Uncertainty and correspondence principles are analyzed.
General quantum constraints on detector noise in continuous linear measurements
NASA Astrophysics Data System (ADS)
Miao, Haixing
2017-01-01
In quantum sensing and metrology, an important class of measurement is the continuous linear measurement, in which the detector is coupled to the system of interest linearly and continuously in time. One key aspect involved is the quantum noise of the detector, arising from quantum fluctuations in the detector input and output. It determines how fast we acquire information about the system and also influences the system evolution in terms of measurement backaction. We therefore often categorize it as the so-called imprecision noise and quantum backaction noise. There is a general Heisenberg-like uncertainty relation that constrains the magnitude of and the correlation between these two types of quantum noise. The main result of this paper is to show that, when the detector becomes ideal, i.e., at the quantum limit with minimum uncertainty, not only does the uncertainty relation takes the equal sign as expected, but also there are two new equalities. This general result is illustrated by using the typical cavity QED setup with the system being either a qubit or a mechanical oscillator. Particularly, the dispersive readout of a qubit state, and the measurement of mechanical motional sideband asymmetry are considered.
Generalized linear mixed model for segregation distortion analysis
2011-01-01
Background Segregation distortion is a phenomenon that the observed genotypic frequencies of a locus fall outside the expected Mendelian segregation ratio. The main cause of segregation distortion is viability selection on linked marker loci. These viability selection loci can be mapped using genome-wide marker information. Results We developed a generalized linear mixed model (GLMM) under the liability model to jointly map all viability selection loci of the genome. Using a hierarchical generalized linear mixed model, we can handle the number of loci several times larger than the sample size. We used a dataset from an F2 mouse family derived from the cross of two inbred lines to test the model and detected a major segregation distortion locus contributing 75% of the variance of the underlying liability. Replicated simulation experiments confirm that the power of viability locus detection is high and the false positive rate is low. Conclusions Not only can the method be used to detect segregation distortion loci, but also used for mapping quantitative trait loci of disease traits using case only data in humans and selected populations in plants and animals. PMID:22078575
A new family of gauges in linearized general relativity
NASA Astrophysics Data System (ADS)
Esposito, Giampiero; Stornaiolo, Cosimo
2000-05-01
For vacuum Maxwell theory in four dimensions, a supplementary condition exists (due to Eastwood and Singer) which is invariant under conformal rescalings of the metric, in agreement with the conformal symmetry of the Maxwell equations. Thus, starting from the de Donder gauge, which is not conformally invariant but is the gravitational counterpart of the Lorenz gauge, one can consider, led by formal analogy, a new family of gauges in general relativity, which involve fifth-order covariant derivatives of metric perturbations. The admissibility of such gauges in the classical theory is first proven in the cases of linearized theory about flat Euclidean space or flat Minkowski spacetime. In the former, the general solution of the equation for the fulfillment of the gauge condition after infinitesimal diffeomorphisms involves a 3-harmonic 1-form and an inverse Fourier transform. In the latter, one needs instead the kernel of powers of the wave operator, and a contour integral. The analysis is also used to put restrictions on the dimensionless parameter occurring in the DeWitt supermetric, while the proof of admissibility is generalized to a suitable class of curved Riemannian backgrounds. Eventually, a non-local construction of the tensor field is obtained which makes it possible to achieve conformal invariance of the above gauges.
Local structure preserving sparse coding for infrared target recognition
Han, Jing; Yue, Jiang; Zhang, Yi; Bai, Lianfa
2017-01-01
Sparse coding performs well in image classification. However, robust target recognition requires a lot of comprehensive template images and the sparse learning process is complex. We incorporate sparsity into a template matching concept to construct a local sparse structure matching (LSSM) model for general infrared target recognition. A local structure preserving sparse coding (LSPSc) formulation is proposed to simultaneously preserve the local sparse and structural information of objects. By adding a spatial local structure constraint into the classical sparse coding algorithm, LSPSc can improve the stability of sparse representation for targets and inhibit background interference in infrared images. Furthermore, a kernel LSPSc (K-LSPSc) formulation is proposed, which extends LSPSc to the kernel space to weaken the influence of the linear structure constraint in nonlinear natural data. Because of the anti-interference and fault-tolerant capabilities, both LSPSc- and K-LSPSc-based LSSM can implement target identification based on a simple template set, which just needs several images containing enough local sparse structures to learn a sufficient sparse structure dictionary of a target class. Specifically, this LSSM approach has stable performance in the target detection with scene, shape and occlusions variations. High performance is demonstrated on several datasets, indicating robust infrared target recognition in diverse environments and imaging conditions. PMID:28323824
Finding Nonoverlapping Substructures of a Sparse Matrix
Pinar, Ali; Vassilevska, Virginia
2005-08-11
Many applications of scientific computing rely on computations on sparse matrices. The design of efficient implementations of sparse matrix kernels is crucial for the overall efficiency of these applications. Due to the high compute-to-memory ratio and irregular memory access patterns, the performance of sparse matrix kernels is often far away from the peak performance on a modern processor. Alternative data structures have been proposed, which split the original matrix A into A{sub d} and A{sub s}, so that A{sub d} contains all dense blocks of a specified size in the matrix, and A{sub s} contains the remaining entries. This enables the use of dense matrix kernels on the entries of A{sub d} producing better memory performance. In this work, we study the problem of finding a maximum number of nonoverlapping dense blocks in a sparse matrix, which is previously not studied in the sparse matrix community. We show that the maximum nonoverlapping dense blocks problem is NP-complete by using a reduction from the maximum independent set problem on cubic planar graphs. We also propose a 2/3-approximation algorithm that runs in linear time in the number of nonzeros in the matrix. This extended abstract focuses on our results for 2x2 dense blocks. However we show that our results can be generalized to arbitrary sized dense blocks, and many other oriented substructures, which can be exploited to improve the memory performance of sparse matrix operations.
Optimization in generalized linear models: A case study
NASA Astrophysics Data System (ADS)
Silva, Eliana Costa e.; Correia, Aldina; Lopes, Isabel Cristina
2016-06-01
The maximum likelihood method is usually chosen to estimate the regression parameters of Generalized Linear Models (GLM) and also for hypothesis testing and goodness of fit tests. The classical method for estimating GLM parameters is the Fisher scores. In this work we propose to compute the estimates of the parameters with two alternative methods: a derivative-based optimization method, namely the BFGS method which is one of the most popular of the quasi-Newton algorithms, and the PSwarm derivative-free optimization method that combines features of a pattern search optimization method with a global Particle Swarm scheme. As a case study we use a dataset of biological parameters (phytoplankton) and chemical and environmental parameters of the water column of a Portuguese reservoir. The results show that, for this dataset, BFGS and PSwarm methods provided a better fit, than Fisher scores method, and can be good alternatives for finding the estimates for the parameters of a GLM.
Adaptive Error Estimation in Linearized Ocean General Circulation Models
NASA Technical Reports Server (NTRS)
Chechelnitsky, Michael Y.
1999-01-01
Data assimilation methods are routinely used in oceanography. The statistics of the model and measurement errors need to be specified a priori. This study addresses the problem of estimating model and measurement error statistics from observations. We start by testing innovation based methods of adaptive error estimation with low-dimensional models in the North Pacific (5-60 deg N, 132-252 deg E) to TOPEX/POSEIDON (TIP) sea level anomaly data, acoustic tomography data from the ATOC project, and the MIT General Circulation Model (GCM). A reduced state linear model that describes large scale internal (baroclinic) error dynamics is used. The methods are shown to be sensitive to the initial guess for the error statistics and the type of observations. A new off-line approach is developed, the covariance matching approach (CMA), where covariance matrices of model-data residuals are "matched" to their theoretical expectations using familiar least squares methods. This method uses observations directly instead of the innovations sequence and is shown to be related to the MT method and the method of Fu et al. (1993). Twin experiments using the same linearized MIT GCM suggest that altimetric data are ill-suited to the estimation of internal GCM errors, but that such estimates can in theory be obtained using acoustic data. The CMA is then applied to T/P sea level anomaly data and a linearization of a global GFDL GCM which uses two vertical modes. We show that the CMA method can be used with a global model and a global data set, and that the estimates of the error statistics are robust. We show that the fraction of the GCM-T/P residual variance explained by the model error is larger than that derived in Fukumori et al.(1999) with the method of Fu et al.(1993). Most of the model error is explained by the barotropic mode. However, we find that impact of the change in the error statistics on the data assimilation estimates is very small. This is explained by the large
Process Setting through General Linear Model and Response Surface Method
NASA Astrophysics Data System (ADS)
Senjuntichai, Angsumalin
2010-10-01
The objective of this study is to improve the efficiency of the flow-wrap packaging process in soap industry through the reduction of defectives. At the 95% confidence level, with the regression analysis, the sealing temperature, temperatures of upper and lower crimper are found to be the significant factors for the flow-wrap process with respect to the number/percentage of defectives. Twenty seven experiments have been designed and performed according to three levels of each controllable factor. With the general linear model (GLM), the suggested values for the sealing temperature, temperatures of upper and lower crimpers are 185, 85 and 85° C, respectively while the response surface method (RSM) provides the optimal process conditions at 186, 89 and 88° C. Due to different assumptions between percentage of defective and all three temperature parameters, the suggested conditions from the two methods are then slightly different. Fortunately, the estimated percentage of defectives at 5.51% under GLM process condition and the predicted percentage of defectives at 4.62% under RSM process condition are not significant different. But at 95% confidence level, the percentage of defectives under RSM condition can be much lower approximately 2.16% than those under GLM condition in accordance with wider variation. Lastly, the percentages of defectives under the conditions suggested by GLM and RSM are reduced by 55.81% and 62.95%, respectively.
Haley, Benjamin M.; Paunesku, Tatjana; Grdina, David J.; Woloschak, Gayle E.; Aravindan, Natarajan
2015-12-09
The US government regulates allowable radiation exposures relying, in large part, on the seventh report from the committee to estimate the Biological Effect of Ionizing Radiation (BEIR VII), which estimated that most contemporary exposures- protracted or low-dose, carry 1.5 fold less risk of carcinogenesis and mortality per Gy than acute exposures of atomic bomb survivors. This correction is known as the dose and dose rate effectiveness factor for the life span study of atomic bomb survivors (DDREF_{LSS}). As a result, it was calculated by applying a linear-quadratic dose response model to data from Japanese atomic bomb survivors and a limited number of animal studies.
Haley, Benjamin M.; Paunesku, Tatjana; Grdina, David J.; ...
2015-12-09
The US government regulates allowable radiation exposures relying, in large part, on the seventh report from the committee to estimate the Biological Effect of Ionizing Radiation (BEIR VII), which estimated that most contemporary exposures- protracted or low-dose, carry 1.5 fold less risk of carcinogenesis and mortality per Gy than acute exposures of atomic bomb survivors. This correction is known as the dose and dose rate effectiveness factor for the life span study of atomic bomb survivors (DDREFLSS). As a result, it was calculated by applying a linear-quadratic dose response model to data from Japanese atomic bomb survivors and a limitedmore » number of animal studies.« less
1982-10-27
sparse matrices as well as other areas. Contents 1. operations on Sparse Matrices .. . . . . . . . . . . . . . . . . . . . . . . . I 1.1 Multi...22 2.1.1 Nonsymmetric systems ............................................. 22 2.1.1.1 General sparse matrices ...46 2.1.2.1 General sparse matrices ......................................... 46 2.1.2.2 Band or profile forms
Kizilkaya, Kadir; Tempelman, Robert J
2005-01-01
We propose a general Bayesian approach to heteroskedastic error modeling for generalized linear mixed models (GLMM) in which linked functions of conditional means and residual variances are specified as separate linear combinations of fixed and random effects. We focus on the linear mixed model (LMM) analysis of birth weight (BW) and the cumulative probit mixed model (CPMM) analysis of calving ease (CE). The deviance information criterion (DIC) was demonstrated to be useful in correctly choosing between homoskedastic and heteroskedastic error GLMM for both traits when data was generated according to a mixed model specification for both location parameters and residual variances. Heteroskedastic error LMM and CPMM were fitted, respectively, to BW and CE data on 8847 Italian Piemontese first parity dams in which residual variances were modeled as functions of fixed calf sex and random herd effects. The posterior mean residual variance for male calves was over 40% greater than that for female calves for both traits. Also, the posterior means of the standard deviation of the herd-specific variance ratios (relative to a unitary baseline) were estimated to be 0.60 ± 0.09 for BW and 0.74 ± 0.14 for CE. For both traits, the heteroskedastic error LMM and CPMM were chosen over their homoskedastic error counterparts based on DIC values. PMID:15588567
A general protocol to afford enantioenriched linear homoprenylic amines.
Bosque, Irene; Foubelo, Francisco; Gonzalez-Gomez, Jose C
2013-11-21
The reaction of a readily obtained chiral branched homoprenylamonium salt with a range of aldehydes, including aliphatic substrates, affords the corresponding linear isomers in good yields and enantioselectivities.
NASA Astrophysics Data System (ADS)
Chen, De-Han; Hofmann, Bernd; Zou, Jun
2017-01-01
We consider the ill-posed operator equation Ax = y with an injective and bounded linear operator A mapping between {{\\ell}2} and a Hilbert space Y, possessing the unique solution {{x}\\dagger}=≤ft\\{{{x}\\dagger}k\\right\\}k=1∞ . For the cases that sparsity {{x}\\dagger}\\in {{\\ell}0} is expected but often slightly violated in practice, we investigate in comparison with the {{\\ell}1} -regularization the elastic-net regularization, where the penalty is a weighted superposition of the {{\\ell}1} -norm and the {{\\ell}2} -norm square, under the assumption that {{x}\\dagger}\\in {{\\ell}1} . There occur two positive parameters in this approach, the weight parameter η and the regularization parameter as the multiplier of the whole penalty in the Tikhonov functional, whereas only one regularization parameter arises in {{\\ell}1} -regularization. Based on the variational inequality approach for the description of the solution smoothness with respect to the forward operator A and exploiting the method of approximate source conditions, we present some results to estimate the rate of convergence for the elastic-net regularization. The occurring rate function contains the rate of the decay {{x}\\dagger}k\\to 0 for k\\to ∞ and the classical smoothness properties of {{x}\\dagger} as an element in {{\\ell}2} .
Li, Jingyi Jessica; Jiang, Ci-Ren; Brown, James B; Huang, Haiyan; Bickel, Peter J
2011-12-13
Since the inception of next-generation mRNA sequencing (RNA-Seq) technology, various attempts have been made to utilize RNA-Seq data in assembling full-length mRNA isoforms de novo and estimating abundance of isoforms. However, for genes with more than a few exons, the problem tends to be challenging and often involves identifiability issues in statistical modeling. We have developed a statistical method called "sparse linear modeling of RNA-Seq data for isoform discovery and abundance estimation" (SLIDE) that takes exon boundaries and RNA-Seq data as input to discern the set of mRNA isoforms that are most likely to present in an RNA-Seq sample. SLIDE is based on a linear model with a design matrix that models the sampling probability of RNA-Seq reads from different mRNA isoforms. To tackle the model unidentifiability issue, SLIDE uses a modified Lasso procedure for parameter estimation. Compared with deterministic isoform assembly algorithms (e.g., Cufflinks), SLIDE considers the stochastic aspects of RNA-Seq reads in exons from different isoforms and thus has increased power in detecting more novel isoforms. Another advantage of SLIDE is its flexibility of incorporating other transcriptomic data such as RACE, CAGE, and EST into its model to further increase isoform discovery accuracy. SLIDE can also work downstream of other RNA-Seq assembly algorithms to integrate newly discovered genes and exons. Besides isoform discovery, SLIDE sequentially uses the same linear model to estimate the abundance of discovered isoforms. Simulation and real data studies show that SLIDE performs as well as or better than major competitors in both isoform discovery and abundance estimation. The SLIDE software package is available at https://sites.google.com/site/jingyijli/SLIDE.zip.
Connections between Generalizing and Justifying: Students' Reasoning with Linear Relationships
ERIC Educational Resources Information Center
Ellis, Amy B.
2007-01-01
Research investigating algebra students' abilities to generalize and justify suggests that they experience difficulty in creating and using appropriate generalizations and proofs. Although the field has documented students' errors, less is known about what students do understand to be general and convincing. This study examines the ways in which…
User's Manual for PCSMS (Parallel Complex Sparse Matrix Solver). Version 1.
NASA Technical Reports Server (NTRS)
Reddy, C. J.
2000-01-01
PCSMS (Parallel Complex Sparse Matrix Solver) is a computer code written to make use of the existing real sparse direct solvers to solve complex, sparse matrix linear equations. PCSMS converts complex matrices into real matrices and use real, sparse direct matrix solvers to factor and solve the real matrices. The solution vector is reconverted to complex numbers. Though, this utility is written for Silicon Graphics (SGI) real sparse matrix solution routines, it is general in nature and can be easily modified to work with any real sparse matrix solver. The User's Manual is written to make the user acquainted with the installation and operation of the code. Driver routines are given to aid the users to integrate PCSMS routines in their own codes.
Generalizing a Categorization of Students' Interpretations of Linear Kinematics Graphs
ERIC Educational Resources Information Center
Bollen, Laurens; De Cock, Mieke; Zuza, Kristina; Guisasola, Jenaro; van Kampen, Paul
2016-01-01
We have investigated whether and how a categorization of responses to questions on linear distance-time graphs, based on a study of Irish students enrolled in an algebra-based course, could be adopted and adapted to responses from students enrolled in calculus-based physics courses at universities in Flanders, Belgium (KU Leuven) and the Basque…
A General Linear Method for Equating with Small Samples
ERIC Educational Resources Information Center
Albano, Anthony D.
2015-01-01
Research on equating with small samples has shown that methods with stronger assumptions and fewer statistical estimates can lead to decreased error in the estimated equating function. This article introduces a new approach to linear observed-score equating, one which provides flexible control over how form difficulty is assumed versus estimated…
On the Feasibility of a Generalized Linear Program
1989-03-01
generealized linear program by applying the same algorithm to a "phase-one" problem without requiring that the initial basic feasible solution to the latter be non-degenerate. secUrMTY C.AMlIS CAYI S OP ?- PAeES( UII -W & ,
Guisan, A.; Edwards, T.C.; Hastie, T.
2002-01-01
An important statistical development of the last 30 years has been the advance in regression analysis provided by generalized linear models (GLMs) and generalized additive models (GAMs). Here we introduce a series of papers prepared within the framework of an international workshop entitled: Advances in GLMs/GAMs modeling: from species distribution to environmental management, held in Riederalp, Switzerland, 6-11 August 2001. We first discuss some general uses of statistical models in ecology, as well as provide a short review of several key examples of the use of GLMs and GAMs in ecological modeling efforts. We next present an overview of GLMs and GAMs, and discuss some of their related statistics used for predictor selection, model diagnostics, and evaluation. Included is a discussion of several new approaches applicable to GLMs and GAMs, such as ridge regression, an alternative to stepwise selection of predictors, and methods for the identification of interactions by a combined use of regression trees and several other approaches. We close with an overview of the papers and how we feel they advance our understanding of their application to ecological modeling. ?? 2002 Elsevier Science B.V. All rights reserved.
Generalizing a categorization of students' interpretations of linear kinematics graphs
NASA Astrophysics Data System (ADS)
Bollen, Laurens; De Cock, Mieke; Zuza, Kristina; Guisasola, Jenaro; van Kampen, Paul
2016-06-01
We have investigated whether and how a categorization of responses to questions on linear distance-time graphs, based on a study of Irish students enrolled in an algebra-based course, could be adopted and adapted to responses from students enrolled in calculus-based physics courses at universities in Flanders, Belgium (KU Leuven) and the Basque Country, Spain (University of the Basque Country). We discuss how we adapted the categorization to accommodate a much more diverse student cohort and explain how the prior knowledge of students may account for many differences in the prevalence of approaches and success rates. Although calculus-based physics students make fewer mistakes than algebra-based physics students, they encounter similar difficulties that are often related to incorrectly dividing two coordinates. We verified that a qualitative understanding of kinematics is an important but not sufficient condition for students to determine a correct value for the speed. When comparing responses to questions on linear distance-time graphs with responses to isomorphic questions on linear water level versus time graphs, we observed that the context of a question influences the approach students use. Neither qualitative understanding nor an ability to find the slope of a context-free graph proved to be a reliable predictor for the approach students use when they determine the instantaneous speed.
Local Sparse Structure Denoising for Low-Light-Level Image.
Han, Jing; Yue, Jiang; Zhang, Yi; Bai, Lianfa
2015-12-01
Sparse and redundant representations perform well in image denoising. However, sparsity-based methods fail to denoise low-light-level (LLL) images because of heavy and complex noise. They consider sparsity on image patches independently and tend to lose the texture structures. To suppress noises and maintain textures simultaneously, it is necessary to embed noise invariant features into the sparse decomposition process. We, therefore, used a local structure preserving sparse coding (LSPSc) formulation to explore the local sparse structures (both the sparsity and local structure) in image. It was found that, with the introduction of spatial local structure constraint into the general sparse coding algorithm, LSPSc could improve the robustness of sparse representation for patches in serious noise. We further used a kernel LSPSc (K-LSPSc) formulation, which extends LSPSc into the kernel space to weaken the influence of linear structure constraint in nonlinear data. Based on the robust LSPSc and K-LSPSc algorithms, we constructed a local sparse structure denoising (LSSD) model for LLL images, which was demonstrated to give high performance in the natural LLL images denoising, indicating that both the LSPSc- and K-LSPSc-based LSSD models have the stable property of noise inhibition and texture details preservation.
NASA Astrophysics Data System (ADS)
Pavošević, Fabijan; Pinski, Peter; Riplinger, Christoph; Neese, Frank; Valeev, Edward F.
2016-04-01
We present a formulation of the explicitly correlated second-order Møller-Plesset (MP2-F12) energy in which all nontrivial post-mean-field steps are formulated with linear computational complexity in system size. The two key ideas are the use of pair-natural orbitals for compact representation of wave function amplitudes and the use of domain approximation to impose the block sparsity. This development utilizes the concepts for sparse representation of tensors described in the context of the domain based local pair-natural orbital-MP2 (DLPNO-MP2) method by us recently [Pinski et al., J. Chem. Phys. 143, 034108 (2015)]. Novel developments reported here include the use of domains not only for the projected atomic orbitals, but also for the complementary auxiliary basis set (CABS) used to approximate the three- and four-electron integrals of the F12 theory, and a simplification of the standard B intermediate of the F12 theory that avoids computation of four-index two-electron integrals that involve two CABS indices. For quasi-1-dimensional systems (n-alkanes), the O (" separators="N ) DLPNO-MP2-F12 method becomes less expensive than the conventional O (" separators="N5 ) MP2-F12 for n between 10 and 15, for double- and triple-zeta basis sets; for the largest alkane, C200H402, in def2-TZVP basis, the observed computational complexity is N˜1.6, largely due to the cubic cost of computing the mean-field operators. The method reproduces the canonical MP2-F12 energy with high precision: 99.9% of the canonical correlation energy is recovered with the default truncation parameters. Although its cost is significantly higher than that of DLPNO-MP2 method, the cost increase is compensated by the great reduction of the basis set error due to explicit correlation.
Hobbs, Brian P; Sargent, Daniel J; Carlin, Bradley P
2012-08-28
Assessing between-study variability in the context of conventional random-effects meta-analysis is notoriously difficult when incorporating data from only a small number of historical studies. In order to borrow strength, historical and current data are often assumed to be fully homogeneous, but this can have drastic consequences for power and Type I error if the historical information is biased. In this paper, we propose empirical and fully Bayesian modifications of the commensurate prior model (Hobbs et al., 2011) extending Pocock (1976), and evaluate their frequentist and Bayesian properties for incorporating patient-level historical data using general and generalized linear mixed regression models. Our proposed commensurate prior models lead to preposterior admissible estimators that facilitate alternative bias-variance trade-offs than those offered by pre-existing methodologies for incorporating historical data from a small number of historical studies. We also provide a sample analysis of a colon cancer trial comparing time-to-disease progression using a Weibull regression model.
Generalized linear IgA dermatosis with palmar involvement.
Norris, Ivy N; Haeberle, M Tye; Callen, Jeffrey P; Malone, Janine C
2015-09-17
Linear IgA bullous dermatosis (LABD) is a sub-epidermal blistering disorder characterized by deposition of IgA along the basement membrane zone (BMZ) as detected by immunofluorescence microscopy. The diagnosis is made by clinicopathologic correlation with immunofluorescence confirmation. Differentiation from other bullous dermatoses is important because therapeutic measures differ. Prompt initiation of the appropriate therapies can have a major impact on outcomes. We present three cases with prominent palmar involvement to alert the clinician of this potential physical exam finding and to consider LABD in the right context.
Sparse matrix test collections
Duff, I.
1996-12-31
This workshop will discuss plans for coordinating and developing sets of test matrices for the comparison and testing of sparse linear algebra software. We will talk of plans for the next release (Release 2) of the Harwell-Boeing Collection and recent work on improving the accessibility of this Collection and others through the World Wide Web. There will only be three talks of about 15 to 20 minutes followed by a discussion from the floor.
NASA Astrophysics Data System (ADS)
Rudy, Ashley C. A.; Lamoureux, Scott F.; Treitz, Paul; van Ewijk, Karin Y.
2016-07-01
To effectively assess and mitigate risk of permafrost disturbance, disturbance-prone areas can be predicted through the application of susceptibility models. In this study we developed regional susceptibility models for permafrost disturbances using a field disturbance inventory to test the transferability of the model to a broader region in the Canadian High Arctic. Resulting maps of susceptibility were then used to explore the effect of terrain variables on the occurrence of disturbances within this region. To account for a large range of landscape characteristics, the model was calibrated using two locations: Sabine Peninsula, Melville Island, NU, and Fosheim Peninsula, Ellesmere Island, NU. Spatial patterns of disturbance were predicted with a generalized linear model (GLM) and generalized additive model (GAM), each calibrated using disturbed and randomized undisturbed locations from both locations and GIS-derived terrain predictor variables including slope, potential incoming solar radiation, wetness index, topographic position index, elevation, and distance to water. Each model was validated for the Sabine and Fosheim Peninsulas using independent data sets while the transferability of the model to an independent site was assessed at Cape Bounty, Melville Island, NU. The regional GLM and GAM validated well for both calibration sites (Sabine and Fosheim) with the area under the receiver operating curves (AUROC) > 0.79. Both models were applied directly to Cape Bounty without calibration and validated equally with AUROC's of 0.76; however, each model predicted disturbed and undisturbed samples differently. Additionally, the sensitivity of the transferred model was assessed using data sets with different sample sizes. Results indicated that models based on larger sample sizes transferred more consistently and captured the variability within the terrain attributes in the respective study areas. Terrain attributes associated with the initiation of disturbances were
Item Purification in Differential Item Functioning Using Generalized Linear Mixed Models
ERIC Educational Resources Information Center
Liu, Qian
2011-01-01
For this dissertation, four item purification procedures were implemented onto the generalized linear mixed model for differential item functioning (DIF) analysis, and the performance of these item purification procedures was investigated through a series of simulations. Among the four procedures, forward and generalized linear mixed model (GLMM)…
Computer analysis of general linear networks using digraphs.
NASA Technical Reports Server (NTRS)
Mcclenahan, J. O.; Chan, S.-P.
1972-01-01
Investigation of the application of digraphs in analyzing general electronic networks, and development of a computer program based on a particular digraph method developed by Chen. The Chen digraph method is a topological method for solution of networks and serves as a shortcut when hand calculations are required. The advantage offered by this method of analysis is that the results are in symbolic form. It is limited, however, by the size of network that may be handled. Usually hand calculations become too tedious for networks larger than about five nodes, depending on how many elements the network contains. Direct determinant expansion for a five-node network is a very tedious process also.
Bayesian generalized linear mixed modeling of Tuberculosis using informative priors
Woldegerima, Woldegebriel Assefa
2017-01-01
TB is rated as one of the world’s deadliest diseases and South Africa ranks 9th out of the 22 countries with hardest hit of TB. Although many pieces of research have been carried out on this subject, this paper steps further by inculcating past knowledge into the model, using Bayesian approach with informative prior. Bayesian statistics approach is getting popular in data analyses. But, most applications of Bayesian inference technique are limited to situations of non-informative prior, where there is no solid external information about the distribution of the parameter of interest. The main aim of this study is to profile people living with TB in South Africa. In this paper, identical regression models are fitted for classical and Bayesian approach both with non-informative and informative prior, using South Africa General Household Survey (GHS) data for the year 2014. For the Bayesian model with informative prior, South Africa General Household Survey dataset for the year 2011 to 2013 are used to set up priors for the model 2014. PMID:28257437
Bayesian generalized linear mixed modeling of Tuberculosis using informative priors.
Ojo, Oluwatobi Blessing; Lougue, Siaka; Woldegerima, Woldegebriel Assefa
2017-01-01
TB is rated as one of the world's deadliest diseases and South Africa ranks 9th out of the 22 countries with hardest hit of TB. Although many pieces of research have been carried out on this subject, this paper steps further by inculcating past knowledge into the model, using Bayesian approach with informative prior. Bayesian statistics approach is getting popular in data analyses. But, most applications of Bayesian inference technique are limited to situations of non-informative prior, where there is no solid external information about the distribution of the parameter of interest. The main aim of this study is to profile people living with TB in South Africa. In this paper, identical regression models are fitted for classical and Bayesian approach both with non-informative and informative prior, using South Africa General Household Survey (GHS) data for the year 2014. For the Bayesian model with informative prior, South Africa General Household Survey dataset for the year 2011 to 2013 are used to set up priors for the model 2014.
Amestoy, Patrick R.; Duff, Iain S.; L'Excellent, Jean-Yves; Li, Xiaoye S.
2001-10-10
We examine the mechanics of the send and receive mechanism of MPI and in particular how we can implement message passing in a robust way so that our performance is not significantly affected by changes to the MPI system. This leads us to using the Isend/Irecv protocol which will entail sometimes significant algorithmic changes. We discuss this within the context of two different algorithms for sparse Gaussian elimination that we have parallelized. One is a multifrontal solver called MUMPS, the other is a supernodal solver called SuperLU. Both algorithms are difficult to parallelize on distributed memory machines. Our initial strategies were based on simple MPI point-to-point communication primitives. With such approaches, the parallel performance of both codes are very sensitive to the MPI implementation, the way MPI internal buffers are used in particular. We then modified our codes to use more sophisticated nonblocking versions of MPI communication. This significantly improved the performance robustness (independent of the MPI buffering mechanism) and scalability, but at the cost of increased code complexity.
NASA Astrophysics Data System (ADS)
Pilipchuk, L. A.; Pilipchuk, A. S.
2016-12-01
For constructing of the solutions of the sparse linear systems we propose effective methods, technologies and their implementation in Wolfram Mathematica. Sparse systems of these types appear in generalized network flow programming problems in the form of restrictions and can be characterized as systems with a large sparse sub-matrix representing the embedded network structure. In addition, such systems arise in estimating traffic in the generalized graph or multigraph on its unobservable part. For computing of each vector of the basis solution space with linear estimate in the worst case we propose effective algorithms and data structures in the case when a support of the multigraph or graph for the sparse systems contains a cycles.
A note on rank reduction in sparse multivariate regression.
Chen, Kun; Chan, Kung-Sik
A reduced-rank regression with sparse singular value decomposition (RSSVD) approach was proposed by Chen et al. for conducting variable selection in a reduced-rank model. To jointly model the multivariate response, the method efficiently constructs a prespecified number of latent variables as some sparse linear combinations of the predictors. Here, we generalize the method to also perform rank reduction, and enable its usage in reduced-rank vector autoregressive (VAR) modeling to perform automatic rank determination and order selection. We show that in the context of stationary time-series data, the generalized approach correctly identifies both the model rank and the sparse dependence structure between the multivariate response and the predictors, with probability one asymptotically. We demonstrate the efficacy of the proposed method by simulations and analyzing a macro-economical multivariate time series using a reduced-rank VAR model.
Doubly robust estimation of generalized partial linear models for longitudinal data with dropouts.
Lin, Huiming; Fu, Bo; Qin, Guoyou; Zhu, Zhongyi
2017-04-03
We develop a doubly robust estimation of generalized partial linear models for longitudinal data with dropouts. Our method extends the highly efficient aggregate unbiased estimating function approach proposed in Qu et al. (2010) to a doubly robust one in the sense that under missing at random (MAR), our estimator is consistent when either the linear conditional mean condition is satisfied or a model for the dropout process is correctly specified. We begin with a generalized linear model for the marginal mean, and then move forward to a generalized partial linear model, allowing for nonparametric covariate effect by using the regression spline smoothing approximation. We establish the asymptotic theory for the proposed method and use simulation studies to compare its finite sample performance with that of Qu's method, the complete-case generalized estimating equation (GEE) and the inverse-probability weighted GEE. The proposed method is finally illustrated using data from a longitudinal cohort study.
P-SPARSLIB: A parallel sparse iterative solution package
Saad, Y.
1994-12-31
Iterative methods are gaining popularity in engineering and sciences at a time where the computational environment is changing rapidly. P-SPARSLIB is a project to build a software library for sparse matrix computations on parallel computers. The emphasis is on iterative methods and the use of distributed sparse matrices, an extension of the domain decomposition approach to general sparse matrices. One of the goals of this project is to develop a software package geared towards specific applications. For example, the author will test the performance and usefulness of P-SPARSLIB modules on linear systems arising from CFD applications. Equally important is the goal of portability. In the long run, the author wishes to ensure that this package is portable on a variety of platforms, including SIMD environments and shared memory environments.
van Meurs, Brian; Wiggert, Nicole; Wicker, Isaac; Lissek, Shmuel
2014-06-01
Fear-conditioning experiments in the anxiety disorders focus almost exclusively on passive-emotional, Pavlovian conditioning, rather than active-behavioral, instrumental conditioning. Paradigms eliciting both types of conditioning are needed to study maladaptive, instrumental behaviors resulting from Pavlovian abnormalities found in clinical anxiety. One such Pavlovian abnormality is generalization of fear from a conditioned danger-cue (CS+) to resembling stimuli. Though lab-based findings repeatedly link overgeneralized Pavlovian-fear to clinical anxiety, no study assesses the degree to which Pavlovian overgeneralization corresponds with maladaptive, overgeneralized instrumental-avoidance. The current effort fills this gap by validating a novel fear-potentiated startle paradigm including Pavlovian and instrumental components. The paradigm is embedded in a computer game during which shapes appear on the screen. One shape paired with electric-shock serves as CS+, and other resembling shapes, presented in the absence of shock, serve as generalization stimuli (GSs). During the game, participants choose whether to behaviorally avoid shock at the cost of poorer performance. Avoidance during CS+ is considered adaptive because shock is a real possibility. By contrast, avoidance during GSs is considered maladaptive because shock is not a realistic prospect and thus unnecessarily compromises performance. Results indicate significant Pavlovian-instrumental relations, with greater generalization of Pavlovian fear associated with overgeneralization of maladaptive instrumental-avoidance.
Yin, Junming; Chen, Xi; Xing, Eric P.
2016-01-01
We consider the problem of sparse variable selection in nonparametric additive models, with the prior knowledge of the structure among the covariates to encourage those variables within a group to be selected jointly. Previous works either study the group sparsity in the parametric setting (e.g., group lasso), or address the problem in the nonparametric setting without exploiting the structural information (e.g., sparse additive models). In this paper, we present a new method, called group sparse additive models (GroupSpAM), which can handle group sparsity in additive models. We generalize the ℓ1/ℓ2 norm to Hilbert spaces as the sparsity-inducing penalty in GroupSpAM. Moreover, we derive a novel thresholding condition for identifying the functional sparsity at the group level, and propose an efficient block coordinate descent algorithm for constructing the estimate. We demonstrate by simulation that GroupSpAM substantially outperforms the competing methods in terms of support recovery and prediction accuracy in additive models, and also conduct a comparative experiment on a real breast cancer dataset.
ERIC Educational Resources Information Center
Schluchter, Mark D.
2008-01-01
In behavioral research, interest is often in examining the degree to which the effect of an independent variable X on an outcome Y is mediated by an intermediary or mediator variable M. This article illustrates how generalized estimating equations (GEE) modeling can be used to estimate the indirect or mediated effect, defined as the amount by…
Zhao, Yingfeng; Liu, Sanyang
2016-01-01
We present a practical branch and bound algorithm for globally solving generalized linear multiplicative programming problem with multiplicative constraints. To solve the problem, a relaxation programming problem which is equivalent to a linear programming is proposed by utilizing a new two-phase relaxation technique. In the algorithm, lower and upper bounds are simultaneously obtained by solving some linear relaxation programming problems. Global convergence has been proved and results of some sample examples and a small random experiment show that the proposed algorithm is feasible and efficient.
Carrasco, Josep L
2010-09-01
The classical concordance correlation coefficient (CCC) to measure agreement among a set of observers assumes data to be distributed as normal and a linear relationship between the mean and the subject and observer effects. Here, the CCC is generalized to afford any distribution from the exponential family by means of the generalized linear mixed models (GLMMs) theory and applied to the case of overdispersed count data. An example of CD34+ cell count data is provided to show the applicability of the procedure. In the latter case, different CCCs are defined and applied to the data by changing the GLMM that fits the data. A simulation study is carried out to explore the behavior of the procedure with a small and moderate sample size.
Efficient, sparse biological network determination
August, Elias; Papachristodoulou, Antonis
2009-01-01
Background Determining the interaction topology of biological systems is a topic that currently attracts significant research interest. Typical models for such systems take the form of differential equations that involve polynomial and rational functions. Such nonlinear models make the problem of determining the connectivity of biochemical networks from time-series experimental data much harder. The use of linear dynamics and linearization techniques that have been proposed in the past can circumvent this, but the general problem of developing efficient algorithms for models that provide more accurate system descriptions remains open. Results We present a network determination algorithm that can treat model descriptions with polynomial and rational functions and which does not make use of linearization. For this purpose, we make use of the observation that biochemical networks are in general 'sparse' and minimize the 1-norm of the decision variables (sum of weighted network connections) while constraints keep the error between data and the network dynamics small. The emphasis of our methodology is on determining the interconnection topology rather than the specific reaction constants and it takes into account the necessary properties that a chemical reaction network should have – something that techniques based on linearization can not. The problem can be formulated as a Linear Program, a convex optimization problem, for which efficient algorithms are available that can treat large data sets efficiently and uncertainties in data or model parameters. Conclusion The presented methodology is able to predict with accuracy and efficiency the connectivity structure of a chemical reaction network with mass action kinetics and of a gene regulatory network from simulation data even if the dynamics of these systems are non-polynomial (rational) and uncertainties in the data are taken into account. It also produces a network structure that can explain the real experimental
Linear and nonlinear associations between general intelligence and personality in Project TALENT.
Major, Jason T; Johnson, Wendy; Deary, Ian J
2014-04-01
Research on the relations of personality traits to intelligence has primarily been concerned with linear associations. Yet, there are no a priori reasons why linear relations should be expected over nonlinear ones, which represent a much larger set of all possible associations. Using 2 techniques, quadratic and generalized additive models, we tested for linear and nonlinear associations of general intelligence (g) with 10 personality scales from Project TALENT (PT), a nationally representative sample of approximately 400,000 American high school students from 1960, divided into 4 grade samples (Flanagan et al., 1962). We departed from previous studies, including one with PT (Reeve, Meyer, & Bonaccio, 2006), by modeling latent quadratic effects directly, controlling the influence of the common factor in the personality scales, and assuming a direction of effect from g to personality. On the basis of the literature, we made 17 directional hypotheses for the linear and quadratic associations. Of these, 53% were supported in all 4 male grades and 58% in all 4 female grades. Quadratic associations explained substantive variance above and beyond linear effects (mean R² between 1.8% and 3.6%) for Sociability, Maturity, Vigor, and Leadership in males and Sociability, Maturity, and Tidiness in females; linear associations were predominant for other traits. We discuss how suited current theories of the personality-intelligence interface are to explain these associations, and how research on intellectually gifted samples may provide a unique way of understanding them. We conclude that nonlinear models can provide incremental detail regarding personality and intelligence associations.
Regression Is a Univariate General Linear Model Subsuming Other Parametric Methods as Special Cases.
ERIC Educational Resources Information Center
Vidal, Sherry
Although the concept of the general linear model (GLM) has existed since the 1960s, other univariate analyses such as the t-test and the analysis of variance models have remained popular. The GLM produces an equation that minimizes the mean differences of independent variables as they are related to a dependent variable. From a computer printout…
Estimation of Complex Generalized Linear Mixed Models for Measurement and Growth
ERIC Educational Resources Information Center
Jeon, Minjeong
2012-01-01
Maximum likelihood (ML) estimation of generalized linear mixed models (GLMMs) is technically challenging because of the intractable likelihoods that involve high dimensional integrations over random effects. The problem is magnified when the random effects have a crossed design and thus the data cannot be reduced to small independent clusters. A…
NASA Astrophysics Data System (ADS)
Volk, Wolfram; Suh, Joungsik
2013-12-01
The prediction of formability is one of the most important tasks in sheet metal process simulation. The common criterion in industrial applications is the Forming Limit Curve (FLC). The big advantage of FLCs is the easy interpretation of simulation or measurement data in combination with an ISO standard for the experimental determination. However, the conventional FLCs are limited to almost linear and unbroken strain paths, i.e. deformation histories with non-linear strain increments often lead to big differences in comparison to the prediction of the FLC. In this paper a phenomenological approach, the so-called Generalized Forming Limit Concept (GFLC), is introduced to predict the localized necking on arbitrary deformation history with unlimited number of non-linear strain increments. The GFLC consists of the conventional FLC and an acceptable number of experiments with bi-linear deformation history. With the idea of the new defined "Principle of Equivalent Pre-Forming" every deformation state built up of two linear strain increments can be transformed to a pure linear strain path with the same used formability of the material. In advance this procedure can be repeated as often as necessary. Therefore, it allows a robust and cost effective analysis of beginning instability in Finite Element Analysis (FEA) for arbitrary deformation histories. In addition, the GFLC is fully downwards compatible to the established FLC for pure linear strain paths.
Flexible sparse regularization
NASA Astrophysics Data System (ADS)
Lorenz, Dirk A.; Resmerita, Elena
2017-01-01
The seminal paper of Daubechies, Defrise, DeMol made clear that {{\\ell }}p spaces with p\\in [1,2) and p-powers of the corresponding norms are appropriate settings for dealing with reconstruction of sparse solutions of ill-posed problems by regularization. It seems that the case p = 1 provides the best results in most of the situations compared to the cases p\\in (1,2). An extensive literature gives great credit also to using {{\\ell }}p spaces with p\\in (0,1) together with the corresponding quasi-norms, although one has to tackle challenging numerical problems raised by the non-convexity of the quasi-norms. In any of these settings, either superlinear, linear or sublinear, the question of how to choose the exponent p has been not only a numerical issue, but also a philosophical one. In this work we introduce a more flexible way of sparse regularization by varying exponents. We introduce the corresponding functional analytic framework, that leaves the setting of normed spaces but works with so-called F-norms. One curious result is that there are F-norms which generate the ℓ 1 space, but they are strictly convex, while the ℓ 1-norm is just convex.
Implementing general quantum measurements on linear optical and solid-state qubits
NASA Astrophysics Data System (ADS)
Ota, Yukihiro; Ashhab, Sahel; Nori, Franco
2013-03-01
We show a systematic construction for implementing general measurements on a single qubit, including both strong (or projection) and weak measurements. We mainly focus on linear optical qubits. The present approach is composed of simple and feasible elements, i.e., beam splitters, wave plates, and polarizing beam splitters. We show how the parameters characterizing the measurement operators are controlled by the linear optical elements. We also propose a method for the implementation of general measurements in solid-state qubits. Furthermore, we show an interesting application of the general measurements, i.e., entanglement amplification. YO is partially supported by the SPDR Program, RIKEN. SA and FN acknowledge ARO, NSF grant No. 0726909, JSPS-RFBR contract No. 12-02-92100, Grant-in-Aid for Scientific Research (S), MEXT Kakenhi on Quantum Cybernetics, and the JSPS via its FIRST program.
The linear stability of plane stagnation-point flow against general disturbances
NASA Astrophysics Data System (ADS)
Brattkus, K.; Davis, S. H.
1991-02-01
The linear-stability theory of plane stagnation-point flow against an infinite flat plate is re-examined. Disturbances are generalized from those of Goertler type to include other types of variations along the plate. It is shown that Hiemenz flow is linearly stable and that the Goertler-type modes are those that decay slowest. This work then rationalizes the use of such self-similar disturbances on Hiemenz flow and shows how questions of disturbance structure can be approached on other self-similar flows.
The linear stability of plane stagnation-point flow against general disturbances
NASA Technical Reports Server (NTRS)
Brattkus, K.; Davis, S. H.
1991-01-01
The linear-stability theory of plane stagnation-point flow against an infinite flat plate is re-examined. Disturbances are generalized from those of Goertler type to include other types of variations along the plate. It is shown that Hiemenz flow is linearly stable and that the Goertler-type modes are those that decay slowest. This work then rationalizes the use of such self-similar disturbances on Hiemenz flow and shows how questions of disturbance structure can be approached on other self-similar flows.
Estimate of influenza cases using generalized linear, additive and mixed models.
Oviedo, Manuel; Domínguez, Ángela; Pilar Muñoz, M
2015-01-01
We investigated the relationship between reported cases of influenza in Catalonia (Spain). Covariates analyzed were: population, age, data of report of influenza, and health region during 2010-2014 using data obtained from the SISAP program (Institut Catala de la Salut - Generalitat of Catalonia). Reported cases were related with the study of covariates using a descriptive analysis. Generalized Linear Models, Generalized Additive Models and Generalized Additive Mixed Models were used to estimate the evolution of the transmission of influenza. Additive models can estimate non-linear effects of the covariates by smooth functions; and mixed models can estimate data dependence and variability in factor variables using correlations structures and random effects, respectively. The incidence rate of influenza was calculated as the incidence per 100 000 people. The mean rate was 13.75 (range 0-27.5) in the winter months (December, January, February) and 3.38 (range 0-12.57) in the remaining months. Statistical analysis showed that Generalized Additive Mixed Models were better adapted to the temporal evolution of influenza (serial correlation 0.59) than classical linear models.
Empirical Bayes Estimation of Coefficients in the General Linear Model from Data of Deficient Rank.
ERIC Educational Resources Information Center
Braun, Henry I.; And Others
1983-01-01
Empirical Bayes methods are shown to provide a practical alternative to standard least squares methods in fitting high dimensional models to sparse data. An example concerning prediction bias in educational testing is presented as an illustration. (Author)
Semiparametric Analysis of Heterogeneous Data Using Varying-Scale Generalized Linear Models.
Xie, Minge; Simpson, Douglas G; Carroll, Raymond J
2008-01-01
This article describes a class of heteroscedastic generalized linear regression models in which a subset of the regression parameters are rescaled nonparametrically, and develops efficient semiparametric inferences for the parametric components of the models. Such models provide a means to adapt for heterogeneity in the data due to varying exposures, varying levels of aggregation, and so on. The class of models considered includes generalized partially linear models and nonparametrically scaled link function models as special cases. We present an algorithm to estimate the scale function nonparametrically, and obtain asymptotic distribution theory for regression parameter estimates. In particular, we establish that the asymptotic covariance of the semiparametric estimator for the parametric part of the model achieves the semiparametric lower bound. We also describe bootstrap-based goodness-of-scale test. We illustrate the methodology with simulations, published data, and data from collaborative research on ultrasound safety.
NASA Technical Reports Server (NTRS)
Szyld, D. B.
1984-01-01
A brief description of the Model of the World Economy implemented at the Institute for Economic Analysis is presented, together with our experience in converting the software to vector code. For each time period, the model is reduced to a linear system of over 2000 variables. The matrix of coefficients has a bordered block diagonal structure, and we show how some of the matrix operations can be carried out on all diagonal blocks at once.
A review of linear response theory for general differentiable dynamical systems
NASA Astrophysics Data System (ADS)
Ruelle, David
2009-04-01
The classical theory of linear response applies to statistical mechanics close to equilibrium. Away from equilibrium, one may describe the microscopic time evolution by a general differentiable dynamical system, identify nonequilibrium steady states (NESS) and study how these vary under perturbations of the dynamics. Remarkably, it turns out that for uniformly hyperbolic dynamical systems (those satisfying the 'chaotic hypothesis'), the linear response away from equilibrium is very similar to the linear response close to equilibrium: the Kramers-Kronig dispersion relations hold, and the fluctuation-dispersion theorem survives in a modified form (which takes into account the oscillations around the 'attractor' corresponding to the NESS). If the chaotic hypothesis does not hold, two new phenomena may arise. The first is a violation of linear response in the sense that the NESS does not depend differentiably on parameters (but this nondifferentiability may be hard to see experimentally). The second phenomenon is a violation of the dispersion relations: the susceptibility has singularities in the upper half complex plane. These 'acausal' singularities are actually due to 'energy nonconservation': for a small periodic perturbation of the system, the amplitude of the linear response is arbitrarily large. This means that the NESS of the dynamical system under study is not 'inert' but can give energy to the outside world. An 'active' NESS of this sort is very different from an equilibrium state, and it would be interesting to see what happens for active states to the Gallavotti-Cohen fluctuation theorem.
NASA Astrophysics Data System (ADS)
Borzov, V. V.; Damaskinsky, E. V.
2017-02-01
We consider the families of polynomials P = { P n ( x)} n=0 ∞ and Q = { Q n ( x)} n=0 ∞ orthogonal on the real line with respect to the respective probability measures μ and ν. We assume that { Q n ( x)} n=0 ∞ and { P n ( x)} n=0 ∞ are connected by linear relations. In the case k = 2, we describe all pairs (P,Q) for which the algebras A P and A Q of generalized oscillators generated by { Qn(x)} n=0 ∞ and { Pn(x)} n=0 ∞ coincide. We construct generalized oscillators corresponding to pairs (P,Q) for arbitrary k ≥ 1.
NASA Technical Reports Server (NTRS)
Wiggins, R. A.
1972-01-01
The discrete general linear inverse problem reduces to a set of m equations in n unknowns. There is generally no unique solution, but we can find k linear combinations of parameters for which restraints are determined. The parameter combinations are given by the eigenvectors of the coefficient matrix. The number k is determined by the ratio of the standard deviations of the observations to the allowable standard deviations in the resulting solution. Various linear combinations of the eigenvectors can be used to determine parameter resolution and information distribution among the observations. Thus we can determine where information comes from among the observations and exactly how it constraints the set of possible models. The application of such analyses to surface-wave and free-oscillation observations indicates that (1) phase, group, and amplitude observations for any particular mode provide basically the same type of information about the model; (2) observations of overtones can enhance the resolution considerably; and (3) the degree of resolution has generally been overestimated for many model determinations made from surface waves.
Application of the Hyper-Poisson Generalized Linear Model for Analyzing Motor Vehicle Crashes.
Khazraee, S Hadi; Sáez-Castillo, Antonio Jose; Geedipally, Srinivas Reddy; Lord, Dominique
2015-05-01
The hyper-Poisson distribution can handle both over- and underdispersion, and its generalized linear model formulation allows the dispersion of the distribution to be observation-specific and dependent on model covariates. This study's objective is to examine the potential applicability of a newly proposed generalized linear model framework for the hyper-Poisson distribution in analyzing motor vehicle crash count data. The hyper-Poisson generalized linear model was first fitted to intersection crash data from Toronto, characterized by overdispersion, and then to crash data from railway-highway crossings in Korea, characterized by underdispersion. The results of this study are promising. When fitted to the Toronto data set, the goodness-of-fit measures indicated that the hyper-Poisson model with a variable dispersion parameter provided a statistical fit as good as the traditional negative binomial model. The hyper-Poisson model was also successful in handling the underdispersed data from Korea; the model performed as well as the gamma probability model and the Conway-Maxwell-Poisson model previously developed for the same data set. The advantages of the hyper-Poisson model studied in this article are noteworthy. Unlike the negative binomial model, which has difficulties in handling underdispersed data, the hyper-Poisson model can handle both over- and underdispersed crash data. Although not a major issue for the Conway-Maxwell-Poisson model, the effect of each variable on the expected mean of crashes is easily interpretable in the case of this new model.
Tussupbayev, Samat; Govind, Niranjan; Lopata, Kenneth A.; Cramer, Christopher J.
2015-03-10
We assess the performance of real-time time-dependent density functional theory (RT-TDDFT) for the calculation of absorption spectra of 12 organic dye molecules relevant to photovoltaics and dye sensitized solar cells with 8 exchange-correlation functionals (3 traditional, 3 global hybrids, and 2 range-separated hybrids). We compare the calculations with traditional linear-response (LR) TDDFT. In addition, we demonstrate the efficacy of the RT-TDDFT approach to calculate wide absorption spectra of two large chromophores relevant to photovoltaics and molecular switches.
Unified Einstein-Virasoro Master Equation in the General Non-Linear Sigma Model
Boer, J. de; Halpern, M.B.
1996-06-05
The Virasoro master equation (VME) describes the general affine-Virasoro construction $T=L^abJ_aJ_b+iD^a \\dif J_a$ in the operator algebra of the WZW model, where $L^ab$ is the inverse inertia tensor and $D^a $ is the improvement vector. In this paper, we generalize this construction to find the general (one-loop) Virasoro construction in the operator algebra of the general non-linear sigma model. The result is a unified Einstein-Virasoro master equation which couples the spacetime spin-two field $L^ab$ to the background fields of the sigma model. For a particular solution $L_G^ab$, the unified system reduces to the canonical stress tensors and conventional Einstein equations of the sigma model, and the system reduces to the general affine-Virasoro construction and the VME when the sigma model is taken to be the WZW action. More generally, the unified system describes a space of conformal field theories which is presumably much larger than the sum of the general affine-Virasoro construction and the sigma model with its canonical stress tensors. We also discuss a number of algebraic and geometrical properties of the system, including its relation to an unsolved problem in the theory of $G$-structures on manifolds with torsion.
Fitting host-parasitoid models with CV2 > 1 using hierarchical generalized linear models.
Perry, J N; Noh, M S; Lee, Y; Alston, R D; Norowi, H M; Powell, W; Rennolls, K
2000-01-01
The powerful general Pacala-Hassell host-parasitoid model for a patchy environment, which allows host density-dependent heterogeneity (HDD) to be distinguished from between-patch, host density-independent heterogeneity (HDI), is reformulated within the class of the generalized linear model (GLM) family. This improves accessibility through the provision of general software within well-known statistical systems, and allows a rich variety of models to be formulated. Covariates such as age class, host density and abiotic factors may be included easily. For the case where there is no HDI, the formulation is a simple GLM. When there is HDI in addition to HDD, the formulation is a hierarchical generalized linear model. Two forms of HDI model are considered, both with between-patch variability: one has binomial variation within patches and one has extra-binomial, overdispersed variation within patches. Examples are given demonstrating parameter estimation with standard errors, and hypothesis testing. For one example given, the extra-binomial component of the HDI heterogeneity in parasitism is itself shown to be strongly density dependent. PMID:11416907
Block sparse Cholesky algorithms on advanced uniprocessor computers
Ng, E.G.; Peyton, B.W.
1991-12-01
As with many other linear algebra algorithms, devising a portable implementation of sparse Cholesky factorization that performs well on the broad range of computer architectures currently available is a formidable challenge. Even after limiting our attention to machines with only one processor, as we have done in this report, there are still several interesting issues to consider. For dense matrices, it is well known that block factorization algorithms are the best means of achieving this goal. We take this approach for sparse factorization as well. This paper has two primary goals. First, we examine two sparse Cholesky factorization algorithms, the multifrontal method and a blocked left-looking sparse Cholesky method, in a systematic and consistent fashion, both to illustrate the strengths of the blocking techniques in general and to obtain a fair evaluation of the two approaches. Second, we assess the impact of various implementation techniques on time and storage efficiency, paying particularly close attention to the work-storage requirement of the two methods and their variants.
HYPOTHESIS TESTING FOR HIGH-DIMENSIONAL SPARSE BINARY REGRESSION
Mukherjee, Rajarshi; Pillai, Natesh S.; Lin, Xihong
2015-01-01
In this paper, we study the detection boundary for minimax hypothesis testing in the context of high-dimensional, sparse binary regression models. Motivated by genetic sequencing association studies for rare variant effects, we investigate the complexity of the hypothesis testing problem when the design matrix is sparse. We observe a new phenomenon in the behavior of detection boundary which does not occur in the case of Gaussian linear regression. We derive the detection boundary as a function of two components: a design matrix sparsity index and signal strength, each of which is a function of the sparsity of the alternative. For any alternative, if the design matrix sparsity index is too high, any test is asymptotically powerless irrespective of the magnitude of signal strength. For binary design matrices with the sparsity index that is not too high, our results are parallel to those in the Gaussian case. In this context, we derive detection boundaries for both dense and sparse regimes. For the dense regime, we show that the generalized likelihood ratio is rate optimal; for the sparse regime, we propose an extended Higher Criticism Test and show it is rate optimal and sharp. We illustrate the finite sample properties of the theoretical results using simulation studies. PMID:26246645
Normality of raw data in general linear models: The most widespread myth in statistics
Kery, Marc; Hatfield, Jeff S.
2003-01-01
In years of statistical consulting for ecologists and wildlife biologists, by far the most common misconception we have come across has been the one about normality in general linear models. These comprise a very large part of the statistical models used in ecology and include t tests, simple and multiple linear regression, polynomial regression, and analysis of variance (ANOVA) and covariance (ANCOVA). There is a widely held belief that the normality assumption pertains to the raw data rather than to the model residuals. We suspect that this error may also occur in countless published studies, whenever the normality assumption is tested prior to analysis. This may lead to the use of nonparametric alternatives (if there are any), when parametric tests would indeed be appropriate, or to use of transformations of raw data, which may introduce hidden assumptions such as multiplicative effects on the natural scale in the case of log-transformed data. Our aim here is to dispel this myth. We very briefly describe relevant theory for two cases of general linear models to show that the residuals need to be normally distributed if tests requiring normality are to be used, such as t and F tests. We then give two examples demonstrating that the distribution of the response variable may be nonnormal, and yet the residuals are well behaved. We do not go into the issue of how to test normality; instead we display the distributions of response variables and residuals graphically.
Stochastic convex sparse principal component analysis.
Baytas, Inci M; Lin, Kaixiang; Wang, Fei; Jain, Anil K; Zhou, Jiayu
2016-12-01
Principal component analysis (PCA) is a dimensionality reduction and data analysis tool commonly used in many areas. The main idea of PCA is to represent high-dimensional data with a few representative components that capture most of the variance present in the data. However, there is an obvious disadvantage of traditional PCA when it is applied to analyze data where interpretability is important. In applications, where the features have some physical meanings, we lose the ability to interpret the principal components extracted by conventional PCA because each principal component is a linear combination of all the original features. For this reason, sparse PCA has been proposed to improve the interpretability of traditional PCA by introducing sparsity to the loading vectors of principal components. The sparse PCA can be formulated as an ℓ1 regularized optimization problem, which can be solved by proximal gradient methods. However, these methods do not scale well because computation of the exact gradient is generally required at each iteration. Stochastic gradient framework addresses this challenge by computing an expected gradient at each iteration. Nevertheless, stochastic approaches typically have low convergence rates due to the high variance. In this paper, we propose a convex sparse principal component analysis (Cvx-SPCA), which leverages a proximal variance reduced stochastic scheme to achieve a geometric convergence rate. We further show that the convergence analysis can be significantly simplified by using a weak condition which allows a broader class of objectives to be applied. The efficiency and effectiveness of the proposed method are demonstrated on a large-scale electronic medical record cohort.
Random generalized linear model: a highly accurate and interpretable ensemble predictor
2013-01-01
Background Ensemble predictors such as the random forest are known to have superior accuracy but their black-box predictions are difficult to interpret. In contrast, a generalized linear model (GLM) is very interpretable especially when forward feature selection is used to construct the model. However, forward feature selection tends to overfit the data and leads to low predictive accuracy. Therefore, it remains an important research goal to combine the advantages of ensemble predictors (high accuracy) with the advantages of forward regression modeling (interpretability). To address this goal several articles have explored GLM based ensemble predictors. Since limited evaluations suggested that these ensemble predictors were less accurate than alternative predictors, they have found little attention in the literature. Results Comprehensive evaluations involving hundreds of genomic data sets, the UCI machine learning benchmark data, and simulations are used to give GLM based ensemble predictors a new and careful look. A novel bootstrap aggregated (bagged) GLM predictor that incorporates several elements of randomness and instability (random subspace method, optional interaction terms, forward variable selection) often outperforms a host of alternative prediction methods including random forests and penalized regression models (ridge regression, elastic net, lasso). This random generalized linear model (RGLM) predictor provides variable importance measures that can be used to define a “thinned” ensemble predictor (involving few features) that retains excellent predictive accuracy. Conclusion RGLM is a state of the art predictor that shares the advantages of a random forest (excellent predictive accuracy, feature importance measures, out-of-bag estimates of accuracy) with those of a forward selected generalized linear model (interpretability). These methods are implemented in the freely available R software package randomGLM. PMID:23323760
Chen, Zhe; Purdon, Patrick L; Pierce, Eric T; Harrell, Grace; Walsh, John; Salazar, Andres F; Tavares, Casie L; Brown, Emery N; Barbieri, Riccardo
2009-01-01
Quantitative evaluation of respiratory sinus arrhythmia (RSA) may provide important information in clinical practice of anesthesia and postoperative care. In this paper, we apply a point process method to assess dynamic RSA during propofol general anesthesia. Specifically, an inverse Gaussian probability distribution is used to model the heartbeat interval, whereas the instantaneous mean is identified by a linear or bilinear bivariate regression on the previous R-R intervals and respiratory measures. The estimated second-order bilinear interaction allows us to evaluate the nonlinear component of the RSA. The instantaneous RSA gain and phase can be estimated with an adaptive point process filter. The algorithm's ability to track non-stationary dynamics is demonstrated using one clinical recording. Our proposed statistical indices provide a valuable quantitative assessment of instantaneous cardiorespiratory control and heart rate variability (HRV) during general anesthesia.
Followill, David S; Stovall, Marilyn S; Kry, Stephen F; Ibbott, Geoffrey S
2003-01-01
The shielding calculations for high energy (>10 MV) linear accelerators must include the photoneutron production within the head of the accelerator. Procedures have been described to calculate the treatment room door shielding based on the neutron source strength (Q value) for a specific accelerator and energy combination. Unfortunately, there is currently little data in the literature stating the neutron source strengths for the most widely used linear accelerators. In this study, the neutron fluence for 36 linear accelerators, including models from Varian, Siemens, Elekta/Philips, and General Electric, was measured using gold-foil activation. Several of the models and energy combinations had multiple measurements. The neutron fluence measured in the patient plane was independent of the surface area of the room, suggesting that neutron fluence is more dependent on the direct neutron fluence from the head of the accelerator than from room scatter. Neutron source strength, Q, was determined from the measured neutron fluences. As expected, Q increased with increasing photon energy. The Q values ranged from 0.02 for a 10 MV beam to 1.44(x10(12)) neutrons per photon Gy for a 25 MV beam. The most comprehensive set of neutron source strength values, Q, for the current accelerators in clinical use are presented for use in calculating room shielding.
Wave packet dynamics in one-dimensional linear and nonlinear generalized Fibonacci lattices.
Zhang, Zhenjun; Tong, Peiqing; Gong, Jiangbin; Li, Baowen
2011-05-01
The spreading of an initially localized wave packet in one-dimensional linear and nonlinear generalized Fibonacci (GF) lattices is studied numerically. The GF lattices can be classified into two classes depending on whether or not the lattice possesses the Pisot-Vijayaraghavan property. For linear GF lattices of the first class, both the second moment and the participation number grow with time. For linear GF lattices of the second class, in the regime of a weak on-site potential, wave packet spreading is close to ballistic diffusion, whereas in the regime of a strong on-site potential, it displays stairlike growth in both the second moment and the participation number. Nonlinear GF lattices are then investigated in parallel. For the first class of nonlinear GF lattices, the second moment of the wave packet still grows with time, but the corresponding participation number does not grow simultaneously. For the second class of nonlinear GF lattices, an analogous phenomenon is observed for the weak on-site potential only. For a strong on-site potential that leads to an enhanced nonlinear self-trapping effect, neither the second moment nor the participation number grows with time. The results can be useful in guiding experiments on the expansion of noninteracting or interacting cold atoms in quasiperiodic optical lattices.
Thermodynamic bounds and general properties of optimal efficiency and power in linear responses
NASA Astrophysics Data System (ADS)
Jiang, Jian-Hua
2014-10-01
We study the optimal exergy efficiency and power for thermodynamic systems with an Onsager-type "current-force" relationship describing the linear response to external influences. We derive, in analytic forms, the maximum efficiency and optimal efficiency for maximum power for a thermodynamic machine described by a N ×N symmetric Onsager matrix with arbitrary integer N. The figure of merit is expressed in terms of the largest eigenvalue of the "coupling matrix" which is solely determined by the Onsager matrix. Some simple but general relationships between the power and efficiency at the conditions for (i) maximum efficiency and (ii) optimal efficiency for maximum power are obtained. We show how the second law of thermodynamics bounds the optimal efficiency and the Onsager matrix and relate those bounds together. The maximum power theorem (Jacobi's Law) is generalized to all thermodynamic machines with a symmetric Onsager matrix in the linear-response regime. We also discuss systems with an asymmetric Onsager matrix (such as systems under magnetic field) for a particular situation and we show that the reversible limit of efficiency can be reached at finite output power. Cooperative effects are found to improve the figure of merit significantly in systems with multiply cross-correlated responses. Application to example systems demonstrates that the theory is helpful in guiding the search for high performance materials and structures in energy researches.
Vectorized Sparse Elimination.
1984-03-01
Grids," Proc. 6th Symposium on Reservoir Simulation , New Orleans, Feb. 1-2, 1982, pp. 489-506. [51 Arya, S., and D. A. Calahan, "Optimal Scheduling of...of Computer Architecture on Direct Sparse Matrix Routines in Petroleum Reservoir Simulation ," Sparse Matrix Symposium, Fairfield Glade, TE, October
On relating the generalized equivalent uniform dose formalism to the linear-quadratic model.
Djajaputra, David; Wu, Qiuwen
2006-12-01
Two main approaches are commonly used in the literature for computing the equivalent uniform dose (EUD) in radiotherapy. The first approach is based on the cell-survival curve as defined in the linear-quadratic model. The second approach assumes that EUD can be computed as the generalized mean of the dose distribution with an appropriate fitting parameter. We have analyzed the connection between these two formalisms by deriving explicit formulas for the EUD which are applicable to normal distributions. From these formulas we have established an explicit connection between the two formalisms. We found that the EUD parameter has strong dependence on the parameters that characterize the distribution, namely the mean dose and the standard deviation around the mean. By computing the corresponding parameters for clinical dose distributions, which in general do not follow the normal distribution, we have shown that our results are also applicable to actual dose distributions. Our analysis suggests that caution should be used in using generalized EUD approach for reporting and analyzing dose distributions.
Model Averaging Methods for Weight Trimming in Generalized Linear Regression Models.
Elliott, Michael R
2009-03-01
In sample surveys where units have unequal probabilities of inclusion, associations between the inclusion probability and the statistic of interest can induce bias in unweighted estimates. This is true even in regression models, where the estimates of the population slope may be biased if the underlying mean model is misspecified or the sampling is nonignorable. Weights equal to the inverse of the probability of inclusion are often used to counteract this bias. Highly disproportional sample designs have highly variable weights; weight trimming reduces large weights to a maximum value, reducing variability but introducing bias. Most standard approaches are ad hoc in that they do not use the data to optimize bias-variance trade-offs. This article uses Bayesian model averaging to create "data driven" weight trimming estimators. We extend previous results for linear regression models (Elliott 2008) to generalized linear regression models, developing robust models that approximate fully-weighted estimators when bias correction is of greatest importance, and approximate unweighted estimators when variance reduction is critical.
Fan, Yurui; Huang, Guohe; Veawab, Amornvadee
2012-01-01
In this study, a generalized fuzzy linear programming (GFLP) method was developed to deal with uncertainties expressed as fuzzy sets that exist in the constraints and objective function. A stepwise interactive algorithm (SIA) was advanced to solve GFLP model and generate solutions expressed as fuzzy sets. To demonstrate its application, the developed GFLP method was applied to a regional sulfur dioxide (SO2) control planning model to identify effective SO2 mitigation polices with a minimized system performance cost under uncertainty. The results were obtained to represent the amount of SO2 allocated to different control measures from different sources. Compared with the conventional interval-parameter linear programming (ILP) approach, the solutions obtained through GFLP were expressed as fuzzy sets, which can provide intervals for the decision variables and objective function, as well as related possibilities. Therefore, the decision makers can make a tradeoff between model stability and the plausibility based on solutions obtained through GFLP and then identify desired policies for SO2-emission control under uncertainty.
Two-stage method of estimation for general linear growth curve models.
Stukel, T A; Demidenko, E
1997-06-01
We extend the linear random-effects growth curve model (REGCM) (Laird and Ware, 1982, Biometrics 38, 963-974) to study the effects of population covariates on one or more characteristics of the growth curve when the characteristics are expressed as linear combinations of the growth curve parameters. This definition includes the actual growth curve parameters (the usual model) or any subset of these parameters. Such an analysis would be cumbersome using standard growth curve methods because it would require reparameterization of the original growth curve. We implement a two-stage method of estimation based on the two-stage growth curve model used to describe the response. The resulting generalized least squares (GLS) estimator for the population parameters is consistent, asymptotically efficient, and multivariate normal when the number of individuals is large. It is also robust to model misspecification in terms of bias and efficiency of the parameter estimates compared to maximum likelihood with the usual REGCM. We apply the method to a study of factors affecting the growth rate of salmonellae in a cubic growth model, a characteristic that cannot be analyzed easily using standard techniques.
Wu, Jiayang; Cao, Pan; Hu, Xiaofeng; Jiang, Xinhong; Pan, Ting; Yang, Yuxing; Qiu, Ciyuan; Tremblay, Christine; Su, Yikai
2014-10-20
We propose and experimentally demonstrate an all-optical temporal differential-equation solver that can be used to solve ordinary differential equations (ODEs) characterizing general linear time-invariant (LTI) systems. The photonic device implemented by an add-drop microring resonator (MRR) with two tunable interferometric couplers is monolithically integrated on a silicon-on-insulator (SOI) wafer with a compact footprint of ~60 μm × 120 μm. By thermally tuning the phase shifts along the bus arms of the two interferometric couplers, the proposed device is capable of solving first-order ODEs with two variable coefficients. The operation principle is theoretically analyzed, and system testing of solving ODE with tunable coefficients is carried out for 10-Gb/s optical Gaussian-like pulses. The experimental results verify the effectiveness of the fabricated device as a tunable photonic ODE solver.
General linear codes for fault-tolerant matrix operations on processor arrays
NASA Technical Reports Server (NTRS)
Nair, V. S. S.; Abraham, J. A.
1988-01-01
Various checksum codes have been suggested for fault-tolerant matrix computations on processor arrays. Use of these codes is limited due to potential roundoff and overflow errors. Numerical errors may also be misconstrued as errors due to physical faults in the system. In this a set of linear codes is identified which can be used for fault-tolerant matrix operations such as matrix addition, multiplication, transposition, and LU-decomposition, with minimum numerical error. Encoding schemes are given for some of the example codes which fall under the general set of codes. With the help of experiments, a rule of thumb for the selection of a particular code for a given application is derived.
Generalization of the ordinary state-based peridynamic model for isotropic linear viscoelasticity
NASA Astrophysics Data System (ADS)
Delorme, Rolland; Tabiai, Ilyass; Laberge Lebel, Louis; Lévesque, Martin
2017-02-01
This paper presents a generalization of the original ordinary state-based peridynamic model for isotropic linear viscoelasticity. The viscoelastic material response is represented using the thermodynamically acceptable Prony series approach. It can feature as many Prony terms as required and accounts for viscoelastic spherical and deviatoric components. The model was derived from an equivalence between peridynamic viscoelastic parameters and those appearing in classical continuum mechanics, by equating the free energy densities expressed in both frameworks. The model was simplified to a uni-dimensional expression and implemented to simulate a creep-recovery test. This implementation was finally validated by comparing peridynamic predictions to those predicted from classical continuum mechanics. An exact correspondence between peridynamics and the classical continuum approach was shown when the peridynamic horizon becomes small, meaning peridynamics tends toward classical continuum mechanics. This work provides a clear and direct means to researchers dealing with viscoelastic phenomena to tackle their problem within the peridynamic framework.
NASA Astrophysics Data System (ADS)
Rust, H. W.; Vrac, M.; Lengaigne, M.; Sultan, B.
2012-04-01
Changes in precipitation patterns with potentially less precipitation and an increasing risk for droughts pose a threat to water resources and agricultural yields in Senegal. Precipitation in this region is dominated by the West-African Monsoon being active from May to October, a seasonal pattern with inter-annual to decadal variability in the 20th century which is likely to be affected by climate change. We built a generalized linear model for a full spatial description of rainfall in Senegal. The model uses season, location, and a discrete set of weather types as predictors and yields a spatially continuous description of precipitation occurrences and intensities. Weather types have been defined on NCEP/NCAR reanalysis using zonal and meridional winds, as well as relative humidity. This model is suitable for downscaling precipitation, particularly precipitation occurrences relevant for drough risk mapping.
Solving the Linear Balance Equation on the Globe as a Generalized Inverse Problem
NASA Technical Reports Server (NTRS)
Lu, Huei-Iin; Robertson, Franklin R.
1999-01-01
A generalized (pseudo) inverse technique was developed to facilitate a better understanding of the numerical effects of tropical singularities inherent in the spectral linear balance equation (LBE). Depending upon the truncation, various levels of determinancy are manifest. The traditional fully-determined (FD) systems give rise to a strong response, while the under-determined (UD) systems yield a weak response to the tropical singularities. The over-determined (OD) systems result in a modest response and a large residual in the tropics. The FD and OD systems can be alternatively solved by the iterative method. Differences in the solutions of an UD system exist between the inverse technique and the iterative method owing to the non- uniqueness of the problem. A realistic balanced wind was obtained by solving the principal components of the spectral LBE in terms of vorticity in an intermediate resolution. Improved solutions were achieved by including the singular-component solutions which best fit the observed wind data.
Sparse Representation of Smooth Linear Operators
1990-08-01
received study by many authors, resulting in constructions with a variety of properties. Meyer [13] constructed orthonormal wavelets for which h E CI(R...Lemmas 2.3 and 2.4; in fact, substitution of the finite sums which determine the elements of UTUT for the integrals in those lemmas yields the...some k the orthogonal matrices U1,..., U, defined in Section 4.1 have been computed (1 = log2(n/k)). We now present a procedure for computation of UTUT
Structured sparse models for classification
NASA Astrophysics Data System (ADS)
Castrodad, Alexey
The main focus of this thesis is the modeling and classification of high dimensional data using structured sparsity. Sparse models, where data is assumed to be well represented as a linear combination of a few elements from a dictionary, have gained considerable attention in recent years, and its use has led to state-of-the-art results in many signal and image processing tasks. The success of sparse modeling is highly due to its ability to efficiently use the redundancy of the data and find its underlying structure. On a classification setting, we capitalize on this advantage to properly model and separate the structure of the classes. We design and validate modeling solutions to challenging problems arising in computer vision and remote sensing. We propose both supervised and unsupervised schemes for the modeling of human actions from motion imagery under a wide variety of acquisition condi- tions. In the supervised case, the main goal is to classify the human actions in the video given a predefined set of actions to learn from. In the unsupervised case, the main goal is to an- alyze the spatio-temporal dynamics of the individuals in the scene without having any prior information on the actions themselves. We also propose a model for remotely sensed hysper- spectral imagery, where the main goal is to perform automatic spectral source separation and mapping at the subpixel level. Finally, we present a sparse model for sensor fusion to exploit the common structure and enforce collaboration of hyperspectral with LiDAR data for better mapping capabilities. In all these scenarios, we demonstrate that these data can be expressed as a combination of atoms from a class-structured dictionary. These data representation becomes essentially a "mixture of classes," and by directly exploiting the sparse codes, one can attain highly accurate classification performance with relatively unsophisticated classifiers.
Dose-shaping using targeted sparse optimization
Sayre, George A.; Ruan, Dan
2013-07-15
Purpose: Dose volume histograms (DVHs) are common tools in radiation therapy treatment planning to characterize plan quality. As statistical metrics, DVHs provide a compact summary of the underlying plan at the cost of losing spatial information: the same or similar dose-volume histograms can arise from substantially different spatial dose maps. This is exactly the reason why physicians and physicists scrutinize dose maps even after they satisfy all DVH endpoints numerically. However, up to this point, little has been done to control spatial phenomena, such as the spatial distribution of hot spots, which has significant clinical implications. To this end, the authors propose a novel objective function that enables a more direct tradeoff between target coverage, organ-sparing, and planning target volume (PTV) homogeneity, and presents our findings from four prostate cases, a pancreas case, and a head-and-neck case to illustrate the advantages and general applicability of our method.Methods: In designing the energy minimization objective (E{sub tot}{sup sparse}), the authors utilized the following robust cost functions: (1) an asymmetric linear well function to allow differential penalties for underdose, relaxation of prescription dose, and overdose in the PTV; (2) a two-piece linear function to heavily penalize high dose and mildly penalize low and intermediate dose in organs-at risk (OARs); and (3) a total variation energy, i.e., the L{sub 1} norm applied to the first-order approximation of the dose gradient in the PTV. By minimizing a weighted sum of these robust costs, general conformity to dose prescription and dose-gradient prescription is achieved while encouraging prescription violations to follow a Laplace distribution. In contrast, conventional quadratic objectives are associated with a Gaussian distribution of violations, which is less forgiving to large violations of prescription than the Laplace distribution. As a result, the proposed objective E{sub tot
Sampling schemes and parameter estimation for nonlinear Bernoulli-Gaussian sparse models
NASA Astrophysics Data System (ADS)
Boudineau, Mégane; Carfantan, Hervé; Bourguignon, Sébastien; Bazot, Michael
2016-06-01
We address the sparse approximation problem in the case where the data are approximated by the linear combination of a small number of elementary signals, each of these signals depending non-linearly on additional parameters. Sparsity is explicitly expressed through a Bernoulli-Gaussian hierarchical model in a Bayesian framework. Posterior mean estimates are computed using Markov Chain Monte-Carlo algorithms. We generalize the partially marginalized Gibbs sampler proposed in the linear case in [1], and build an hybrid Hastings-within-Gibbs algorithm in order to account for the nonlinear parameters. All model parameters are then estimated in an unsupervised procedure. The resulting method is evaluated on a sparse spectral analysis problem. It is shown to converge more efficiently than the classical joint estimation procedure, with only a slight increase of the computational cost per iteration, consequently reducing the global cost of the estimation procedure.
Evolving sparse stellar populations
NASA Astrophysics Data System (ADS)
Bruzual, Gustavo; Gladis Magris, C.; Hernández-Pérez, Fabiola
2017-03-01
We examine the role that stochastic fluctuations in the IMF and in the number of interacting binaries have on the spectro-photometric properties of sparse stellar populations as a function of age and metallicity.
Canary, Jana D; Blizzard, Leigh; Barry, Ronald P; Hosmer, David W; Quinn, Stephen J
2016-05-01
Generalized linear models (GLM) with a canonical logit link function are the primary modeling technique used to relate a binary outcome to predictor variables. However, noncanonical links can offer more flexibility, producing convenient analytical quantities (e.g., probit GLMs in toxicology) and desired measures of effect (e.g., relative risk from log GLMs). Many summary goodness-of-fit (GOF) statistics exist for logistic GLM. Their properties make the development of GOF statistics relatively straightforward, but it can be more difficult under noncanonical links. Although GOF tests for logistic GLM with continuous covariates (GLMCC) have been applied to GLMCCs with log links, we know of no GOF tests in the literature specifically developed for GLMCCs that can be applied regardless of link function chosen. We generalize the Tsiatis GOF statistic originally developed for logistic GLMCCs, (TG), so that it can be applied under any link function. Further, we show that the algebraically related Hosmer-Lemeshow (HL) and Pigeon-Heyse (J(2) ) statistics can be applied directly. In a simulation study, TG, HL, and J(2) were used to evaluate the fit of probit, log-log, complementary log-log, and log models, all calculated with a common grouping method. The TG statistic consistently maintained Type I error rates, while those of HL and J(2) were often lower than expected if terms with little influence were included. Generally, the statistics had similar power to detect an incorrect model. An exception occurred when a log GLMCC was incorrectly fit to data generated from a logistic GLMCC. In this case, TG had more power than HL or J(2) .
Sparse recovery via convex optimization
NASA Astrophysics Data System (ADS)
Randall, Paige Alicia
This thesis considers the problem of estimating a sparse signal from a few (possibly noisy) linear measurements. In other words, we have y = Ax + z where A is a measurement matrix with more columns than rows, x is a sparse signal to be estimated, z is a noise vector, and y is a vector of measurements. This setup arises frequently in many problems ranging from MRI imaging to genomics to compressed sensing.We begin by relating our setup to an error correction problem over the reals, where a received encoded message is corrupted by a few arbitrary errors, as well as smaller dense errors. We show that under suitable conditions on the encoding matrix and on the number of arbitrary errors, one is able to accurately recover the message.We next show that we are able to achieve oracle optimality for x, up to a log factor and a factor of sqrt{s}, when we require the matrix A to obey an incoherence property. The incoherence property is novel in that it allows the coherence of A to be as large as O(1/ log n) and still allows sparsities as large as O(m/log n). This is in contrast to other existing results involving coherence where the coherence can only be as large as O(1/sqrt{m}) to allow sparsities as large as O(sqrt{m}). We also do not make the common assumption that the matrix A obeys a restricted eigenvalue condition.We then show that we can recover a (non-sparse) signal from a few linear measurements when the signal has an exactly sparse representation in an overcomplete dictionary. We again only require that the dictionary obey an incoherence property.Finally, we introduce the method of l_1 analysis and show that it is guaranteed to give good recovery of a signal from a few measurements, when the signal can be well represented in a dictionary. We require that the combined measurement/dictionary matrix satisfies a uniform uncertainty principle and we compare our results with the more standard l_1 synthesis approach.All our methods involve solving an l_1 minimization
Sparse Regression by Projection and Sparse Discriminant Analysis.
Qi, Xin; Luo, Ruiyan; Carroll, Raymond J; Zhao, Hongyu
2015-04-01
Recent years have seen active developments of various penalized regression methods, such as LASSO and elastic net, to analyze high dimensional data. In these approaches, the direction and length of the regression coefficients are determined simultaneously. Due to the introduction of penalties, the length of the estimates can be far from being optimal for accurate predictions. We introduce a new framework, regression by projection, and its sparse version to analyze high dimensional data. The unique nature of this framework is that the directions of the regression coefficients are inferred first, and the lengths and the tuning parameters are determined by a cross validation procedure to achieve the largest prediction accuracy. We provide a theoretical result for simultaneous model selection consistency and parameter estimation consistency of our method in high dimension. This new framework is then generalized such that it can be applied to principal components analysis, partial least squares and canonical correlation analysis. We also adapt this framework for discriminant analysis. Compared to the existing methods, where there is relatively little control of the dependency among the sparse components, our method can control the relationships among the components. We present efficient algorithms and related theory for solving the sparse regression by projection problem. Based on extensive simulations and real data analysis, we demonstrate that our method achieves good predictive performance and variable selection in the regression setting, and the ability to control relationships between the sparse components leads to more accurate classification. In supplemental materials available online, the details of the algorithms and theoretical proofs, and R codes for all simulation studies are provided.
General linear response formula for non integrable systems obeying the Vlasov equation
NASA Astrophysics Data System (ADS)
Patelli, Aurelio; Ruffo, Stefano
2014-11-01
Long-range interacting N-particle systems get trapped into long-living out-of-equilibrium stationary states called quasi-stationary states (QSS). We study here the response to a small external perturbation when such systems are settled into a QSS. In the N → ∞ limit the system is described by the Vlasov equation and QSS are mapped into stable stationary solutions of such equation. We consider this problem in the context of a model that has recently attracted considerable attention, the Hamiltonian mean field (HMF) model. For such a model, stationary inhomogeneous and homogeneous states determine an integrable dynamics in the mean-field effective potential and an action-angle transformation allows one to derive an exact linear response formula. However, such a result would be of limited interest if restricted to the integrable case. In this paper, we show how to derive a general linear response formula which does not use integrability as a requirement. The presence of conservation laws (mass, energy, momentum, etc.) and of further Casimir invariants can be imposed a posteriori. We perform an analysis of the infinite time asymptotics of the response formula for a specific observable, the magnetization in the HMF model, as a result of the application of an external magnetic field, for two stationary stable distributions: the Boltzmann-Gibbs equilibrium distribution and the Fermi-Dirac one. When compared with numerical simulations the predictions of the theory are very good away from the transition energy from inhomogeneous to homogeneous states. Contribution to the Topical Issue "Theory and Applications of the Vlasov Equation", edited by Francesco Pegoraro, Francesco Califano, Giovanni Manfredi and Philip J. Morrison.
Sparse Extreme Learning Machine for Classification
Bai, Zuo; Huang, Guang-Bin; Wang, Danwei; Wang, Han; Westover, M. Brandon
2016-01-01
Extreme learning machine (ELM) was initially proposed for single-hidden-layer feedforward neural networks (SLFNs). In the hidden layer (feature mapping), nodes are randomly generated independently of training data. Furthermore, a unified ELM was proposed, providing a single framework to simplify and unify different learning methods, such as SLFNs, least square support vector machines, proximal support vector machines, and so on. However, the solution of unified ELM is dense, and thus, usually plenty of storage space and testing time are required for large-scale applications. In this paper, a sparse ELM is proposed as an alternative solution for classification, reducing storage space and testing time. In addition, unified ELM obtains the solution by matrix inversion, whose computational complexity is between quadratic and cubic with respect to the training size. It still requires plenty of training time for large-scale problems, even though it is much faster than many other traditional methods. In this paper, an efficient training algorithm is specifically developed for sparse ELM. The quadratic programming problem involved in sparse ELM is divided into a series of smallest possible sub-problems, each of which are solved analytically. Compared with SVM, sparse ELM obtains better generalization performance with much faster training speed. Compared with unified ELM, sparse ELM achieves similar generalization performance for binary classification applications, and when dealing with large-scale binary classification problems, sparse ELM realizes even faster training speed than unified ELM. PMID:25222727
Sparse extreme learning machine for classification.
Bai, Zuo; Huang, Guang-Bin; Wang, Danwei; Wang, Han; Westover, M Brandon
2014-10-01
Extreme learning machine (ELM) was initially proposed for single-hidden-layer feedforward neural networks (SLFNs). In the hidden layer (feature mapping), nodes are randomly generated independently of training data. Furthermore, a unified ELM was proposed, providing a single framework to simplify and unify different learning methods, such as SLFNs, least square support vector machines, proximal support vector machines, and so on. However, the solution of unified ELM is dense, and thus, usually plenty of storage space and testing time are required for large-scale applications. In this paper, a sparse ELM is proposed as an alternative solution for classification, reducing storage space and testing time. In addition, unified ELM obtains the solution by matrix inversion, whose computational complexity is between quadratic and cubic with respect to the training size. It still requires plenty of training time for large-scale problems, even though it is much faster than many other traditional methods. In this paper, an efficient training algorithm is specifically developed for sparse ELM. The quadratic programming problem involved in sparse ELM is divided into a series of smallest possible sub-problems, each of which are solved analytically. Compared with SVM, sparse ELM obtains better generalization performance with much faster training speed. Compared with unified ELM, sparse ELM achieves similar generalization performance for binary classification applications, and when dealing with large-scale binary classification problems, sparse ELM realizes even faster training speed than unified ELM.
Sparse matrix-vector multiplication on a reconfigurable supercomputer
Dubois, David H; Dubois, Andrew J; Boorman, Thomas M; Connor, Carolyn M; Poole, Steve
2008-01-01
Double precision floating point Sparse Matrix-Vector Multiplication (SMVM) is a critical computational kernel used in iterative solvers for systems of sparse linear equations. The poor data locality exhibited by sparse matrices along with the high memory bandwidth requirements of SMVM result in poor performance on general purpose processors. Field Programmable Gate Arrays (FPGAs) offer a possible alternative with their customizable and application-targeted memory sub-system and processing elements. In this work we investigate two separate implementations of the SMVM on an SRC-6 MAPStation workstation. The first implementation investigates the peak performance capability, while the second implementation balances the amount of instantiated logic with the available sustained bandwidth of the FPGA subsystem. Both implementations yield the same sustained performance with the second producing a much more efficient solution. The metrics of processor and application balance are introduced to help provide some insight into the efficiencies of the FPGA and CPU based solutions explicitly showing the tight coupling of the available bandwidth to peak floating point performance. Due to the FPGA's ability to balance the amount of implemented logic to the available memory bandwidth it can provide a much more efficient solution. Finally, making use of the lessons learned implementing the SMVM, we present an fully implemented nonpreconditioned Conjugate Gradient Algorithm utilizing the second SMVM design.
Development and validation of a general purpose linearization program for rigid aircraft models
NASA Technical Reports Server (NTRS)
Duke, E. L.; Antoniewicz, R. F.
1985-01-01
A FORTRAN program that provides the user with a powerful and flexible tool for the linearization of aircraft models is discussed. The program LINEAR numerically determines a linear systems model using nonlinear equations of motion and a user-supplied, nonlinear aerodynamic model. The system model determined by LINEAR consists of matrices for both the state and observation equations. The program has been designed to allow easy selection and definition of the state, control, and observation variables to be used in a particular model. Also, included in the report is a comparison of linear and nonlinear models for a high performance aircraft.
Predicting estuarine use patterns of juvenile fish with Generalized Linear Models
NASA Astrophysics Data System (ADS)
Vasconcelos, R. P.; Le Pape, O.; Costa, M. J.; Cabral, H. N.
2013-03-01
Statistical models are key for estimating fish distributions based on environmental variables, and validation is generally advocated as indispensable but seldom applied. Generalized Linear Models were applied to distributions of juvenile Solea solea, Solea senegalensis, Platichthys flesus and Dicentrarchus labrax in response to environmental variables throughout Portuguese estuaries. Species-specific Delta models with two sub-models were used: Binomial (presence/absence); Gamma (density when present). Models were fitted and tested on separate data sets to estimate the accuracy and robustness of predictions. Temperature, salinity and mud content in sediment were included in most models for presence/absence; salinity and depth in most models for density (when present). In Binomial models (presence/absence), goodness-of-fit, accuracy and robustness varied concurrently among species, and fair to high accuracy and robustness were attained for all species, in models with poor to high goodness-of-fit. But in Gamma models (density when present), goodness-of-fit was not indicative of accuracy and robustness. Only for Platichthys flesus were Gamma and also coupled Delta models (density) accurate and robust, despite some moderate bias and inconsistency in predicted density. The accuracy and robustness of final density estimations were defined by the accuracy and robustness of the estimations of presence/absence and density (when present) provided by the sub-models. The mismatches between goodness-of-fit, accuracy and robustness of positive density models, as well as the difference in performance of presence/absence and density models demonstrated the importance of validation procedures in the evaluation of the value of habitat suitability models as predictive tools.
NASA Astrophysics Data System (ADS)
Elliott, J.; de Souza, R. S.; Krone-Martins, A.; Cameron, E.; Ishida, E. E. O.; Hilbe, J.
2015-04-01
Machine learning techniques offer a precious tool box for use within astronomy to solve problems involving so-called big data. They provide a means to make accurate predictions about a particular system without prior knowledge of the underlying physical processes of the data. In this article, and the companion papers of this series, we present the set of Generalized Linear Models (GLMs) as a fast alternative method for tackling general astronomical problems, including the ones related to the machine learning paradigm. To demonstrate the applicability of GLMs to inherently positive and continuous physical observables, we explore their use in estimating the photometric redshifts of galaxies from their multi-wavelength photometry. Using the gamma family with a log link function we predict redshifts from the PHoto-z Accuracy Testing simulated catalogue and a subset of the Sloan Digital Sky Survey from Data Release 10. We obtain fits that result in catastrophic outlier rates as low as ∼1% for simulated and ∼2% for real data. Moreover, we can easily obtain such levels of precision within a matter of seconds on a normal desktop computer and with training sets that contain merely thousands of galaxies. Our software is made publicly available as a user-friendly package developed in Python, R and via an interactive web application. This software allows users to apply a set of GLMs to their own photometric catalogues and generates publication quality plots with minimum effort. By facilitating their ease of use to the astronomical community, this paper series aims to make GLMs widely known and to encourage their implementation in future large-scale projects, such as the Large Synoptic Survey Telescope.
Shin, Yongyun; Raudenbush, Stephen W
2013-09-28
This article extends single-level missing data methods to efficient estimation of a Q-level nested hierarchical general linear model given ignorable missing data with a general missing pattern at any of the Q levels. The key idea is to reexpress a desired hierarchical model as the joint distribution of all variables including the outcome that are subject to missingness, conditional on all of the covariates that are completely observed and to estimate the joint model under normal theory. The unconstrained joint model, however, identifies extraneous parameters that are not of interest in subsequent analysis of the hierarchical model and that rapidly multiply as the number of levels, the number of variables subject to missingness, and the number of random coefficients grow. Therefore, the joint model may be extremely high dimensional and difficult to estimate well unless constraints are imposed to avoid the proliferation of extraneous covariance components at each level. Furthermore, the over-identified hierarchical model may produce considerably biased inferences. The challenge is to represent the constraints within the framework of the Q-level model in a way that is uniform without regard to Q; in a way that facilitates efficient computation for any number of Q levels; and also in a way that produces unbiased and efficient analysis of the hierarchical model. Our approach yields Q-step recursive estimation and imputation procedures whose qth-step computation involves only level-q data given higher-level computation components. We illustrate the approach with a study of the growth in body mass index analyzing a national sample of elementary school children.
Generalized linear discriminant analysis: a unified framework and efficient model selection.
Ji, Shuiwang; Ye, Jieping
2008-10-01
High-dimensional data are common in many domains, and dimensionality reduction is the key to cope with the curse-of-dimensionality. Linear discriminant analysis (LDA) is a well-known method for supervised dimensionality reduction. When dealing with high-dimensional and low sample size data, classical LDA suffers from the singularity problem. Over the years, many algorithms have been developed to overcome this problem, and they have been applied successfully in various applications. However, there is a lack of a systematic study of the commonalities and differences of these algorithms, as well as their intrinsic relationships. In this paper, a unified framework for generalized LDA is proposed, which elucidates the properties of various algorithms and their relationships. Based on the proposed framework, we show that the matrix computations involved in LDA-based algorithms can be simplified so that the cross-validation procedure for model selection can be performed efficiently. We conduct extensive experiments using a collection of high-dimensional data sets, including text documents, face images, gene expression data, and gene expression pattern images, to evaluate the proposed theories and algorithms.
Profile local linear estimation of generalized semiparametric regression model for longitudinal data
Sun, Liuquan; Zhou, Jie
2013-01-01
This paper studies the generalized semiparametric regression model for longitudinal data where the covariate effects are constant for some and time-varying for others. Different link functions can be used to allow more flexible modelling of longitudinal data. The nonparametric components of the model are estimated using a local linear estimating equation and the parametric components are estimated through a profile estimating function. The method automatically adjusts for heterogeneity of sampling times, allowing the sampling strategy to depend on the past sampling history as well as possibly time-dependent covariates without specifically model such dependence. A K -fold cross-validation bandwidth selection is proposed as a working tool for locating an appropriate bandwidth. A criteria for selecting the link function is proposed to provide better fit of the data. Large sample properties of the proposed estimators are investigated. Large sample pointwise and simultaneous confidence intervals for the regression coefficients are constructed. Formal hypothesis testing procedures are proposed to check for the covariate effects and whether the effects are time-varying. A simulation study is conducted to examine the finite sample performances of the proposed estimation and hypothesis testing procedures. The methods are illustrated with a data example. PMID:23471814
NASA Astrophysics Data System (ADS)
Vandenberg-Rodes, Alexander; Moftakhari, Hamed R.; AghaKouchak, Amir; Shahbaba, Babak; Sanders, Brett F.; Matthew, Richard A.
2016-11-01
Nuisance flooding corresponds to minor and frequent flood events that have significant socioeconomic and public health impacts on coastal communities. Yearly averaged local mean sea level can be used as proxy to statistically predict the impacts of sea level rise (SLR) on the frequency of nuisance floods (NFs). In this study, we use generalized linear models (GLM) and Gaussian Process (GP) models combined to (i) estimate the frequency of NF associated with the change in mean sea level, and (ii) quantify the associated uncertainties via a novel and statistically robust approach. We calibrate our models to the water level data from 18 tide gauges along the coasts of United States, and after validation, we estimate the frequency of NF associated with the SLR projections in year 2030 (under RCPs 2.6 and 8.5), along with their 90% bands, at each gauge. The historical NF-SLR data are very noisy, and show large changes in variability (heteroscedasticity) with SLR. Prior models in the literature do not properly account for the observed heteroscedasticity, and thus their projected uncertainties are highly suspect. Among the models used in this study, the Negative Binomial Distribution GLM with GP best characterizes the uncertainties associated with NF estimates; on validation data ≈93% of the points fall within the 90% credible limit, showing our approach to be a robust model for uncertainty quantification.
Characterizing the performance of the Conway-Maxwell Poisson generalized linear model.
Francis, Royce A; Geedipally, Srinivas Reddy; Guikema, Seth D; Dhavala, Soma Sekhar; Lord, Dominique; LaRocca, Sarah
2012-01-01
Count data are pervasive in many areas of risk analysis; deaths, adverse health outcomes, infrastructure system failures, and traffic accidents are all recorded as count events, for example. Risk analysts often wish to estimate the probability distribution for the number of discrete events as part of doing a risk assessment. Traditional count data regression models of the type often used in risk assessment for this problem suffer from limitations due to the assumed variance structure. A more flexible model based on the Conway-Maxwell Poisson (COM-Poisson) distribution was recently proposed, a model that has the potential to overcome the limitations of the traditional model. However, the statistical performance of this new model has not yet been fully characterized. This article assesses the performance of a maximum likelihood estimation method for fitting the COM-Poisson generalized linear model (GLM). The objectives of this article are to (1) characterize the parameter estimation accuracy of the MLE implementation of the COM-Poisson GLM, and (2) estimate the prediction accuracy of the COM-Poisson GLM using simulated data sets. The results of the study indicate that the COM-Poisson GLM is flexible enough to model under-, equi-, and overdispersed data sets with different sample mean values. The results also show that the COM-Poisson GLM yields accurate parameter estimates. The COM-Poisson GLM provides a promising and flexible approach for performing count data regression.
Garcia, J M; Teodoro, F; Cerdeira, R; Coelho, L M R; Kumar, Prashant; Carvalho, M G
2016-09-01
A methodology to predict PM10 concentrations in urban outdoor environments is developed based on the generalized linear models (GLMs). The methodology is based on the relationship developed between atmospheric concentrations of air pollutants (i.e. CO, NO2, NOx, VOCs, SO2) and meteorological variables (i.e. ambient temperature, relative humidity (RH) and wind speed) for a city (Barreiro) of Portugal. The model uses air pollution and meteorological data from the Portuguese monitoring air quality station networks. The developed GLM considers PM10 concentrations as a dependent variable, and both the gaseous pollutants and meteorological variables as explanatory independent variables. A logarithmic link function was considered with a Poisson probability distribution. Particular attention was given to cases with air temperatures both below and above 25°C. The best performance for modelled results against the measured data was achieved for the model with values of air temperature above 25°C compared with the model considering all ranges of air temperatures and with the model considering only temperature below 25°C. The model was also tested with similar data from another Portuguese city, Oporto, and results found to behave similarly. It is concluded that this model and the methodology could be adopted for other cities to predict PM10 concentrations when these data are not available by measurements from air quality monitoring stations or other acquisition means.
A generalized linear model for peak calling in ChIP-Seq data.
Xu, Jialin; Zhang, Yu
2012-06-01
Chromatin immunoprecipitation followed by massively parallel sequencing (ChIP-Seq) has become a routine for detecting genome-wide protein-DNA interaction. The success of ChIP-Seq data analysis highly depends on the quality of peak calling (i.e., to detect peaks of tag counts at a genomic location and evaluate if the peak corresponds to a real protein-DNA interaction event). The challenges in peak calling include (1) how to combine the forward and the reverse strand tag data to improve the power of peak calling and (2) how to account for the variation of tag data observed across different genomic locations. We introduce a new peak calling method based on the generalized linear model (GLMNB) that utilizes negative binomial distribution to model the tag count data and account for the variation of background tags that may randomly bind to the DNA sequence at varying levels due to local genomic structures and sequence contents. We allow local shifting of peaks observed on the forward and the reverse stands, such that at each potential binding site, a binding profile representing the pattern of a real peak signal is fitted to best explain the observed tag data with maximum likelihood. Our method can also detect multiple peaks within a local region if there are multiple binding sites in the region.
The overlooked potential of Generalized Linear Models in astronomy, I: Binomial regression
NASA Astrophysics Data System (ADS)
de Souza, R. S.; Cameron, E.; Killedar, M.; Hilbe, J.; Vilalta, R.; Maio, U.; Biffi, V.; Ciardi, B.; Riggs, J. D.
2015-09-01
Revealing hidden patterns in astronomical data is often the path to fundamental scientific breakthroughs; meanwhile the complexity of scientific enquiry increases as more subtle relationships are sought. Contemporary data analysis problems often elude the capabilities of classical statistical techniques, suggesting the use of cutting edge statistical methods. In this light, astronomers have overlooked a whole family of statistical techniques for exploratory data analysis and robust regression, the so-called Generalized Linear Models (GLMs). In this paper-the first in a series aimed at illustrating the power of these methods in astronomical applications-we elucidate the potential of a particular class of GLMs for handling binary/binomial data, the so-called logit and probit regression techniques, from both a maximum likelihood and a Bayesian perspective. As a case in point, we present the use of these GLMs to explore the conditions of star formation activity and metal enrichment in primordial minihaloes from cosmological hydro-simulations including detailed chemistry, gas physics, and stellar feedback. We predict that for a dark mini-halo with metallicity ≈ 1.3 × 10-4Z⨀, an increase of 1.2 × 10-2 in the gas molecular fraction, increases the probability of star formation occurrence by a factor of 75%. Finally, we highlight the use of receiver operating characteristic curves as a diagnostic for binary classifiers, and ultimately we use these to demonstrate the competitive predictive performance of GLMs against the popular technique of artificial neural networks.
Chen, Gang; Adleman, Nancy E.; Saad, Ziad S.; Leibenluft, Ellen; Cox, RobertW.
2014-01-01
All neuroimaging packages can handle group analysis with t-tests or general linear modeling (GLM). However, they are quite hamstrung when there are multiple within-subject factors or when quantitative covariates are involved in the presence of a within-subject factor. In addition, sphericity is typically assumed for the variance–covariance structure when there are more than two levels in a within-subject factor. To overcome such limitations in the traditional AN(C)OVA and GLM, we adopt a multivariate modeling (MVM) approach to analyzing neuroimaging data at the group level with the following advantages: a) there is no limit on the number of factors as long as sample sizes are deemed appropriate; b) quantitative covariates can be analyzed together with within- subject factors; c) when a within-subject factor is involved, three testing methodologies are provided: traditional univariate testing (UVT)with sphericity assumption (UVT-UC) and with correction when the assumption is violated (UVT-SC), and within-subject multivariate testing (MVT-WS); d) to correct for sphericity violation at the voxel level, we propose a hybrid testing (HT) approach that achieves equal or higher power via combining traditional sphericity correction methods (Greenhouse–Geisser and Huynh–Feldt) with MVT-WS. PMID:24954281
Fast inference in generalized linear models via expected log-likelihoods
Ramirez, Alexandro D.; Paninski, Liam
2015-01-01
Generalized linear models play an essential role in a wide variety of statistical applications. This paper discusses an approximation of the likelihood in these models that can greatly facilitate computation. The basic idea is to replace a sum that appears in the exact log-likelihood by an expectation over the model covariates; the resulting “expected log-likelihood” can in many cases be computed significantly faster than the exact log-likelihood. In many neuroscience experiments the distribution over model covariates is controlled by the experimenter and the expected log-likelihood approximation becomes particularly useful; for example, estimators based on maximizing this expected log-likelihood (or a penalized version thereof) can often be obtained with orders of magnitude computational savings compared to the exact maximum likelihood estimators. A risk analysis establishes that these maximum EL estimators often come with little cost in accuracy (and in some cases even improved accuracy) compared to standard maximum likelihood estimates. Finally, we find that these methods can significantly decrease the computation time of marginal likelihood calculations for model selection and of Markov chain Monte Carlo methods for sampling from the posterior parameter distribution. We illustrate our results by applying these methods to a computationally-challenging dataset of neural spike trains obtained via large-scale multi-electrode recordings in the primate retina. PMID:23832289
Friese, Daniel H; Ruud, Kenneth
2016-02-07
We present the theory of three-photon circular dichroism (3PCD), a novel non-linear chiroptical property not yet described in the literature. We derive the observable absorption cross section including the orientational average of the necessary seventh-rank tensors and provide origin-independent expressions for 3PCD using either a velocity-gauge treatment of the electric dipole operator or a length-gauge formulation using London atomic orbitals. We present the first numerical results for hydrogen peroxide, 3-methylcyclopentanone (MCP) and 4-helicene, including also a study of the origin dependence and basis set convergence of 3PCD. We find that for the 3PCD-brightest low-lying Rydberg state of hydrogen peroxide, the dichroism is extremely basis set dependent, with basis set convergence not being reached before a sextuple-zeta basis is used, whereas for the MCP and 4-helicene molecules, the basis set dependence is more moderate and at the triple-zeta level the 3PCD contributions are more or less converged irrespective of whether the considered states are Rydberg states or not. The character of the 3PCD-brightest states in MCP is characterized by a fairly large charge-transfer character from the carbonyl group to the ring system. In general, the quadrupole contributions to 3PCD are found to be very small.
Fast inference in generalized linear models via expected log-likelihoods.
Ramirez, Alexandro D; Paninski, Liam
2014-04-01
Generalized linear models play an essential role in a wide variety of statistical applications. This paper discusses an approximation of the likelihood in these models that can greatly facilitate computation. The basic idea is to replace a sum that appears in the exact log-likelihood by an expectation over the model covariates; the resulting "expected log-likelihood" can in many cases be computed significantly faster than the exact log-likelihood. In many neuroscience experiments the distribution over model covariates is controlled by the experimenter and the expected log-likelihood approximation becomes particularly useful; for example, estimators based on maximizing this expected log-likelihood (or a penalized version thereof) can often be obtained with orders of magnitude computational savings compared to the exact maximum likelihood estimators. A risk analysis establishes that these maximum EL estimators often come with little cost in accuracy (and in some cases even improved accuracy) compared to standard maximum likelihood estimates. Finally, we find that these methods can significantly decrease the computation time of marginal likelihood calculations for model selection and of Markov chain Monte Carlo methods for sampling from the posterior parameter distribution. We illustrate our results by applying these methods to a computationally-challenging dataset of neural spike trains obtained via large-scale multi-electrode recordings in the primate retina.
Population decoding of motor cortical activity using a generalized linear model with hidden states.
Lawhern, Vernon; Wu, Wei; Hatsopoulos, Nicholas; Paninski, Liam
2010-06-15
Generalized linear models (GLMs) have been developed for modeling and decoding population neuronal spiking activity in the motor cortex. These models provide reasonable characterizations between neural activity and motor behavior. However, they lack a description of movement-related terms which are not observed directly in these experiments, such as muscular activation, the subject's level of attention, and other internal or external states. Here we propose to include a multi-dimensional hidden state to address these states in a GLM framework where the spike count at each time is described as a function of the hand state (position, velocity, and acceleration), truncated spike history, and the hidden state. The model can be identified by an Expectation-Maximization algorithm. We tested this new method in two datasets where spikes were simultaneously recorded using a multi-electrode array in the primary motor cortex of two monkeys. It was found that this method significantly improves the model-fitting over the classical GLM, for hidden dimensions varying from 1 to 4. This method also provides more accurate decoding of hand state (reducing the mean square error by up to 29% in some cases), while retaining real-time computational efficiency. These improvements on representation and decoding over the classical GLM model suggest that this new approach could contribute as a useful tool to motor cortical decoding and prosthetic applications.
Adaptive feature extraction using sparse coding for machinery fault diagnosis
NASA Astrophysics Data System (ADS)
Liu, Haining; Liu, Chengliang; Huang, Yixiang
2011-02-01
In the signal processing domain, there has been growing interest in sparse coding with a learned dictionary instead of a predefined one, which is advocated as an effective mathematical description for the underlying principle of mammalian sensory systems in processing information. In this paper, sparse coding is introduced as a feature extraction technique for machinery fault diagnosis and an adaptive feature extraction scheme is proposed based on it. The two core problems of sparse coding, i.e., dictionary learning and coefficients solving, are discussed in detail. A natural extension of sparse coding, shift-invariant sparse coding, is also introduced. Then, the vibration signals of rolling element bearings are taken as the target signals to verify the proposed scheme, and shift-invariant sparse coding is used for vibration analysis. With the purpose of diagnosing the different fault conditions of bearings, features are extracted following the proposed scheme: basis functions are separately learned from each class of vibration signals trying to capture the defective impulses; a redundant dictionary is built by merging all the learned basis functions; based on the redundant dictionary, the diagnostic information is made explicit in the solved sparse representations of vibration signals; sparse features are formulated in terms of activations of atoms. The multiclass linear discriminant analysis (LDA) classifier is used to test the discriminability of the extracted sparse features and the adaptability of the learned atoms. The experiments show that sparse coding is an effective feature extraction technique for machinery fault diagnosis.
Dictionary learning method for joint sparse representation-based image fusion
NASA Astrophysics Data System (ADS)
Zhang, Qiheng; Fu, Yuli; Li, Haifeng; Zou, Jian
2013-05-01
Recently, sparse representation (SR) and joint sparse representation (JSR) have attracted a lot of interest in image fusion. The SR models signals by sparse linear combinations of prototype signal atoms that make a dictionary. The JSR indicates that different signals from the various sensors of the same scene form an ensemble. These signals have a common sparse component and each individual signal owns an innovation sparse component. The JSR offers lower computational complexity compared with SR. First, for JSR-based image fusion, we give a new fusion rule. Then, motivated by the method of optimal directions (MOD), for JSR, we propose a novel dictionary learning method (MODJSR) whose dictionary updating procedure is derived by employing the JSR structure one time with singular value decomposition (SVD). MODJSR has lower complexity than the K-SVD algorithm which is often used in previous JSR-based fusion algorithms. To capture the image details more efficiently, we proposed the generalized JSR in which the signals ensemble depends on two dictionaries. MODJSR is extended to MODGJSR in this case. MODJSR/MODGJSR can simultaneously carry out dictionary learning, denoising, and fusion of noisy source images. Some experiments are given to demonstrate the validity of the MODJSR/MODGJSR for image fusion.
Grassmannian sparse representations
NASA Astrophysics Data System (ADS)
Azary, Sherif; Savakis, Andreas
2015-05-01
We present Grassmannian sparse representations (GSR), a sparse representation Grassmann learning framework for efficient classification. Sparse representation classification offers a powerful approach for recognition in a variety of contexts. However, a major drawback of sparse representation methods is their computational performance and memory utilization for high-dimensional data. A Grassmann manifold is a space that promotes smooth surfaces where points represent subspaces and the relationship between points is defined by the mapping of an orthogonal matrix. Grassmann manifolds are well suited for computer vision problems because they promote high between-class discrimination and within-class clustering, while offering computational advantages by mapping each subspace onto a single point. The GSR framework combines Grassmannian kernels and sparse representations, including regularized least squares and least angle regression, to improve high accuracy recognition while overcoming the drawbacks of performance and dependencies on high dimensional data distributions. The effectiveness of GSR is demonstrated on computationally intensive multiview action sequences, three-dimensional action sequences, and face recognition datasets.
Sparse distributed memory overview
NASA Technical Reports Server (NTRS)
Raugh, Mike
1990-01-01
The Sparse Distributed Memory (SDM) project is investigating the theory and applications of massively parallel computing architecture, called sparse distributed memory, that will support the storage and retrieval of sensory and motor patterns characteristic of autonomous systems. The immediate objectives of the project are centered in studies of the memory itself and in the use of the memory to solve problems in speech, vision, and robotics. Investigation of methods for encoding sensory data is an important part of the research. Examples of NASA missions that may benefit from this work are Space Station, planetary rovers, and solar exploration. Sparse distributed memory offers promising technology for systems that must learn through experience and be capable of adapting to new circumstances, and for operating any large complex system requiring automatic monitoring and control. Sparse distributed memory is a massively parallel architecture motivated by efforts to understand how the human brain works. Sparse distributed memory is an associative memory, able to retrieve information from cues that only partially match patterns stored in the memory. It is able to store long temporal sequences derived from the behavior of a complex system, such as progressive records of the system's sensory data and correlated records of the system's motor controls.
Fast Solution in Sparse LDA for Binary Classification
NASA Technical Reports Server (NTRS)
Moghaddam, Baback
2010-01-01
An algorithm that performs sparse linear discriminant analysis (Sparse-LDA) finds near-optimal solutions in far less time than the prior art when specialized to binary classification (of 2 classes). Sparse-LDA is a type of feature- or variable- selection problem with numerous applications in statistics, machine learning, computer vision, computational finance, operations research, and bio-informatics. Because of its combinatorial nature, feature- or variable-selection problems are NP-hard or computationally intractable in cases involving more than 30 variables or features. Therefore, one typically seeks approximate solutions by means of greedy search algorithms. The prior Sparse-LDA algorithm was a greedy algorithm that considered the best variable or feature to add/ delete to/ from its subsets in order to maximally discriminate between multiple classes of data. The present algorithm is designed for the special but prevalent case of 2-class or binary classification (e.g. 1 vs. 0, functioning vs. malfunctioning, or change versus no change). The present algorithm provides near-optimal solutions on large real-world datasets having hundreds or even thousands of variables or features (e.g. selecting the fewest wavelength bands in a hyperspectral sensor to do terrain classification) and does so in typical computation times of minutes as compared to days or weeks as taken by the prior art. Sparse LDA requires solving generalized eigenvalue problems for a large number of variable subsets (represented by the submatrices of the input within-class and between-class covariance matrices). In the general (fullrank) case, the amount of computation scales at least cubically with the number of variables and thus the size of the problems that can be solved is limited accordingly. However, in binary classification, the principal eigenvalues can be found using a special analytic formula, without resorting to costly iterative techniques. The present algorithm exploits this analytic
A generalized harmonic balance method for forced non-linear oscillations: the subharmonic cases
NASA Astrophysics Data System (ADS)
Wu, J. J.
1992-12-01
This paper summarizes and extends results in two previous papers, published in conference proceedings, on a variant of the generalized harmonic balance method (GHB) and its application to obtain subharmonic solutions of forced non-linear oscillation problems. This method was introduced as an alternative to the method of multiple scales, and it essentially consists of two parts. First, the part of the multiple scales method used to reduce the problem to a set of differential equations is used to express the solution as a sum of terms of various harmonics with unknown, time dependent coefficients. Second, the form of solution so obtained is substituted into the original equation and the coefficients of each harmonic are set to zero. Key equations of approximations for a subharmonic case are derived for the cases of both "small" damping and excitations, and "Large" damping and excitations, which are shown to be identical, in the intended order of approximation, to those obtained by Nayfeh using the method of multiple scales. Detailed numerical formulations, including the derivation of the initial conditions, are presented, as well as some numerical results for the frequency-response relations and the time evolution of various harmonic components. Excellent agreement is demonstrated between results by GHB and by integrating the original differential equation directly. The improved efficiency in obtaining numerical solutions using GHB as compared with integrating the original differential equation is demonstrated also. For the case of large damping and excitations and for non-trivial solutions, it is noted that there exists a threshold value of the force beyond which no subharmonic excitations are possible.
Generalized Functional Linear Models for Gene-based Case-Control Association Studies
Mills, James L.; Carter, Tonia C.; Lobach, Iryna; Wilson, Alexander F.; Bailey-Wilson, Joan E.; Weeks, Daniel E.; Xiong, Momiao
2014-01-01
By using functional data analysis techniques, we developed generalized functional linear models for testing association between a dichotomous trait and multiple genetic variants in a genetic region while adjusting for covariates. Both fixed and mixed effect models are developed and compared. Extensive simulations show that Rao's efficient score tests of the fixed effect models are very conservative since they generate lower type I errors than nominal levels, and global tests of the mixed effect models generate accurate type I errors. Furthermore, we found that the Rao's efficient score test statistics of the fixed effect models have higher power than the sequence kernel association test (SKAT) and its optimal unified version (SKAT-O) in most cases when the causal variants are both rare and common. When the causal variants are all rare (i.e., minor allele frequencies less than 0.03), the Rao's efficient score test statistics and the global tests have similar or slightly lower power than SKAT and SKAT-O. In practice, it is not known whether rare variants or common variants in a gene are disease-related. All we can assume is that a combination of rare and common variants influences disease susceptibility. Thus, the improved performance of our models when the causal variants are both rare and common shows that the proposed models can be very useful in dissecting complex traits. We compare the performance of our methods with SKAT and SKAT-O on real neural tube defects and Hirschsprung's disease data sets. The Rao's efficient score test statistics and the global tests are more sensitive than SKAT and SKAT-O in the real data analysis. Our methods can be used in either gene-disease genome-wide/exome-wide association studies or candidate gene analyses. PMID:25203683
Generalized functional linear models for gene-based case-control association studies.
Fan, Ruzong; Wang, Yifan; Mills, James L; Carter, Tonia C; Lobach, Iryna; Wilson, Alexander F; Bailey-Wilson, Joan E; Weeks, Daniel E; Xiong, Momiao
2014-11-01
By using functional data analysis techniques, we developed generalized functional linear models for testing association between a dichotomous trait and multiple genetic variants in a genetic region while adjusting for covariates. Both fixed and mixed effect models are developed and compared. Extensive simulations show that Rao's efficient score tests of the fixed effect models are very conservative since they generate lower type I errors than nominal levels, and global tests of the mixed effect models generate accurate type I errors. Furthermore, we found that the Rao's efficient score test statistics of the fixed effect models have higher power than the sequence kernel association test (SKAT) and its optimal unified version (SKAT-O) in most cases when the causal variants are both rare and common. When the causal variants are all rare (i.e., minor allele frequencies less than 0.03), the Rao's efficient score test statistics and the global tests have similar or slightly lower power than SKAT and SKAT-O. In practice, it is not known whether rare variants or common variants in a gene region are disease related. All we can assume is that a combination of rare and common variants influences disease susceptibility. Thus, the improved performance of our models when the causal variants are both rare and common shows that the proposed models can be very useful in dissecting complex traits. We compare the performance of our methods with SKAT and SKAT-O on real neural tube defects and Hirschsprung's disease datasets. The Rao's efficient score test statistics and the global tests are more sensitive than SKAT and SKAT-O in the real data analysis. Our methods can be used in either gene-disease genome-wide/exome-wide association studies or candidate gene analyses.
A general linear model-based approach for inferring selection to climate
2013-01-01
Background Many efforts have been made to detect signatures of positive selection in the human genome, especially those associated with expansion from Africa and subsequent colonization of all other continents. However, most approaches have not directly probed the relationship between the environment and patterns of variation among humans. We have designed a method to identify regions of the genome under selection based on Mantel tests conducted within a general linear model framework, which we call MAntel-GLM to Infer Clinal Selection (MAGICS). MAGICS explicitly incorporates population-specific and genome-wide patterns of background variation as well as information from environmental values to provide an improved picture of selection and its underlying causes in human populations. Results Our results significantly overlap with those obtained by other published methodologies, but MAGICS has several advantages. These include improvements that: limit false positives by reducing the number of independent tests conducted and by correcting for geographic distance, which we found to be a major contributor to selection signals; yield absolute rather than relative estimates of significance; identify specific geographic regions linked most strongly to particular signals of selection; and detect recent balancing as well as directional selection. Conclusions We find evidence of selection associated with climate (P < 10-5) in 354 genes, and among these observe a highly significant enrichment for directional positive selection. Two of our strongest 'hits’, however, ADRA2A and ADRA2C, implicated in vasoconstriction in response to cold and pain stimuli, show evidence of balancing selection. Our results clearly demonstrate evidence of climate-related signals of directional and balancing selection. PMID:24053227
Protein structure validation by generalized linear model root-mean-square deviation prediction.
Bagaria, Anurag; Jaravine, Victor; Huang, Yuanpeng J; Montelione, Gaetano T; Güntert, Peter
2012-02-01
Large-scale initiatives for obtaining spatial protein structures by experimental or computational means have accentuated the need for the critical assessment of protein structure determination and prediction methods. These include blind test projects such as the critical assessment of protein structure prediction (CASP) and the critical assessment of protein structure determination by nuclear magnetic resonance (CASD-NMR). An important aim is to establish structure validation criteria that can reliably assess the accuracy of a new protein structure. Various quality measures derived from the coordinates have been proposed. A universal structural quality assessment method should combine multiple individual scores in a meaningful way, which is challenging because of their different measurement units. Here, we present a method based on a generalized linear model (GLM) that combines diverse protein structure quality scores into a single quantity with intuitive meaning, namely the predicted coordinate root-mean-square deviation (RMSD) value between the present structure and the (unavailable) "true" structure (GLM-RMSD). For two sets of structural models from the CASD-NMR and CASP projects, this GLM-RMSD value was compared with the actual accuracy given by the RMSD value to the corresponding, experimentally determined reference structure from the Protein Data Bank (PDB). The correlation coefficients between actual (model vs. reference from PDB) and predicted (model vs. "true") heavy-atom RMSDs were 0.69 and 0.76, for the two datasets from CASD-NMR and CASP, respectively, which is considerably higher than those for the individual scores (-0.24 to 0.68). The GLM-RMSD can thus predict the accuracy of protein structures more reliably than individual coordinate-based quality scores.
Determinants of hospital closure in South Korea: use of a hierarchical generalized linear model.
Noh, Maengseok; Lee, Youngjo; Yun, Sung-Cheol; Lee, Sang-Il; Lee, Moo-Song; Khang, Young-Ho
2006-11-01
Understanding causes of hospital closure is important if hospitals are to survive and continue to fulfill their missions as the center for health care in their neighborhoods. Knowing which hospitals are most susceptible to closure can be of great use for hospital administrators and others interested in hospital performance. Although prior studies have identified a range of factors associated with increased risk of hospital closure, most are US-based and do not directly relate to health care systems in other countries. We examined determinants of hospital closure in a nationally representative sample: 805 hospitals established in South Korea before 1996 were examined-hospitals established in 1996 or after were excluded. Major organizational changes (survival vs. closure) were followed for all South Korean hospitals from 1996 through 2002. With the use of a hierarchical generalized linear model, a frailty model was used to control correlation among repeated measurements for risk factors for hospital closure. Results showed that ownership and hospital size were significantly associated with hospital closure. Urban hospitals were less likely to close than rural hospitals. However, the urban location of a hospital was not associated with hospital closure after adjustment for the proportion of elderly. Two measures for hospital competition (competitive beds and 1-Hirshman--Herfindalh index) were positively associated with risk of hospital closure before and after adjustment for confounders. In addition, annual 10% change in competitive beds was significantly predictive of hospital closure. In conclusion, yearly trends in hospital competition as well as the level of hospital competition each year affected hospital survival. Future studies need to examine the contribution of internal factors such as management strategies and financial status to hospital closure in South Korea.
NASA Technical Reports Server (NTRS)
Holdaway, Daniel; Kent, James
2015-01-01
The linearity of a selection of common advection schemes is tested and examined with a view to their use in the tangent linear and adjoint versions of an atmospheric general circulation model. The schemes are tested within a simple offline one-dimensional periodic domain as well as using a simplified and complete configuration of the linearised version of NASA's Goddard Earth Observing System version 5 (GEOS-5). All schemes which prevent the development of negative values and preserve the shape of the solution are confirmed to have nonlinear behaviour. The piecewise parabolic method (PPM) with certain flux limiters, including that used by default in GEOS-5, is found to support linear growth near the shocks. This property can cause the rapid development of unrealistically large perturbations within the tangent linear and adjoint models. It is shown that these schemes with flux limiters should not be used within the linearised version of a transport scheme. The results from tests using GEOS-5 show that the current default scheme (a version of PPM) is not suitable for the tangent linear and adjoint model, and that using a linear third-order scheme for the linearised model produces better behaviour. Using the third-order scheme for the linearised model improves the correlations between the linear and non-linear perturbation trajectories for cloud liquid water and cloud liquid ice in GEOS-5.
Finding nonoverlapping substructures of a sparse matrix
Pinar, Ali; Vassilevska, Virginia
2004-08-09
Many applications of scientific computing rely on computations on sparse matrices, thus the design of efficient implementations of sparse matrix kernels is crucial for the overall efficiency of these applications. Due to the high compute-to-memory ratio and irregular memory access patterns, the performance of sparse matrix kernels is often far away from the peak performance on a modern processor. Alternative data structures have been proposed, which split the original matrix A into A{sub d} and A{sub s}, so that A{sub d} contains all dense blocks of a specified size in the matrix, and A{sub s} contains the remaining entries. This enables the use of dense matrix kernels on the entries of A{sub d} producing better memory performance. In this work, we study the problem of finding a maximum number of non overlapping rectangular dense blocks in a sparse matrix, which has not been studied in the sparse matrix community. We show that the maximum non overlapping dense blocks problem is NP-complete by using a reduction from the maximum independent set problem on cubic planar graphs. We also propose a 2/3-approximation algorithm for 2 times 2 blocks that runs in linear time in the number of nonzeros in the matrix. We discuss alternatives to rectangular blocks such as diagonal blocks and cross blocks and present complexity analysis and approximation algorithms.
On the Global and Linear Convergence of the Generalized Alternating Direction Method of Multipliers
2012-08-01
This paper shows that global linear convergence can be guaranteed under the above assumptions on strong convexity and Lipschitz gradient on one of the...linear convergence can be guaranteed under the above assumptions on strong convexity and Lipschitz gradient on one of the two functions, along with certain...extensive literature on the ADM and its applications , there are very few results on its rate of convergence until the very recent past. Work [13] shows
NASA Astrophysics Data System (ADS)
Irmak, Suat; Mutiibwa, Denis
2010-08-01
The 1-D and single layer combination-based energy balance Penman-Monteith (PM) model has limitations in practical application due to the lack of canopy resistance (rc) data for different vegetation surfaces. rc could be estimated by inversion of the PM model if the actual evapotranspiration (ETa) rate is known, but this approach has its own set of issues. Instead, an empirical method of estimating rc is suggested in this study. We investigated the relationships between primary micrometeorological parameters and rc and developed seven models to estimate rc for a nonstressed maize canopy on an hourly time step using a generalized-linear modeling approach. The most complex rc model uses net radiation (Rn), air temperature (Ta), vapor pressure deficit (VPD), relative humidity (RH), wind speed at 3 m (u3), aerodynamic resistance (ra), leaf area index (LAI), and solar zenith angle (Θ). The simplest model requires Rn, Ta, and RH. We present the practical implementation of all models via experimental validation using scaled up rc data obtained from the dynamic diffusion porometer-measured leaf stomatal resistance through an extensive field campaign in 2006. For further validation, we estimated ETa by solving the PM model using the modeled rc from all seven models and compared the PM ETa estimates with the Bowen ratio energy balance system (BREBS)-measured ETa for an independent data set in 2005. The relationships between hourly rc versus Ta, RH, VPD, Rn, incoming shortwave radiation (Rs), u3, wind direction, LAI, Θ, and ra were presented and discussed. We demonstrated the negative impact of exclusion of LAI when modeling rc, whereas exclusion of ra and Θ did not impact the performance of the rc models. Compared to the calibration results, the validation root mean square difference between observed and modeled rc increased by 5 s m-1 for all rc models developed, ranging from 9.9 s m-1 for the most complex model to 22.8 s m-1 for the simplest model, as compared with the
Resistant multiple sparse canonical correlation.
Coleman, Jacob; Replogle, Joseph; Chandler, Gabriel; Hardin, Johanna
2016-04-01
Canonical correlation analysis (CCA) is a multivariate technique that takes two datasets and forms the most highly correlated possible pairs of linear combinations between them. Each subsequent pair of linear combinations is orthogonal to the preceding pair, meaning that new information is gleaned from each pair. By looking at the magnitude of coefficient values, we can find out which variables can be grouped together, thus better understanding multiple interactions that are otherwise difficult to compute or grasp intuitively. CCA appears to have quite powerful applications to high-throughput data, as we can use it to discover, for example, relationships between gene expression and gene copy number variation. One of the biggest problems of CCA is that the number of variables (often upwards of 10,000) makes biological interpretation of linear combinations nearly impossible. To limit variable output, we have employed a method known as sparse canonical correlation analysis (SCCA), while adding estimation which is resistant to extreme observations or other types of deviant data. In this paper, we have demonstrated the success of resistant estimation in variable selection using SCCA. Additionally, we have used SCCA to find multiple canonical pairs for extended knowledge about the datasets at hand. Again, using resistant estimators provided more accurate estimates than standard estimators in the multiple canonical correlation setting. R code is available and documented at https://github.com/hardin47/rmscca.
Evidence for the conjecture that sampling generalized cat states with linear optics is hard
NASA Astrophysics Data System (ADS)
Rohde, Peter P.; Motes, Keith R.; Knott, Paul A.; Fitzsimons, Joseph; Munro, William J.; Dowling, Jonathan P.
2015-01-01
Boson sampling has been presented as a simplified model for linear optical quantum computing. In the boson-sampling model, Fock states are passed through a linear optics network and sampled via number-resolved photodetection. It has been shown that this sampling problem likely cannot be efficiently classically simulated. This raises the question as to whether there are other quantum states of light for which the equivalent sampling problem is also computationally hard. We present evidence, without using a full complexity proof, that a very broad class of quantum states of light—arbitrary superpositions of two or more coherent states—when evolved via passive linear optics and sampled with number-resolved photodetection, likely implements a classically hard sampling problem.
NASA Astrophysics Data System (ADS)
Shirokov, M. E.
2013-11-01
The method of complementary channel for analysis of reversibility (sufficiency) of a quantum channel with respect to families of input states (pure states for the most part) are considered and applied to Bosonic linear (quasi-free) channels, in particular, to Bosonic Gaussian channels. The obtained reversibility conditions for Bosonic linear channels have clear physical interpretation and their sufficiency is also shown by explicit construction of reversing channels. The method of complementary channel gives possibility to prove necessity of these conditions and to describe all reversed families of pure states in the Schrodinger representation. Some applications in quantum information theory are considered. Conditions for existence of discrete classical-quantum subchannels and of completely depolarizing subchannels of a Bosonic linear channel are presented.
Shirokov, M. E.
2013-11-15
The method of complementary channel for analysis of reversibility (sufficiency) of a quantum channel with respect to families of input states (pure states for the most part) are considered and applied to Bosonic linear (quasi-free) channels, in particular, to Bosonic Gaussian channels. The obtained reversibility conditions for Bosonic linear channels have clear physical interpretation and their sufficiency is also shown by explicit construction of reversing channels. The method of complementary channel gives possibility to prove necessity of these conditions and to describe all reversed families of pure states in the Schrodinger representation. Some applications in quantum information theory are considered. Conditions for existence of discrete classical-quantum subchannels and of completely depolarizing subchannels of a Bosonic linear channel are presented.
NASA Technical Reports Server (NTRS)
Tamma, Kumar K.; Railkar, Sudhir B.
1987-01-01
The present paper describes the development of a new hybrid computational approach for applicability for nonlinear/linear thermal structural analysis. The proposed transfinite element approach is a hybrid scheme as it combines the modeling versatility of contemporary finite elements in conjunction with transform methods and the classical Bubnov-Galerkin schemes. Applicability of the proposed formulations for nonlinear analysis is also developed. Several test cases are presented to include nonlinear/linear unified thermal-stress and thermal-stress wave propagations. Comparative results validate the fundamental capablities of the proposed hybrid transfinite element methodology.
Huppert, Theodore J.
2016-01-01
Abstract. Functional near-infrared spectroscopy (fNIRS) is a noninvasive neuroimaging technique that uses low levels of light to measure changes in cerebral blood oxygenation levels. In the majority of NIRS functional brain studies, analysis of this data is based on a statistical comparison of hemodynamic levels between a baseline and task or between multiple task conditions by means of a linear regression model: the so-called general linear model. Although these methods are similar to their implementation in other fields, particularly for functional magnetic resonance imaging, the specific application of these methods in fNIRS research differs in several key ways related to the sources of noise and artifacts unique to fNIRS. In this brief communication, we discuss the application of linear regression models in fNIRS and the modifications needed to generalize these models in order to deal with structured (colored) noise due to systemic physiology and noise heteroscedasticity due to motion artifacts. The objective of this work is to present an overview of these noise properties in the context of the linear model as it applies to fNIRS data. This work is aimed at explaining these mathematical issues to the general fNIRS experimental researcher but is not intended to be a complete mathematical treatment of these concepts. PMID:26989756
Protein family classification using sparse Markov transducers.
Eskin, E; Grundy, W N; Singer, Y
2000-01-01
In this paper we present a method for classifying proteins into families using sparse Markov transducers (SMTs). Sparse Markov transducers, similar to probabilistic suffix trees, estimate a probability distribution conditioned on an input sequence. SMTs generalize probabilistic suffix trees by allowing for wild-cards in the conditioning sequences. Because substitutions of amino acids are common in protein families, incorporating wildcards into the model significantly improves classification performance. We present two models for building protein family classifiers using SMTs. We also present efficient data structures to improve the memory usage of the models. We evaluate SMTs by building protein family classifiers using the Pfam database and compare our results to previously published results.
Recent advances toward a general purpose linear-scaling quantum force field.
Giese, Timothy J; Huang, Ming; Chen, Haoyuan; York, Darrin M
2014-09-16
Conspectus There is need in the molecular simulation community to develop new quantum mechanical (QM) methods that can be routinely applied to the simulation of large molecular systems in complex, heterogeneous condensed phase environments. Although conventional methods, such as the hybrid quantum mechanical/molecular mechanical (QM/MM) method, are adequate for many problems, there remain other applications that demand a fully quantum mechanical approach. QM methods are generally required in applications that involve changes in electronic structure, such as when chemical bond formation or cleavage occurs, when molecules respond to one another through polarization or charge transfer, or when matter interacts with electromagnetic fields. A full QM treatment, rather than QM/MM, is necessary when these features present themselves over a wide spatial range that, in some cases, may span the entire system. Specific examples include the study of catalytic events that involve delocalized changes in chemical bonds, charge transfer, or extensive polarization of the macromolecular environment; drug discovery applications, where the wide range of nonstandard residues and protonation states are challenging to model with purely empirical MM force fields; and the interpretation of spectroscopic observables. Unfortunately, the enormous computational cost of conventional QM methods limit their practical application to small systems. Linear-scaling electronic structure methods (LSQMs) make possible the calculation of large systems but are still too computationally intensive to be applied with the degree of configurational sampling often required to make meaningful comparison with experiment. In this work, we present advances in the development of a quantum mechanical force field (QMFF) suitable for application to biological macromolecules and condensed phase simulations. QMFFs leverage the benefits provided by the LSQM and QM/MM approaches to produce a fully QM method that is able to
Sparse inpainting and isotropy
NASA Astrophysics Data System (ADS)
Feeney, Stephen M.; Marinucci, Domenico; McEwen, Jason D.; Peiris, Hiranya V.; Wandelt, Benjamin D.; Cammarota, Valentina
2014-01-01
Sparse inpainting techniques are gaining in popularity as a tool for cosmological data analysis, in particular for handling data which present masked regions and missing observations. We investigate here the relationship between sparse inpainting techniques using the spherical harmonic basis as a dictionary and the isotropy properties of cosmological maps, as for instance those arising from cosmic microwave background (CMB) experiments. In particular, we investigate the possibility that inpainted maps may exhibit anisotropies in the behaviour of higher-order angular polyspectra. We provide analytic computations and simulations of inpainted maps for a Gaussian isotropic model of CMB data, suggesting that the resulting angular trispectrum may exhibit small but non-negligible deviations from isotropy.
A unified approach to sparse signal processing
NASA Astrophysics Data System (ADS)
Marvasti, Farokh; Amini, Arash; Haddadi, Farzan; Soltanolkotabi, Mahdi; Khalaj, Babak Hossein; Aldroubi, Akram; Sanei, Saeid; Chambers, Janathon
2012-12-01
A unified view of the area of sparse signal processing is presented in tutorial form by bringing together various fields in which the property of sparsity has been successfully exploited. For each of these fields, various algorithms and techniques, which have been developed to leverage sparsity, are described succinctly. The common potential benefits of significant reduction in sampling rate and processing manipulations through sparse signal processing are revealed. The key application domains of sparse signal processing are sampling, coding, spectral estimation, array processing, component analysis, and multipath channel estimation. In terms of the sampling process and reconstruction algorithms, linkages are made with random sampling, compressed sensing, and rate of innovation. The redundancy introduced by channel coding in finite and real Galois fields is then related to over-sampling with similar reconstruction algorithms. The error locator polynomial (ELP) and iterative methods are shown to work quite effectively for both sampling and coding applications. The methods of Prony, Pisarenko, and MUltiple SIgnal Classification (MUSIC) are next shown to be targeted at analyzing signals with sparse frequency domain representations. Specifically, the relations of the approach of Prony to an annihilating filter in rate of innovation and ELP in coding are emphasized; the Pisarenko and MUSIC methods are further improvements of the Prony method under noisy environments. The iterative methods developed for sampling and coding applications are shown to be powerful tools in spectral estimation. Such narrowband spectral estimation is then related to multi-source location and direction of arrival estimation in array processing. Sparsity in unobservable source signals is also shown to facilitate source separation in sparse component analysis; the algorithms developed in this area such as linear programming and matching pursuit are also widely used in compressed sensing. Finally
ERIC Educational Resources Information Center
Yan, Jun; Aseltine, Robert H., Jr.; Harel, Ofer
2013-01-01
Comparing regression coefficients between models when one model is nested within another is of great practical interest when two explanations of a given phenomenon are specified as linear models. The statistical problem is whether the coefficients associated with a given set of covariates change significantly when other covariates are added into…
NASA Technical Reports Server (NTRS)
Kanerva, Pentti
1988-01-01
Theoretical models of the human brain and proposed neural-network computers are developed analytically. Chapters are devoted to the mathematical foundations, background material from computer science, the theory of idealized neurons, neurons as address decoders, and the search of memory for the best match. Consideration is given to sparse memory, distributed storage, the storage and retrieval of sequences, the construction of distributed memory, and the organization of an autonomous learning system.
Fast wavelet based sparse approximate inverse preconditioner
Wan, W.L.
1996-12-31
Incomplete LU factorization is a robust preconditioner for both general and PDE problems but unfortunately not easy to parallelize. Recent study of Huckle and Grote and Chow and Saad showed that sparse approximate inverse could be a potential alternative while readily parallelizable. However, for special class of matrix A that comes from elliptic PDE problems, their preconditioners are not optimal in the sense that independent of mesh size. A reason may be that no good sparse approximate inverse exists for the dense inverse matrix. Our observation is that for this kind of matrices, its inverse entries typically have piecewise smooth changes. We can take advantage of this fact and use wavelet compression techniques to construct a better sparse approximate inverse preconditioner. We shall show numerically that our approach is effective for this kind of matrices.
Hybrid approximate message passing for generalized group sparsity
NASA Astrophysics Data System (ADS)
Fletcher, Alyson K.; Rangan, Sundeep
2013-09-01
We consider the problem of estimating a group sparse vector x ∈ Rn under a generalized linear measurement model. Group sparsity of x means the activity of different components of the vector occurs in groups - a feature common in estimation problems in image processing, simultaneous sparse approximation and feature selection with grouped variables. Unfortunately, many current group sparse estimation methods require that the groups are non-overlapping. This work considers problems with what we call generalized group sparsity where the activity of the different components of x are modeled as functions of a small number of boolean latent variables. We show that this model can incorporate a large class of overlapping group sparse problems including problems in sparse multivariable polynomial regression and gene expression analysis. To estimate vectors with such group sparse structures, the paper proposes to use a recently-developed hybrid generalized approximate message passing (HyGAMP) method. Approximate message passing (AMP) refers to a class of algorithms based on Gaussian and quadratic approximations of loopy belief propagation for estimation of random vectors under linear measurements. The HyGAMP method extends the AMP framework to incorporate priors on x described by graphical models of which generalized group sparsity is a special case. We show that the HyGAMP algorithm is computationally efficient, general and offers superior performance in certain synthetic data test cases.
1980-11-01
generalized nodel described by Eykhoff [1, 2], Astrom and Eykhoff [3], and on pages 209-220 of Eykhoff [4]. The origin of the general- ized model can be...aspects of process-parameter estimation," IEEE Trans. Auto. Control, October 1963, pp. 347-357. 3. K. J. Astrom and P. Eykhoff, "System
de Dieu Tapsoba, Jean; Lee, Shen-Ming; Wang, Ching-Yun
2013-01-01
Data collected in many epidemiological or clinical research studies are often contaminated with measurement errors that may be of classical or Berkson error type. The measurement error may also be a combination of both classical and Berkson errors and failure to account for both errors could lead to unreliable inference in many situations. We consider regression analysis in generalized linear models when some covariates are prone to a mixture of Berkson and classical errors and calibration data are available only for some subjects in a subsample. We propose an expected estimating equation approach to accommodate both errors in generalized linear regression analyses. The proposed method can consistently estimate the classical and Berkson error variances based on the available data, without knowing the mixture percentage. Its finite-sample performance is investigated numerically. Our method is illustrated by an application to real data from an HIV vaccine study. PMID:24009099
Fernandes, L.; Friedlander, A.; Guedes, M.; Judice, J.
2001-07-01
This paper addresses a General Linear Complementarity Problem (GLCP) that has found applications in global optimization. It is shown that a solution of the GLCP can be computed by finding a stationary point of a differentiable function over a set defined by simple bounds on the variables. The application of this result to the solution of bilinear programs and LCPs is discussed. Some computational evidence of its usefulness is included in the last part of the paper.
de Souza, Juliana Bottoni; Reisen, Valdério Anselmo; Santos, Jane Méri; Franco, Glaura Conceição
2014-01-01
OBJECTIVE To analyze the association between concentrations of air pollutants and admissions for respiratory causes in children. METHODS Ecological time series study. Daily figures for hospital admissions of children aged < 6, and daily concentrations of air pollutants (PM10, SO2, NO2, O3 and CO) were analyzed in the Região da Grande Vitória, ES, Southeastern Brazil, from January 2005 to December 2010. For statistical analysis, two techniques were combined: Poisson regression with generalized additive models and principal model component analysis. Those analysis techniques complemented each other and provided more significant estimates in the estimation of relative risk. The models were adjusted for temporal trend, seasonality, day of the week, meteorological factors and autocorrelation. In the final adjustment of the model, it was necessary to include models of the Autoregressive Moving Average Models (p, q) type in the residuals in order to eliminate the autocorrelation structures present in the components. RESULTS For every 10:49 μg/m3 increase (interquartile range) in levels of the pollutant PM10 there was a 3.0% increase in the relative risk estimated using the generalized additive model analysis of main components-seasonal autoregressive – while in the usual generalized additive model, the estimate was 2.0%. CONCLUSIONS Compared to the usual generalized additive model, in general, the proposed aspect of generalized additive model − principal component analysis, showed better results in estimating relative risk and quality of fit. PMID:25119940
SPARSKIT: A basic tool kit for sparse matrix computations
NASA Technical Reports Server (NTRS)
Saad, Youcef
1990-01-01
Presented here are the main features of a tool package for manipulating and working with sparse matrices. One of the goals of the package is to provide basic tools to facilitate the exchange of software and data between researchers in sparse matrix computations. The starting point is the Harwell/Boeing collection of matrices for which the authors provide a number of tools. Among other things, the package provides programs for converting data structures, printing simple statistics on a matrix, plotting a matrix profile, and performing linear algebra operations with sparse matrices.
A general algorithm for control problems with variable parameters and quasi-linear models
NASA Astrophysics Data System (ADS)
Bayón, L.; Grau, J. M.; Ruiz, M. M.; Suárez, P. M.
2015-12-01
This paper presents an algorithm that is able to solve optimal control problems in which the modelling of the system contains variable parameters, with the added complication that, in certain cases, these parameters can lead to control problems governed by quasi-linear equations. Combining the techniques of Pontryagin's Maximum Principle and the shooting method, an algorithm has been developed that is not affected by the values of the parameters, being able to solve conventional problems as well as cases in which the optimal solution is shown to be bang-bang with singular arcs.
Michaelides, Angelos; Liu, Z-P; Zhang, C J; Alavi, Ali; King, David A; Hu, P
2003-04-02
The activation energy to reaction is a key quantity that controls catalytic activity. Having used ab inito calculations to determine an extensive and broad ranging set of activation energies and enthalpy changes for surface-catalyzed reactions, we show that linear relationships exist between dissociation activation energies and enthalpy changes. Known in the literature as empirical Brønsted-Evans-Polanyi (BEP) relationships, we identify and discuss the physical origin of their presence in heterogeneous catalysis. The key implication is that merely from knowledge of adsorption energies the barriers to catalytic elementary reaction steps can be estimated.
A substructure coupling procedure applicable to general linear time-invariant dynamic systems
NASA Technical Reports Server (NTRS)
Howsman, T. G.; Craig, R. R., Jr.
1984-01-01
A substructure synthesis procedure applicable to structural systems containing general nonconservative terms is presented. In their final form, the nonself-adjoint substructure equations of motion are cast in state vector form through the use of a variational principle. A reduced-order mode for each substructure is implemented by representing the substructure as a combination of a small number of Ritz vectors. For the method presented, the substructure Ritz vectors are identified as a truncated set of substructure eigenmodes, which are typically complex, along with a set of generalized real attachment modes. The formation of the generalized attachment modes does not require any knowledge of the substructure flexible modes; hence, only the eigenmodes used explicitly as Ritz vectors need to be extracted from the substructure eigenproblem. An example problem is presented to illustrate the method.
Marín-Sanguino, Alberto; Torres, Néstor V
2003-08-01
A new method is proposed for the optimization of biochemical systems. The method, based on the separation of the stoichiometric and kinetic aspects of the system, follows the general approach used in the previously presented indirect optimization method (IOM) developed within biochemical systems theory. It is called GMA-IOM because it makes use of the generalized mass action (GMA) as the model system representation form. The GMA representation avoids flux aggregation and thus prevents possible stoichiometric errors. The optimization of a system is used to illustrate and compare the features, advantages and shortcomings of both versions of the IOM method as a general strategy for designing improved microbial strains of biotechnological interest. Special attention has been paid to practical problems for the actual implementation of the new proposed strategy, such as the total protein content of the engineered strain or the deviation from the original steady state and its influence on cell viability.
General theory of spherically symmetric boundary-value problems of the linear transport theory.
NASA Technical Reports Server (NTRS)
Kanal, M.
1972-01-01
A general theory of spherically symmetric boundary-value problems of the one-speed neutron transport theory is presented. The formulation is also applicable to the 'gray' problems of radiative transfer. The Green's function for the purely absorbing medium is utilized in obtaining the normal mode expansion of the angular densities for both interior and exterior problems. As the integral equations for unknown coefficients are regular, a general class of reduction operators is introduced to reduce such regular integral equations to singular ones with a Cauchy-type kernel. Such operators then permit one to solve the singular integral equations by the standard techniques due to Muskhelishvili. We discuss several spherically symmetric problems. However, the treatment is kept sufficiently general to deal with problems lacking azimuthal symmetry. In particular the procedure seems to work for regions whose boundary coincides with one of the coordinate surfaces for which the Helmholtz equation is separable.
NASA Technical Reports Server (NTRS)
Nemeth, Michael P.; Schultz, Marc R.
2012-01-01
A detailed exact solution is presented for laminated-composite circular cylinders with general wall construction and that undergo axisymmetric deformations. The overall solution is formulated in a general, systematic way and is based on the solution of a single fourth-order, nonhomogeneous ordinary differential equation with constant coefficients in which the radial displacement is the dependent variable. Moreover, the effects of general anisotropy are included and positive-definiteness of the strain energy is used to define uniquely the form of the basis functions spanning the solution space of the ordinary differential equation. Loading conditions are considered that include axisymmetric edge loads, surface tractions, and temperature fields. Likewise, all possible axisymmetric boundary conditions are considered. Results are presented for five examples that demonstrate a wide range of behavior for specially orthotropic and fully anisotropic cylinders.
and Drayton Munster, Miroslav Stoyanov
2013-09-20
Sparse Grids are the family of methods of choice for multidimensional integration and interpolation in low to moderate number of dimensions. The method is to select extend a one dimensional set of abscissas, weights and basis functions by taking a subset of all possible tensor products. The module provides the ability to create global and local approximations based on polynomials and wavelets. The software has three components, a library, a wrapper for the library that provides a command line interface via text files ad a MATLAB interface via the command line tool.
Sparse matrix methods based on orthogonality and conjugacy
NASA Technical Reports Server (NTRS)
Lawson, C. L.
1973-01-01
A matrix having a high percentage of zero elements is called spares. In the solution of systems of linear equations or linear least squares problems involving large sparse matrices, significant saving of computer cost can be achieved by taking advantage of the sparsity. The conjugate gradient algorithm and a set of related algorithms are described.
Sparse Bayesian Learning for DOA Estimation with Mutual Coupling
Dai, Jisheng; Hu, Nan; Xu, Weichao; Chang, Chunqi
2015-01-01
Sparse Bayesian learning (SBL) has given renewed interest to the problem of direction-of-arrival (DOA) estimation. It is generally assumed that the measurement matrix in SBL is precisely known. Unfortunately, this assumption may be invalid in practice due to the imperfect manifold caused by unknown or misspecified mutual coupling. This paper describes a modified SBL method for joint estimation of DOAs and mutual coupling coefficients with uniform linear arrays (ULAs). Unlike the existing method that only uses stationary priors, our new approach utilizes a hierarchical form of the Student t prior to enforce the sparsity of the unknown signal more heavily. We also provide a distinct Bayesian inference for the expectation-maximization (EM) algorithm, which can update the mutual coupling coefficients more efficiently. Another difference is that our method uses an additional singular value decomposition (SVD) to reduce the computational complexity of the signal reconstruction process and the sensitivity to the measurement noise. PMID:26501284
Robust conic generalized partial linear models using RCMARS method - A robustification of CGPLM
NASA Astrophysics Data System (ADS)
Özmen, Ayşe; Weber, Gerhard Wilhelm
2012-11-01
GPLM is a combination of two different regression models each of which is used to apply on different parts of the data set. It is also adequate to high dimensional, non-normal and nonlinear data sets having the flexibility to reflect all anomalies effectively. In our previous study, Conic GPLM (CGPLM) was introduced using CMARS and Logistic Regression. According to a comparison with CMARS, CGPLM gives better results. In this study, we include the existence of uncertainty in the future scenarios into CMARS and linear/logit regression part in CGPLM and robustify it with robust optimization which is dealt with data uncertainty. Moreover, we apply RCGPLM on a small data set as a numerical experience from the financial sector.
Quasi-Linear Parameter Varying Representation of General Aircraft Dynamics Over Non-Trim Region
NASA Technical Reports Server (NTRS)
Shin, Jong-Yeob
2007-01-01
For applying linear parameter varying (LPV) control synthesis and analysis to a nonlinear system, it is required that a nonlinear system be represented in the form of an LPV model. In this paper, a new representation method is developed to construct an LPV model from a nonlinear mathematical model without the restriction that an operating point must be in the neighborhood of equilibrium points. An LPV model constructed by the new method preserves local stabilities of the original nonlinear system at "frozen" scheduling parameters and also represents the original nonlinear dynamics of a system over a non-trim region. An LPV model of the motion of FASER (Free-flying Aircraft for Subscale Experimental Research) is constructed by the new method.
Linear stability of plane Poiseuille flow over a generalized Stokes layer
NASA Astrophysics Data System (ADS)
Quadrio, Maurizio; Martinelli, Fulvio; Schmid, Peter J.
2011-12-01
Linear stability of plane Poiseuille flow subject to spanwise velocity forcing applied at the wall is studied. The forcing is stationary and sinusoidally distributed along the streamwise direction. The long-term aim of the study is to explore a possible relationship between the modification induced by the wall forcing to the stability characteristic of the unforced Poiseuille flow and the signifcant capabilities demonstrated by the same forcing in reducing turbulent friction drag. We present in this paper the statement of the mathematical problem, which is considerably more complex that the classic Orr-Sommerfeld-Squire approach, owing to the streamwise-varying boundary condition. We also report some preliminary results which, although not yet conclusive, describe the effects of the wall forcing on modal and non-modal characteristics of the flow stability.
Unsupervised analysis of polyphonic music by sparse coding.
Abdallah, Samer A; Plumbley, Mark D
2006-01-01
We investigate a data-driven approach to the analysis and transcription of polyphonic music, using a probabilistic model which is able to find sparse linear decompositions of a sequence of short-term Fourier spectra. The resulting system represents each input spectrum as a weighted sum of a small number of "atomic" spectra chosen from a larger dictionary; this dictionary is, in turn, learned from the data in such a way as to represent the given training set in an (information theoretically) efficient way. When exposed to examples of polyphonic music, most of the dictionary elements take on the spectral characteristics of individual notes in the music, so that the sparse decomposition can be used to identify the notes in a polyphonic mixture. Our approach differs from other methods of polyphonic analysis based on spectral decomposition by combining all of the following: (a) a formulation in terms of an explicitly given probabilistic model, in which the process estimating which notes are present corresponds naturally with the inference of latent variables in the model; (b) a particularly simple generative model, motivated by very general considerations about efficient coding, that makes very few assumptions about the musical origins of the signals being processed; and (c) the ability to learn a dictionary of atomic spectra (most of which converge to harmonic spectral profiles associated with specific notes) from polyphonic examples alone-no separate training on monophonic examples is required.
NASA Technical Reports Server (NTRS)
Kaul, Upender K.
2005-01-01
A three-dimensional numerical solver based on finite-difference solution of three-dimensional elastodynamic equations in generalized curvilinear coordinates has been developed and used to generate data such as radial and tangential stresses over various gear component geometries under rotation. The geometries considered are an annulus, a thin annular disk, and a thin solid disk. The solution is based on first principles and does not involve lumped parameter or distributed parameter systems approach. The elastodynamic equations in the velocity-stress formulation that are considered here have been used in the solution of problems of geophysics where non-rotating Cartesian grids are considered. For arbitrary geometries, these equations along with the appropriate boundary conditions have been cast in generalized curvilinear coordinates in the present study.
Online learning control using adaptive critic designs with sparse kernel machines.
Xu, Xin; Hou, Zhongsheng; Lian, Chuanqiang; He, Haibo
2013-05-01
In the past decade, adaptive critic designs (ACDs), including heuristic dynamic programming (HDP), dual heuristic programming (DHP), and their action-dependent ones, have been widely studied to realize online learning control of dynamical systems. However, because neural networks with manually designed features are commonly used to deal with continuous state and action spaces, the generalization capability and learning efficiency of previous ACDs still need to be improved. In this paper, a novel framework of ACDs with sparse kernel machines is presented by integrating kernel methods into the critic of ACDs. To improve the generalization capability as well as the computational efficiency of kernel machines, a sparsification method based on the approximately linear dependence analysis is used. Using the sparse kernel machines, two kernel-based ACD algorithms, that is, kernel HDP (KHDP) and kernel DHP (KDHP), are proposed and their performance is analyzed both theoretically and empirically. Because of the representation learning and generalization capability of sparse kernel machines, KHDP and KDHP can obtain much better performance than previous HDP and DHP with manually designed neural networks. Simulation and experimental results of two nonlinear control problems, that is, a continuous-action inverted pendulum problem and a ball and plate control problem, demonstrate the effectiveness of the proposed kernel ACD methods.
Chuang, Chun-Fu; Sun, Yeong-Jeu; Wang, Wen-June
2012-12-01
In this study, exponential finite-time synchronization for generalized Lorenz chaotic systems is investigated. The significant contribution of this paper is that master-slave synchronization is achieved within a pre-specified convergence time and with a simple linear control. The designed linear control consists of two parts: one achieves exponential synchronization, and the other realizes finite-time synchronization within a guaranteed convergence time. Furthermore, the control gain depends on the parameters of the exponential convergence rate, the finite-time convergence rate, the bound of the initial states of the master system, and the system parameter. In addition, the proposed approach can be directly and efficiently applied to secure communication. Finally, four numerical examples are provided to demonstrate the feasibility and correctness of the obtained results.
NASA Technical Reports Server (NTRS)
Yedavalli, R. K.
1992-01-01
The problem of analyzing and designing controllers for linear systems subject to real parameter uncertainty is considered. An elegant, unified theory for robust eigenvalue placement is presented for a class of D-regions defined by algebraic inequalities by extending the nominal matrix root clustering theory of Gutman and Jury (1981) to linear uncertain time systems. The author presents explicit conditions for matrix root clustering for different D-regions and establishes the relationship between the eigenvalue migration range and the parameter range. The bounds are all obtained by one-shot computation in the matrix domain and do not need any frequency sweeping or parameter gridding. The method uses the generalized Lyapunov theory for getting the bounds.
Fingerprint Compression Based on Sparse Representation.
Shao, Guangqi; Wu, Yanping; A, Yong; Liu, Xiao; Guo, Tiande
2014-02-01
A new fingerprint compression algorithm based on sparse representation is introduced. Obtaining an overcomplete dictionary from a set of fingerprint patches allows us to represent them as a sparse linear combination of dictionary atoms. In the algorithm, we first construct a dictionary for predefined fingerprint image patches. For a new given fingerprint images, represent its patches according to the dictionary by computing l(0)-minimization and then quantize and encode the representation. In this paper, we consider the effect of various factors on compression results. Three groups of fingerprint images are tested. The experiments demonstrate that our algorithm is efficient compared with several competing compression techniques (JPEG, JPEG 2000, and WSQ), especially at high compression ratios. The experiments also illustrate that the proposed algorithm is robust to extract minutiae.
Feature selection using sparse Bayesian inference
NASA Astrophysics Data System (ADS)
Brandes, T. Scott; Baxter, James R.; Woodworth, Jonathan
2014-06-01
A process for selecting a sparse subset of features that maximize discrimination between target classes is described in a Bayesian framework. Demonstrated on high range resolution radar (HRR) signature data, this has the effect of selecting the most informative range bins for a classification task. The sparse Bayesian classifier (SBC) model is directly compared against Fisher's linear discriminant analysis (LDA), showing a clear performance gain with the Bayesian framework using HRRs from the publicly available MSTAR data set. The discriminative power of the selected features from the SBC is shown to be particularly dominant over LDA when only a few features are selected or when there is a shift in training and testing data sets, as demonstrated by training on a specific target type and testing on a slightly different target type.
Classical and Generalized Solutions of Time-Dependent Linear Differential Algebraic Equations
1993-10-15
matrix pencils, [G59]. The book [GrM86] also contains a treatment of the general system (1.1) utilizing a condition of "transferabilitv’" which...C(t) and N(t) are analytic functions of t and N(t) is nilpotent upper (or lower) triangular for all t E J. From the structure of N(t), it follows that...the operator Y(t)l7 n is nilpotent , so that (1.2b) has the unique solution z = E (-1)k(N(t)-)kg, and (1.2a) is k=1 it an explicit ODE. But no
Learning Stable Multilevel Dictionaries for Sparse Representations.
Thiagarajan, Jayaraman J; Ramamurthy, Karthikeyan Natesan; Spanias, Andreas
2015-09-01
Sparse representations using learned dictionaries are being increasingly used with success in several data processing and machine learning applications. The increasing need for learning sparse models in large-scale applications motivates the development of efficient, robust, and provably good dictionary learning algorithms. Algorithmic stability and generalizability are desirable characteristics for dictionary learning algorithms that aim to build global dictionaries, which can efficiently model any test data similar to the training samples. In this paper, we propose an algorithm to learn dictionaries for sparse representations from large scale data, and prove that the proposed learning algorithm is stable and generalizable asymptotically. The algorithm employs a 1-D subspace clustering procedure, the K-hyperline clustering, to learn a hierarchical dictionary with multiple levels. We also propose an information-theoretic scheme to estimate the number of atoms needed in each level of learning and develop an ensemble approach to learn robust dictionaries. Using the proposed dictionaries, the sparse code for novel test data can be computed using a low-complexity pursuit procedure. We demonstrate the stability and generalization characteristics of the proposed algorithm using simulations. We also evaluate the utility of the multilevel dictionaries in compressed recovery and subspace learning applications.
Casals, Martí; Girabent-Farrés, Montserrat; Carrasco, Josep L.
2014-01-01
Background Modeling count and binary data collected in hierarchical designs have increased the use of Generalized Linear Mixed Models (GLMMs) in medicine. This article presents a systematic review of the application and quality of results and information reported from GLMMs in the field of clinical medicine. Methods A search using the Web of Science database was performed for published original articles in medical journals from 2000 to 2012. The search strategy included the topic “generalized linear mixed models”,“hierarchical generalized linear models”, “multilevel generalized linear model” and as a research domain we refined by science technology. Papers reporting methodological considerations without application, and those that were not involved in clinical medicine or written in English were excluded. Results A total of 443 articles were detected, with an increase over time in the number of articles. In total, 108 articles fit the inclusion criteria. Of these, 54.6% were declared to be longitudinal studies, whereas 58.3% and 26.9% were defined as repeated measurements and multilevel design, respectively. Twenty-two articles belonged to environmental and occupational public health, 10 articles to clinical neurology, 8 to oncology, and 7 to infectious diseases and pediatrics. The distribution of the response variable was reported in 88% of the articles, predominantly Binomial (n = 64) or Poisson (n = 22). Most of the useful information about GLMMs was not reported in most cases. Variance estimates of random effects were described in only 8 articles (9.2%). The model validation, the method of covariate selection and the method of goodness of fit were only reported in 8.0%, 36.8% and 14.9% of the articles, respectively. Conclusions During recent years, the use of GLMMs in medical literature has increased to take into account the correlation of data when modeling qualitative data or counts. According to the current recommendations, the quality of
Chen, Zhe; Putrino, David F; Ba, Demba E; Ghosh, Soumya; Barbieri, Riccardo; Brown, Emery N
2009-01-01
Identification of multiple simultaneously recorded neural spike train recordings is an important task in understanding neuronal dependency, functional connectivity, and temporal causality in neural systems. An assessment of the functional connectivity in a group of ensemble cells was performed using a regularized point process generalized linear model (GLM) that incorporates temporal smoothness or contiguity of the solution. An efficient convex optimization algorithm was then developed for the regularized solution. The point process model was applied to an ensemble of neurons recorded from the cat motor cortex during a skilled reaching task. The implications of this analysis to the coding of skilled movement in primary motor cortex is discussed.
Percolation on Sparse Networks
NASA Astrophysics Data System (ADS)
Karrer, Brian; Newman, M. E. J.; Zdeborová, Lenka
2014-11-01
We study percolation on networks, which is used as a model of the resilience of networked systems such as the Internet to attack or failure and as a simple model of the spread of disease over human contact networks. We reformulate percolation as a message passing process and demonstrate how the resulting equations can be used to calculate, among other things, the size of the percolating cluster and the average cluster size. The calculations are exact for sparse networks when the number of short loops in the network is small, but even on networks with many short loops we find them to be highly accurate when compared with direct numerical simulations. By considering the fixed points of the message passing process, we also show that the percolation threshold on a network with few loops is given by the inverse of the leading eigenvalue of the so-called nonbacktracking matrix.
NASA Technical Reports Server (NTRS)
Denning, Peter J.
1989-01-01
Sparse distributed memory was proposed be Pentti Kanerva as a realizable architecture that could store large patterns and retrieve them based on partial matches with patterns representing current sensory inputs. This memory exhibits behaviors, both in theory and in experiment, that resemble those previously unapproached by machines - e.g., rapid recognition of faces or odors, discovery of new connections between seemingly unrelated ideas, continuation of a sequence of events when given a cue from the middle, knowing that one doesn't know, or getting stuck with an answer on the tip of one's tongue. These behaviors are now within reach of machines that can be incorporated into the computing systems of robots capable of seeing, talking, and manipulating. Kanerva's theory is a break with the Western rationalistic tradition, allowing a new interpretation of learning and cognition that respects biology and the mysteries of individual human beings.
Sparseness Analysis in the Pretraining of Deep Neural Networks.
Li, Jun; Zhang, Tong; Luo, Wei; Yang, Jian; Yuan, Xiao-Tong; Zhang, Jian
2016-03-31
A major progress in deep multilayer neural networks (DNNs) is the invention of various unsupervised pretraining methods to initialize network parameters which lead to good prediction accuracy. This paper presents the sparseness analysis on the hidden unit in the pretraining process. In particular, we use the L₁-norm to measure sparseness and provide some sufficient conditions for that pretraining leads to sparseness with respect to the popular pretraining models--such as denoising autoencoders (DAEs) and restricted Boltzmann machines (RBMs). Our experimental results demonstrate that when the sufficient conditions are satisfied, the pretraining models lead to sparseness. Our experiments also reveal that when using the sigmoid activation functions, pretraining plays an important sparseness role in DNNs with sigmoid (Dsigm), and when using the rectifier linear unit (ReLU) activation functions, pretraining becomes less effective for DNNs with ReLU (Drelu). Luckily, Drelu can reach a higher recognition accuracy than DNNs with pretraining (DAEs and RBMs), as it can capture the main benefit (such as sparseness-encouraging) of pretraining in Dsigm. However, ReLU is not adapted to the different firing rates in biological neurons, because the firing rate actually changes along with the varying membrane resistances. To address this problem, we further propose a family of rectifier piecewise linear units (RePLUs) to fit the different firing rates. The experimental results show that the performance of RePLU is better than ReLU, and is comparable with those with some pretraining techniques, such as RBMs and DAEs.
Sparse Representation for Time-Series Classification
2015-02-08
February 8, 2015 16:49 World Scientific Review Volume - 9in x 6in ” time - series classification” page 1 Chapter 1 Sparse Representation for Time - Series ...studies the problem of time - series classification and presents an overview of recent developments in the area of feature extraction and information...problem of target classification, and more generally time - series classification, in two main directions, feature extraction and information fusion. 1
Jiang, Fei; Ma, Yanyuan; Wang, Yuanjia
2015-01-01
We propose a generalized partially linear functional single index risk score model for repeatedly measured outcomes where the index itself is a function of time. We fuse the nonparametric kernel method and regression spline method, and modify the generalized estimating equation to facilitate estimation and inference. We use local smoothing kernel to estimate the unspecified coefficient functions of time, and use B-splines to estimate the unspecified function of the single index component. The covariance structure is taken into account via a working model, which provides valid estimation and inference procedure whether or not it captures the true covariance. The estimation method is applicable to both continuous and discrete outcomes. We derive large sample properties of the estimation procedure and show different convergence rate of each component of the model. The asymptotic properties when the kernel and regression spline methods are combined in a nested fashion has not been studied prior to this work even in the independent data case. PMID:26283801
Jiang, Fei; Ma, Yanyuan; Wang, Yuanjia
We propose a generalized partially linear functional single index risk score model for repeatedly measured outcomes where the index itself is a function of time. We fuse the nonparametric kernel method and regression spline method, and modify the generalized estimating equation to facilitate estimation and inference. We use local smoothing kernel to estimate the unspecified coefficient functions of time, and use B-splines to estimate the unspecified function of the single index component. The covariance structure is taken into account via a working model, which provides valid estimation and inference procedure whether or not it captures the true covariance. The estimation method is applicable to both continuous and discrete outcomes. We derive large sample properties of the estimation procedure and show different convergence rate of each component of the model. The asymptotic properties when the kernel and regression spline methods are combined in a nested fashion has not been studied prior to this work even in the independent data case.
Biohybrid Control of General Linear Systems Using the Adaptive Filter Model of Cerebellum
Wilson, Emma D.; Assaf, Tareq; Pearson, Martin J.; Rossiter, Jonathan M.; Dean, Paul; Anderson, Sean R.; Porrill, John
2015-01-01
The adaptive filter model of the cerebellar microcircuit has been successfully applied to biological motor control problems, such as the vestibulo-ocular reflex (VOR), and to sensory processing problems, such as the adaptive cancelation of reafferent noise. It has also been successfully applied to problems in robotics, such as adaptive camera stabilization and sensor noise cancelation. In previous applications to inverse control problems, the algorithm was applied to the velocity control of a plant dominated by viscous and elastic elements. Naive application of the adaptive filter model to the displacement (as opposed to velocity) control of this plant results in unstable learning and control. To be more generally useful in engineering problems, it is essential to remove this restriction to enable the stable control of plants of any order. We address this problem here by developing a biohybrid model reference adaptive control (MRAC) scheme, which stabilizes the control algorithm for strictly proper plants. We evaluate the performance of this novel cerebellar-inspired algorithm with MRAC scheme in the experimental control of a dielectric electroactive polymer, a class of artificial muscle. The results show that the augmented cerebellar algorithm is able to accurately control the displacement response of the artificial muscle. The proposed solution not only greatly extends the practical applicability of the cerebellar-inspired algorithm, but may also shed light on cerebellar involvement in a wider range of biological control tasks. PMID:26257638
Biohybrid Control of General Linear Systems Using the Adaptive Filter Model of Cerebellum.
Wilson, Emma D; Assaf, Tareq; Pearson, Martin J; Rossiter, Jonathan M; Dean, Paul; Anderson, Sean R; Porrill, John
2015-01-01
The adaptive filter model of the cerebellar microcircuit has been successfully applied to biological motor control problems, such as the vestibulo-ocular reflex (VOR), and to sensory processing problems, such as the adaptive cancelation of reafferent noise. It has also been successfully applied to problems in robotics, such as adaptive camera stabilization and sensor noise cancelation. In previous applications to inverse control problems, the algorithm was applied to the velocity control of a plant dominated by viscous and elastic elements. Naive application of the adaptive filter model to the displacement (as opposed to velocity) control of this plant results in unstable learning and control. To be more generally useful in engineering problems, it is essential to remove this restriction to enable the stable control of plants of any order. We address this problem here by developing a biohybrid model reference adaptive control (MRAC) scheme, which stabilizes the control algorithm for strictly proper plants. We evaluate the performance of this novel cerebellar-inspired algorithm with MRAC scheme in the experimental control of a dielectric electroactive polymer, a class of artificial muscle. The results show that the augmented cerebellar algorithm is able to accurately control the displacement response of the artificial muscle. The proposed solution not only greatly extends the practical applicability of the cerebellar-inspired algorithm, but may also shed light on cerebellar involvement in a wider range of biological control tasks.
NASA Astrophysics Data System (ADS)
Altaleb, Anas; Saeed, Muhammad Sarwar; Hussain, Iqtadar; Aslam, Muhammad
2017-03-01
The aim of this work is to synthesize 8*8 substitution boxes (S-boxes) for block ciphers. The confusion creating potential of an S-box depends on its construction technique. In the first step, we have applied the algebraic action of the projective general linear group PGL(2,GF(28)) on Galois field GF(28). In step 2 we have used the permutations of the symmetric group S256 to construct new kind of S-boxes. To explain the proposed extension scheme, we have given an example and constructed one new S-box. The strength of the extended S-box is computed, and an insight is given to calculate the confusion-creating potency. To analyze the security of the S-box some popular algebraic and statistical attacks are performed as well. The proposed S-box has been analyzed by bit independent criterion, linear approximation probability test, non-linearity test, strict avalanche criterion, differential approximation probability test, and majority logic criterion. A comparison of the proposed S-box with existing S-boxes shows that the analyses of the extended S-box are comparatively better.
Yu, Guoshen; Sapiro, Guillermo; Mallat, Stéphane
2012-05-01
A general framework for solving image inverse problems with piecewise linear estimations is introduced in this paper. The approach is based on Gaussian mixture models, which are estimated via a maximum a posteriori expectation-maximization algorithm. A dual mathematical interpretation of the proposed framework with a structured sparse estimation is described, which shows that the resulting piecewise linear estimate stabilizes the estimation when compared with traditional sparse inverse problem techniques. We demonstrate that, in a number of image inverse problems, including interpolation, zooming, and deblurring of narrow kernels, the same simple and computationally efficient algorithm yields results in the same ballpark as that of the state of the art.
Generalized Uncertainty Quantification for Linear Inverse Problems in X-ray Imaging
Fowler, Michael James
2014-04-25
In industrial and engineering applications, X-ray radiography has attained wide use as a data collection protocol for the assessment of material properties in cases where direct observation is not possible. The direct measurement of nuclear materials, particularly when they are under explosive or implosive loading, is not feasible, and radiography can serve as a useful tool for obtaining indirect measurements. In such experiments, high energy X-rays are pulsed through a scene containing material of interest, and a detector records a radiograph by measuring the radiation that is not attenuated in the scene. One approach to the analysis of these radiographs is to model the imaging system as an operator that acts upon the object being imaged to produce a radiograph. In this model, the goal is to solve an inverse problem to reconstruct the values of interest in the object, which are typically material properties such as density or areal density. The primary objective in this work is to provide quantitative solutions with uncertainty estimates for three separate applications in X-ray radiography: deconvolution, Abel inversion, and radiation spot shape reconstruction. For each problem, we introduce a new hierarchical Bayesian model for determining a posterior distribution on the unknowns and develop efficient Markov chain Monte Carlo (MCMC) methods for sampling from the posterior. A Poisson likelihood, based on a noise model for photon counts at the detector, is combined with a prior tailored to each application: an edge-localizing prior for deconvolution; a smoothing prior with non-negativity constraints for spot reconstruction; and a full covariance sampling prior based on a Wishart hyperprior for Abel inversion. After developing our methods in a general setting, we demonstrate each model on both synthetically generated datasets, including those from a well known radiation transport code, and real high energy radiographs taken at two U. S. Department of Energy
The generalized cross-validation method applied to geophysical linear traveltime tomography
NASA Astrophysics Data System (ADS)
Bassrei, A.; Oliveira, N. P.
2009-12-01
The oil industry is the major user of Applied Geophysics methods for the subsurface imaging. Among different methods, the so-called seismic (or exploration seismology) methods are the most important. Tomography was originally developed for medical imaging and was introduced in exploration seismology in the 1980's. There are two main classes of geophysical tomography: those that use only the traveltimes between sources and receivers, which is a cinematic approach and those that use the wave amplitude itself, being a dynamic approach. Tomography is a kind of inverse problem, and since inverse problems are usually ill-posed, it is necessary to use some method to reduce their deficiencies. These difficulties of the inverse procedure are associated with the fact that the involved matrix is ill-conditioned. To compensate this shortcoming, it is appropriate to use some technique of regularization. In this work we make use of regularization with derivative matrices, also called smoothing. There is a crucial problem in regularization, which is the selection of the regularization parameter lambda. We use generalized cross validation (GCV) as a tool for the selection of lambda. GCV chooses the regularization parameter associated with the best average prediction for all possible omissions of one datum, corresponding to the minimizer of GCV function. GCV is used for an application in traveltime tomography, where the objective is to obtain the 2-D velocity distribution from the measured values of the traveltimes between sources and receivers. We present results with synthetic data, using a geological model that simulates different features, like a fault and a reservoir. The results using GCV are very good, including those contaminated with noise, and also using different regularization orders, attesting the feasibility of this technique.
Valeri, Linda; Lin, Xihong; VanderWeele, Tyler J
2014-12-10
Mediation analysis is a popular approach to examine the extent to which the effect of an exposure on an outcome is through an intermediate variable (mediator) and the extent to which the effect is direct. When the mediator is mis-measured, the validity of mediation analysis can be severely undermined. In this paper, we first study the bias of classical, non-differential measurement error on a continuous mediator in the estimation of direct and indirect causal effects in generalized linear models when the outcome is either continuous or discrete and exposure-mediator interaction may be present. Our theoretical results as well as a numerical study demonstrate that in the presence of non-linearities, the bias of naive estimators for direct and indirect effects that ignore measurement error can take unintuitive directions. We then develop methods to correct for measurement error. Three correction approaches using method of moments, regression calibration, and SIMEX are compared. We apply the proposed method to the Massachusetts General Hospital lung cancer study to evaluate the effect of genetic variants mediated through smoking on lung cancer risk.
NASA Astrophysics Data System (ADS)
Lu, Y.; Chatterjee, S.
2014-11-01
Exponential family statistical distributions, including the well-known normal, binomial, Poisson, and exponential distributions, are overwhelmingly used in data analysis. In the presence of covariates, an exponential family distributional assumption for the response random variables results in a generalized linear model. However, it is rarely ensured that the parameters of the assumed distributions are stable through the entire duration of the data collection process. A failure of stability leads to nonsmoothness and nonlinearity in the physical processes that result in the data. In this paper, we propose testing for stability of parameters of exponential family distributions and generalized linear models. A rejection of the hypothesis of stable parameters leads to change detection. We derive the related likelihood ratio test statistic. We compare the performance of this test statistic to the popular normal distributional assumption dependent cumulative sum (Gaussian CUSUM) statistic in change detection problems. We study Atlantic tropical storms using the techniques developed here, so to understand whether the nature of these tropical storms has remained stable over the last few decades.
NASA Astrophysics Data System (ADS)
Koss, Hans; Rance, Mark; Palmer, Arthur G.
2017-01-01
Exploration of dynamic processes in proteins and nucleic acids by spin-locking NMR experiments has been facilitated by the development of theoretical expressions for the R1ρ relaxation rate constant covering a variety of kinetic situations. Herein, we present a generalized approximation to the chemical exchange, Rex, component of R1ρ for arbitrary kinetic schemes, assuming the presence of a dominant major site population, derived from the negative reciprocal trace of the inverse Bloch-McConnell evolution matrix. This approximation is equivalent to first-order truncation of the characteristic polynomial derived from the Bloch-McConnell evolution matrix. For three- and four-site chemical exchange, the first-order approximations are sufficient to distinguish different kinetic schemes. We also introduce an approach to calculate R1ρ for linear N-site schemes, using the matrix determinant lemma to reduce the corresponding 3N × 3N Bloch-McConnell evolution matrix to a 3 × 3 matrix. The first- and second order-expansions of the determinant of this 3 × 3 matrix are closely related to previously derived equations for two-site exchange. The second-order approximations for linear N-site schemes can be used to obtain more accurate approximations for non-linear N-site schemes, such as triangular three-site or star four-site topologies. The expressions presented herein provide powerful means for the estimation of Rex contributions for both low (CEST-limit) and high (R1ρ-limit) radiofrequency field strengths, provided that the population of one state is dominant. The general nature of the new expressions allows for consideration of complex kinetic situations in the analysis of NMR spin relaxation data.
Sparseness- and continuity-constrained seismic imaging
NASA Astrophysics Data System (ADS)
Herrmann, Felix J.
2005-04-01
Non-linear solution strategies to the least-squares seismic inverse-scattering problem with sparseness and continuity constraints are proposed. Our approach is designed to (i) deal with substantial amounts of additive noise (SNR < 0 dB); (ii) use the sparseness and locality (both in position and angle) of directional basis functions (such as curvelets and contourlets) on the model: the reflectivity; and (iii) exploit the near invariance of these basis functions under the normal operator, i.e., the scattering-followed-by-imaging operator. Signal-to-noise ratio and the continuity along the imaged reflectors are significantly enhanced by formulating the solution of the seismic inverse problem in terms of an optimization problem. During the optimization, sparseness on the basis and continuity along the reflectors are imposed by jointly minimizing the l1- and anisotropic diffusion/total-variation norms on the coefficients and reflectivity, respectively. [Joint work with Peyman P. Moghaddam was carried out as part of the SINBAD project, with financial support secured through ITF (the Industry Technology Facilitator) from the following organizations: BG Group, BP, ExxonMobil, and SHELL. Additional funding came from the NSERC Discovery Grants 22R81254.
Automatic target recognition via sparse representations
NASA Astrophysics Data System (ADS)
Estabridis, Katia
2010-04-01
Automatic target recognition (ATR) based on the emerging technology of Compressed Sensing (CS) can considerably improve accuracy, speed and cost associated with these types of systems. An image based ATR algorithm has been built upon this new theory, which can perform target detection and recognition in a low dimensional space. Compressed dictionaries (A) are formed to include rotational information for a scale of interest. The algorithm seeks to identify y(test sample) as a linear combination of the dictionary elements : y=Ax, where A ∈ Rnxm(n<
Aerial Scene Recognition using Efficient Sparse Representation
Cheriyadat, Anil M
2012-01-01
Advanced scene recognition systems for processing large volumes of high-resolution aerial image data are in great demand today. However, automated scene recognition remains a challenging problem. Efficient encoding and representation of spatial and structural patterns in the imagery are key in developing automated scene recognition algorithms. We describe an image representation approach that uses simple and computationally efficient sparse code computation to generate accurate features capable of producing excellent classification performance using linear SVM kernels. Our method exploits unlabeled low-level image feature measurements to learn a set of basis vectors. We project the low-level features onto the basis vectors and use simple soft threshold activation function to derive the sparse features. The proposed technique generates sparse features at a significantly lower computational cost than other methods~\\cite{Yang10, newsam11}, yet it produces comparable or better classification accuracy. We apply our technique to high-resolution aerial image datasets to quantify the aerial scene classification performance. We demonstrate that the dense feature extraction and representation methods are highly effective for automatic large-facility detection on wide area high-resolution aerial imagery.
Parallel preconditioning techniques for sparse CG solvers
Basermann, A.; Reichel, B.; Schelthoff, C.
1996-12-31
Conjugate gradient (CG) methods to solve sparse systems of linear equations play an important role in numerical methods for solving discretized partial differential equations. The large size and the condition of many technical or physical applications in this area result in the need for efficient parallelization and preconditioning techniques of the CG method. In particular for very ill-conditioned matrices, sophisticated preconditioner are necessary to obtain both acceptable convergence and accuracy of CG. Here, we investigate variants of polynomial and incomplete Cholesky preconditioners that markedly reduce the iterations of the simply diagonally scaled CG and are shown to be well suited for massively parallel machines.
Estimating sparse precision matrices
NASA Astrophysics Data System (ADS)
Padmanabhan, Nikhil; White, Martin; Zhou, Harrison H.; O'Connell, Ross
2016-08-01
We apply a method recently introduced to the statistical literature to directly estimate the precision matrix from an ensemble of samples drawn from a corresponding Gaussian distribution. Motivated by the observation that cosmological precision matrices are often approximately sparse, the method allows one to exploit this sparsity of the precision matrix to more quickly converge to an asymptotic 1/sqrt{N_sim} rate while simultaneously providing an error model for all of the terms. Such an estimate can be used as the starting point for further regularization efforts which can improve upon the 1/sqrt{N_sim} limit above, and incorporating such additional steps is straightforward within this framework. We demonstrate the technique with toy models and with an example motivated by large-scale structure two-point analysis, showing significant improvements in the rate of convergence. For the large-scale structure example, we find errors on the precision matrix which are factors of 5 smaller than for the sample precision matrix for thousands of simulations or, alternatively, convergence to the same error level with more than an order of magnitude fewer simulations.
NASA Astrophysics Data System (ADS)
Edwards, C. L.; Edwards, M. L.
2009-05-01
MEMS micro-mirror technology offers the opportunity to replace larger optical actuators with smaller, faster ones for lidar, network switching, and other beam steering applications. Recent developments in modeling and simulation of MEMS two-axis (tip-tilt) mirrors have resulted in closed-form solutions that are expressed in terms of physical, electrical and environmental parameters related to the MEMS device. The closed-form analytical expressions enable dynamic time-domain simulations without excessive computational overhead and are referred to as the Micro-mirror Pointing Model (MPM). Additionally, these first-principle models have been experimentally validated with in-situ static, dynamic, and stochastic measurements illustrating their reliability. These models have assumed that the mirror has a rectangular shape. Because the corners can limit the dynamic operation of a rectangular mirror, it is desirable to shape the mirror, e.g., mitering the corners. Presented in this paper is the formulation of a generalized electrostatic micromirror (GEM) model with an arbitrary convex piecewise linear shape that is readily implemented in MATLAB and SIMULINK for steady-state and dynamic simulations. Additionally, such a model permits an arbitrary shaped mirror to be approximated as a series of linearly tapered segments. Previously, "effective area" arguments were used to model a non-rectangular shaped mirror with an equivalent rectangular one. The GEM model shows the limitations of this approach and provides a pre-fabrication tool for designing mirror shapes.
Lazar, Ann A; Zerbe, Gary O
2011-12-01
Researchers often compare the relationship between an outcome and covariate for two or more groups by evaluating whether the fitted regression curves differ significantly. When they do, researchers need to determine the "significance region," or the values of the covariate where the curves significantly differ. In analysis of covariance (ANCOVA), the Johnson-Neyman procedure can be used to determine the significance region; for the hierarchical linear model (HLM), the Miyazaki and Maier (M-M) procedure has been suggested. However, neither procedure can assume nonnormally distributed data. Furthermore, the M-M procedure produces biased (downward) results because it uses the Wald test, does not control the inflated Type I error rate due to multiple testing, and requires implementing multiple software packages to determine the significance region. In this article, we address these limitations by proposing solutions for determining the significance region suitable for generalized linear (mixed) model (GLM or GLMM). These proposed solutions incorporate test statistics that resolve the biased results, control the Type I error rate using Scheffé's method, and uses a single statistical software package to determine the significance region.
ERIC Educational Resources Information Center
Xu, Xueli; von Davier, Matthias
2008-01-01
The general diagnostic model (GDM) utilizes located latent classes for modeling a multidimensional proficiency variable. In this paper, the GDM is extended by employing a log-linear model for multiple populations that assumes constraints on parameters across multiple groups. This constrained model is compared to log-linear models that assume…
Tsai, Miao-Yu
2015-03-01
The problem of variable selection in the generalized linear-mixed models (GLMMs) is pervasive in statistical practice. For the purpose of variable selection, many methodologies for determining the best subset of explanatory variables currently exist according to the model complexity and differences between applications. In this paper, we develop a "higher posterior probability model with bootstrap" (HPMB) approach to select explanatory variables without fitting all possible GLMMs involving a small or moderate number of explanatory variables. Furthermore, to save computational load, we propose an efficient approximation approach with Laplace's method and Taylor's expansion to approximate intractable integrals in GLMMs. Simulation studies and an application of HapMap data provide evidence that this selection approach is computationally feasible and reliable for exploring true candidate genes and gene-gene associations, after adjusting for complex structures among clusters.
Chen, Vivian Yi-Ju; Yang, Tse-Chuan
2012-08-01
An increasing interest in exploring spatial non-stationarity has generated several specialized analytic software programs; however, few of these programs can be integrated natively into a well-developed statistical environment such as SAS. We not only developed a set of SAS macro programs to fill this gap, but also expanded the geographically weighted generalized linear modeling (GWGLM) by integrating the strengths of SAS into the GWGLM framework. Three features distinguish our work. First, the macro programs of this study provide more kernel weighting functions than the existing programs. Second, with our codes the users are able to better specify the bandwidth selection process compared to the capabilities of existing programs. Third, the development of the macro programs is fully embedded in the SAS environment, providing great potential for future exploration of complicated spatially varying coefficient models in other disciplines. We provided three empirical examples to illustrate the use of the SAS macro programs and demonstrated the advantages explained above.
NASA Astrophysics Data System (ADS)
Wu, Jingjing; Liu, Wei; Liu, Zhengjun; Liu, Shutian
2015-03-01
We introduce a chosen-plaintext attack scheme on general optical cryptosystems that use linear canonical transform and phase encoding based on correlated imaging. The plaintexts are chosen as Gaussian random real number matrixes, and the corresponding ciphertexts are regarded as prior knowledge of the proposed attack method. To establish the reconstruct of the secret plaintext, correlated imaging is employed using the known resources. Differing from the reported attack methods, there is no need to decipher the distribution of the decryption key. The original secret image can be directly recovered by the attack in the absence of decryption key. In addition, the improved cryptosystems combined with pixel scrambling operations are also vulnerable to the proposed attack method. Necessary mathematical derivations and numerical simulations are carried out to demonstrate the validity of the proposed attack scheme.
Blumberg, Leonid M; Desmet, Gert
2015-09-25
The separation performance metrics defined in Part 1 of this series are applied to the evaluation of general separation performance of linear solvent strength (LSS) gradient LC. Among the evaluated metrics was the peak capacity of an arbitrary segment of a chromatogram. Also evaluated were the peak width, the separability of two solutes, the utilization of separability, and the speed of analysis-all at an arbitrary point of a chromatogram. The means are provided to express all these metrics as functions of an arbitrary time during LC analysis, as functions of an arbitrary outlet solvent strength changing during the analysis, as functions of parameters of the solutes eluting during the analysis, and as functions of several other factors. The separation performance of gradient LC is compared with the separation performance of temperature-programmed GC evaluated in Part 2.
Sparse Methods for Biomedical Data.
Ye, Jieping; Liu, Jun
2012-06-01
Following recent technological revolutions, the investigation of massive biomedical data with growing scale, diversity, and complexity has taken a center stage in modern data analysis. Although complex, the underlying representations of many biomedical data are often sparse. For example, for a certain disease such as leukemia, even though humans have tens of thousands of genes, only a few genes are relevant to the disease; a gene network is sparse since a regulatory pathway involves only a small number of genes; many biomedical signals are sparse or compressible in the sense that they have concise representations when expressed in a proper basis. Therefore, finding sparse representations is fundamentally important for scientific discovery. Sparse methods based on the [Formula: see text] norm have attracted a great amount of research efforts in the past decade due to its sparsity-inducing property, convenient convexity, and strong theoretical guarantees. They have achieved great success in various applications such as biomarker selection, biological network construction, and magnetic resonance imaging. In this paper, we review state-of-the-art sparse methods and their applications to biomedical data.
Sparse Methods for Biomedical Data
Ye, Jieping; Liu, Jun
2013-01-01
Following recent technological revolutions, the investigation of massive biomedical data with growing scale, diversity, and complexity has taken a center stage in modern data analysis. Although complex, the underlying representations of many biomedical data are often sparse. For example, for a certain disease such as leukemia, even though humans have tens of thousands of genes, only a few genes are relevant to the disease; a gene network is sparse since a regulatory pathway involves only a small number of genes; many biomedical signals are sparse or compressible in the sense that they have concise representations when expressed in a proper basis. Therefore, finding sparse representations is fundamentally important for scientific discovery. Sparse methods based on the ℓ1 norm have attracted a great amount of research efforts in the past decade due to its sparsity-inducing property, convenient convexity, and strong theoretical guarantees. They have achieved great success in various applications such as biomarker selection, biological network construction, and magnetic resonance imaging. In this paper, we review state-of-the-art sparse methods and their applications to biomedical data. PMID:24076585
Wang, Chi; Dominici, Francesca; Parmigiani, Giovanni; Zigler, Corwin Matthew
2015-09-01
Confounder selection and adjustment are essential elements of assessing the causal effect of an exposure or treatment in observational studies. Building upon work by Wang et al. (2012, Biometrics 68, 661-671) and Lefebvre et al. (2014, Statistics in Medicine 33, 2797-2813), we propose and evaluate a Bayesian method to estimate average causal effects in studies with a large number of potential confounders, relatively few observations, likely interactions between confounders and the exposure of interest, and uncertainty on which confounders and interaction terms should be included. Our method is applicable across all exposures and outcomes that can be handled through generalized linear models. In this general setting, estimation of the average causal effect is different from estimation of the exposure coefficient in the outcome model due to noncollapsibility. We implement a Bayesian bootstrap procedure to integrate over the distribution of potential confounders and to estimate the causal effect. Our method permits estimation of both the overall population causal effect and effects in specified subpopulations, providing clear characterization of heterogeneous exposure effects that may vary considerably across different covariate profiles. Simulation studies demonstrate that the proposed method performs well in small sample size situations with 100-150 observations and 50 covariates. The method is applied to data on 15,060 US Medicare beneficiaries diagnosed with a malignant brain tumor between 2000 and 2009 to evaluate whether surgery reduces hospital readmissions within 30 days of diagnosis.
Mullah, Muhammad Abu Shadeque; Benedetti, Andrea
2016-11-01
Besides being mainly used for analyzing clustered or longitudinal data, generalized linear mixed models can also be used for smoothing via restricting changes in the fit at the knots in regression splines. The resulting models are usually called semiparametric mixed models (SPMMs). We investigate the effect of smoothing using SPMMs on the correlation and variance parameter estimates for serially correlated longitudinal normal, Poisson and binary data. Through simulations, we compare the performance of SPMMs to other simpler methods for estimating the nonlinear association such as fractional polynomials, and using a parametric nonlinear function. Simulation results suggest that, in general, the SPMMs recover the true curves very well and yield reasonable estimates of the correlation and variance parameters. However, for binary outcomes, SPMMs produce biased estimates of the variance parameters for high serially correlated data. We apply these methods to a dataset investigating the association between CD4 cell count and time since seroconversion for HIV infected men enrolled in the Multicenter AIDS Cohort Study.
Optical double-image encryption and authentication by sparse representation.
Mohammed, Emad A; Saadon, H L
2016-12-10
An optical double-image encryption and authentication method by sparse representation is proposed. The information from double-image encryption can be integrated into a sparse representation. Unlike the traditional double-image encryption technique, only sparse (partial) data from the encrypted data is adopted for the authentication process. Simulation results demonstrate that the correct authentication results are achieved even with partial information from the encrypted data. The randomly selected sparse encrypted information will be used as an effective key for a security system. Therefore, the proposed method is feasible, effective, and can provide an additional security layer for optical security systems. In addition, the method also achieved the general requirements of storage and transmission due to a high reduction of the encrypted information.
Rey deCastro, B; Neuberg, Donna
2007-05-30
Biological assays often utilize experimental designs where observations are replicated at multiple levels, and where each level represents a separate component of the assay's overall variance. Statistical analysis of such data usually ignores these design effects, whereas more sophisticated methods would improve the statistical power of assays. This report evaluates the statistical performance of an in vitro MCF-7 cell proliferation assay (E-SCREEN) by identifying the optimal generalized linear mixed model (GLMM) that accurately represents the assay's experimental design and variance components. Our statistical assessment found that 17beta-oestradiol cell culture assay data were best modelled with a GLMM configured with a reciprocal link function, a gamma error distribution, and three sources of design variation: plate-to-plate; well-to-well, and the interaction between plate-to-plate variation and dose. The gamma-distributed random error of the assay was estimated to have a coefficient of variation (COV) = 3.2 per cent, and a variance component score test described by X. Lin found that each of the three variance components were statistically significant. The optimal GLMM also confirmed the estrogenicity of five weakly oestrogenic polychlorinated biphenyls (PCBs 17, 49, 66, 74, and 128). Based on information criteria, the optimal gamma GLMM consistently out-performed equivalent naive normal and log-normal linear models, both with and without random effects terms. Because the gamma GLMM was by far the best model on conceptual and empirical grounds, and requires only trivially more effort to use, we encourage its use and suggest that naive models be avoided when possible.
Hughes, Vanessa K; Langlois, Neil E I
2010-12-01
Bruises can have medicolegal significance such that the age of a bruise may be an important issue. This study sought to determine if colorimetry or reflectance spectrophotometry could be employed to objectively estimate the age of bruises. Based on a previously described method, reflectance spectrophotometric scans were obtained from bruises using a Cary 100 Bio spectrophotometer fitted with a fibre-optic reflectance probe. Measurements were taken from the bruise and a control area. Software was used to calculate the first derivative at 490 and 480 nm; the proportion of oxygenated hemoglobin was calculated using an isobestic point method and a software application converted the scan data into colorimetry data. In addition, data on factors that might be associated with the determination of the age of a bruise: subject age, subject sex, degree of trauma, bruise size, skin color, body build, and depth of bruise were recorded. From 147 subjects, 233 reflectance spectrophotometry scans were obtained for analysis. The age of the bruises ranged from 0.5 to 231.5 h. A General Linear Model analysis method was used. This revealed that colorimetric measurement of the yellowness of a bruise accounted for 13% of the bruise age. By incorporation of the other recorded data (as above), yellowness could predict up to 32% of the age of a bruise-implying that 68% of the variation was dependent on other factors. However, critical appraisal of the model revealed that the colorimetry method of determining the age of a bruise was affected by skin tone and required a measure of the proportion of oxygenated hemoglobin, which is obtained by spectrophotometric methods. Using spectrophotometry, the first derivative at 490 nm alone accounted for 18% of the bruise age estimate. When additional factors (subject sex, bruise depth and oxygenation of hemoglobin) were included in the General Linear Model this increased to 31%-implying that 69% of the variation was dependent on other factors. This
An Assessment of Iterative Reconstruction Methods for Sparse Ultrasound Imaging
Valente, Solivan A.; Zibetti, Marcelo V. W.; Pipa, Daniel R.; Maia, Joaquim M.; Schneider, Fabio K.
2017-01-01
Ultrasonic image reconstruction using inverse problems has recently appeared as an alternative to enhance ultrasound imaging over beamforming methods. This approach depends on the accuracy of the acquisition model used to represent transducers, reflectivity, and medium physics. Iterative methods, well known in general sparse signal reconstruction, are also suited for imaging. In this paper, a discrete acquisition model is assessed by solving a linear system of equations by an ℓ1-regularized least-squares minimization, where the solution sparsity may be adjusted as desired. The paper surveys 11 variants of four well-known algorithms for sparse reconstruction, and assesses their optimization parameters with the goal of finding the best approach for iterative ultrasound imaging. The strategy for the model evaluation consists of using two distinct datasets. We first generate data from a synthetic phantom that mimics real targets inside a professional ultrasound phantom device. This dataset is contaminated with Gaussian noise with an estimated SNR, and all methods are assessed by their resulting images and performances. The model and methods are then assessed with real data collected by a research ultrasound platform when scanning the same phantom device, and results are compared with beamforming. A distinct real dataset is finally used to further validate the proposed modeling. Although high computational effort is required by iterative methods, results show that the discrete model may lead to images closer to ground-truth than traditional beamforming. However, computing capabilities of current platforms need to evolve before frame rates currently delivered by ultrasound equipments are achievable. PMID:28282862
M-estimation for robust sparse unmixing of hyperspectral images
NASA Astrophysics Data System (ADS)
Toomik, Maria; Lu, Shijian; Nelson, James D. B.
2016-10-01
Hyperspectral unmixing methods often use a conventional least squares based lasso which assumes that the data follows the Gaussian distribution. The normality assumption is an approximation which is generally invalid for real imagery data. We consider a robust (non-Gaussian) approach to sparse spectral unmixing of remotely sensed imagery which reduces the sensitivity of the estimator to outliers and relaxes the linearity assumption. The method consists of several appropriate penalties. We propose to use an lp norm with 0 < p < 1 in the sparse regression problem, which induces more sparsity in the results, but makes the problem non-convex. On the other hand, the problem, though non-convex, can be solved quite straightforwardly with an extensible algorithm based on iteratively reweighted least squares. To deal with the huge size of modern spectral libraries we introduce a library reduction step, similar to the multiple signal classification (MUSIC) array processing algorithm, which not only speeds up unmixing but also yields superior results. In the hyperspectral setting we extend the traditional least squares method to the robust heavy-tailed case and propose a generalised M-lasso solution. M-estimation replaces the Gaussian likelihood with a fixed function ρ(e) that restrains outliers. The M-estimate function reduces the effect of errors with large amplitudes or even assigns the outliers zero weights. Our experimental results on real hyperspectral data show that noise with large amplitudes (outliers) often exists in the data. This ability to mitigate the influence of such outliers can therefore offer greater robustness. Qualitative hyperspectral unmixing results on real hyperspectral image data corroborate the efficacy of the proposed method.
Towards an Accurate Performance Modeling of Parallel SparseFactorization
Grigori, Laura; Li, Xiaoye S.
2006-05-26
We present a performance model to analyze a parallel sparseLU factorization algorithm on modern cached-based, high-end parallelarchitectures. Our model characterizes the algorithmic behavior bytakingaccount the underlying processor speed, memory system performance, aswell as the interconnect speed. The model is validated using theSuperLU_DIST linear system solver, the sparse matrices from realapplications, and an IBM POWER3 parallel machine. Our modelingmethodology can be easily adapted to study performance of other types ofsparse factorizations, such as Cholesky or QR.
NASA Astrophysics Data System (ADS)
Asong, Zilefac E.; Khaliq, M. N.; Wheater, H. S.
2016-11-01
Based on the Generalized Linear Model (GLM) framework, a multisite stochastic modelling approach is developed using daily observations of precipitation and minimum and maximum temperatures from 120 sites located across the Canadian Prairie Provinces: Alberta, Saskatchewan and Manitoba. Temperature is modeled using a two-stage normal-heteroscedastic model by fitting mean and variance components separately. Likewise, precipitation occurrence and conditional precipitation intensity processes are modeled separately. The relationship between precipitation and temperature is accounted for by using transformations of precipitation as covariates to predict temperature fields. Large scale atmospheric covariates from the National Center for Environmental Prediction Reanalysis-I, teleconnection indices, geographical site attributes, and observed precipitation and temperature records are used to calibrate these models for the 1971-2000 period. Validation of the developed models is performed on both pre- and post-calibration period data. Results of the study indicate that the developed models are able to capture spatiotemporal characteristics of observed precipitation and temperature fields, such as inter-site and inter-variable correlation structure, and systematic regional variations present in observed sequences. A number of simulated weather statistics ranging from seasonal means to characteristics of temperature and precipitation extremes and some of the commonly used climate indices are also found to be in close agreement with those derived from observed data. This GLM-based modelling approach will be developed further for multisite statistical downscaling of Global Climate Model outputs to explore climate variability and change in this region of Canada.
Xiao, Xun; Geyer, Veikko F.; Bowne-Anderson, Hugo; Howard, Jonathon; Sbalzarini, Ivo F.
2016-01-01
Biological filaments, such as actin filaments, microtubules, and cilia, are often imaged using different light-microscopy techniques. Reconstructing the filament curve from the acquired images constitutes the filament segmentation problem. Since filaments have lower dimensionality than the image itself, there is an inherent trade-off between tracing the filament with sub-pixel accuracy and avoiding noise artifacts. Here, we present a globally optimal filament segmentation method based on B-spline vector level-sets and a generalized linear model for the pixel intensity statistics. We show that the resulting optimization problem is convex and can hence be solved with global optimality. We introduce a simple and efficient algorithm to compute such optimal filament segmentations, and provide an open-source implementation as an ImageJ/Fiji plugin. We further derive an information-theoretic lower bound on the filament segmentation error, quantifying how well an algorithm could possibly do given the information in the image. We show that our algorithm asymptotically reaches this bound in the spline coefficients. We validate our method in comprehensive benchmarks, compare with other methods, and show applications from fluorescence, phase-contrast, and dark-field microscopy. PMID:27104582
Uga, Minako; Dan, Ippeita; Sano, Toshifumi; Dan, Haruka; Watanabe, Eiju
2014-01-01
Abstract. An increasing number of functional near-infrared spectroscopy (fNIRS) studies utilize a general linear model (GLM) approach, which serves as a standard statistical method for functional magnetic resonance imaging (fMRI) data analysis. While fMRI solely measures the blood oxygen level dependent (BOLD) signal, fNIRS measures the changes of oxy-hemoglobin (oxy-Hb) and deoxy-hemoglobin (deoxy-Hb) signals at a temporal resolution severalfold higher. This suggests the necessity of adjusting the temporal parameters of a GLM for fNIRS signals. Thus, we devised a GLM-based method utilizing an adaptive hemodynamic response function (HRF). We sought the optimum temporal parameters to best explain the observed time series data during verbal fluency and naming tasks. The peak delay of the HRF was systematically changed to achieve the best-fit model for the observed oxy- and deoxy-Hb time series data. The optimized peak delay showed different values for each Hb signal and task. When the optimized peak delays were adopted, the deoxy-Hb data yielded comparable activations with similar statistical power and spatial patterns to oxy-Hb data. The adaptive HRF method could suitably explain the behaviors of both Hb parameters during tasks with the different cognitive loads during a time course, and thus would serve as an objective method to fully utilize the temporal structures of all fNIRS data. PMID:26157973
Planeta, Josef; Karásek, Pavel; Hohnová, Barbora; Sťavíková, Lenka; Roth, Michal
2012-08-10
Biphasic solvent systems composed of an ionic liquid (IL) and supercritical carbon dioxide (scCO(2)) have become frequented in synthesis, extractions and electrochemistry. In the design of related applications, information on interphase partitioning of the target organics is essential, and the infinite-dilution partition coefficients of the organic solutes in IL-scCO(2) systems can conveniently be obtained by supercritical fluid chromatography. The data base of experimental partition coefficients obtained previously in this laboratory has been employed to test a generalized predictive model for the solute partition coefficients. The model is an amended version of that described before by Hiraga et al. (J. Supercrit. Fluids, in press). Because of difficulty of the problem to be modeled, the model involves several different concepts - linear solvation energy relationships, density-dependent solvent power of scCO(2), regular solution theory, and the Flory-Huggins theory of athermal solutions. The model shows a moderate success in correlating the infinite-dilution solute partition coefficients (K-factors) in individual IL-scCO(2) systems at varying temperature and pressure. However, larger K-factor data sets involving multiple IL-scCO(2) systems appear to be beyond reach of the model, especially when the ILs involved pertain to different cation classes.
Felleki, M; Lee, D; Lee, Y; Gilmour, A R; Rönnegård, L
2012-12-01
The possibility of breeding for uniform individuals by selecting animals expressing a small response to environment has been studied extensively in animal breeding. Bayesian methods for fitting models with genetic components in the residual variance have been developed for this purpose, but have limitations due to the computational demands. We use the hierarchical (h)-likelihood from the theory of double hierarchical generalized linear models (DHGLM) to derive an estimation algorithm that is computationally feasible for large datasets. Random effects for both the mean and residual variance parts of the model are estimated together with their variance/covariance components. An important feature of the algorithm is that it can fit a correlation between the random effects for mean and variance. An h-likelihood estimator is implemented in the R software and an iterative reweighted least square (IRWLS) approximation of the h-likelihood is implemented using ASReml. The difference in variance component estimates between the two implementations is investigated, as well as the potential bias of the methods, using simulations. IRWLS gives the same results as h-likelihood in simple cases with no severe indication of bias. For more complex cases, only IRWLS could be used, and bias did appear. The IRWLS is applied on the pig litter size data previously analysed by Sorensen & Waagepetersen (2003) using Bayesian methodology. The estimates we obtained by using IRWLS are similar to theirs, with the estimated correlation between the random genetic effects being -0·52 for IRWLS and -0·62 in Sorensen & Waagepetersen (2003).
Johnson, Glen D; Mesler, Kristine; Kacica, Marilyn A
2017-02-06
Objective The objective is to estimate community needs with respect to risky adolescent sexual behavior in a way that is risk-adjusted for multiple community factors. Methods Generalized linear mixed modeling was applied for estimating teen pregnancy and sexually transmitted disease (STD) incidence by postal ZIP code in New York State, in a way that adjusts for other community covariables and residual spatial autocorrelation. A community needs index was then obtained by summing the risk-adjusted estimates of pregnancy and STD cases. Results Poisson regression with a spatial random effect was chosen among competing modeling approaches. Both the risk-adjusted caseloads and rates were computed for ZIP codes, which allowed risk-based prioritization to help guide funding decisions for a comprehensive adolescent pregnancy prevention program. Conclusions This approach provides quantitative evidence of community needs with respect to risky adolescent sexual behavior, while adjusting for other community-level variables and stabilizing estimates in areas with small populations. Therefore, it was well accepted by the affected groups and proved valuable for program planning. This methodology may also prove valuable for follow up program evaluation. Current research is directed towards further improving the statistical modeling approach and applying to different health and behavioral outcomes, along with different predictor variables.
Vock, David M.; Davidian, Marie; Tsiatis, Anastasios A.
2014-01-01
Generalized linear and nonlinear mixed models (GMMMs and NLMMs) are commonly used to represent non-Gaussian or nonlinear longitudinal or clustered data. A common assumption is that the random effects are Gaussian. However, this assumption may be unrealistic in some applications, and misspecification of the random effects density may lead to maximum likelihood parameter estimators that are inconsistent, biased, and inefficient. Because testing if the random effects are Gaussian is difficult, previous research has recommended using a flexible random effects density. However, computational limitations have precluded widespread use of flexible random effects densities for GLMMs and NLMMs. We develop a SAS macro, SNP_NLMM, that overcomes the computational challenges to fit GLMMs and NLMMs where the random effects are assumed to follow a smooth density that can be represented by the seminonparametric formulation proposed by Gallant and Nychka (1987). The macro is flexible enough to allow for any density of the response conditional on the random effects and any nonlinear mean trajectory. We demonstrate the SNP_NLMM macro on a GLMM of the disease progression of toenail infection and on a NLMM of intravenous drug concentration over time. PMID:24688453
Mendes, T M; Guimarães-Okamoto, P T C; Machado-de-Avila, R A; Oliveira, D; Melo, M M; Lobato, Z I; Kalapothakis, E; Chávez-Olórtegui, C
2015-06-01
This communication describes the general characteristics of the venom from the Brazilian scorpion Tityus fasciolatus, which is an endemic species found in the central Brazil (States of Goiás and Minas Gerais), being responsible for sting accidents in this area. The soluble venom obtained from this scorpion is toxic to mice being the LD50 is 2.984 mg/kg (subcutaneally). SDS-PAGE of the soluble venom resulted in 10 fractions ranged in size from 6 to 10-80 kDa. Sheep were employed for anti-T. fasciolatus venom serum production. Western blotting analysis showed that most of these venom proteins are immunogenic. T. fasciolatus anti-venom revealed consistent cross-reactivity with venom antigens from Tityus serrulatus. Using known primers for T. serrulatus toxins, we have identified three toxins sequences from T. fasciolatus venom. Linear epitopes of these toxins were localized and fifty-five overlapping pentadecapeptides covering complete amino acid sequence of the three toxins were synthesized in cellulose membrane (spot-synthesis technique). The epitopes were located on the 3D structures and some important residues for structure/function were identified.
Xiao, Xun; Geyer, Veikko F; Bowne-Anderson, Hugo; Howard, Jonathon; Sbalzarini, Ivo F
2016-08-01
Biological filaments, such as actin filaments, microtubules, and cilia, are often imaged using different light-microscopy techniques. Reconstructing the filament curve from the acquired images constitutes the filament segmentation problem. Since filaments have lower dimensionality than the image itself, there is an inherent trade-off between tracing the filament with sub-pixel accuracy and avoiding noise artifacts. Here, we present a globally optimal filament segmentation method based on B-spline vector level-sets and a generalized linear model for the pixel intensity statistics. We show that the resulting optimization problem is convex and can hence be solved with global optimality. We introduce a simple and efficient algorithm to compute such optimal filament segmentations, and provide an open-source implementation as an ImageJ/Fiji plugin. We further derive an information-theoretic lower bound on the filament segmentation error, quantifying how well an algorithm could possibly do given the information in the image. We show that our algorithm asymptotically reaches this bound in the spline coefficients. We validate our method in comprehensive benchmarks, compare with other methods, and show applications from fluorescence, phase-contrast, and dark-field microscopy.
Prates, Marcos O; Aseltine, Robert H; Dey, Dipak K; Yan, Jun
2013-11-01
Unhealthy alcohol use is one of the leading causes of morbidity and mortality in the United States. Brief interventions with high-risk drinkers during an emergency department (ED) visit are of great interest due to their possible efficacy and low cost. In a collaborative study with patients recruited at 14 academic ED across the United States, we examined the self-reported number of drinks per week by each patient following the exposure to a brief intervention. Count data with overdispersion have been mostly analyzed with generalized linear mixed models (GLMMs), of which only a limited number of link functions are available. Different choices of link function provide different fit and predictive power for a particular dataset. We propose a class of link functions from an alternative way to incorporate random effects in a GLMM, which encompasses many existing link functions as special cases. The methodology is naturally implemented in a Bayesian framework, with competing links selected with Bayesian model selection criteria such as the conditional predictive ordinate (CPO). In application to the ED intervention study, all models suggest that the intervention was effective in reducing the number of drinks, but some new models are found to significantly outperform the traditional model as measured by CPO. The validity of CPO in link selection is confirmed in a simulation study that shared the same characteristics as the count data from high-risk drinkers. The dataset and the source code for the best fitting model are available in Supporting Information.
NASA Astrophysics Data System (ADS)
de Souza, R. S.; Hilbe, J. M.; Buelens, B.; Riggs, J. D.; Cameron, E.; Ishida, E. E. O.; Chies-Santos, A. L.; Killedar, M.
2015-10-01
In this paper, the third in a series illustrating the power of generalized linear models (GLMs) for the astronomical community, we elucidate the potential of the class of GLMs which handles count data. The size of a galaxy's globular cluster (GC) population (NGC) is a prolonged puzzle in the astronomical literature. It falls in the category of count data analysis, yet it is usually modelled as if it were a continuous response variable. We have developed a Bayesian negative binomial regression model to study the connection between NGC and the following galaxy properties: central black hole mass, dynamical bulge mass, bulge velocity dispersion and absolute visual magnitude. The methodology introduced herein naturally accounts for heteroscedasticity, intrinsic scatter, errors in measurements in both axes (either discrete or continuous) and allows modelling the population of GCs on their natural scale as a non-negative integer variable. Prediction intervals of 99 per cent around the trend for expected NGC comfortably envelope the data, notably including the Milky Way, which has hitherto been considered a problematic outlier. Finally, we demonstrate how random intercept models can incorporate information of each particular galaxy morphological type. Bayesian variable selection methodology allows for automatically identifying galaxy types with different productions of GCs, suggesting that on average S0 galaxies have a GC population 35 per cent smaller than other types with similar brightness.
Monda, D.P.; Galat, D.L.; Finger, S.E.; Kaiser, M.S.
1995-01-01
Toxicity of un-ionized ammonia (NH3-N) to the midge, Chironomus riparius was compared, using laboratory culture (well) water and sewage effluent (≈0.4 mg/L NH3-N) in two 96-h, static-renewal toxicity experiments. A generalized linear model was used for data analysis. For the first and second experiments, respectively, LC50 values were 9.4 mg/L (Test 1A) and 6.6 mg/L (Test 2A) for ammonia in well water, and 7.8 mg/L (Test 1B) and 4.1 mg/L (Test 2B) for ammonia in sewage effluent. Slopes of dose-response curves for Tests 1A and 2A were equal, but mortality occurred at lower NH3-N concentrations in Test 2A (unequal intercepts). Response ofC. riparius to NH3 in effluent was not consistent; dose-response curves for tests 1B and 2B differed in slope and intercept. Nevertheless, C. riparius was more sensitive to ammonia in effluent than in well water in both experiments, indicating a synergistic effect of ammonia in sewage effluent. These results demonstrate the advantages of analyzing the organisms entire range of response, as opposed to generating LC50 values, which represent only one point on the dose-response curve.
Gonçalves, Nuno R; Whelan, Robert; Foxe, John J; Lalor, Edmund C
2014-08-15
Noninvasive investigation of human sensory processing with high temporal resolution typically involves repeatedly presenting discrete stimuli and extracting an average event-related response from scalp recorded neuroelectric or neuromagnetic signals. While this approach is and has been extremely useful, it suffers from two drawbacks: a lack of naturalness in terms of the stimulus and a lack of precision in terms of the cortical response generators. Here we show that a linear modeling approach that exploits functional specialization in sensory systems can be used to rapidly obtain spatiotemporally precise responses to complex sensory stimuli using electroencephalography (EEG). We demonstrate the method by example through the controlled modulation of the contrast and coherent motion of visual stimuli. Regressing the data against these modulation signals produces spatially focal, highly temporally resolved response measures that are suggestive of specific activation of visual areas V1 and V6, respectively, based on their onset latency, their topographic distribution and the estimated location of their sources. We discuss our approach by comparing it with fMRI/MRI informed source analysis methods and, in doing so, we provide novel information on the timing of coherent motion processing in human V6. Generalizing such an approach has the potential to facilitate the rapid, inexpensive spatiotemporal localization of higher perceptual functions in behaving humans.
NASA Astrophysics Data System (ADS)
Asong, Z. E.; Khaliq, M. N.; Wheater, H. S.
2016-08-01
In this study, a multisite multivariate statistical downscaling approach based on the Generalized Linear Model (GLM) framework is developed to downscale daily observations of precipitation and minimum and maximum temperatures from 120 sites located across the Canadian Prairie Provinces: Alberta, Saskatchewan and Manitoba. First, large scale atmospheric covariates from the National Center for Environmental Prediction (NCEP) Reanalysis-I, teleconnection indices, geographical site attributes, and observed precipitation and temperature records are used to calibrate GLMs for the 1971-2000 period. Then the calibrated models are used to generate daily sequences of precipitation and temperature for the 1962-2005 historical (conditioned on NCEP predictors), and future period (2006-2100) using outputs from five CMIP5 (Coupled Model Intercomparison Project Phase-5) Earth System Models corresponding to Representative Concentration Pathway (RCP): RCP2.6, RCP4.5, and RCP8.5 scenarios. The results indicate that the fitted GLMs are able to capture spatiotemporal characteristics of observed precipitation and temperature fields. According to the downscaled future climate, mean precipitation is projected to increase in summer and decrease in winter while minimum temperature is expected to warm faster than the maximum temperature. Climate extremes are projected to intensify with increased radiative forcing.
Wang, Pengwei; Wang, Zhishun; He, Lianghua
2012-03-30
Functional Magnetic Resonance Imaging (fMRI), measuring Blood Oxygen Level-Dependent (BOLD), is a widely used tool to reveal spatiotemporal pattern of neural activity in human brain. Standard analysis of fMRI data relies on a general linear model and the model is constructed by convolving the task stimuli with a hypothesized hemodynamic response function (HRF). To capture possible phase shifts in the observed BOLD response, the informed basis functions including canonical HRF and its temporal derivative, have been proposed to extend the hypothesized hemodynamic response in order to obtain a good fitting model. Different t contrasts are constructed from the estimated model parameters for detecting the neural activity between different task conditions. However, the estimated model parameters corresponding to the orthogonal basis functions have different physical meanings. It remains unclear how to combine the neural features detected by the two basis functions and construct t contrasts for further analyses. In this paper, we have proposed a novel method for representing multiple basis functions in complex domain to model the task-driven fMRI data. Using this method, we can treat each pair of model parameters, corresponding respectively to canonical HRF and its temporal derivative, as one complex number for each task condition. Using the specific rule we have defined, we can conveniently perform arithmetical operations on the estimated model parameters and generate different t contrasts. We validate this method using the fMRI data acquired from twenty-two healthy participants who underwent an auditory stimulation task.
Tian, Fenghua; Liu, Hanli
2014-01-15
One of the main challenges in functional diffuse optical tomography (DOT) is to accurately recover the depth of brain activation, which is even more essential when differentiating true brain signals from task-evoked artifacts in the scalp. Recently, we developed a depth-compensated algorithm (DCA) to minimize the depth localization error in DOT. However, the semi-infinite model that was used in DCA deviated significantly from the realistic human head anatomy. In the present work, we incorporated depth-compensated DOT (DC-DOT) with a standard anatomical atlas of human head. Computer simulations and human measurements of sensorimotor activation were conducted to examine and prove the depth specificity and quantification accuracy of brain atlas-based DC-DOT. In addition, node-wise statistical analysis based on the general linear model (GLM) was also implemented and performed in this study, showing the robustness of DC-DOT that can accurately identify brain activation at the correct depth for functional brain imaging, even when co-existing with superficial artifacts.
Learn Sparse Dictionaries for Edit Propagation.
Xiaowu Chen; Jianwei Li; Dongqing Zou; Qinping Zhao
2016-04-01
With the increasing availability of high-resolution images, videos, and 3D models, the demand for scalable large data processing techniques increases. We introduce a method of sparse dictionary learning for edit propagation of large input data. Previous approaches for edit propagation typically employ a global optimization over the whole set of pixels (or vertexes), incurring a prohibitively high memory and time-consumption for large input data. Rather than propagating an edit pixel by pixel, we follow the principle of sparse representation to obtain a representative and compact dictionary and perform edit propagation on the dictionary instead. The sparse dictionary provides an intrinsic basis for input data, and the coding coefficients capture the linear relationship between all pixels and the dictionary atoms. The learned dictionary is then optimized by a novel scheme, which maximizes the Kullback-Leibler divergence between each atom pair to remove redundant atoms. To enable local edit propagation for images or videos with similar appearance, a dictionary learning strategy is proposed by considering range constraint to better account for the global distribution of pixels in their feature space. We show several applications of the sparsity-based edit propagation, including video recoloring, theme editing, and seamless cloning, operating on both color and texture features. Our approach can also be applied to computer graphics tasks, such as 3D surface deformation. We demonstrate that with an atom-to-pixel ratio in the order of 0.01% signifying a significant reduction on memory consumption, our method still maintains a high degree of visual fidelity.
Joint sparse representation for robust multimodal biometrics recognition.
Shekhar, Sumit; Patel, Vishal M; Nasrabadi, Nasser M; Chellappa, Rama
2014-01-01
Traditional biometric recognition systems rely on a single biometric signature for authentication. While the advantage of using multiple sources of information for establishing the identity has been widely recognized, computational models for multimodal biometrics recognition have only recently received attention. We propose a multimodal sparse representation method, which represents the test data by a sparse linear combination of training data, while constraining the observations from different modalities of the test subject to share their sparse representations. Thus, we simultaneously take into account correlations as well as coupling information among biometric modalities. A multimodal quality measure is also proposed to weigh each modality as it gets fused. Furthermore, we also kernelize the algorithm to handle nonlinearity in data. The optimization problem is solved using an efficient alternative direction method. Various experiments show that the proposed method compares favorably with competing fusion-based methods.
Sparse and powerful cortical spikes.
Wolfe, Jason; Houweling, Arthur R; Brecht, Michael
2010-06-01
Activity in cortical networks is heterogeneous, sparse and often precisely timed. The functional significance of sparseness and precise spike timing is debated, but our understanding of the developmental and synaptic mechanisms that shape neuronal discharge patterns has improved. Evidence for highly specialized, selective and abstract cortical response properties is accumulating. Singe-cell stimulation experiments demonstrate a high sensitivity of cortical networks to the action potentials of some, but not all, single neurons. It is unclear how this sensitivity of cortical networks to small perturbations comes about and whether it is a generic property of cortex. The unforeseen sensitivity to cortical spikes puts serious constraints on the nature of neural coding schemes.
NASA Astrophysics Data System (ADS)
Guo, Yang; Sivalingam, Kantharuban; Valeev, Edward F.; Neese, Frank
2016-03-01
Multi-reference (MR) electronic structure methods, such as MR configuration interaction or MR perturbation theory, can provide reliable energies and properties for many molecular phenomena like bond breaking, excited states, transition states or magnetic properties of transition metal complexes and clusters. However, owing to their inherent complexity, most MR methods are still too computationally expensive for large systems. Therefore the development of more computationally attractive MR approaches is necessary to enable routine application for large-scale chemical systems. Among the state-of-the-art MR methods, second-order N-electron valence state perturbation theory (NEVPT2) is an efficient, size-consistent, and intruder-state-free method. However, there are still two important bottlenecks in practical applications of NEVPT2 to large systems: (a) the high computational cost of NEVPT2 for large molecules, even with moderate active spaces and (b) the prohibitive cost for treating large active spaces. In this work, we address problem (a) by developing a linear scaling "partially contracted" NEVPT2 method. This development uses the idea of domain-based local pair natural orbitals (DLPNOs) to form a highly efficient algorithm. As shown previously in the framework of single-reference methods, the DLPNO concept leads to an enormous reduction in computational effort while at the same time providing high accuracy (approaching 99.9% of the correlation energy), robustness, and black-box character. In the DLPNO approach, the virtual space is spanned by pair natural orbitals that are expanded in terms of projected atomic orbitals in large orbital domains, while the inactive space is spanned by localized orbitals. The active orbitals are left untouched. Our implementation features a highly efficient "electron pair prescreening" that skips the negligible inactive pairs. The surviving pairs are treated using the partially contracted NEVPT2 formalism. A detailed comparison
Guo, Yang; Sivalingam, Kantharuban; Valeev, Edward F; Neese, Frank
2016-03-07
Multi-reference (MR) electronic structure methods, such as MR configuration interaction or MR perturbation theory, can provide reliable energies and properties for many molecular phenomena like bond breaking, excited states, transition states or magnetic properties of transition metal complexes and clusters. However, owing to their inherent complexity, most MR methods are still too computationally expensive for large systems. Therefore the development of more computationally attractive MR approaches is necessary to enable routine application for large-scale chemical systems. Among the state-of-the-art MR methods, second-order N-electron valence state perturbation theory (NEVPT2) is an efficient, size-consistent, and intruder-state-free method. However, there are still two important bottlenecks in practical applications of NEVPT2 to large systems: (a) the high computational cost of NEVPT2 for large molecules, even with moderate active spaces and (b) the prohibitive cost for treating large active spaces. In this work, we address problem (a) by developing a linear scaling "partially contracted" NEVPT2 method. This development uses the idea of domain-based local pair natural orbitals (DLPNOs) to form a highly efficient algorithm. As shown previously in the framework of single-reference methods, the DLPNO concept leads to an enormous reduction in computational effort while at the same time providing high accuracy (approaching 99.9% of the correlation energy), robustness, and black-box character. In the DLPNO approach, the virtual space is spanned by pair natural orbitals that are expanded in terms of projected atomic orbitals in large orbital domains, while the inactive space is spanned by localized orbitals. The active orbitals are left untouched. Our implementation features a highly efficient "electron pair prescreening" that skips the negligible inactive pairs. The surviving pairs are treated using the partially contracted NEVPT2 formalism. A detailed comparison
NASA Astrophysics Data System (ADS)
Gutiérrez Frez, Luis; Pantoja, José
2015-09-01
We construct a complex linear Weil representation ρ of the generalized special linear group G={SL}_*^{1}(2,A_n) (A_n=K[x]/< x^nrangle , K the quadratic extension of the finite field k of q elements, q odd), where A_n is endowed with a second class involution. After the construction of a specific data, the representation is defined on the generators of a Bruhat presentation of G, via linear operators satisfying the relations of the presentation. The structure of a unitary group U associated to G is described. Using this group we obtain a first decomposition of ρ.
A sparse matrix based full-configuration interaction algorithm.
Rolik, Zoltán; Szabados, Agnes; Surján, Péter R
2008-04-14
We present an algorithm related to the full-configuration interaction (FCI) method that makes complete use of the sparse nature of the coefficient vector representing the many-electron wave function in a determinantal basis. Main achievements of the presented sparse FCI (SFCI) algorithm are (i) development of an iteration procedure that avoids the storage of FCI size vectors; (ii) development of an efficient algorithm to evaluate the effect of the Hamiltonian when both the initial and the product vectors are sparse. As a result of point (i) large disk operations can be skipped which otherwise may be a bottleneck of the procedure. At point (ii) we progress by adopting the implementation of the linear transformation by Olsen et al. [J. Chem Phys. 89, 2185 (1988)] for the sparse case, getting the algorithm applicable to larger systems and faster at the same time. The error of a SFCI calculation depends only on the dropout thresholds for the sparse vectors, and can be tuned by controlling the amount of system memory passed to the procedure. The algorithm permits to perform FCI calculations on single node workstations for systems previously accessible only by supercomputers.
2010-01-01
Background Near-infrared spectroscopy (NIRS) is a non-invasive neuroimaging technique that recently has been developed to measure the changes of cerebral blood oxygenation associated with brain activities. To date, for functional brain mapping applications, there is no standard on-line method for analysing NIRS data. Methods In this paper, a novel on-line NIRS data analysis framework taking advantages of both the general linear model (GLM) and the Kalman estimator is devised. The Kalman estimator is used to update the GLM coefficients recursively, and one critical coefficient regarding brain activities is then passed to a t-statistical test. The t-statistical test result is used to update a topographic brain activation map. Meanwhile, a set of high-pass filters is plugged into the GLM to prevent very low-frequency noises, and an autoregressive (AR) model is used to prevent the temporal correlation caused by physiological noises in NIRS time series. A set of data recorded in finger tapping experiments is studied using the proposed framework. Results The obtained results suggest that the method can effectively track the task related brain activation areas, and prevent the noise distortion in the estimation while the experiment is running. Thereby, the potential of the proposed method for real-time NIRS-based brain imaging was demonstrated. Conclusions This paper presents a novel on-line approach for analysing NIRS data for functional brain mapping applications. This approach demonstrates the potential of a real-time-updating topographic brain activation map. PMID:21138595
NASA Astrophysics Data System (ADS)
Kim, Y.; Katz, R. W.; Rajagopalan, B.; Podesta, G. P.
2009-12-01
Climate forecasts and climate change scenarios are typically provided in the form of monthly or seasonally aggregated totals or means. But time series of daily weather (e.g., precipitation amount, minimum and maximum temperature) are commonly required for use in agricultural decision-making. Stochastic weather generators constitute one technique to temporally downscale such climate information. The recently introduced approach for stochastic weather generators, based generalized linear modeling (GLM), is convenient for this purpose, especially with covariates to account for seasonality and teleconnections (e.g., with the El Niño phenomenon). Yet one important limitation of stochastic weather generators is a marked tendency to underestimate the observed interannual variance of seasonally aggregated variables. To reduce this “overdispersion” phenomenon, we incorporate time series of seasonal total precipitation and seasonal mean minimum and maximum temperature in the GLM weather generator as covariates. These seasonal time series are smoothed using locally weighted scatterplot smoothing (LOESS) to avoid introducing underdispersion. Because the aggregate variables appear explicitly in the weather generator, downscaling to daily sequences can be readily implemented. The proposed method is applied to time series of daily weather at Pergamino and Pilar in the Argentine Pampas. Seasonal precipitation and temperature forecasts produced by the International Research Institute for Climate and Society (IRI) are used as prototypes. In conjunction with the GLM weather generator, a resampling scheme is used to translate the uncertainty in the seasonal forecasts (the IRI format only specifies probabilities for three categories: below normal, near normal, and above normal) into the corresponding uncertainty for the daily weather statistics. The method is able to generate potentially useful shifts in the probability distributions of seasonally aggregated precipitation and
NASA Astrophysics Data System (ADS)
Widyaningsih, Yekti; Saefuddin, Asep; Notodiputro, Khairil A.; Wigena, Aji H.
2012-05-01
The objective of this research is to build a nested generalized linear mixed model using an ordinal response variable with some covariates. There are three main jobs in this paper, i.e. parameters estimation procedure, simulation, and implementation of the model for the real data. At the part of parameters estimation procedure, concepts of threshold, nested random effect, and computational algorithm are described. The simulations data are built for 3 conditions to know the effect of different parameter values of random effect distributions. The last job is the implementation of the model for the data about poverty in 9 districts of Java Island. The districts are Kuningan, Karawang, and Majalengka chose randomly in West Java; Temanggung, Boyolali, and Cilacap from Central Java; and Blitar, Ngawi, and Jember from East Java. The covariates in this model are province, number of bad nutrition cases, number of farmer families, and number of health personnel. In this modeling, all covariates are grouped as ordinal scale. Unit observation in this research is sub-district (kecamatan) nested in district, and districts (kabupaten) are nested in province. For the result of simulation, ARB (Absolute Relative Bias) and RRMSE (Relative Root of mean square errors) scale is used. They show that prov parameters have the highest bias, but more stable RRMSE in all conditions. The simulation design needs to be improved by adding other condition, such as higher correlation between covariates. Furthermore, as the result of the model implementation for the data, only number of farmer family and number of medical personnel have significant contributions to the level of poverty in Central Java and East Java province, and only district 2 (Karawang) of province 1 (West Java) has different random effect from the others. The source of the data is PODES (Potensi Desa) 2008 from BPS (Badan Pusat Statistik).
Sparse Identification of Nonlinear Dynamics (SINDy)
NASA Astrophysics Data System (ADS)
Brunton, Steven; Proctor, Joshua; Kutz, Nathan
2016-11-01
This work develops a general new framework to discover the governing equations underlying a dynamical system simply from data measurements, leveraging advances in sparsity techniques and machine learning. The so-called sparse identification of nonlinear dynamics (SINDy) method results in models that are parsimonious, balancing model complexity with descriptive ability while avoiding over fitting. The only assumption about the structure of the model is that there are only a few important terms that govern the dynamics, so that the equations are sparse in the space of possible functions; this assumption holds for many physical systems in an appropriate basis. We demonstrate the algorithm on a wide range of problems, from simple canonical systems, including the chaotic Lorenz system, to the canonical fluid vortex shedding behind an circular cylinder at Re=100. We also show that this method generalizes to parameterized systems and systems that are time-varying or have external forcing. With abundant data and elusive laws, data-driven discovery of dynamics will continue to play an increasingly important role in the characterization and control of fluid dynamics.
Blind source separation by sparse decomposition
NASA Astrophysics Data System (ADS)
Zibulevsky, Michael; Pearlmutter, Barak A.
2000-04-01
The blind source separation problem is to extract the underlying source signals from a set of their linear mixtures, where the mixing matrix is unknown. This situation is common, eg in acoustics, radio, and medical signal processing. We exploit the property of the sources to have a sparse representation in a corresponding signal dictionary. Such a dictionary may consist of wavelets, wavelet packets, etc., or be obtained by learning from a given family of signals. Starting from the maximum a posteriori framework, which is applicable to the case of more sources than mixtures, we derive a few other categories of objective functions, which provide faster and more robust computations, when there are an equal number of sources and mixtures. Our experiments with artificial signals and with musical sounds demonstrate significantly better separation than other known techniques.
Sparse, Decorrelated Odor Coding in the Mushroom Body Enhances Learned Odor Discrimination
Lin, Andrew C.; Bygrave, Alexei; de Calignon, Alix; Lee, Tzumin; Miesenböck, Gero
2014-01-01
Summary Sparse coding may be a general strategy of neural systems to augment memory capacity. In Drosophila, sparse odor coding by the Kenyon cells of the mushroom body is thought to generate a large number of precisely addressable locations for the storage of odor-specific memories. However, it remains untested how sparse coding relates to behavioral performance. Here we demonstrate that sparseness is controlled by a negative feedback circuit between Kenyon cells and the GABAergic anterior paired lateral (APL) neuron. Systematic activation and blockade of each leg of this feedback circuit show that Kenyon cells activate APL and APL inhibits Kenyon cells. Disrupting the Kenyon cell-APL feedback loop decreases the sparseness of Kenyon cell odor responses, increases inter-odor correlations, and prevents flies from learning to discriminate similar, but not dissimilar, odors. These results suggest that feedback inhibition suppresses Kenyon cell activity to maintain sparse, decorrelated odor coding and thus the odor-specificity of memories. PMID:24561998
Space-Time Approximation with Sparse Grids
Griebel, M; Oeltz, D; Vassilevski, P S
2005-04-14
In this article we introduce approximation spaces for parabolic problems which are based on the tensor product construction of a multiscale basis in space and a multiscale basis in time. Proper truncation then leads to so-called space-time sparse grid spaces. For a uniform discretization of the spatial space of dimension d with O(N{sup d}) degrees of freedom, these spaces involve for d > 1 also only O(N{sup d}) degrees of freedom for the discretization of the whole space-time problem. But they provide the same approximation rate as classical space-time Finite Element spaces which need O(N{sup d+1}) degrees of freedoms. This makes these approximation spaces well suited for conventional parabolic and for time-dependent optimization problems. We analyze the approximation properties and the dimension of these sparse grid space-time spaces for general stable multiscale bases. We then restrict ourselves to an interpolatory multiscale basis, i.e. a hierarchical basis. Here, to be able to handle also complicated spatial domains {Omega}, we construct the hierarchical basis from a given spatial Finite Element basis as follows: First we determine coarse grid points recursively over the levels by the coarsening step of the algebraic multigrid method. Then, we derive interpolatory prolongation operators between the respective coarse and fine grid points by a least squares approach. This way we obtain an algebraic hierarchical basis for the spatial domain which we then use in our space-time sparse grid approach. We give numerical results on the convergence rate of the interpolation error of these spaces for various space-time problems with two spatial dimensions. Also implementational issues, data structures and questions of adaptivity are addressed to some extent.
ERIC Educational Resources Information Center
Chen, Haiwen
2012-01-01
In this article, linear item response theory (IRT) observed-score equating is compared under a generalized kernel equating framework with Levine observed-score equating for nonequivalent groups with anchor test design. Interestingly, these two equating methods are closely related despite being based on different methodologies. Specifically, when…
ERIC Educational Resources Information Center
Bashaw, W. L., Ed.; Findley, Warren G., Ed.
This volume contains the five major addresses and subsequent discussion from the Symposium on the General Linear Models Approach to the Analysis of Experimental Data in Educational Research, which was held in 1967 in Athens, Georgia. The symposium was designed to produce systematic information, including new methodology, for dissemination to the…
ERIC Educational Resources Information Center
Dimitrov, Dimiter M.; Raykov, Tenko; AL-Qataee, Abdullah Ali
2015-01-01
This article is concerned with developing a measure of general academic ability (GAA) for high school graduates who apply to colleges, as well as with the identification of optimal weights of the GAA indicators in a linear combination that yields a composite score with maximal reliability and maximal predictive validity, employing the framework of…
Stable Restoration and Separation of Approximately Sparse Signals
2011-07-02
dictionary. Particular applications covered by our framework include the restoration of signals impaired by impulse noise , narrowband interference, or...representation in a second general dictionary. Particular applications covered by our framework include the restoration of signals impaired by impulse noise ...applications (see [1–17] and references therein), including: • Impulse noise : The recovery of approximately sparse signals corrupted by impulse noise [13
A General Family of Limited Information Goodness-of-Fit Statistics for Multinomial Data
ERIC Educational Resources Information Center
Joe, Harry; Maydeu-Olivares, Alberto
2010-01-01
Maydeu-Olivares and Joe (J. Am. Stat. Assoc. 100:1009-1020, "2005"; Psychometrika 71:713-732, "2006") introduced classes of chi-square tests for (sparse) multidimensional multinomial data based on low-order marginal proportions. Our extension provides general conditions under which quadratic forms in linear functions of cell residuals are…
An evaluation of GPU acceleration for sparse reconstruction
NASA Astrophysics Data System (ADS)
Braun, Thomas R.
2010-04-01
Image processing applications typically parallelize well. This gives a developer interested in data throughput several different implementation options, including multiprocessor machines, general purpose computation on the graphics processor, and custom gate-array designs. Herein, we will investigate these first two options for dictionary learning and sparse reconstruction, specifically focusing on the K-SVD algorithm for dictionary learning and the Batch Orthogonal Matching Pursuit for sparse reconstruction. These methods have been shown to provide state of the art results for image denoising, classification, and object recognition. We'll explore the GPU implementation and show that GPUs are not significantly better or worse than CPUs for this application.
Guided wavefield reconstruction from sparse measurements
NASA Astrophysics Data System (ADS)
Mesnil, Olivier; Ruzzene, Massimo
2016-02-01
Guided wave measurements are at the basis of several Non-Destructive Evaluation (NDE) techniques. Although sparse measurements of guided wave obtained using piezoelectric sensors can efficiently detect and locate defects, extensive informa-tion on the shape and subsurface location of defects can be extracted from full-field measurements acquired by Laser Doppler Vibrometers (LDV). Wavefield acquisition from LDVs is generally a slow operation due to the fact that the wave propagation to record must be repeated for each point measurement and the initial conditions must be reached between each measurement. In this research, a Sparse Wavefield Reconstruction (SWR) process using Compressed Sensing is developed. The goal of this technique is to reduce the number of point measurements needed to apply NDE techniques by at least one order of magnitude by extrapolating the knowledge of a few randomly chosen measured pixels over an over-sampled grid. To achieve this, the Lamb wave propagation equation is used to formulate a basis of shape functions in which the wavefield has a sparse representation, in order to comply with the Compressed Sensing requirements and use l1-minimization solvers. The main assumption of this reconstruction process is that every material point of the studied area is a potential source. The Compressed Sensing matrix is defined as being the contribution that would have been received at a measurement location from each possible source, using the dispersion relations of the specimen computed using a Semi-Analytical Finite Element technique. The measurements are then processed through an l1-minimizer to find a minimum corresponding to the set of active sources and their corresponding excitation functions. This minimum represents the best combination of the parameters of the model matching the sparse measurements. Wavefields are then reconstructed using the propagation equation. The set of active sources found by minimization contains all the wave
Image fusion via nonlocal sparse K-SVD dictionary learning.
Li, Ying; Li, Fangyi; Bai, Bendu; Shen, Qiang
2016-03-01
Image fusion aims to merge two or more images captured via various sensors of the same scene to construct a more informative image by integrating their details. Generally, such integration is achieved through the manipulation of the representations of the images concerned. Sparse representation plays an important role in the effective description of images, offering a great potential in a variety of image processing tasks, including image fusion. Supported by sparse representation, in this paper, an approach for image fusion by the use of a novel dictionary learning scheme is proposed. The nonlocal self-similarity property of the images is exploited, not only at the stage of learning the underlying description dictionary but during the process of image fusion. In particular, the property of nonlocal self-similarity is combined with the traditional sparse dictionary. This results in an improved learned dictionary, hereafter referred to as the nonlocal sparse K-SVD dictionary (where K-SVD stands for the K times singular value decomposition that is commonly used in the literature), and abbreviated to NL_SK_SVD. The performance of the NL_SK_SVD dictionary is applied for image fusion using simultaneous orthogonal matching pursuit. The proposed approach is evaluated with different types of images, and compared with a number of alternative image fusion techniques. The resultant superior fused images using the present approach demonstrates the efficacy of the NL_SK_SVD dictionary in sparse image representation.
Bayesian Learning in Sparse Graphical Factor Models via Variational Mean-Field Annealing.
Yoshida, Ryo; West, Mike
2010-05-01
We describe a class of sparse latent factor models, called graphical factor models (GFMs), and relevant sparse learning algorithms for posterior mode estimation. Linear, Gaussian GFMs have sparse, orthogonal factor loadings matrices, that, in addition to sparsity of the implied covariance matrices, also induce conditional independence structures via zeros in the implied precision matrices. We describe the models and their use for robust estimation of sparse latent factor structure and data/signal reconstruction. We develop computational algorithms for model exploration and posterior mode search, addressing the hard combinatorial optimization involved in the search over a huge space of potential sparse configurations. A mean-field variational technique coupled with annealing is developed to successively generate "artificial" posterior distributions that, at the limiting temperature in the annealing schedule, define required posterior modes in the GFM parameter space. Several detailed empirical studies and comparisons to related approaches are discussed, including analyses of handwritten digit image and cancer gene expression data.
Technical note: A significance test for data-sparse zones in scatter plots
NASA Astrophysics Data System (ADS)
Vetrova, V. V.; Bardsley, W. E.
2012-04-01
Data-sparse zones in scatter plots of hydrological variables can be of interest in various contexts. For example, a well-defined data-sparse zone may indicate inhibition of one variable by another. It is of interest therefore to determine whether data-sparse regions in scatter plots are of sufficient extent to be beyond random chance. We consider the specific situation of data-sparse regions defined by a linear internal boundary within a scatter plot defined over a rectangular region. An Excel VBA macro is provided for carrying out a randomisation-based significance test of the data-sparse region, taking into account both the within-region number of data points and the extent of the region. Example applications are given with respect to a rainfall time series from Israel and also to validation scatter plots from a seasonal forecasting model for lake inflows in New Zealand.
Technical Note: A significance test for data-sparse zones in scatter plots
NASA Astrophysics Data System (ADS)
Vetrova, V. V.; Bardsley, W. E.
2012-01-01
Data-sparse zones in scatter plots of hydrological variables can be of interest in various contexts. For example, a well-defined data-sparse zone may indicate inhibition of one variable by another. It is of interest therefore to determine whether data-sparse regions in scatter plots are of sufficient extent to be beyond random chance. We consider the specific situation of data-sparse regions defined by a linear internal boundary within a scatter plot defined over a rectangular region. An Excel VBA macro is provided for carrying out a randomisation-based significance test of the data-sparse region, taking into account both the within-region number of data points and the extent of the region. Example applications are given with respect to a rainfall time series from Israel and to validation scatter plots from a seasonal forecasting model for lake inflows in New Zealand.
Neonatal atlas construction using sparse representation.
Shi, Feng; Wang, Li; Wu, Guorong; Li, Gang; Gilmore, John H; Lin, Weili; Shen, Dinggang
2014-09-01
Atlas construction generally includes first an image registration step to normalize all images into a common space and then an atlas building step to fuse the information from all the aligned images. Although numerous atlas construction studies have been performed to improve the accuracy of the image registration step, unweighted or simply weighted average is often used in the atlas building step. In this article, we propose a novel patch-based sparse representation method for atlas construction after all images have been registered into the common space. By taking advantage of local sparse representation, more anatomical details can be recovered in the built atlas. To make the anatomical structures spatially smooth in the atlas, the anatomical feature constraints on group structure of representations and also the overlapping of neighboring patches are imposed to ensure the anatomical consistency between neighboring patches. The proposed method has been applied to 73 neonatal MR images with poor spatial resolution and low tissue contrast, for constructing a neonatal brain atlas with sharp anatomical details. Experimental results demonstrate that the proposed method can significantly enhance the quality of the constructed atlas by discovering more anatomical details especially in the highly convoluted cortical regions. The resulting atlas demonstrates superior performance of our atlas when applied to spatially normalizing three different neonatal datasets, compared with other start-of-the-art neonatal brain atlases.
Protein family classification using sparse markov transducers.
Eskin, Eleazar; Noble, William Stafford; Singer, Yoram
2003-01-01
We present a method for classifying proteins into families based on short subsequences of amino acids using a new probabilistic model called sparse Markov transducers (SMT). We classify a protein by estimating probability distributions over subsequences of amino acids from the protein. Sparse Markov transducers, similar to probabilistic suffix trees, estimate a probability distribution conditioned on an input sequence. SMTs generalize probabilistic suffix trees by allowing for wild-cards in the conditioning sequences. Since substitutions of amino acids are common in protein families, incorporating wild-cards into the model significantly improves classification performance. We present two models for building protein family classifiers using SMTs. As protein databases become larger, data driven learning algorithms for probabilistic models such as SMTs will require vast amounts of memory. We therefore describe and use efficient data structures to improve the memory usage of SMTs. We evaluate SMTs by building protein family classifiers using the Pfam and SCOP databases and compare our results to previously published results and state-of-the-art protein homology detection methods. SMTs outperform previous probabilistic suffix tree methods and under certain conditions perform comparably to state-of-the-art protein homology methods.
Double shrinking sparse dimension reduction.
Zhou, Tianyi; Tao, Dacheng
2013-01-01
Learning tasks such as classification and clustering usually perform better and cost less (time and space) on compressed representations than on the original data. Previous works mainly compress data via dimension reduction. In this paper, we propose "double shrinking" to compress image data on both dimensionality and cardinality via building either sparse low-dimensional representations or a sparse projection matrix for dimension reduction. We formulate a double shrinking model (DSM) as an l(1) regularized variance maximization with constraint ||x||(2)=1, and develop a double shrinking algorithm (DSA) to optimize DSM. DSA is a path-following algorithm that can build the whole solution path of locally optimal solutions of different sparse levels. Each solution on the path is a "warm start" for searching the next sparser one. In each iteration of DSA, the direction, the step size, and the Lagrangian multiplier are deduced from the Karush-Kuhn-Tucker conditions. The magnitudes of trivial variables are shrunk and the importances of critical variables are simultaneously augmented along the selected direction with the determined step length. Double shrinking can be applied to manifold learning and feature selections for better interpretation of features, and can be combined with classification and clustering to boost their performance. The experimental results suggest that double shrinking produces efficient and effective data compression.
Highly parallel sparse Cholesky factorization
NASA Technical Reports Server (NTRS)
Gilbert, John R.; Schreiber, Robert
1990-01-01
Several fine grained parallel algorithms were developed and compared to compute the Cholesky factorization of a sparse matrix. The experimental implementations are on the Connection Machine, a distributed memory SIMD machine whose programming model conceptually supplies one processor per data element. In contrast to special purpose algorithms in which the matrix structure conforms to the connection structure of the machine, the focus is on matrices with arbitrary sparsity structure. The most promising algorithm is one whose inner loop performs several dense factorizations simultaneously on a 2-D grid of processors. Virtually any massively parallel dense factorization algorithm can be used as the key subroutine. The sparse code attains execution rates comparable to those of the dense subroutine. Although at present architectural limitations prevent the dense factorization from realizing its potential efficiency, it is concluded that a regular data parallel architecture can be used efficiently to solve arbitrarily structured sparse problems. A performance model is also presented and it is used to analyze the algorithms.
Sparse Matrices in MATLAB: Design and Implementation
NASA Technical Reports Server (NTRS)
Gilbert, John R.; Moler, Cleve; Schreiber, Robert
1992-01-01
The matrix computation language and environment MATLAB is extended to include sparse matrix storage and operations. The only change to the outward appearance of the MATLAB language is a pair of commands to create full or sparse matrices. Nearly all the operations of MATLAB now apply equally to full or sparse matrices, without any explicit action by the user. The sparse data structure represents a matrix in space proportional to the number of nonzero entries, and most of the operations compute sparse results in time proportional to the number of arithmetic operations on nonzeros.
Lewis, Robert Michael (College of William and Mary, Williamsburg, VA); Torczon, Virginia Joanne (College of William and Mary, Williamsburg, VA); Kolda, Tamara Gibson
2006-08-01
We consider the solution of nonlinear programs in the case where derivatives of the objective function and nonlinear constraints are unavailable. To solve such problems, we propose an adaptation of a method due to Conn, Gould, Sartenaer, and Toint that proceeds by approximately minimizing a succession of linearly constrained augmented Lagrangians. Our modification is to use a derivative-free generating set direct search algorithm to solve the linearly constrained subproblems. The stopping criterion proposed by Conn, Gould, Sartenaer and Toint for the approximate solution of the subproblems requires explicit knowledge of derivatives. Such information is presumed absent in the generating set search method we employ. Instead, we show that stationarity results for linearly constrained generating set search methods provide a derivative-free stopping criterion, based on a step-length control parameter, that is sufficient to preserve the convergence properties of the original augmented Lagrangian algorithm.
Cadmium-hazard mapping using a general linear regression model (Irr-Cad) for rapid risk assessment.
Simmons, Robert W; Noble, Andrew D; Pongsakul, P; Sukreeyapongse, O; Chinabut, N
2009-02-01
Research undertaken over the last 40 years has identified the irrefutable relationship between the long-term consumption of cadmium (Cd)-contaminated rice and human Cd disease. In order to protect public health and livelihood security, the ability to accurately and rapidly determine spatial Cd contamination is of high priority. During 2001-2004, a General Linear Regression Model Irr-Cad was developed to predict the spatial distribution of soil Cd in a Cd/Zn co-contaminated cascading irrigated rice-based system in Mae Sot District, Tak Province, Thailand (Longitude E 98 degrees 59'-E 98 degrees 63' and Latitude N 16 degrees 67'-16 degrees 66'). The results indicate that Irr-Cad accounted for 98% of the variance in mean Field Order total soil Cd. Preliminary validation indicated that Irr-Cad 'predicted' mean Field Order total soil Cd, was significantly (p < 0.001) correlated (R (2) = 0.92) with 'observed' mean Field Order total soil Cd values. Field Order is determined by a given field's proximity to primary outlets from in-field irrigation channels and subsequent inter-field irrigation flows. This in turn determines Field Order in Irrigation Sequence (Field Order(IS)). Mean Field Order total soil Cd represents the mean total soil Cd (aqua regia-digested) for a given Field Order(IS). In 2004-2005, Irr-Cad was utilized to evaluate the spatial distribution of total soil Cd in a 'high-risk' area of Mae Sot District. Secondary validation on six randomly selected field groups verified that Irr-Cad predicted mean Field Order total soil Cd and was significantly (p < 0.001) correlated with the observed mean Field Order total soil Cd with R (2) values ranging from 0.89 to 0.97. The practical applicability of Irr-Cad is in its minimal input requirements, namely the classification of fields in terms of Field Order(IS), strategic sampling of all primary fields and laboratory based determination of total soil Cd (T-Cd(P)) and the use of a weighed coefficient for Cd (Coeff
Computational Methods for Sparse Solution of Linear Inverse Problems
2009-03-01
methods from harmonic analysis [5]. For example, natural images can be approximated with relatively few wavelet coefficients. As a consequence, in many...performed efficiently. For example, the cost of these products is O(N logN) when Φ is constructed from Fourier or wavelet bases. For algorithms that...stream community has proposed efficient algorithms for computing near-optimal histograms and wavelet -packet approximations from compressive samples [4
Evaluating Sparse Linear System Solvers on Scalable Parallel Architectures
2008-10-01
iterations will be necessary to assure sufficient accuracy whenever we do not use a direct method to solve (1.3) or (1.5). The overall SPIKE algorithm...boosting is activated, SPIKE is not used as a direct solver but rather as a preconditioner. In this case outer iterations via a Krylov subspace method ...robustness. Preconditioning aims to improve the robustness of iterative methods by transforming the system into M−1Ax = M−1f, or AM−1(Mx) = f. (3.2
Suppression of Doppler Ambiguities for Linear Sparse Arrays
2006-04-01
06, Verona NY. Government Purpose Rights 14. ABSTRACT A key trade-off in airborne or spaceborne synthetic aperture radar (SAR) design involves the...trade-off in airborne or spaceborne synthetic aperture radar (SAR) design involves the pulse repetition frequency (PRF) and the number and location of...optimal weight application and without (i.e., using uniform weights). Also, MC-type results are shown for two key synthetic aperture radar (SAR
Sparse coding based feature representation method for remote sensing images
NASA Astrophysics Data System (ADS)
Oguslu, Ender
In this dissertation, we study sparse coding based feature representation method for the classification of multispectral and hyperspectral images (HSI). The existing feature representation systems based on the sparse signal model are computationally expensive, requiring to solve a convex optimization problem to learn a dictionary. A sparse coding feature representation framework for the classification of HSI is presented that alleviates the complexity of sparse coding through sub-band construction, dictionary learning, and encoding steps. In the framework, we construct the dictionary based upon the extracted sub-bands from the spectral representation of a pixel. In the encoding step, we utilize a soft threshold function to obtain sparse feature representations for HSI. Experimental results showed that a randomly selected dictionary could be as effective as a dictionary learned from optimization. The new representation usually has a very high dimensionality requiring a lot of computational resources. In addition, the spatial information of the HSI data has not been included in the representation. Thus, we modify the framework by incorporating the spatial information of the HSI pixels and reducing the dimension of the new sparse representations. The enhanced model, called sparse coding based dense feature representation (SC-DFR), is integrated with a linear support vector machine (SVM) and a composite kernels SVM (CKSVM) classifiers to discriminate different types of land cover. We evaluated the proposed algorithm on three well known HSI datasets and compared our method to four recently developed classification methods: SVM, CKSVM, simultaneous orthogonal matching pursuit (SOMP) and image fusion and recursive filtering (IFRF). The results from the experiments showed that the proposed method can achieve better overall and average classification accuracies with a much more compact representation leading to more efficient sparse models for HSI classification. To further
Optimized sparse-particle aerosol representations for modeling cloud-aerosol interactions
NASA Astrophysics Data System (ADS)
Fierce, Laura; McGraw, Robert
2016-04-01
Sparse representations of atmospheric aerosols are needed for efficient regional- and global-scale chemical transport models. Here we introduce a new framework for representing aerosol distributions, based on the method of moments. Given a set of moment constraints, we show how linear programming can be used to identify collections of sparse particles that approximately maximize distributional entropy. The collections of sparse particles derived from this approach reproduce CCN activity of the exact model aerosol distributions with high accuracy. Additionally, the linear programming techniques described in this study can be used to bound key aerosol properties, such as the number concentration of CCN. Unlike the commonly used sparse representations, such as modal and sectional schemes, the maximum-entropy moment-based approach is not constrained to pre-determined size bins or assumed distribution shapes. This study is a first step toward a new aerosol simulation scheme that will track multivariate aerosol distributions with sufficient computational efficiency for large-scale simulations.
Spatiotemporal System Identification With Continuous Spatial Maps and Sparse Estimation.
Aram, Parham; Kadirkamanathan, Visakan; Anderson, Sean R
2015-11-01
We present a framework for the identification of spatiotemporal linear dynamical systems. We use a state-space model representation that has the following attributes: 1) the number of spatial observation locations are decoupled from the model order; 2) the model allows for spatial heterogeneity; 3) the model representation is continuous over space; and 4) the model parameters can be identified in a simple and sparse estimation procedure. The model identification procedure we propose has four steps: 1) decomposition of the continuous spatial field using a finite set of basis functions where spatial frequency analysis is used to determine basis function width and spacing, such that the main spatial frequency contents of the underlying field can be captured; 2) initialization of states in closed form; 3) initialization of state-transition and input matrix model parameters using sparse regression-the least absolute shrinkage and selection operator method; and 4) joint state and parameter estimation using an iterative Kalman-filter/sparse-regression algorithm. To investigate the performance of the proposed algorithm we use data generated by the Kuramoto model of spatiotemporal cortical dynamics. The identification algorithm performs successfully, predicting the spatiotemporal field with high accuracy, whilst the sparse regression leads to a compact model.
Beam hardening correction for sparse-view CT reconstruction
NASA Astrophysics Data System (ADS)
Liu, Wenlei; Rong, Junyan; Gao, Peng; Liao, Qimei; Lu, HongBing
2015-03-01
Beam hardening, which is caused by spectrum polychromatism of the X-ray beam, may result in various artifacts in the reconstructed image and degrade image quality. The artifacts would be further aggravated for the sparse-view reconstruction due to insufficient sampling data. Considering the advantages of the total-variation (TV) minimization in CT reconstruction with sparse-view data, in this paper, we propose a beam hardening correction method for sparse-view CT reconstruction based on Brabant's modeling. In this correction model for beam hardening, the attenuation coefficient of each voxel at the effective energy is modeled and estimated linearly, and can be applied in an iterative framework, such as simultaneous algebraic reconstruction technique (SART). By integrating the correction model into the forward projector of the algebraic reconstruction technique (ART), the TV minimization can recover images when only a limited number of projections are available. The proposed method does not need prior information about the beam spectrum. Preliminary validation using Monte Carlo simulations indicates that the proposed method can provide better reconstructed images from sparse-view projection data, with effective suppression of artifacts caused by beam hardening. With appropriate modeling of other degrading effects such as photon scattering, the proposed framework may provide a new way for low-dose CT imaging.
NASA Technical Reports Server (NTRS)
Utku, S.
1969-01-01
A general purpose digital computer program for the in-core solution of linear equilibrium problems of structural mechanics is documented. The program requires minimum input for the description of the problem. The solution is obtained by means of the displacement method and the finite element technique. Almost any geometry and structure may be handled because of the availability of linear, triangular, quadrilateral, tetrahedral, hexahedral, conical, triangular torus, and quadrilateral torus elements. The assumption of piecewise linear deflection distribution insures monotonic convergence of the deflections from the stiffer side with decreasing mesh size. The stresses are provided by the best-fit strain tensors in the least squares at the mesh points where the deflections are given. The selection of local coordinate systems whenever necessary is automatic. The core memory is used by means of dynamic memory allocation, an optional mesh-point relabelling scheme and imposition of the boundary conditions during the assembly time.
Fogolari, Federico; Corazza, Alessandra; Esposito, Gennaro
2015-04-05
The generalized Born model in the Onufriev, Bashford, and Case (Onufriev et al., Proteins: Struct Funct Genet 2004, 55, 383) implementation has emerged as one of the best compromises between accuracy and speed of computation. For simulations of nucleic acids, however, a number of issues should be addressed: (1) the generalized Born model is based on a linear model and the linearization of the reference Poisson-Boltmann equation may be questioned for highly charged systems as nucleic acids; (2) although much attention has been given to potentials, solvation forces could be much less sensitive to linearization than the potentials; and (3) the accuracy of the Onufriev-Bashford-Case (OBC) model for nucleic acids depends on fine tuning of parameters. Here, we show that the linearization of the Poisson Boltzmann equation has mild effects on computed forces, and that with optimal choice of the OBC model parameters, solvation forces, essential for molecular dynamics simulations, agree well with those computed using the reference Poisson-Boltzmann model.
1975-04-15
paper is a compromise in the same nature as the 2SLS. We use the Moore - Penrose (MP) generalized inverse to... Moore - Penrose generalized inverse ; Indirect Least Squares; 1’wo Stage Least Squares; Instrumental Variables; Limited Information Maximum L-..clihood...Abstract -In this paper , we propose a procedure based on the use of the Moore - Penrose inverse of matrices for deriving unique Indirect Least Squares
Ordering Unstructured Meshes for Sparse Matrix Computations on Leading Parallel Systems
NASA Technical Reports Server (NTRS)
Oliker, Leonid; Li, Xiaoye; Heber, Gerd; Biswas, Rupak
2000-01-01
The ability of computers to solve hitherto intractable problems and simulate complex processes using mathematical models makes them an indispensable part of modern science and engineering. Computer simulations of large-scale realistic applications usually require solving a set of non-linear partial differential equations (PDES) over a finite region. For example, one thrust area in the DOE Grand Challenge projects is to design future accelerators such as the SpaHation Neutron Source (SNS). Our colleagues at SLAC need to model complex RFQ cavities with large aspect ratios. Unstructured grids are currently used to resolve the small features in a large computational domain; dynamic mesh adaptation will be added in the future for additional efficiency. The PDEs for electromagnetics are discretized by the FEM method, which leads to a generalized eigenvalue problem Kx = AMx, where K and M are the stiffness and mass matrices, and are very sparse. In a typical cavity model, the number of degrees of freedom is about one million. For such large eigenproblems, direct solution techniques quickly reach the memory limits. Instead, the most widely-used methods are Krylov subspace methods, such as Lanczos or Jacobi-Davidson. In all the Krylov-based algorithms, sparse matrix-vector multiplication (SPMV) must be performed repeatedly. Therefore, the efficiency of SPMV usually determines the eigensolver speed. SPMV is also one of the most heavily used kernels in large-scale numerical simulations.
Discovering governing equations from data by sparse identification of nonlinear dynamical systems
Brunton, Steven L.; Proctor, Joshua L.; Kutz, J. Nathan
2016-01-01
Extracting governing equations from data is a central challenge in many diverse areas of science and engineering. Data are abundant whereas models often remain elusive, as in climate science, neuroscience, ecology, finance, and epidemiology, to name only a few examples. In this work, we combine sparsity-promoting techniques and machine learning with nonlinear dynamical systems to discover governing equations from noisy measurement data. The only assumption about the structure of the model is that there are only a few important terms that govern the dynamics, so that the equations are sparse in the space of possible functions; this assumption holds for many physical systems in an appropriate basis. In particular, we use sparse regression to determine the fewest terms in the dynamic governing equations required to accurately represent the data. This results in parsimonious models that balance accuracy with model complexity to avoid overfitting. We demonstrate the algorithm on a wide range of problems, from simple canonical systems, including linear and nonlinear oscillators and the chaotic Lorenz system, to the fluid vortex shedding behind an obstacle. The fluid example illustrates the ability of this method to discover the underlying dynamics of a system that took experts in the community nearly 30 years to resolve. We also show that this method generalizes to parameterized systems and systems that are time-varying or have external forcing. PMID:27035946
Chen, Zhe; Putrino, David F; Ghosh, Soumya; Barbieri, Riccardo; Brown, Emery N
2011-04-01
The ability to accurately infer functional connectivity between ensemble neurons using experimentally acquired spike train data is currently an important research objective in computational neuroscience. Point process generalized linear models and maximum likelihood estimation have been proposed as effective methods for the identification of spiking dependency between neurons. However, unfavorable experimental conditions occasionally results in insufficient data collection due to factors such as low neuronal firing rates or brief recording periods, and in these cases, the standard maximum likelihood estimate becomes unreliable. The present studies compares the performance of different statistical inference procedures when applied to the estimation of functional connectivity in neuronal assemblies with sparse spiking data. Four inference methods were compared: maximum likelihood estimation, penalized maximum likelihood estimation, using either l(2) or l(1) regularization, and hierarchical Bayesian estimation based on a variational Bayes algorithm. Algorithmic performances were compared using well-established goodness-of-fit measures in benchmark simulation studies, and the hierarchical Bayesian approach performed favorably when compared with the other algorithms, and this approach was then successfully applied to real spiking data recorded from the cat motor cortex. The identification of spiking dependencies in physiologically acquired data was encouraging, since their sparse nature would have previously precluded them from successful analysis using traditional methods.
Sparse Coding for Alpha Matting.
Johnson, Jubin; Varnousfaderani, Ehsan Shahrian; Cholakkal, Hisham; Rajan, Deepu
2016-07-01
Existing color sampling-based alpha matting methods use the compositing equation to estimate alpha at a pixel from the pairs of foreground ( F ) and background ( B ) samples. The quality of the matte depends on the selected ( F,B ) pairs. In this paper, the matting problem is reinterpreted as a sparse coding of pixel features, wherein the sum of the codes gives the estimate of the alpha matte from a set of unpaired F and B samples. A non-parametric probabilistic segmentation provides a certainty measure on the pixel belonging to foreground or background, based on which a dictionary is formed for use in sparse coding. By removing the restriction to conform to ( F,B ) pairs, this method allows for better alpha estimation from multiple F and B samples. The same framework is extended to videos, where the requirement of temporal coherence is handled effectively. Here, the dictionary is formed by samples from multiple frames. A multi-frame graph model, as opposed to a single image as for image matting, is proposed that can be solved efficiently in closed form. Quantitative and qualitative evaluations on a benchmark dataset are provided to show that the proposed method outperforms the current stateoftheart in image and video matting.
Sparse Coding for Alpha Matting.
Johnson, Jubin; Varnousfaderani, Ehsan; Cholakkal, Hisham; Rajan, Deepu
2016-04-21
Existing color sampling based alpha matting methods use the compositing equation to estimate alpha at a pixel from pairs of foreground (F) and background (B) samples. The quality of the matte depends on the selected (F,B) pairs. In this paper, the matting problem is reinterpreted as a sparse coding of pixel features, wherein the sum of the codes gives the estimate of the alpha matte from a set of unpaired F and B samples. A non-parametric probabilistic segmentation provides a certainty measure on the pixel belonging to foreground or background, based on which a dictionary is formed for use in sparse coding. By removing the restriction to conform to (F,B) pairs, this method allows for better alpha estimation from multiple F and B samples. The same framework is extended to videos, where the requirement of temporal coherence is handled effectively. Here, the dictionary is formed by samples from multiple frames. A multi-frame graph model, as opposed to a single image as for image matting, is proposed that can be solved efficiently in closed form. Quantitative and qualitative evaluations on a benchmark dataset are provided to show that the proposed method outperforms current state-of-the-art in image and video matting.
Universal Priors for Sparse Modeling(PREPRINT)
2009-08-01
UNIVERSAL PRIORS FOR SPARSE MODELING By Ignacio Ramı́rez Federico Lecumberry and Guillermo Sapiro IMA Preprint Series # 2276 ( August 2009...8-98) Prescribed by ANSI Std Z39-18 Universal Priors for Sparse Modeling (Invited Paper) Ignacio Ramı́rez#1, Federico Lecumberry ∗2, Guillermo Sapiro...I. Ramirez, F. Lecumberry , and G. Sapiro. Sparse modeling with univer- sal priors and learned incoherent dictionaries. Submitted to NIPS, 2009. [22
Discriminative Sparse Representations in Hyperspectral Imagery
2010-03-01
classification , and unsupervised labeling (clustering) [2, 3, 4, 5, 6, 7, 8]. Recently, a non-parametric (Bayesian) approach to sparse modeling and com...DISCRIMINATIVE SPARSE REPRESENTATIONS IN HYPERSPECTRAL IMAGERY By Alexey Castrodad, Zhengming Xing John Greer, Edward Bosch Lawrence Carin and...00-00-2010 to 00-00-2010 4. TITLE AND SUBTITLE Discriminative Sparse Representations in Hyperspectral Imagery 5a. CONTRACT NUMBER 5b. GRANT
Jäntschi, Lorentz
2016-01-01
Multiple linear regression analysis is widely used to link an outcome with predictors for better understanding of the behaviour of the outcome of interest. Usually, under the assumption that the errors follow a normal distribution, the coefficients of the model are estimated by minimizing the sum of squared deviations. A new approach based on maximum likelihood estimation is proposed for finding the coefficients on linear models with two predictors without any constrictive assumptions on the distribution of the errors. The algorithm was developed, implemented, and tested as proof-of-concept using fourteen sets of compounds by investigating the link between activity/property (as outcome) and structural feature information incorporated by molecular descriptors (as predictors). The results on real data demonstrated that in all investigated cases the power of the error is significantly different by the convenient value of two when the Gauss-Laplace distribution was used to relax the constrictive assumption of the normal distribution of the error. Therefore, the Gauss-Laplace distribution of the error could not be rejected while the hypothesis that the power of the error from Gauss-Laplace distribution is normal distributed also failed to be rejected. PMID:28090215
Jäntschi, Lorentz; Bálint, Donatella; Bolboacă, Sorana D
2016-01-01
Multiple linear regression analysis is widely used to link an outcome with predictors for better understanding of the behaviour of the outcome of interest. Usually, under the assumption that the errors follow a normal distribution, the coefficients of the model are estimated by minimizing the sum of squared deviations. A new approach based on maximum likelihood estimation is proposed for finding the coefficients on linear models with two predictors without any constrictive assumptions on the distribution of the errors. The algorithm was developed, implemented, and tested as proof-of-concept using fourteen sets of compounds by investigating the link between activity/property (as outcome) and structural feature information incorporated by molecular descriptors (as predictors). The results on real data demonstrated that in all investigated cases the power of the error is significantly different by the convenient value of two when the Gauss-Laplace distribution was used to relax the constrictive assumption of the normal distribution of the error. Therefore, the Gauss-Laplace distribution of the error could not be rejected while the hypothesis that the power of the error from Gauss-Laplace distribution is normal distributed also failed to be rejected.
Kim, Hyunwoo J.; Adluru, Nagesh; Collins, Maxwell D.; Chung, Moo K.; Bendlin, Barbara B.; Johnson, Sterling C.; Davidson, Richard J.; Singh, Vikas
2014-01-01
Linear regression is a parametric model which is ubiquitous in scientific analysis. The classical setup where the observations and responses, i.e., (xi, yi) pairs, are Euclidean is well studied. The setting where yi is manifold valued is a topic of much interest, motivated by applications in shape analysis, topic modeling, and medical imaging. Recent work gives strategies for max-margin classifiers, principal components analysis, and dictionary learning on certain types of manifolds. For parametric regression specifically, results within the last year provide mechanisms to regress one real-valued parameter, xi ∈ R, against a manifold-valued variable, yi ∈ . We seek to substantially extend the operating range of such methods by deriving schemes for multivariate multiple linear regression —a manifold-valued dependent variable against multiple independent variables, i.e., f : Rn → . Our variational algorithm efficiently solves for multiple geodesic bases on the manifold concurrently via gradient updates. This allows us to answer questions such as: what is the relationship of the measurement at voxel y to disease when conditioned on age and gender. We show applications to statistical analysis of diffusion weighted images, which give rise to regression tasks on the manifold GL(n)/O(n) for diffusion tensor images (DTI) and the Hilbert unit sphere for orientation distribution functions (ODF) from high angular resolution acquisition. The companion open-source code is available on nitrc.org/projects/riem_mglm. PMID:25580070
A performance study of sparse Cholesky factorization on INTEL iPSC/860
NASA Technical Reports Server (NTRS)
Zubair, M.; Ghose, M.
1992-01-01
The problem of Cholesky factorization of a sparse matrix has been very well investigated on sequential machines. A number of efficient codes exist for factorizing large unstructured sparse matrices. However, there is a lack of such efficient codes on parallel machines in general, and distributed machines in particular. Some of the issues that are critical to the implementation of sparse Cholesky factorization on a distributed memory parallel machine are ordering, partitioning and mapping, load balancing, and ordering of various tasks within a processor. Here, we focus on the effect of various partitioning schemes on the performance of sparse Cholesky factorization on the Intel iPSC/860. Also, a new partitioning heuristic for structured as well as unstructured sparse matrices is proposed, and its performance is compared with other schemes.
Image fusion using sparse overcomplete feature dictionaries
Brumby, Steven P.; Bettencourt, Luis; Kenyon, Garrett T.; Chartrand, Rick; Wohlberg, Brendt
2015-10-06
Approaches for deciding what individuals in a population of visual system "neurons" are looking for using sparse overcomplete feature dictionaries are provided. A sparse overcomplete feature dictionary may be learned for an image dataset and a local sparse representation of the image dataset may be built using the learned feature dictionary. A local maximum pooling operation may be applied on the local sparse representation to produce a translation-tolerant representation of the image dataset. An object may then be classified and/or clustered within the translation-tolerant representation of the image dataset using a supervised classification algorithm and/or an unsupervised clustering algorithm.
Accelerated Gibbs Sampling for Infinite Sparse Factor Analysis
Andrzejewski, D M
2011-09-12
The Indian Buffet Process (IBP) gives a probabilistic model of sparse binary matrices with an unbounded number of columns. This construct can be used, for example, to model a fixed numer of observed data points (rows) associated with an unknown number of latent features (columns). Markov Chain Monte Carlo (MCMC) methods are often used for IBP inference, and in this technical note, we provide a detailed review of the derivations of collapsed and accelerated Gibbs samplers for the linear-Gaussian infinite latent feature model. We also discuss and explain update equations for hyperparameter resampling in a 'full Bayesian' treatment and present a novel slice sampler capable of extending the accelerated Gibbs sampler to the case of infinite sparse factor analysis by allowing the use of real-valued latent features.
NASA Astrophysics Data System (ADS)
Aragón, J. L.; Vázquez Polo, G.; Gómez, A.
A computational algorithm for the generation of quasiperiodic tiles based on the cut and projection method is presented. The algorithm is capable of projecting any type of lattice embedded in any euclidean space onto any subspace making it possible to generate quasiperiodic tiles with any desired symmetry. The simplex method of linear programming and the Moore-Penrose generalized inverse are used to construct the cut (strip) in the higher dimensional space which is to be projected.
NASA Astrophysics Data System (ADS)
Tsuboi, Zengo
2013-05-01
In [1] (Z. Tsuboi, Nucl. Phys. B 826 (2010) 399, arxiv:arXiv:0906.2039), we proposed Wronskian-like solutions of the T-system for [ M , N ]-hook of the general linear superalgebra gl (M | N). We have generalized these Wronskian-like solutions to the ones for the general T-hook, which is a union of [M1 ,N1 ]-hook and [M2 ,N2 ]-hook (M =M1 +M2, N =N1 +N2). These solutions are related to Weyl-type supercharacter formulas of infinite dimensional unitarizable modules of gl (M | N). Our solutions also include a Wronskian-like solution discussed in [2] (N. Gromov, V. Kazakov, S. Leurent, Z. Tsuboi, JHEP 1101 (2011) 155, arxiv:arXiv:1010.2720) in relation to the AdS5 /CFT4 spectral problem.
Optimized Color Filter Arrays for Sparse Representation Based Demosaicking.
Li, Jia; Bai, Chenyan; Lin, Zhouchen; Yu, Jian
2017-03-08
Demosaicking is the problem of reconstructing a color image from the raw image captured by a digital color camera that covers its only imaging sensor with a color filter array (CFA). Sparse representation based demosaicking has been shown to produce superior reconstruction quality. However, almost all existing algorithms in this category use the CFAs which are not specifically optimized for the algorithms. In this paper, we consider optimally designing CFAs for sparse representation based demosaicking, where the dictionary is well-chosen. The fact that CFAs correspond to the projection matrices used in compressed sensing inspires us to optimize CFAs via minimizing the mutual coherence. This is more challenging than that for traditional projection matrices because CFAs have physical realizability constraints. However, most of the existing methods for minimizing the mutual coherence require that the projection matrices should be unconstrained, making them inapplicable for designing CFAs. We consider directly minimizing the mutual coherence with the CFA's physical realizability constraints as a generalized fractional programming problem, which needs to find sufficiently accurate solutions to a sequence of nonconvex nonsmooth minimization problems. We adapt the redistributed proximal bundle method to address this issue. Experiments on benchmark images testify to the superiority of the proposed method. In particular, we show that a simple sparse representation based demosaicking algorithm with our specifically optimized CFA can outperform LSSC [1]. To the best of our knowledge, it is the first sparse representation based demosaicking algorithm that beats LSSC in terms of CPSNR.
Sparse and stable Markowitz portfolios.
Brodie, Joshua; Daubechies, Ingrid; De Mol, Christine; Giannone, Domenico; Loris, Ignace
2009-07-28
We consider the problem of portfolio selection within the classical Markowitz mean-variance framework, reformulated as a constrained least-squares regression problem. We propose to add to the objective function a penalty proportional to the sum of the absolute values of the portfolio weights. This penalty regularizes (stabilizes) the optimization problem, encourages sparse portfolios (i.e., portfolios with only few active positions), and allows accounting for transaction costs. Our approach recovers as special cases the no-short-positions portfolios, but does allow for short positions in limited number. We implement this methodology on two benchmark data sets constructed by Fama and French. Using only a modest amount of training data, we construct portfolios whose out-of-sample performance, as measured by Sharpe ratio, is consistently and significantly better than that of the naïve evenly weighted portfolio.
Feature selection and multi-kernel learning for sparse representation on a manifold.
Wang, Jim Jing-Yan; Bensmail, Halima; Gao, Xin
2014-03-01
Sparse representation has been widely studied as a part-based data representation method and applied in many scientific and engineering fields, such as bioinformatics and medical imaging. It seeks to represent a data sample as a sparse linear combination of some basic items in a dictionary. Gao et al. (2013) recently proposed Laplacian sparse coding by regularizing the sparse codes with an affinity graph. However, due to the noisy features and nonlinear distribution of the data samples, the affinity graph constructed directly from the original feature space is not necessarily a reliable reflection of the intrinsic manifold of the data samples. To overcome this problem, we integrate feature selection and multiple kernel learning into the sparse coding on the manifold. To this end, unified objectives are defined for feature selection, multiple kernel learning, sparse coding, and graph regularization. By optimizing the objective functions iteratively, we develop novel data representation algorithms with feature selection and multiple kernel learning respectively. Experimental results on two challenging tasks, N-linked glycosylation prediction and mammogram retrieval, demonstrate that the proposed algorithms outperform the traditional sparse coding methods.
NASA Technical Reports Server (NTRS)
Ustino, Eugene A.
2006-01-01
This slide presentation reviews the observable radiances as functions of atmospheric parameters and of surface parameters; the mathematics of atmospheric weighting functions (WFs) and surface partial derivatives (PDs) are presented; and the equation of the forward radiative transfer (RT) problem is presented. For non-scattering atmospheres this can be done analytically, and all WFs and PDs can be computed analytically using the direct linearization approach. For scattering atmospheres, in general case, the solution of the forward RT problem can be obtained only numerically, but we need only two numerical solutions: one of the forward RT problem and one of the adjoint RT problem to compute all WFs and PDs we can think of. In this presentation we discuss applications of both the linearization and adjoint approaches
NASA Technical Reports Server (NTRS)
Tal-Ezer, Hillel
1987-01-01
During the process of solving a mathematical model numerically, there is often a need to operate on a vector v by an operator which can be expressed as f(A) while A is NxN matrix (ex: exp(A), sin(A), A sup -1). Except for very simple matrices, it is impractical to construct the matrix f(A) explicitly. Usually an approximation to it is used. In the present research, an algorithm is developed which uses a polynomial approximation to f(A). It is reduced to a problem of approximating f(z) by a polynomial in z while z belongs to the domain D in the complex plane which includes all the eigenvalues of A. This problem of approximation is approached by interpolating the function f(z) in a certain set of points which is known to have some maximal properties. The approximation thus achieved is almost best. Implementing the algorithm to some practical problem is described. Since a solution to a linear system Ax = b is x= A sup -1 b, an iterative solution to it can be regarded as a polynomial approximation to f(A) = A sup -1. Implementing the algorithm in this case is also described.
Index statistical properties of sparse random graphs
NASA Astrophysics Data System (ADS)
Metz, F. L.; Stariolo, Daniel A.
2015-10-01
Using the replica method, we develop an analytical approach to compute the characteristic function for the probability PN(K ,λ ) that a large N ×N adjacency matrix of sparse random graphs has K eigenvalues below a threshold λ . The method allows to determine, in principle, all moments of PN(K ,λ ) , from which the typical sample-to-sample fluctuations can be fully characterized. For random graph models with localized eigenvectors, we show that the index variance scales linearly with N ≫1 for |λ |>0 , with a model-dependent prefactor that can be exactly calculated. Explicit results are discussed for Erdös-Rényi and regular random graphs, both exhibiting a prefactor with a nonmonotonic behavior as a function of λ . These results contrast with rotationally invariant random matrices, where the index variance scales only as lnN , with an universal prefactor that is independent of λ . Numerical diagonalization results confirm the exactness of our approach and, in addition, strongly support the Gaussian nature of the index fluctuations.
Sparse representation for the ISAR image reconstruction
NASA Astrophysics Data System (ADS)
Hu, Mengqi; Montalbo, John; Li, Shuxia; Sun, Ligang; Qiao, Zhijun G.
2016-05-01
In this paper, a sparse representation of the data for an inverse synthetic aperture radar (ISAR) system is provided in two dimensions. The proposed sparse representation motivates the use a of a Convex Optimization that recovers the image with far less samples, which is required by Nyquist-Shannon sampling theorem to increases the efficiency and decrease the cost of calculation in radar imaging.
Dictionary construction in sparse methods for image restoration
Wohlberg, Brendt
2010-01-01
Sparsity-based methods have achieved very good performance in a wide variety of image restoration problems, including denoising, inpainting, super-resolution, and source separation. These methods are based on the assumption that the image to be reconstructed may be represented as a superposition of a few known components, and the appropriate linear combination of components is estimated by solving an optimization such as Basis Pursuit De-Noising (BPDN). Considering that the K-SVD constructs a dictionary which has been optimised for mean performance over a training set, it is not too surprising that better performance can be achieved by selecting a custom dictionary for each individual block to be reconstructed. The nearest neighbor dictionary construction can be understood geometrically as a method for estimating the local projection into the manifold of image blocks, whereas the K-SVD dictionary makes more sense within a source-coding framework (it is presented as a generalization of the k-means algorithm for constructing a VQ codebook), is therefore, it could be argued, less appropriate in principle, for reconstruction problems. One can, of course, motivate the use of the K-SVD in reconstruction application on practical grounds, avoiding the computational expense of constructing a different dictionary for each block to be denoised. Since the performance of the nearest neighbor dictionary decreases when the dictionary becomes sufficiently large, this method is also superior to the approach of utilizing the entire training set as a dictionary (and this can also be understood within the image block manifold model). In practical terms, the tradeoff is between the computational cost of a nearest neighbor search (which can be achieved very efficiently), or of increased cost at the sparse optimization.
NASA Astrophysics Data System (ADS)
Hargrove, W. W.; Kumar, J.; Hoffman, F. M.; Potter, K. M.; Mills, R. T.
2012-12-01
Up-scaling from sparse measurements to a continuous raster of estimated values is a common problem in Earth System Science. We present a new general-purpose empirical imputation method based on associative clustering, which associates sparse measurements of dependent variables with particular multivariate clustered combinations of the independent variables, and then uses several methods to estimate values for unmeasured clusters, based on directional proximity in multidimensional data space, at both the cluster and map cell levels of resolution. We demonstrate this new imputation tool on tree species range distribution maps, which describe the suitable extent and expected growth performance of a particular tree species over a wide area. Range maps having continuous estimates of tree growth performance are more useful than more classical tree range maps that simply show binary occurence suitability. The USDA Forest Service Forest Inventory Assessment (FIA) plots provide information about the occurence and growth performance for various tree species across the US, but such measurements are limited to FIA plots. Using Associative Clustering, we scale up the discontinuous FIA Inventory growth measurements into continuous maps that show the expected growth and suitabilty for individual tree species covering the Continental United States. A multivariate cluster analysis was applied to global output from a General Circulation Model (GCM) consisting of 17 variables downscaled to 4km2 resolution. Present global growing conditions were divided into 30 thousand relatively homogeneous ecoregions describing climatic and topographic conditions. At every mapcell a multi-linear regression was applied in 17 dimensional hyperspace to derive the suitability of a tree species where not measured using the forest inventory data. The continuous species distribution maps obtained were compared and validated against existing tree range suitability maps. Associative Clustering is intended
Yang, Alice C; Kretzler, Madison; Sudarski, Sonja; Gulani, Vikas; Seiberlich, Nicole
2016-06-01
The family of sparse reconstruction techniques, including the recently introduced compressed sensing framework, has been extensively explored to reduce scan times in magnetic resonance imaging (MRI). While there are many different methods that fall under the general umbrella of sparse reconstructions, they all rely on the idea that a priori information about the sparsity of MR images can be used to reconstruct full images from undersampled data. This review describes the basic ideas behind sparse reconstruction techniques, how they could be applied to improve MRI, and the open challenges to their general adoption in a clinical setting. The fundamental principles underlying different classes of sparse reconstructions techniques are examined, and the requirements that each make on the undersampled data outlined. Applications that could potentially benefit from the accelerations that sparse reconstructions could provide are described, and clinical studies using sparse reconstructions reviewed. Lastly, technical and clinical challenges to widespread implementation of sparse reconstruction techniques, including optimization, reconstruction times, artifact appearance, and comparison with current gold standards, are discussed.
Conjugate gradient type methods for linear systems with complex symmetric coefficient matrices
NASA Technical Reports Server (NTRS)
Freund, Roland
1989-01-01
We consider conjugate gradient type methods for the solution of large sparse linear system Ax equals b with complex symmetric coefficient matrices A equals A(T). Such linear systems arise in important applications, such as the numerical solution of the complex Helmholtz equation. Furthermore, most complex non-Hermitian linear systems which occur in practice are actually complex symmetric. We investigate conjugate gradient type iterations which are based on a variant of the nonsymmetric Lanczos algorithm for complex symmetric matrices. We propose a new approach with iterates defined by a quasi-minimal residual property. The resulting algorithm presents several advantages over the standard biconjugate gradient method. We also include some remarks on the obvious approach to general complex linear systems by solving equivalent real linear systems for the real and imaginary parts of x. Finally, numerical experiments for linear systems arising from the complex Helmholtz equation are reported.
Large-scale sparse singular value computations
NASA Technical Reports Server (NTRS)
Berry, Michael W.
1992-01-01
Four numerical methods for computing the singular value decomposition (SVD) of large sparse matrices on a multiprocessor architecture are presented. Lanczos and subspace iteration-based methods for determining several of the largest singular triplets (singular values and corresponding left and right-singular vectors) for sparse matrices arising from two practical applications: information retrieval and seismic reflection tomography are emphasized. The target architectures for implementations are the CRAY-2S/4-128 and Alliant FX/80. The sparse SVD problem is well motivated by recent information-retrieval techniques in which dominant singular values and their corresponding singular vectors of large sparse term-document matrices are desired, and by nonlinear inverse problems from seismic tomography applications which require approximate pseudo-inverses of large sparse Jacobian matrices.
Manifold Kernel Sparse Representation of Symmetric Positive-Definite Matrices and Its Applications.
Wu, Yuwei; Jia, Yunde; Li, Peihua; Zhang, Jian; Yuan, Junsong
2015-11-01
The symmetric positive-definite (SPD) matrix, as a connected Riemannian manifold, has become increasingly popular for encoding image information. Most existing sparse models are still primarily developed in the Euclidean space. They do not consider the non-linear geometrical structure of the data space, and thus are not directly applicable to the Riemannian manifold. In this paper, we propose a novel sparse representation method of SPD matrices in the data-dependent manifold kernel space. The graph Laplacian is incorporated into the kernel space to better reflect the underlying geometry of SPD matrices. Under the proposed framework, we design two different positive definite kernel functions that can be readily transformed to the corresponding manifold kernels. The sparse representation obtained has more discriminating power. Extensive experimental results demonstrate good performance of manifold kernel sparse codes in image classification, face recognition, and visual tracking.
Sparse partial least squares regression for simultaneous dimension reduction and variable selection.
Chun, Hyonho; Keleş, Sündüz
2010-01-01
Partial least squares regression has been an alternative to ordinary least squares for handling multicollinearity in several areas of scientific research since the 1960s. It has recently gained much attention in the analysis of high dimensional genomic data. We show that known asymptotic consistency of the partial least squares estimator for a univariate response does not hold with the very large p and small n paradigm. We derive a similar result for a multivariate response regression with partial least squares. We then propose a sparse partial least squares formulation which aims simultaneously to achieve good predictive performance and variable selection by producing sparse linear combinations of the original predictors. We provide an efficient implementation of sparse partial least squares regression and compare it with well-known variable selection and dimension reduction approaches via simulation experiments. We illustrate the practical utility of sparse partial least squares regression in a joint analysis of gene expression and genomewide binding data.
Sparse distributed memory: Principles and operation
NASA Technical Reports Server (NTRS)
Flynn, M. J.; Kanerva, P.; Bhadkamkar, N.
1989-01-01
Sparse distributed memory is a generalized random access memory (RAM) for long (1000 bit) binary words. Such words can be written into and read from the memory, and they can also be used to address the memory. The main attribute of the memory is sensitivity to similarity, meaning that a word can be read back not only by giving the original write address but also by giving one close to it as measured by the Hamming distance between addresses. Large memories of this kind are expected to have wide use in speech recognition and scene analysis, in signal detection and verification, and in adaptive control of automated equipment, in general, in dealing with real world information in real time. The memory can be realized as a simple, massively parallel computer. Digital technology has reached a point where building large memories is becoming practical. Major design issues were resolved which were faced in building the memories. The design is described of a prototype memory with 256 bit addresses and from 8 to 128 K locations for 256 bit words. A key aspect of the design is extensive use of dynamic RAM and other standard components.
NASA Astrophysics Data System (ADS)
Lins, R. M.; Ferreira, M. D. C.; Proença, S. P. B.; Duarte, C. A.
2015-12-01
In this study, a recovery-based a-posteriori error estimator originally proposed for the Corrected XFEM is investigated in the framework of the stable generalized FEM (SGFEM). Both Heaviside and branch functions are adopted to enrich the approximations in the SGFEM. Some necessary adjustments to adapt the expressions defining the enhanced stresses in the original error estimator are discussed in the SGFEM framework. Relevant aspects such as effectivity indexes, error distribution, convergence rates and accuracy of the recovered stresses are used in order to highlight the main findings and the effectiveness of the error estimator. Two benchmark problems of the 2-D fracture mechanics are selected to assess the robustness of the error estimator hereby investigated. The main findings of this investigation are: the SGFEM shows higher accuracy than G/XFEM and a reduced sensitivity to blending element issues. The error estimator can accurately capture these features of both methods.
Lipparini, Filippo; Scalmani, Giovanni; Frisch, Michael J.; Lagardère, Louis; Stamm, Benjamin; Cancès, Eric; Maday, Yvon; Piquemal, Jean-Philip; Mennucci, Benedetta
2014-11-14
We present the general theory and implementation of the Conductor-like Screening Model according to the recently developed ddCOSMO paradigm. The various quantities needed to apply ddCOSMO at different levels of theory, including quantum mechanical descriptions, are discussed in detail, with a particular focus on how to compute the integrals needed to evaluate the ddCOSMO solvation energy and its derivatives. The overall computational cost of a ddCOSMO computation is then analyzed and decomposed in the various steps: the different relative weights of such contributions are then discussed for both ddCOSMO and the fastest available alternative discretization to the COSMO equations. Finally, the scaling of the cost of the various steps with respect to the size of the solute is analyzed and discussed, showing how ddCOSMO opens significantly new possibilities when cheap or hybrid molecular mechanics/quantum mechanics methods are used to describe the solute.
Zheng, Xueying; Qin, Guoyou; Tu, Dongsheng
2017-02-19
Motivated by the analysis of quality of life data from a clinical trial on early breast cancer, we propose in this paper a generalized partially linear mean-covariance regression model for longitudinal proportional data, which are bounded in a closed interval. Cholesky decomposition of the covariance matrix for within-subject responses and generalized estimation equations are used to estimate unknown parameters and the nonlinear function in the model. Simulation studies are performed to evaluate the performance of the proposed estimation procedures. Our new model is also applied to analyze the data from the cancer clinical trial that motivated this research. In comparison with available models in the literature, the proposed model does not require specific parametric assumptions on the density function of the longitudinal responses and the probability function of the boundary values and can capture dynamic changes of time or other interested variables on both mean and covariance of the correlated proportional responses. Copyright © 2017 John Wiley & Sons, Ltd.
NASA Astrophysics Data System (ADS)
Malekan, Mohammad; Barros, Felicio Bruzzi
2016-11-01
Using the locally-enriched strategy to enrich a small/local part of the problem by generalized/extended finite element method (G/XFEM) leads to non-optimal convergence rate and ill-conditioning system of equations due to presence of blending elements. The local enrichment can be chosen from polynomial, singular, branch or numerical types. The so-called stable version of G/XFEM method provides a well-conditioning approach when only singular functions are used in the blending elements. This paper combines numeric enrichment functions obtained from global-local G/XFEM method with the polynomial enrichment along with a well-conditioning approach, stable G/XFEM, in order to show the robustness and effectiveness of the approach. In global-local G/XFEM, the enrichment functions are constructed numerically from the solution of a local problem. Furthermore, several enrichment strategies are adopted along with the global-local enrichment. The results obtained with these enrichments strategies are discussed in detail, considering convergence rate in strain energy, growth rate of condition number, and computational processing. Numerical experiments show that using geometrical enrichment along with stable G/XFEM for global-local strategy improves the convergence rate and the conditioning of the problem. In addition, results shows that using polynomial enrichment for global problem simultaneously with global-local enrichments lead to ill-conditioned system matrices and bad convergence rate.
Prostate segmentation by sparse representation based classification
Gao, Yaozong; Liao, Shu; Shen, Dinggang
2012-01-01
the elastic net in order to obtain a smooth and clear prostate boundary in the classification result. (3) Residue-based linear regression is incorporated to improve the classification performance and to extend SRC from hard classification to soft classification. (4) Iterative SRC is proposed by using context information to iteratively refine the classification results. Results: The proposed method has been comprehensively evaluated on a dataset consisting of 330 CT images from 24 patients. The effectiveness of the extended SRC has been validated by comparing it with the traditional SRC based on the proposed four extensions. The experimental results show that our extended SRC can obtain not only more accurate classification results but also smoother and clearer prostate boundary than the traditional SRC. Besides, the comparison with other five state-of-the-art prostate segmentation methods indicates that our method can achieve better performance than other methods under comparison. Conclusions: The authors have proposed a novel prostate segmentation method based on the sparse representation based classification, which can achieve considerably accurate segmentation results in CT prostate segmentation. PMID:23039673
Extracting pure endmembers using symmetric sparse representation for hyperspectral imagery
NASA Astrophysics Data System (ADS)
Sun, Weiwei; Liu, Chun; Sun, Yanwei; Li, Weiyue; Li, Jialin
2016-10-01
This article proposes a symmetric sparse representation (SSR) method to extract pure endmembers from hyperspectral imagery (HSI). The SSR combines the features of the linear unmixing model and the sparse subspace clustering model of endmembers, and it assumes that the desired endmembers and all the HSI pixel points can be sparsely represented by each other. It formulates the endmember extraction problem into a famous program of archetypal analysis, and accordingly, extracting pure endmembers can be transformed as finding the archetypes in the minimal convex hull containing all the HSI pixel points. The vector quantization scheme is adopted to help in carefully choosing the initial pure endmembers, and the archetypal analysis program is solved using the simple projected gradient algorithm. Seven state-of-the-art methods are implemented to make comparisons with the SSR on both synthetic and real hyperspectral images. Experimental results show that the SSR outperforms all the seven methods in spectral angle distance and root-mean-square error, and it can be a good alternative choice for extracting pure endmembers from HSI data.
Implementations and applications of the sparse Radon transform
NASA Astrophysics Data System (ADS)
Trad, Daniel Osvaldo
The Radon transform (RT) has many desirable properties which make it particularly useful for multiple removal and interpolation of seismic reflections. However many practical difficulties arise as a consequence of poor sampling and limited aperture in the offset dimension. Furthermore the ever increasing volumes of seismic data make computing time a key issue in any practical implementation. The standard implementations of the Radon transform used in seismic processing fulfill very well the requirement of a fast transform but do not allow proper handling of problems associated with sampling and aperture. Many of these difficulties can be partially solved by using inverse theory to compute the transform subject to a sparseness constraint. The main thrust and contribution of this thesis lies in the exploration of the sparseness constraint and the design and implementation of the RT. Although this technique reduces sampling and aperture problems, it also considerably increases the computation time. Some of the possible solutions to decrease computation time discussed in this thesis are conjugate gradient methods, irregularly sampled model space and efficient operations with sparse matrices. Real data often have very complicated structure that makes sparseness criteria difficult to implement. Noise, non hyperbolic events and amplitude variation with offset conspire against sparseness. Therefore, the success of this method depends on the applied algorithms and on a delicate balance between sparseness and fit of data. Several real data examples of multiple removal and interpolation show the success of the proposed algorithms to achieve this balance. Another aspect of this thesis is the design of new applications for the Radon transform in seismic processing. Many new applications can be developed by designing new types of Radon operators. Some new applications implemented in this thesis are elliptical and hybrid linear-hyperbolic Radon transforms that should prove to be
Van Den Berg, W; Rossing, W A H
2005-03-01
In 1-year experiments, the final population density of nematodes is usually modeled as a function of initial density. Often, estimation of the parameters is precarious because nematode measurements, although laborious and expensive, are imprecise and the range in initial densities may be small. The estimation procedure can be improved by using orthogonal regression with a parameter for initial density on each experimental unit. In multi-year experiments parameters of a dynamic model can be estimated with optimization techniques like simulated annealing or Bayesian methods such as Markov chain Monte Carlo (MCMC). With these algorithms information from different experiments can be combined. In multi-year dynamic models, the stability of the steady states is an important issue. With chaotic dynamics, prediction of densities and associated economic loss will be possible only on a short timescale. In this study, a generic model was developed that describes population dynamics in crop rotations. Mathematical analysis showed stable steady states do exist for this dynamic model. Using the Metropolis algorithm, the model was fitted to data from a multi-year experiment on Pratylenchus penetrans dynamics with treatments that varied between years. For three crops, parameters for a yield loss assessment model were available and gross margin of the six possible rotations comprising these three crops and a fallow year were compared at the steady state of nematode density. Sensitivity of mean gross margin to changes in the parameter estimates was investigated. We discuss the general applicability of the dynamic rotation model and the opportunities arising from combination of the model with Bayesian calibration techniques for more efficient utilization and collection of data relevant for economic evaluation of crop rotations.
Sparse-aperture adaptive optics
NASA Astrophysics Data System (ADS)
Tuthill, Peter; Lloyd, James; Ireland, Michael; Martinache, Frantz; Monnier, John; Woodruff, Henry; ten Brummelaar, Theo; Turner, Nils; Townes, Charles
2006-06-01
Aperture masking interferometry and Adaptive Optics (AO) are two of the competing technologies attempting to recover diffraction-limited performance from ground-based telescopes. However, there are good arguments that these techniques should be viewed as complementary, not competitive. Masking has been shown to deliver superior PSF calibration, rejection of atmospheric noise and robust recovery of phase information through the use of closure phases. However, this comes at the penalty of loss of flux at the mask, restricting the technique to bright targets. Adaptive optics, on the other hand, can reach a fainter class of objects but suffers from the difficulty of calibration of the PSF which can vary with observational parameters such as seeing, airmass and source brightness. Here we present results from a fusion of these two techniques: placing an aperture mask downstream of an AO system. The precision characterization of the PSF enabled by sparse-aperture interferometry can now be applied to deconvolution of AO images, recovering structure from the traditionally-difficult regime within the core of the AO-corrected transfer function. Results of this program from the Palomar and Keck adaptive optical systems are presented.
Mathematical strategies for filtering complex systems: Regularly spaced sparse observations
Harlim, J. Majda, A.J.
2008-05-01
Real time filtering of noisy turbulent signals through sparse observations on a regularly spaced mesh is a notoriously difficult and important prototype filtering problem. Simpler off-line test criteria are proposed here as guidelines for filter performance for these stiff multi-scale filtering problems in the context of linear stochastic partial differential equations with turbulent solutions. Filtering turbulent solutions of the stochastically forced dissipative advection equation through sparse observations is developed as a stringent test bed for filter performance with sparse regular observations. The standard ensemble transform Kalman filter (ETKF) has poor skill on the test bed and even suffers from filter divergence, surprisingly, at observable times with resonant mean forcing and a decaying energy spectrum in the partially observed signal. Systematic alternative filtering strategies are developed here including the Fourier Domain Kalman Filter (FDKF) and various reduced filters called Strongly Damped Approximate Filter (SDAF), Variance Strongly Damped Approximate Filter (VSDAF), and Reduced Fourier Domain Kalman Filter (RFDKF) which operate only on the primary Fourier modes associated with the sparse observation mesh while nevertheless, incorporating into the approximate filter various features of the interaction with the remaining modes. It is shown below that these much cheaper alternative filters have significant skill on the test bed of turbulent solutions which exceeds ETKF and in various regimes often exceeds FDKF, provided that the approximate filters are guided by the off-line test criteria. The skill of the various approximate filters depends on the energy spectrum of the turbulent signal and the observation time relative to the decorrelation time of the turbulence at a given spatial scale in a precise fashion elucidated here.
Sparse High Dimensional Models in Economics
Fan, Jianqing; Lv, Jinchi; Qi, Lei
2010-01-01
This paper reviews the literature on sparse high dimensional models and discusses some applications in economics and finance. Recent developments of theory, methods, and implementations in penalized least squares and penalized likelihood methods are highlighted. These variable selection methods are proved to be effective in high dimensional sparse modeling. The limits of dimensionality that regularization methods can handle, the role of penalty functions, and their statistical properties are detailed. Some recent advances in ultra-high dimensional sparse modeling are also briefly discussed. PMID:22022635
Estimation of Sparse Directed Acyclic Graphs for Multivariate Counts Data
Han, Sung Won; Zhong, Hua
2016-01-01
Summary The next-generation sequencing data, called high throughput sequencing data, are recorded as count data, which is generally far from normal distribution. Under the assumption that the count data follow the Poisson log-normal distribution, this paper provides an L1-penalized likelihood framework and an efficient search algorithm to estimate the structure of sparse directed acyclic graphs (DAGs) for multivariate counts data. In searching for the solution, we use iterative optimization procedures to estimate the adjacency matrix and the variance matrix of the latent variables. The simulation result shows that our proposed method outperforms the approach which assumes multivariate normal distributions, and the log-transformation approach. It also shows that the proposed method outperforms the rank-based PC method under sparse network or hub network structures. As a real data example, we demonstrate the efficiency of the proposed method in estimating the gene regulatory networks of the ovarian cancer study. PMID:26849781
Numerical linear algebra algorithms and software
NASA Astrophysics Data System (ADS)
Dongarra, Jack J.; Eijkhout, Victor
2000-11-01
The increasing availability of advanced-architecture computers has a significant effect on all spheres of scientific computation, including algorithm research and software development in numerical linear algebra. Linear algebra - in particular, the solution of linear systems of equations - lies at the heart of most calculations in scientific computing. This paper discusses some of the recent developments in linear algebra designed to exploit these advanced-architecture computers. We discuss two broad classes of algorithms: those for dense, and those for sparse matrices.
Sparse alignment for robust tensor learning.
Lai, Zhihui; Wong, Wai Keung; Xu, Yong; Zhao, Cairong; Sun, Mingming
2014-10-01
Multilinear/tensor extensions of manifold learning based algorithms have been widely used in computer vision and pattern recognition. This paper first provides a systematic analysis of the multilinear extensions for the most popular methods by using alignment techniques, thereby obtaining a general tensor alignment framework. From this framework, it is easy to show that the manifold learning based tensor learning methods are intrinsically different from the alignment techniques. Based on the alignment framework, a robust tensor learning method called sparse tensor alignment (STA) is then proposed for unsupervised tensor feature extraction. Different from the existing tensor learning methods, L1- and L2-norms are introduced to enhance the robustness in the alignment step of the STA. The advantage of the proposed technique is that the difficulty in selecting the size of the local neighborhood can be avoided in the manifold learning based tensor feature extraction algorithms. Although STA is an unsupervised learning method, the sparsity encodes the discriminative information in the alignment step and provides the robustness of STA. Extensive experiments on the well-known image databases as well as action and hand gesture databases by encoding object images as tensors demonstrate that the proposed STA algorithm gives the most competitive performance when compared with the tensor-based unsupervised learning methods.
Sparse distributed memory prototype: Principles of operation
NASA Technical Reports Server (NTRS)
Flynn, Michael J.; Kanerva, Pentti; Ahanin, Bahram; Bhadkamkar, Neal; Flaherty, Paul; Hickey, Philip
1988-01-01
Sparse distributed memory is a generalized random access memory (RAM) for long binary words. Such words can be written into and read from the memory, and they can be used to address the memory. The main attribute of the memory is sensitivity to similarity, meaning that a word can be read back not only by giving the original right address but also by giving one close to it as measured by the Hamming distance between addresses. Large memories of this kind are expected to have wide use in speech and scene analysis, in signal detection and verification, and in adaptive control of automated equipment. The memory can be realized as a simple, massively parallel computer. Digital technology has reached a point where building large memories is becoming practical. The research is aimed at resolving major design issues that have to be faced in building the memories. The design of a prototype memory with 256-bit addresses and from 8K to 128K locations for 256-bit words is described. A key aspect of the design is extensive use of dynamic RAM and other standard components.
Partitioning sparse matrices with eigenvectors of graphs
NASA Technical Reports Server (NTRS)
Pothen, Alex; Simon, Horst D.; Liou, Kang-Pu
1990-01-01
The problem of computing a small vertex separator in a graph arises in the context of computing a good ordering for the parallel factorization of sparse, symmetric matrices. An algebraic approach for computing vertex separators is considered in this paper. It is shown that lower bounds on separator sizes can be obtained in terms of the eigenvalues of the Laplacian matrix associated with a graph. The Laplacian eigenvectors of grid graphs can be computed from Kronecker products involving the eigenvectors of path graphs, and these eigenvectors can be used to compute good separators in grid graphs. A heuristic algorithm is designed to compute a vertex separator in a general graph by first computing an edge separator in the graph from an eigenvector of the Laplacian matrix, and then using a maximum matching in a subgraph to compute the vertex separator. Results on the quality of the separators computed by the spectral algorithm are presented, and these are compared with separators obtained from other algorithms for computing separators. Finally, the time required to compute the Laplacian eigenvector is reported, and the accuracy with which the eigenvector must be computed to obtain good separators is considered. The spectral algorithm has the advantage that it can be implemented on a medium-size multiprocessor in a straightforward manner.
Structured sparse priors for image classification.
Srinivas, Umamahesh; Suo, Yuanming; Dao, Minh; Monga, Vishal; Tran, Trac D
2015-06-01
Model-based compressive sensing (CS) exploits the structure inherent in sparse signals for the design of better signal recovery algorithms. This information about structure is often captured in the form of a prior on the sparse coefficients, with the Laplacian being the most common such choice (leading to l1 -norm minimization). Recent work has exploited the discriminative capability of sparse representations for image classification by employing class-specific dictionaries in the CS framework. Our contribution is a logical extension of these ideas into structured sparsity for classification. We introduce the notion of discriminative class-specific priors in conjunction with class specific dictionaries, specifically the spike-and-slab prior widely applied in Bayesian sparse regression. Significantly, the proposed framework takes the burden off the demand for abundant training image samples necessary for the success of sparsity-based classification schemes. We demonstrate this practical benefit of our approach in important applications, such as face recognition and object categorization.
Robust feature point matching with sparse model.
Jiang, Bo; Tang, Jin; Luo, Bin; Lin, Liang
2014-12-01
Feature point matching that incorporates pairwise constraints can be cast as an integer quadratic programming (IQP) problem. Since it is NP-hard, approximate methods are required. The optimal solution for IQP matching problem is discrete, binary, and thus sparse in nature. This motivates us to use sparse model for feature point matching problem. The main advantage of the proposed sparse feature point matching (SPM) method is that it generates sparse solution and thus naturally imposes the discrete mapping constraints approximately in the optimization process. Therefore, it can optimize the IQP matching problem in an approximate discrete domain. In addition, an efficient algorithm can be derived to solve SPM problem. Promising experimental results on both synthetic points sets matching and real-world image feature sets matching tasks show the effectiveness of the proposed feature point matching method.
Online Dictionary Learning for Sparse Coding
2009-04-01
cessing tasks such as denoising (Elad & Aharon, 2006) as well as higher-level tasks such as classification (Raina et al., 2007; Mairal et al., 2008a...Bruckstein, A. M. (2006). The K- SVD : An algorithm for designing of overcomplete dic- tionaries for sparse representations. IEEE Trans. SP...Tibshirani, R. (2004). Least angle regression. Ann. Statist. Elad, M., & Aharon, M. (2006). Image denoising via sparse and redundant representations
Sparse CSEM inversion driven by seismic coherence
NASA Astrophysics Data System (ADS)
Guo, Zhenwei; Dong, Hefeng; Kristensen, Åge
2016-12-01
Marine controlled source electromagnetic (CSEM) data inversion for hydrocarbon exploration is often challenging due to high computational cost, physical memory requirement and low resolution of the obtained resistivity map. This paper aims to enhance both the speed and resolution of CSEM inversion by introducing structural geological information in the inversion algorithm. A coarse mesh is generated for Occam’s inversion, where the parameters are fewer than in the fine regular mesh. This sparse mesh is defined as a coherence-based irregular (IC) sparse mesh, which is based on vertices extracted from available geological information. Inversion results on synthetic data illustrate that the IC sparse mesh has a smaller inversion computational cost compared to the regular dense (RD) mesh. It also has a higher resolution than with a regular sparse (RS) mesh for the same number of estimated parameters. In order to study how the IC sparse mesh reduces the computational time, four different meshes are generated for Occam’s inversion. As a result, an IC sparse mesh can reduce the computational cost while it keeps the resolution as good as a fine regular mesh. The IC sparse mesh reduces the computational cost of the matrix operation for model updates. When the number of estimated parameters reduces to a limited value, the computational cost is independent of the number of parameters. For a testing model with two resistive layers, the inversion result using an IC sparse mesh has higher resolution in both horizontal and vertical directions. Overall, the model representing significant geological information in the IC mesh can improve the resolution of the resistivity models obtained from inversion of CSEM data.
Visual tracking via robust multitask sparse prototypes
NASA Astrophysics Data System (ADS)
Zhang, Huanlong; Hu, Shiqiang; Yu, Junyang
2015-03-01
Sparse representation has been applied to an online subspace learning-based tracking problem. To handle partial occlusion effectively, some researchers introduce l1 regularization to principal component analysis (PCA) reconstruction. However, in these traditional tracking methods, the representation of each object observation is often viewed as an individual task so the inter-relationship between PCA basis vectors is ignored. We propose a new online visual tracking algorithm with multitask sparse prototypes, which combines multitask sparse learning with PCA-based subspace representation. We first extend a visual tracking algorithm with sparse prototypes in multitask learning framework to mine inter-relations between subtasks. Then, to avoid the problem that enforcing all subtasks to share the same structure may result in degraded tracking results, we impose group sparse constraints on the coefficients of PCA basis vectors and element-wise sparse constraints on the error coefficients, respectively. Finally, we show that the proposed optimization problem can be effectively solved using the accelerated proximal gradient method with the fast convergence. Experimental results compared with the state-of-the-art tracking methods demonstrate that the proposed algorithm achieves favorable performance when the object undergoes partial occlusion, motion blur, and illumination changes.
The MUSIC algorithm for sparse objects: a compressed sensing analysis
NASA Astrophysics Data System (ADS)
Fannjiang, Albert C.
2011-03-01
The multiple signal classification (MUSIC) algorithm, and its extension for imaging sparse extended objects, with noisy data is analyzed by compressed sensing (CS) techniques. A thresholding rule is developed to augment the standard MUSIC algorithm. The notion of restricted isometry property (RIP) and an upper bound on the restricted isometry constant (RIC) are employed to establish sufficient conditions for the exact localization by MUSIC with or without noise. In the noiseless case, the sufficient condition gives an upper bound on the numbers of random sampling and incident directions necessary for exact localization. In the noisy case, the sufficient condition assumes additionally an upper bound for the noise-to-object ratio in terms of the RIC and the dynamic range of objects. This bound points to the super-resolution capability of the MUSIC algorithm. Rigorous comparison of performance between MUSIC and the CS minimization principle, basis pursuit denoising (BPDN), is given. In general, the MUSIC algorithm guarantees to recover, with high probability, s scatterers with n= {O}(s^2) random sampling and incident directions and sufficiently high frequency. For the favorable imaging geometry where the scatterers are distributed on a transverse plane MUSIC guarantees to recover, with high probability, s scatterers with a median frequency and n= {O}(s) random sampling/incident directions. Moreover, for the problems of spectral estimation and source localizations both BPDN and MUSIC guarantee, with high probability, to identify exactly the frequencies of random signals with the number n= {O}(s) of sampling times. However, in the absence of abundant realizations of signals, BPDN is the preferred method for spectral estimation. Indeed, BPDN can identify the frequencies approximately with just one realization of signals with the recovery error at worst linearly proportional to the noise level. Numerical results confirm that BPDN outperforms MUSIC in the well
Caçola, Priscila M; Pant, Mohan D
2014-10-01
The purpose was to use a multi-level statistical technique to analyze how children's age, motor proficiency, and cognitive styles interact to affect accuracy on reach estimation tasks via Motor Imagery and Visual Imagery. Results from the Generalized Linear Mixed Model analysis (GLMM) indicated that only the 7-year-old age group had significant random intercepts for both tasks. Motor proficiency predicted accuracy in reach tasks, and cognitive styles (object scale) predicted accuracy in the motor imagery task. GLMM analysis is suitable to explore age and other parameters of development. In this case, it allowed an assessment of motor proficiency interacting with age to shape how children represent, plan, and act on the environment.
The sparse matrix transform for covariance estimation and analysis of high dimensional signals.
Cao, Guangzhi; Bachega, Leonardo R; Bouman, Charles A
2011-03-01
Covariance estimation for high dimensional signals is a classically difficult problem in statistical signal analysis and machine learning. In this paper, we propose a maximum likelihood (ML) approach to covariance estimation, which employs a novel non-linear sparsity constraint. More specifically, the covariance is constrained to have an eigen decomposition which can be represented as a sparse matrix transform (SMT). The SMT is formed by a product of pairwise coordinate rotations known as Givens rotations. Using this framework, the covariance can be efficiently estimated using greedy optimization of the log-likelihood function, and the number of Givens rotations can be efficiently computed using a cross-validation procedure. The resulting estimator is generally positive definite and well-conditioned, even when the sample size is limited. Experiments on a combination of simulated data, standard hyperspectral data, and face image sets show that the SMT-based covariance estimates are consistently more accurate than both traditional shrinkage estimates and recently proposed graphical lasso estimates for a variety of different classes and sample sizes. An important property of the new covariance estimate is that it naturally yields a fast implementation of the estimated eigen-transformation using the SMT representation. In fact, the SMT can be viewed as a generalization of the classical fast Fourier transform (FFT) in that it uses "butterflies" to represent an orthonormal transform. However, unlike the FFT, the SMT can be used for fast eigen-signal analysis of general non-stationary signals.
Sparse recovery of the multimodal and dispersive characteristics of Lamb waves.
Harley, Joel B; Moura, José M F
2013-05-01
Guided waves in plates, known as Lamb waves, are characterized by complex, multimodal, and frequency dispersive wave propagation, which distort signals and make their analysis difficult. Estimating these multimodal and dispersive characteristics from experimental data becomes a difficult, underdetermined inverse problem. To accurately and robustly recover these multimodal and dispersive properties, this paper presents a methodology referred to as sparse wavenumber analysis based on sparse recovery methods. By utilizing a general model for Lamb waves, waves propagating in a plate structure, and robust l1 optimization strategies, sparse wavenumber analysis accurately recovers the Lamb wave's frequency-wavenumber representation with a limited number of surface mounted transducers. This is demonstrated with both simulated and experimental data in the presence of multipath reflections. With accurate frequency-wavenumber representations, sparse wavenumber synthesis is then used to accurately remove multipath interference in each measurement and predict the responses between arbitrary points on a plate.
Brief announcement: Hypergraph parititioning for parallel sparse matrix-matrix multiplication
Ballard, Grey; Druinsky, Alex; Knight, Nicholas; Schwartz, Oded
2015-01-01
The performance of parallel algorithms for sparse matrix-matrix multiplication is typically determined by the amount of interprocessor communication performed, which in turn depends on the nonzero structure of the input matrices. In this paper, we characterize the communication cost of a sparse matrix-matrix multiplication algorithm in terms of the size of a cut of an associated hypergraph that encodes the computation for a given input nonzero structure. Obtaining an optimal algorithm corresponds to solving a hypergraph partitioning problem. Furthermore, our hypergraph model generalizes several existing models for sparse matrix-vector multiplication, and we can leverage hypergraph partitioners developed for that computation to improve application-specific algorithms for multiplying sparse matrices.
Brief announcement: Hypergraph parititioning for parallel sparse matrix-matrix multiplication
Ballard, Grey; Druinsky, Alex; Knight, Nicholas; ...
2015-01-01
The performance of parallel algorithms for sparse matrix-matrix multiplication is typically determined by the amount of interprocessor communication performed, which in turn depends on the nonzero structure of the input matrices. In this paper, we characterize the communication cost of a sparse matrix-matrix multiplication algorithm in terms of the size of a cut of an associated hypergraph that encodes the computation for a given input nonzero structure. Obtaining an optimal algorithm corresponds to solving a hypergraph partitioning problem. Furthermore, our hypergraph model generalizes several existing models for sparse matrix-vector multiplication, and we can leverage hypergraph partitioners developed for that computationmore » to improve application-specific algorithms for multiplying sparse matrices.« less
Threshold partitioning of sparse matrices and applications to Markov chains
Choi, Hwajeong; Szyld, D.B.
1996-12-31
It is well known that the order of the variables and equations of a large, sparse linear system influences the performance of classical iterative methods. In particular if, after a symmetric permutation, the blocks in the diagonal have more nonzeros, classical block methods have a faster asymptotic rate of convergence. In this paper, different ordering and partitioning algorithms for sparse matrices are presented. They are modifications of PABLO. In the new algorithms, in addition to the location of the nonzeros, the values of the entries are taken into account. The matrix resulting after the symmetric permutation has dense blocks along the diagonal, and small entries in the off-diagonal blocks. Parameters can be easily adjusted to obtain, for example, denser blocks, or blocks with elements of larger magnitude. In particular, when the matrices represent Markov chains, the permuted matrices are well suited for block iterative methods that find the corresponding probability distribution. Applications to three types of methods are explored: (1) Classical block methods, such as Block Gauss Seidel. (2) Preconditioned GMRES, where a block diagonal preconditioner is used. (3) Iterative aggregation method (also called aggregation/disaggregation) where the partition obtained from the ordering algorithm with certain parameters is used as an aggregation scheme. In all three cases, experiments are presented which illustrate the performance of the methods with the new orderings. The complexity of the new algorithms is linear in the number of nonzeros and the order of the matrix, and thus adding little computational effort to the overall solution.
NASA Astrophysics Data System (ADS)
Vossos, Spyridon; Vossos, Elias
2016-08-01
closed LSTT is reduced, if one RIO has small velocity wrt another RIO. Thus, we have infinite number of closed LSTTs, each one with the corresponding SR theory. In case that we relate accelerated observers with variable metric of spacetime, we have the case of General Relativity (GR). For being that clear, we produce a generalized Schwarzschild metric, which is in accordance with any SR based on this closed complex LSTT and Einstein equations. The application of this kind of transformations to the SR and GR is obvious. But, the results may be applied to any linear space of dimension four endowed with steady or variable metric, whose elements (four- vectors) have spatial part (vector) with Euclidean metric.
Sparse Coding and Counting for Robust Visual Tracking
Liu, Risheng; Wang, Jing; Shang, Xiaoke; Wang, Yiyang; Su, Zhixun; Cai, Yu
2016-01-01
In this paper, we propose a novel sparse coding and counting method under Bayesian framework for visual tracking. In contrast to existing methods, the proposed method employs the combination of L0 and L1 norm to regularize the linear coefficients of incrementally updated linear basis. The sparsity constraint enables the tracker to effectively handle difficult challenges, such as occlusion or image corruption. To achieve real-time processing, we propose a fast and efficient numerical algorithm for solving the proposed model. Although it is an NP-hard problem, the proposed accelerated proximal gradient (APG) approach is guaranteed to converge to a solution quickly. Besides, we provide a closed solution of combining L0 and L1 regularized representation to obtain better sparsity. Experimental results on challenging video sequences demonstrate that the proposed method achieves state-of-the-art results both in accuracy and speed. PMID:27992474
An Efficient Scheme for Updating Sparse Cholesky Factors
NASA Technical Reports Server (NTRS)
Raghavan, Padma
2002-01-01
Raghavan had earlier developed the software package DCSPACK which can be used for solving sparse linear systems where the coefficient matrix is symmetric and positive definite (this project was not funded by NASA but by agencies such as NSF). DSCPACK-S is the serial code and DSCPACK-P is a parallel implementation suitable for multiprocessors or networks-of-workstations with message passing using MCI. The main algorithm used is the Cholesky factorization of a sparse symmetric positive positive definite matrix A = LL(T). The code can also compute the factorization A = LDL(T). The complexity of the software arises from several factors relating to the sparsity of the matrix A. A sparse N x N matrix A has typically less that cN nonzeroes where c is a small constant. If the matrix were dense, it would have O(N2) nonzeroes. The most complicated part of such sparse Cholesky factorization relates to fill-in, i.e., zeroes in the original matrix that become nonzeroes in the factor L. An efficient implementation depends to a large extent on complex data structures and on techniques from graph theory to reduce, identify, and manage fill. DSCPACK is based on an efficient multifrontal implementation with fill-managing algorithms and implementation arising from earlier research by Raghavan and others. Sparse Cholesky factorization is typically a four step process: (1) ordering to compute a fill-reducing numbering, (2) symbolic factorization to determine the nonzero structure of L, (3) numeric factorization to compute L, and, (4) triangular solution to solve L(T)x = y and Ly = b. The first two steps are symbolic and are performed using the graph of the matrix. The numeric factorization step is of dominant cost and there are several schemes for improving performance by exploiting the nested and dense structure of groups of columns in the factor. The latter are aimed at better utilization of the cache-memory hierarchy on modem processors to prevent cache-misses and provide execution
Optimal linear estimation under unknown nonlinear transform
Yi, Xinyang; Wang, Zhaoran; Caramanis, Constantine; Liu, Han
2016-01-01
Linear regression studies the problem of estimating a model parameter β* ∈ℝp, from n observations {(yi,xi)}i=1n from linear model yi = 〈xi, β*〉 + εi. We consider a significant generalization in which the relationship between 〈xi, β*〉 and yi is noisy, quantized to a single bit, potentially nonlinear, noninvertible, as well as unknown. This model is known as the single-index model in statistics, and, among other things, it represents a significant generalization of one-bit compressed sensing. We propose a novel spectral-based estimation procedure and show that we can recover β* in settings (i.e., classes of link function f) where previous algorithms fail. In general, our algorithm requires only very mild restrictions on the (unknown) functional relationship between yi and 〈xi, β*〉. We also consider the high dimensional setting where β* is sparse, and introduce a two-stage nonconvex framework that addresses estimation challenges in high dimensional regimes where p ≫ n. For a broad class of link functions between 〈xi, β*〉 and yi, we establish minimax lower bounds that demonstrate the optimality of our estimators in both the classical and high dimensional regimes.
Piccardo, Matteo; Bloino, Julien; Barone, Vincenzo
2015-01-01
Models going beyond the rigid-rotor and the harmonic oscillator levels are mandatory for providing accurate theoretical predictions for several spectroscopic properties. Different strategies have been devised for this purpose. Among them, the treatment by perturbation theory of the molecular Hamiltonian after its expansion in power series of products of vibrational and rotational operators, also referred to as vibrational perturbation theory (VPT), is particularly appealing for its computational efficiency to treat medium-to-large systems. Moreover, generalized (GVPT) strategies combining the use of perturbative and variational formalisms can be adopted to further improve the accuracy of the results, with the first approach used for weakly coupled terms, and the second one to handle tightly coupled ones. In this context, the GVPT formulation for asymmetric, symmetric, and linear tops is revisited and fully generalized to both minima and first-order saddle points of the molecular potential energy surface. The computational strategies and approximations that can be adopted in dealing with GVPT computations are pointed out, with a particular attention devoted to the treatment of symmetry and degeneracies. A number of tests and applications are discussed, to show the possibilities of the developments, as regards both the variety of treatable systems and eligible methods. © 2015 Wiley Periodicals, Inc. PMID:26345131
Piccardo, Matteo; Bloino, Julien; Barone, Vincenzo
2015-08-05
Models going beyond the rigid-rotor and the harmonic oscillator levels are mandatory for providing accurate theoretical predictions for several spectroscopic properties. Different strategies have been devised for this purpose. Among them, the treatment by perturbation theory of the molecular Hamiltonian after its expansion in power series of products of vibrational and rotational operators, also referred to as vibrational perturbation theory (VPT), is particularly appealing for its computational efficiency to treat medium-to-large systems. Moreover, generalized (GVPT) strategies combining the use of perturbative and variational formalisms can be adopted to further improve the accuracy of the results, with the first approach used for weakly coupled terms, and the second one to handle tightly coupled ones. In this context, the GVPT formulation for asymmetric, symmetric, and linear tops is revisited and fully generalized to both minima and first-order saddle points of the molecular potential energy surface. The computational strategies and approximations that can be adopted in dealing with GVPT computations are pointed out, with a particular attention devoted to the treatment of symmetry and degeneracies. A number of tests and applications are discussed, to show the possibilities of the developments, as regards both the variety of treatable systems and eligible methods.
An empirical investigation of sparse distributed memory using discrete speech recognition
NASA Technical Reports Server (NTRS)
Danforth, Douglas G.
1990-01-01
Presented here is a step by step analysis of how the basic Sparse Distributed Memory (SDM) model can be modified to enhance its generalization capabilities for classification tasks. Data is taken from speech generated by a single talker. Experiments are used to investigate the theory of associative memories and the question of generalization from specific instances.
Odille, Fabrice G J; Jónsson, Stefán; Stjernqvist, Susann; Rydén, Tobias; Wärnmark, Kenneth
2007-01-01
A general mathematical model for the characterization of the dynamic (kinetically labile) association of supramolecular assemblies in solution is presented. It is an extension of the equal K (EK) model by the stringent use of linear algebra to allow for the simultaneous presence of an unlimited number of different units in the resulting assemblies. It allows for the analysis of highly complex dynamic equilibrium systems in solution, including both supramolecular homo- and copolymers without the recourse to extensive approximations, in a field in which other analytical methods are difficult. The derived mathematical methodology makes it possible to analyze dynamic systems such as supramolecular copolymers regarding for instance the degree of polymerization, the distribution of a given monomer in different copolymers as well as its position in an aggregate. It is to date the only general means to characterize weak supramolecular systems. The model was fitted to NMR dilution titration data by using the program Matlab, and a detailed algorithm for the optimization of the different parameters has been developed. The methodology is applied to a case study, a hydrogen-bonded supramolecular system, salen 4+porphyrin 5. The system is formally a two-component system but in reality a three-component system. This results in a complex dynamic system in which all monomers are associated to each other by hydrogen bonding with different association constants, resulting in homo- and copolymers 4n5m as well as cyclic structures 6 and 7, in addition to free 4 and 5. The system was analyzed by extensive NMR dilution titrations at variable temperatures. All chemical shifts observed at different temperatures were used in the fitting to obtain the DeltaH degrees and DeltaS degrees values producing the best global fit. From the derived general mathematical expressions, system 4+5 could be characterized with respect to above-mentioned parameters.
Shevenell, L.A.; Beauchamp, J.J.
1994-11-01
Several waste disposal sites are located on or adjacent to the karstic Maynardville Limestone (Cmn) and the Copper Ridge Dolomite (Ccr) at the Oak Ridge Y-12 Plant. These formations receive contaminants in groundwaters from nearby disposal sites, which can be transported quite rapidly due to the karst flow system. In order to evaluate transport processes through the karst aquifer, the solutional aspects of the formations must be characterized. As one component of this characterization effort, statistical analyses were conducted on the data related to cavities in order to determine if a suitable model could be identified that is capable of predicting the probability of cavity size or distribution in locations for which drilling data are not available. Existing data on the locations (East, North coordinates), depths (and elevations), and sizes of known conduits and other water zones were used in the analyses. Two different models were constructed in the attempt to predict the distribution of cavities in the vicinity of the Y-12 Plant: General Linear Models (GLM), and Logistic Regression Models (LOG). Each of the models attempted was very sensitive to the data set used. Models based on subsets of the full data set were found to do an inadequate job of predicting the behavior of the full data set. The fact that the Ccr and Cmn data sets differ significantly is not surprising considering the hydrogeology of the two formations differs. Flow in the Cmn is generally at elevations between 600 and 950 ft and is dominantly strike parallel through submerged, partially mud-filled cavities with sizes up to 40 ft, but more typically less than 5 ft. Recognized flow in the Ccr is generally above 950 ft elevation, with flow both parallel and perpendicular to geologic strike through conduits, which tend to be large than those on the Cnm, and are often not fully saturated at the shallower depths.
NASA Astrophysics Data System (ADS)
Sun, Yankui; Li, Shan; Sun, Zhongyang
2017-01-01
We propose a framework for automated detection of dry age-related macular degeneration (AMD) and diabetic macular edema (DME) from retina optical coherence tomography (OCT) images, based on sparse coding and dictionary learning. The study aims to improve the classification performance of state-of-the-art methods. First, our method presents a general approach to automatically align and crop retina regions; then it obtains global representations of images by using sparse coding and a spatial pyramid; finally, a multiclass linear support vector machine classifier is employed for classification. We apply two datasets for validating our algorithm: Duke spectral domain OCT (SD-OCT) dataset, consisting of volumetric scans acquired from 45 subjects-15 normal subjects, 15 AMD patients, and 15 DME patients; and clinical SD-OCT dataset, consisting of 678 OCT retina scans acquired from clinics in Beijing-168, 297, and 213 OCT images for AMD, DME, and normal retinas, respectively. For the former dataset, our classifier correctly identifies 100%, 100%, and 93.33% of the volumes with DME, AMD, and normal subjects, respectively, and thus performs much better than the conventional method; for the latter dataset, our classifier leads to a correct classification rate of 99.67%, 99.67%, and 100.00% for DME, AMD, and normal images, respectively.
Robust compressive sensing of sparse signals: a review
NASA Astrophysics Data System (ADS)
Carrillo, Rafael E.; Ramirez, Ana B.; Arce, Gonzalo R.; Barner, Kenneth E.; Sadler, Brian M.
2016-12-01
Compressive sensing generally relies on the ℓ 2 norm for data fidelity, whereas in many applications, robust estimators are needed. Among the scenarios in which robust performance is required, applications where the sampling process is performed in the presence of impulsive noise, i.e., measurements are corrupted by outliers, are of particular importance. This article overviews robust nonlinear reconstruction strategies for sparse signals based on replacing the commonly used ℓ 2 norm by M-estimators as data fidelity functions. The derived methods outperform existing compressed sensing techniques in impulsive environments, while achieving good performance in light-tailed environments, thus offering a robust framework for CS.
JiTTree: A Just-in-Time Compiled Sparse GPU Volume Data Structure.
Labschütz, Matthias; Bruckner, Stefan; Gröller, M Eduard; Hadwiger, Markus; Rautek, Peter
2016-01-01
Sparse volume data structures enable the efficient representation of large but sparse volumes in GPU memory for computation and visualization. However, the choice of a specific data structure for a given data set depends on several factors, such as the memory budget, the sparsity of the data, and data access patterns. In general, there is no single optimal sparse data structure, but a set of several candidates with individual strengths and drawbacks. One solution to this problem are hybrid data structures which locally adapt themselves to the sparsity. However, they typically suffer from increased traversal overhead which limits their utility in many applications. This paper presents JiTTree, a novel sparse hybrid volume data structure that uses just-in-time compilation to overcome these problems. By combining multiple sparse data structures and reducing traversal overhead we leverage their individual advantages. We demonstrate that hybrid data structures adapt well to a large range of data sets. They are especially superior to other sparse data structures for data sets that locally vary in sparsity. Possible optimization criteria are memory, performance and a combination thereof. Through just-in-time (JIT) compilation, JiTTree reduces the traversal overhead of the resulting optimal data structure. As a result, our hybrid volume data structure enables efficient computations on the GPU, while being superior in terms of memory usage when compared to non-hybrid data structures.
Sparse Representation-Based Image Quality Index With Adaptive Sub-Dictionaries.
Li, Leida; Cai, Hao; Zhang, Yabin; Lin, Weisi; Kot, Alex C; Sun, Xingming
2016-08-01
Distortions cause structural changes in digital images, leading to degraded visual quality. Dictionary-based sparse representation has been widely studied recently due to its ability to extract inherent image structures. Meantime, it can extract image features with slightly higher level semantics. Intuitively, sparse representation can be used for image quality assessment, because visible distortions can cause significant changes to the sparse features. In this paper, a new sparse representation-based image quality assessment model is proposed based on the construction of adaptive sub-dictionaries. An overcomplete dictionary trained from natural images is employed to capture the structure changes between the reference and distorted images by sparse feature extraction via adaptive sub-dictionary selection. Based on the observation that image sparse features are invariant to weak degradations and the perceived image quality is generally influenced by diverse issues, three auxiliary quality features are added, including gradient, color, and luminance information. The proposed method is not sensitive to training images, so a universal dictionary can be adopted for quality evaluation. Extensive experiments on five public image quality databases demonstrate that the proposed method produces the state-of-the-art results, and it delivers consistently well performances when tested in different image quality databases.
Deploying temporary networks for upscaling of sparse network stations
NASA Astrophysics Data System (ADS)
Coopersmith, Evan J.; Cosh, Michael H.; Bell, Jesse E.; Kelly, Victoria; Hall, Mark; Palecki, Michael A.; Temimi, Marouane
2016-10-01
Soil observations networks at the national scale play an integral role in hydrologic modeling, drought assessment, agricultural decision support, and our ability to understand climate change. Understanding soil moisture variability is necessary to apply these measurements to model calibration, business and consumer applications, or even human health issues. The installation of soil moisture sensors as sparse, national networks is necessitated by limited financial resources. However, this results in the incomplete sampling of the local heterogeneity of soil type, vegetation cover, topography, and the fine spatial distribution of precipitation events. To this end, temporary networks can be installed in the areas surrounding a permanent installation within a sparse network. The temporary networks deployed in this study provide a more representative average at the 3 km and 9 km scales, localized about the permanent gauge. The value of such temporary networks is demonstrated at test sites in Millbrook, New York and Crossville, Tennessee. The capacity of a single U.S. Climate Reference Network (USCRN) sensor set to approximate the average of a temporary network at the 3 km and 9 km scales using a simple linear scaling function is tested. The capacity of a temporary network to provide reliable estimates with diminishing numbers of sensors, the temporal stability of those networks, and ultimately, the relationship of the variability of those networks to soil moisture conditions at the permanent sensor are investigated. In this manner, this work demonstrates the single-season installation of a temporary network as a mechanism to characterize the soil moisture variability at a permanent gauge within a sparse network.
VIM-based dynamic sparse grid approach to partial differential equations.
Mei, Shu-Li
2014-01-01
Combining the variational iteration method (VIM) with the sparse grid theory, a dynamic sparse grid approach for nonlinear PDEs is proposed in this paper. In this method, a multilevel interpolation operator is constructed based on the sparse grids theory firstly. The operator is based on the linear combination of the basic functions and independent of them. Second, by means of the precise integration method (PIM), the VIM is developed to solve the nonlinear system of ODEs which is obtained from the discretization of the PDEs. In addition, a dynamic choice scheme on both of the inner and external grid points is proposed. It is different from the traditional interval wavelet collocation method in which the choice of both of the inner and external grid points is dynamic. The numerical experiments show that our method is better than the traditional wavelet collocation method, especially in solving the PDEs with the Nuemann boundary conditions.
Analog system for computing sparse codes
Rozell, Christopher John; Johnson, Don Herrick; Baraniuk, Richard Gordon; Olshausen, Bruno A.; Ortman, Robert Lowell
2010-08-24
A parallel dynamical system for computing sparse representations of data, i.e., where the data can be fully represented in terms of a small number of non-zero code elements, and for reconstructing compressively sensed images. The system is based on the principles of thresholding and local competition that solves a family of sparse approximation problems corresponding to various sparsity metrics. The system utilizes Locally Competitive Algorithms (LCAs), nodes in a population continually compete with neighboring units using (usually one-way) lateral inhibition to calculate coefficients representing an input in an over complete dictionary.
Tensor methods for large, sparse unconstrained optimization
Bouaricha, A.
1996-11-01
Tensor methods for unconstrained optimization were first introduced by Schnabel and Chow [SIAM J. Optimization, 1 (1991), pp. 293-315], who describe these methods for small to moderate size problems. This paper extends these methods to large, sparse unconstrained optimization problems. This requires an entirely new way of solving the tensor model that makes the methods suitable for solving large, sparse optimization problems efficiently. We present test results for sets of problems where the Hessian at the minimizer is nonsingular and where it is singular. These results show that tensor methods are significantly more efficient and more reliable than standard methods based on Newton`s method.
Independence test for sparse data
NASA Astrophysics Data System (ADS)
García, J. E.; González-López, V. A.
2016-06-01
In this paper a new non-parametric independence test is presented. García and González-López (2014) [1] introduced the LIS test for the hypothesis of independence between two continuous random variables, the test proposed in this work is a generalization of the LIS test. The new test does not require the assumption of continuity for the random variables, it test is applied to two datasets and also compared with the Pearson's Chi-squared test.
Bacheler, N.M.; Hightower, J.E.; Burdick, S.M.; Paramore, L.M.; Buckel, J.A.; Pollock, K.H.
2010-01-01
Estimating the selectivity patterns of various fishing gears is a critical component of fisheries stock assessment due to the difficulty in obtaining representative samples from most gears. We used short-term recoveries (n = 3587) of tagged red drum Sciaenops ocellatus to directly estimate age- and length-based selectivity patterns using generalized linear models. The most parsimonious models were selected using AIC, and standard deviations were estimated using simulations. Selectivity of red drum was dependent upon the regulation period in which the fish was caught, the gear used to catch the fish (i.e., hook-and-line, gill nets, pound nets), and the fate of the fish upon recovery (i.e., harvested or released); models including all first-order interactions between main effects outperformed models without interactions. Selectivity of harvested fish was generally dome-shaped and shifted toward larger, older fish in response to regulation changes. Selectivity of caught-and-released red drum was highest on the youngest and smallest fish in the early and middle regulation periods, but increased on larger, legal-sized fish in the late regulation period. These results suggest that catch-and-release mortality has consistently been high for small, young red drum, but has recently become more common in larger, older fish. This method of estimating selectivity from short-term tag recoveries is valuable because it is simpler than full tag-return models, and may be more robust because yearly fishing and natural mortality rates do not need to be modeled and estimated. ?? 2009 Elsevier B.V.
Burdick, Summer M.; Hightower, Joseph E.; Bacheler, Nathan M.; Paramore, Lee M.; Buckel, Jeffrey A.; Pollock, Kenneth H.
2010-01-01
Estimating the selectivity patterns of various fishing gears is a critical component of fisheries stock assessment due to the difficulty in obtaining representative samples from most gears. We used short-term recoveries (n = 3587) of tagged red drum Sciaenops ocellatus to directly estimate age- and length-based selectivity patterns using generalized linear models. The most parsimonious models were selected using AIC, and standard deviations were estimated using simulations. Selectivity of red drum was dependent upon the regulation period in which the fish was caught, the gear used to catch the fish (i.e., hook-and-line, gill nets, pound nets), and the fate of the fish upon recovery (i.e., harvested or released); models including all first-order interactions between main effects outperformed models without interactions. Selectivity of harvested fish was generally dome-shaped and shifted toward larger, older fish in response to regulation changes. Selectivity of caught-and-released red drum was highest on the youngest and smallest fish in the early and middle regulation periods, but increased on larger, legal-sized fish in the late regulation period. These results suggest that catch-and-release mortality has consistently been high for small, young red drum, but has recently become more common in larger, older fish. This method of estimating selectivity from short-term tag recoveries is valuable because it is simpler than full tag-return models, and may be more robust because yearly fishing and natural mortality rates do not need to be modeled and estimated.
NASA Astrophysics Data System (ADS)
Pulquério, Mário; Garrett, Pedro; Santos, Filipe Duarte; Cruz, Maria João
2015-04-01
Portugal is on a climate change hot spot region, where precipitation is expected to decrease with important impacts regarding future water availability. As one of the European countries affected more by droughts in the last decades, it is important to assess how future precipitation regimes will change in order to study its impacts on water resources. Due to the coarse scale of global circulation models, it is often needed to downscale climate variables to the regional or local scale using statistical and/or dynamical techniques. In this study, we tested the use of a generalized linear model, as implemented in the program GLIMCLIM, to downscale precipitation for the center of Portugal where the Tagus basin is located. An analysis of the method performance is done as well as an evaluation of future precipitation trends and extremes for the twenty-first century. Additionally, we perform the first analysis of the evolution of droughts in climate change scenarios by the Standardized Precipitation Index in the study area. Results show that GLIMCLIM is able to capture the precipitation's interannual variation and seasonality correctly. However, summer precipitation is considerably overestimated. Additionally, precipitation extremes are in general well recovered, but high daily rainfall may be overestimated, and dry spell lengths are not correctly recovered by the model. Downscaled projections show a reduction in precipitation between 19 and 28 % at the end of the century. Results indicate that precipitation extremes will decrease and the magnitude of droughts can increase up to three times in relation to the 1961-1990 period which can have strong ecological, social, and economic impacts.
Sparse Multi-Static Arrays for Near-Field Millimeter-Wave Imaging
Sheen, David M.
2013-12-31
This paper describes a novel design technique for sparse multi-static linear arrays. The methods described allow the development of densely sampled linear arrays suitable for high-resolution near-field imaging that require dramatically fewer antenna and switch elements than the previous state of the art. The techniques used are related to sparse array techniques used in radio astronomy applications, but differ significantly in design due to the transmit-receive nature of the arrays, and the application to linear arrays that achieve dense uniform sampling suitable for high-resolution near-field imaging. As many as 3 to 5 or more samples per antenna can be obtained, compared to 1 sample per antenna for the current state of the art. This could dramatically reduce cost and improve performance over current active millimeter-wave imaging systems.
NASA Astrophysics Data System (ADS)
Fujii, Y.; Nakano, T.; Usui, N.; Matsumoto, S.; Tsujino, H.; Kamachi, M.
2014-12-01
This study develops a strategy for tracing a target water mass, and applies it to analyzing the pathway of the North Pacific Intermediate Water (NPIW) from the subarctic gyre to the northwestern part of the subtropical gyre south of Japan in a simulation of an ocean general circulation model. This strategy estimates the pathway of the water mass that travels from an origin to a destination area during a specific period using a conservation property concerning tangent linear and adjoint models. In our analysis, a large fraction of the low salinity origin water mass of NPIW initially comes from the Okhotsk or Bering Sea, flows through the southeastern side of the Kuril Islands, and is advected to the Mixed Water Region (MWR) by the Oyashio current. It then enters the Kuroshio Extension (KE) at the first KE ridge, and is advected eastward by the KE current. However, it deviates southward from the KE axis around 158°E over the Shatsky Rise, or around 170ºE on the western side of the Emperor Seamount Chain, and enters the subtropical gyre. It is finally transported westward by the recirculation flow. This pathway corresponds well to the shortcut route of NPIW from MWR to the region south of Japan inferred from analysis of the long-term freshening trend of NPIW observation.
Rio, Daniel E; Rawlings, Robert R; Woltz, Lawrence A; Gilman, Jodi; Hommer, Daniel W
2013-01-01
A linear time-invariant model based on statistical time series analysis in the Fourier domain for single subjects is further developed and applied to functional MRI (fMRI) blood-oxygen level-dependent (BOLD) multivariate data. This methodology was originally developed to analyze multiple stimulus input evoked response BOLD data. However, to analyze clinical data generated using a repeated measures experimental design, the model has been extended to handle multivariate time series data and demonstrated on control and alcoholic subjects taken from data previously analyzed in the temporal domain. Analysis of BOLD data is typically carried out in the time domain where the data has a high temporal correlation. These analyses generally employ parametric models of the hemodynamic response function (HRF) where prewhitening of the data is attempted using autoregressive (AR) models for the noise. However, this data can be analyzed in the Fourier domain. Here, assumptions made on the noise structure are less restrictive, and hypothesis tests can be constructed based on voxel-specific nonparametric estimates of the hemodynamic transfer function (HRF in the Fourier domain). This is especially important for experimental designs involving multiple states (either stimulus or drug induced) that may alter the form of the response function.
Spence, Jeffrey S; Brier, Matthew R; Hart, John; Ferree, Thomas C
2013-03-01
Linear statistical models are used very effectively to assess task-related differences in EEG power spectral analyses. Mixed models, in particular, accommodate more than one variance component in a multisubject study, where many trials of each condition of interest are measured on each subject. Generally, intra- and intersubject variances are both important to determine correct standard errors for inference on functions of model parameters, but it is often assumed that intersubject variance is the most important consideration in a group study. In this article, we show that, under common assumptions, estimates of some functions of model parameters, including estimates of task-related differences, are properly tested relative to the intrasubject variance component only. A substantial gain in statistical power can arise from the proper separation of variance components when there is more than one source of variability. We first develop this result analytically, then show how it benefits a multiway factoring of spectral, spatial, and temporal components from EEG data acquired in a group of healthy subjects performing a well-studied response inhibition task.
Wen, Xuesong; Li, Jing; Dickson, James S
2014-10-01
Translocation of foodborne pathogens into the interior tissues of pork through moisture enhancement may be of concern if the meat is undercooked. In the present study, a five-strain mixture of Campylobacter jejuni or Salmonella enterica Typhimurium was evenly spread on the surface of fresh pork loins. Pork loins were injected, sliced, vacuum packaged, and stored. After storage, sliced pork was cooked by traditional grilling. Survival of Salmonella Typhimurium and C. jejuni in the interior tissues of the samples were analyzed by enumeration. The populations of these pathogens dropped below the detection limit (10 colony-forming units/g) in most samples that were cooked to 71.1°C or above. The general linear mixed model procedure was used to model the association between risk factors and the presence/absence of these pathogens after cooking. Estimated regression coefficients associated with the fixed effects indicated that the recovery probability of Salmonella Typhimurium was negatively associated with increasing level of enhancement. The effects of moisture enhancement and cooking on the recovery probability of C. jejuni were moderated by storage temperature. Our findings will assist food processors and regulatory agencies with science-based evaluation of the current processing, storage condition, and cooking guideline for moisture-enhanced pork.
NASA Astrophysics Data System (ADS)
Fujii, Yosuke; Nakano, Toshiya; Usui, Norihisa; Matsumoto, Satoshi; Tsujino, Hiroyuki; Kamachi, Masafumi
2013-04-01
This study develops a strategy for tracing a target water mass, and applies it to analyzing the pathway of the North Pacific Intermediate Water (NPIW) from the subarctic gyre to the northwestern part of the subtropical gyre south of Japan in a simulation of an ocean general circulation model. This strategy estimates the pathway of the water mass that travels from an origin to a destination area during a specific period using a conservation property concerning tangent linear and adjoint models. In our analysis, a large fraction of the low salinity origin water mass of NPIW initially comes from the Okhotsk or Bering Sea, flows through the southeastern side of the Kuril Islands, and is advected to the Mixed Water Region (MWR) by the Oyashio current. It then enters the Kuroshio Extension (KE) at the first KE ridge, and is advected eastward by the KE current. However, it deviates southward from the KE axis around 158°E over the Shatsky Rise, or around 170°E on the western side of the Emperor Seamount Chain, and enters the subtropical gyre. It is finally transported westward by the recirculation flow. This pathway corresponds well to the shortcut route of NPIW from MWR to the region south of Japan inferred from analysis of the long-term freshening trend of NPIW observation. Copyright 2013 John Wiley & Sons, Ltd.
Semi-implicit Integration Factor Methods on Sparse Grids for High-Dimensional Systems
Wang, Dongyong; Chen, Weitao; Nie, Qing
2015-01-01
Numerical methods for partial differential equations in high-dimensional spaces are often limited by the curse of dimensionality. Though the sparse grid technique, based on a one-dimensional hierarchical basis through tensor products, is popular for handling challenges such as those associated with spatial discretization, the stability conditions on time step size due to temporal discretization, such as those associated with high-order derivatives in space and stiff reactions, remain. Here, we incorporate the sparse grids with the implicit integration factor method (IIF) that is advantageous in terms of stability conditions for systems containing stiff reactions and diffusions. We combine IIF, in which the reaction is treated implicitly and the diffusion is treated explicitly and exactly, with various sparse grid techniques based on the finite element and finite difference methods and a multi-level combination approach. The overall method is found to be efficient in terms of both storage and computational time for solving a wide range of PDEs in high dimensions. In particular, the IIF with the sparse grid combination technique is flexible and effective in solving systems that may include cross-derivatives and non-constant diffusion coefficients. Extensive numerical simulations in both linear and nonlinear systems in high dimensions, along with applications of diffusive logistic equations and Fokker-Planck equations, demonstrate the accuracy, efficiency, and robustness of the new methods, indicating potential broad applications of the sparse grid-based integration factor method. PMID:25897178
High-performance parallel sparse-direct triangular solves (Invited)
NASA Astrophysics Data System (ADS)
Poulson, J.; Ying, L.
2013-12-01
Geophysical inverse problems are increasingly posed in the frequency domain in a manner which requires solving many challenging heterogeneous 3D Helmholtz or linear elastic wave equations at each iteration. One effective means of solving such problems, at least when there is no large-scale internal resonance, is to use moving-PML "sweeping preconditioners". Each application of the sweeping preconditioner involves performing many modest-sized sparse-direct triangular solves -- unfortunately, one at a time. While P. et al. have shown that, with a careful implementation of a distributed sparse-direct solver [1,2], challenging 3D problems approaching a billion degrees of freedom can be solved in a few minutes using less than 10,000 cores, this talk discusses how to leverage the existence of many right-hand sides in order to increase the performance of the preconditioner applications by orders of magnitude. [1] http://github.com/poulson/Clique [2] http://github.com/poulson/PSP
Sparse Downscaling and Adaptive Fusion of Multi-sensor Precipitation
NASA Astrophysics Data System (ADS)
Ebtehaj, M.; Foufoula, E.
2011-12-01
The past decades have witnessed a remarkable emergence of new sources of multiscale multi-sensor precipitation data including data from global spaceborne active and passive sensors, regional ground based weather surveillance radars and local rain-gauges. Resolution enhancement of remotely sensed rainfall and optimal integration of multi-sensor data promise a posteriori estimates of precipitation fluxes with increased accuracy and resolution to be used in hydro-meteorological applications. In this context, new frameworks are proposed for resolution enhancement and multiscale multi-sensor precipitation data fusion, which capitalize on two main observations: (1) sparseness of remotely sensed precipitation fields in appropriately chosen transformed domains, (e.g., in wavelet space) which promotes the use of the newly emerged theory of sparse representation and compressive sensing for resolution enhancement; (2) a conditionally Gaussian Scale Mixture (GSM) parameterization in the wavelet domain which allows exploiting the efficient linear estimation methodologies, while capturing the non-Gaussian data structure of rainfall. The proposed methodologies are demonstrated using a data set of coincidental observations of precipitation reflectivity images by the spaceborne precipitation radar (PR) aboard the Tropical Rainfall Measurement Mission (TRMM) satellite and ground-based NEXRAD weather surveillance Doppler radars. Uniqueness and stability of the solution, capturing non-Gaussian singular structure of rainfall, reduced uncertainty of estimation and efficiency of computation are the main advantages of the proposed methodologies over the commonly used standard Gaussian techniques.
Configurable hardware integrate and fire neurons for sparse approximation.
Shapero, Samuel; Rozell, Christopher; Hasler, Paul
2013-09-01
Sparse approximation is an important optimization problem in signal and image processing applications. A Hopfield-Network-like system of integrate and fire (IF) neurons is proposed as a solution, using the Locally Competitive Algorithm (LCA) to solve an overcomplete L1 sparse approximation problem. A scalable system architecture is described, including IF neurons with a nonlinear firing function, and current-based synapses to provide linear computation. A network of 18 neurons with 12 inputs is implemented on the RASP 2.9v chip, a Field Programmable Analog Array (FPAA) with directly programmable floating gate elements. Said system uses over 1400 floating gates, the largest system programmed on a FPAA to date. The circuit successfully reproduced the outputs of a digital optimization program, converging to within 4.8% RMS, and an objective cost only 1.7% higher on average. The active circuit consumed 559 μA of current at 2.4 V and converges on solutions in 25 μs, with measurement of the converged spike rate taking an additional 1 ms. Extrapolating the scaling trends to a N=1000 node system, the spiking LCA compares favorably with state-of-the-art digital solutions, and analog solutions using a non-spiking approach.
Second SIAM conference on sparse matrices: Abstracts. Final technical report
1996-12-31
This report contains abstracts on the following topics: invited and long presentations (IP1 & LP1); sparse matrix reordering & graph theory I; sparse matrix tools & environments I; eigenvalue computations I; iterative methods & acceleration techniques I; applications I; parallel algorithms I; sparse matrix reordering & graphy theory II; sparse matrix tool & environments II; least squares & optimization I; iterative methods & acceleration techniques II; applications II; eigenvalue computations II; least squares & optimization II; parallel algorithms II; sparse direct methods; iterative methods & acceleration techniques III; eigenvalue computations III; and sparse matrix reordering & graph theory III.
Structured Sparse Method for Hyperspectral Unmixing
NASA Astrophysics Data System (ADS)
Zhu, Feiyun; Wang, Ying; Xiang, Shiming; Fan, Bin; Pan, Chunhong
2014-02-01
Hyperspectral Unmixing (HU) has received increasing attention in the past decades due to its ability of unveiling information latent in hyperspectral data. Unfortunately, most existing methods fail to take advantage of the spatial information in data. To overcome this limitation, we propose a Structured Sparse regularized Nonnegative Matrix Factorization (SS-NMF) method based on the following two aspects. First, we incorporate a graph Laplacian to encode the manifold structures embedded in the hyperspectral data space. In this way, the highly similar neighboring pixels can be grouped together. Second, the lasso penalty is employed in SS-NMF for the fact that pixels in the same manifold structure are sparsely mixed by a common set of relevant bases. These two factors act as a new structured sparse constraint. With this constraint, our method can learn a compact space, where highly similar pixels are grouped to share correlated sparse representations. Experiments on real hyperspectral data sets with different noise levels demonstrate that our method outperforms the state-of-the-art methods significantly.
Sparse matrix orderings for factorized inverse preconditioners
Benzi, M.; Tuama, M.
1998-09-01
The effect of reorderings on the performance of factorized sparse approximate inverse preconditioners is considered. It is shown that certain reorderings can be very beneficial both in the preconditioner construction phase and in terms of the rate of convergence of the preconditioned iteration.
Multilevel sparse functional principal component analysis.
Di, Chongzhi; Crainiceanu, Ciprian M; Jank, Wolfgang S
2014-01-29
We consider analysis of sparsely sampled multilevel functional data, where the basic observational unit is a function and data have a natural hierarchy of basic units. An example is when functions are recorded at multiple visits for each subject. Multilevel functional principal component analysis (MFPCA; Di et al. 2009) was proposed for such data when functions are densely recorded. Here we consider the case when functions are sparsely sampled and may contain only a few observations per function. We exploit the multilevel structure of covariance operators and achieve data reduction by principal component decompositions at both between and within subject levels. We address inherent methodological differences in the sparse sampling context to: 1) estimate the covariance operators; 2) estimate the functional principal component scores; 3) predict the underlying curves. Through simulations the proposed method is able to discover dominating modes of variations and reconstruct underlying curves well even in sparse settings. Our approach is illustrated by two applications, the Sleep Heart Health Study and eBay auctions.
SAR Image Despeckling Via Structural Sparse Representation
NASA Astrophysics Data System (ADS)
Lu, Ting; Li, Shutao; Fang, Leyuan; Benediktsson, Jón Atli
2016-12-01
A novel synthetic aperture radar (SAR) image despeckling method based on structural sparse representation is introduced. The proposed method utilizes the fact that different regions in SAR images correspond to varying terrain reflectivity. Therefore, SAR images can be split into a heterogeneous class (with a varied terrain reflectivity) and a homogeneous class (with a constant terrain reflectivity). In the proposed method, different sparse representation based despeckling schemes are designed by combining the different region characteristics in SAR images. For heterogeneous regions with rich structure and texture information, structural dictionaries are learned to appropriately represent varied structural characteristics. Specifically, each patch in these regions is sparsely coded with the best fitted structural dictionary, thus good structure preservation can be obtained. For homogenous regions without rich structure and texture information, the highly redundant photometric self-similarity is exploited to suppress speckle noise without introducing artifacts. That is achieved by firstly learning the sub-dictionary, then simultaneously sparsely coding for each group of photometrically similar image patches. Visual and objective experimental results demonstrate the superiority of the proposed method over the-state-of-the-art methods.
Maxdenominator Reweighted Sparse Representation for Tumor Classification
Li, Weibiao; Liao, Bo; Zhu, Wen; Chen, Min; Peng, Li; Wei, Xiaohui; Gu, Changlong; Li, Keqin
2017-01-01
The classification of tumors is crucial for the proper treatment of cancer. Sparse representation-based classifier (SRC) exhibits good classification performance and has been successfully used to classify tumors using gene expression profile data. In this study, we propose a three-step maxdenominator reweighted sparse representation classification (MRSRC) method to classify tumors. First, we extract a set of metagenes from the training samples. These metagenes can capture the structures inherent to the data and are more effective for classification than the original gene expression data. Second, we use a reweighted regularization method to obtain the sparse representation coefficients. Reweighted regularization can enhance sparsity and obtain better sparse representation coefficients. Third, we classify the data by utilizing a maxdenominator residual error function. Maxdenominator strategy can reduce the residual error and improve the accuracy of the final classification. Extensive experiments using publicly available gene expression profile data sets show that the performance of MRSRC is comparable with or better than many existing representative methods. PMID:28393883
Accuracy of femur reconstruction from sparse geometric data using a statistical shape model.
Zhang, Ju; Besier, Thor F
2017-04-01
Sparse geometric information from limited field-of-view medical images is often used to reconstruct the femur in biomechanical models of the hip and knee. However, the full femur geometry is needed to establish boundary conditions such as muscle attachment sites and joint axes which define the orientation of joint loads. Statistical shape models have been used to estimate the geometry of the full femur from varying amounts of sparse geometric information. However, the effect that different amounts of sparse data have on reconstruction accuracy has not been systematically assessed. In this study, we compared shape model and linear scaling reconstruction of the full femur surface from varying proportions of proximal and distal partial femur geometry in combination with morphometric and landmark data. We quantified reconstruction error in terms of surface-to-surface error as well as deviations in the reconstructed femur's anatomical coordinate system which is important for biomechanical models. Using a partial proximal femur surface, mean shape model-based reconstruction surface error was 1.8 mm with 0.15° or less anatomic axis error, compared to 19.1 mm and 2.7-5.6° for linear scaling. Similar results were found when using a partial distal surface. However, varying amounts of proximal or distal partial surface data had a negligible effect on reconstruction accuracy. Our results show that given an appropriate set of sparse geometric data, a shape model can reconstruct full femur geometry with far greater accuracy than simple scaling.
Nonlinear Spike-And-Slab Sparse Coding for Interpretable Image Encoding
Shelton, Jacquelyn A.; Sheikh, Abdul-Saboor; Bornschein, Jörg; Sterne, Philip; Lücke, Jörg
2015-01-01
Sparse coding is a popular approach to model natural images but has faced two main challenges: modelling low-level image components (such as edge-like structures and their occlusions) and modelling varying pixel intensities. Traditionally, images are modelled as a sparse linear superposition of dictionary elements, where the probabilistic view of this problem is that the coefficients follow a Laplace or Cauchy prior distribution. We propose a novel model that instead uses a spike-and-slab prior and nonlinear combination of components. With the prior, our model can easily represent exact zeros for e.g. the absence of an image component, such as an edge, and a distribution over non-zero pixel intensities. With the nonlinearity (the nonlinear max combination rule), the idea is to target occlusions; dictionary elements correspond to image components that can occlude each other. There are major consequences of the model assumptions made by both (non)linear approaches, thus the main goal of this paper is to isolate and highlight differences between them. Parameter optimization is analytically and computationally intractable in our model, thus as a main contribution we design an exact Gibbs sampler for efficient inference which we can apply to higher dimensional data using latent variable preselection. Results on natural and artificial occlusion-rich data with controlled forms of sparse structure show that our model can extract a sparse set of edge-like components that closely match the generating process, which we refer to as interpretable components. Furthermore, the sparseness of the solution closely follows the ground-truth number of components/edges in the images. The linear model did not learn such edge-like components with any level of sparsity. This suggests that our model can adaptively well-approximate and characterize the meaningful generation process. PMID:25954947
Nonlinear spike-and-slab sparse coding for interpretable image encoding.
Shelton, Jacquelyn A; Sheikh, Abdul-Saboor; Bornschein, Jörg; Sterne, Philip; Lücke, Jörg
2015-01-01
Sparse coding is a popular approach to model natural images but has faced two main challenges: modelling low-level image components (such as edge-like structures and their occlusions) and modelling varying pixel intensities. Traditionally, images are modelled as a sparse linear superposition of dictionary elements, where the probabilistic view of this problem is that the coefficients follow a Laplace or Cauchy prior distribution. We propose a novel model that instead uses a spike-and-slab prior and nonlinear combination of components. With the prior, our model can easily represent exact zeros for e.g. the absence of an image component, such as an edge, and a distribution over non-zero pixel intensities. With the nonlinearity (the nonlinear max combination rule), the idea is to target occlusions; dictionary elements correspond to image components that can occlude each other. There are major consequences of the model assumptions made by both (non)linear approaches, thus the main goal of this paper is to isolate and highlight differences between them. Parameter optimization is analytically and computationally intractable in our model, thus as a main contribution we design an exact Gibbs sampler for efficient inference which we can apply to higher dimensional data using latent variable preselection. Results on natural and artificial occlusion-rich data with controlled forms of sparse structure show that our model can extract a sparse set of edge-like components that closely match the generating process, which we refer to as interpretable components. Furthermore, the sparseness of the solution closely follows the ground-truth number of components/edges in the images. The linear model did not learn such edge-like components with any level of sparsity. This suggests that our model can adaptively well-approximate and characterize the meaningful generation process.
Sparse matrix transform for fast projection to reduced dimension
Theiler, James P; Cao, Guangzhi; Bouman, Charles A
2010-01-01
We investigate three algorithms that use the sparse matrix transform (SMT) to produce variance-maximizing linear projections to a lower-dimensional space. The SMT expresses the projection as a sequence of Givens rotations and this enables computationally efficient implementation of the projection operator. The baseline algorithm uses the SMT to directly approximate the optimal solution that is given by principal components analysis (PCA). A variant of the baseline begins with a standard SMT solution, but prunes the sequence of Givens rotations to only include those that contribute to the variance maximization. Finally, a simpler and faster third algorithm is introduced; this also estimates the projection operator with a sequence of Givens rotations, but in this case, the rotations are chosen to optimize a criterion that more directly expresses the dimension reduction criterion.
A strategy of car detection via sparse dictionary
NASA Astrophysics Data System (ADS)
Jin, Guo-Qing; Dong, Ying-Hui
2011-06-01
In recent years there is a growing interest in the study of sparse representation for object detection. These approaches heavily depend on local salient image patches, thus weakening the global contribution to the object identification of other less informative signals.Our generic approach not only employs the informative representation by linear transform, but also keeps all the spatial dependence implied among the objects. As an example,car images can be represented using parts from a vocabulary, along with spatial relations observed among them.Our approach is conducted with the quantitative measurement in developing the car detector at every stage. The theory underneath the optimal solution is the maximal mutual information carried out by the system. Our goal is to keep the maximal mutual information transmitted from stage to stage so that only the least uncertainty about the class identification remains based on the observation of classifier's output.
Shirazi, Mohammadali; Lord, Dominique; Dhavala, Soma Sekhar; Geedipally, Srinivas Reddy
2016-06-01
Crash data can often be characterized by over-dispersion, heavy (long) tail and many observations with the value zero. Over the last few years, a small number of researchers have started developing and applying novel and innovative multi-parameter models to analyze such data. These multi-parameter models have been proposed for overcoming the limitations of the traditional negative binomial (NB) model, which cannot handle this kind of data efficiently. The research documented in this paper continues the work related to multi-parameter models. The objective of this paper is to document the development and application of a flexible NB generalized linear model with randomly distributed mixed effects characterized by the Dirichlet process (NB-DP) to model crash data. The objective of the study was accomplished using two datasets. The new model was compared to the NB and the recently introduced model based on the mixture of the NB and Lindley (NB-L) distributions. Overall, the research study shows that the NB-DP model offers a better performance than the NB model once data are over-dispersed and have a heavy tail. The NB-DP performed better than the NB-L when the dataset has a heavy tail, but a smaller percentage of zeros. However, both models performed similarly when the dataset contained a large amount of zeros. In addition to a greater flexibility, the NB-DP provides a clustering by-product that allows the safety analyst to better understand the characteristics of the data, such as the identification of outliers and sources of dispersion.
Vilar, Lara; Gómez, Israel; Martínez-Vega, Javier; Echavarría, Pilar; Riaño, David; Martín, M. Pilar
2016-01-01
The socio-economic factors are of key importance during all phases of wildfire management that include prevention, suppression and restoration. However, modeling these factors, at the proper spatial and temporal scale to understand fire regimes is still challenging. This study analyses socio-economic drivers of wildfire occurrence in central Spain. This site represents a good example of how human activities play a key role over wildfires in the European Mediterranean basin. Generalized Linear Models (GLM) and machine learning Maximum Entropy models (Maxent) predicted wildfire occurrence in the 1980s and also in the 2000s to identify changes between each period in the socio-economic drivers affecting wildfire occurrence. GLM base their estimation on wildfire presence-absence observations whereas Maxent on wildfire presence-only. According to indicators like sensitivity or commission error Maxent outperformed GLM in both periods. It achieved a sensitivity of 38.9% and a commission error of 43.9% for the 1980s, and 67.3% and 17.9% for the 2000s. Instead, GLM obtained 23.33, 64.97, 9.41 and 18.34%, respectively. However GLM performed steadier than Maxent in terms of the overall fit. Both models explained wildfires from predictors such as population density and Wildland Urban Interface (WUI), but differed in their relative contribution. As a result of the urban sprawl and an abandonment of rural areas, predictors like WUI and distance to roads increased their contribution to both models in the 2000s, whereas Forest-Grassland Interface (FGI) influence decreased. This study demonstrates that human component can be modelled with a spatio-temporal dimension to integrate it into wildfire risk assessment. PMID:27557113
Lin, Zi-Jing; Li, Lin; Cazzell, Mary; Liu, Hanli
2014-01-01
Diffuse optical tomography (DOT) is a variant of functional near infrared spectroscopy and has the capability of mapping or reconstructing three dimensional (3D) hemodynamic changes due to brain activity. Common methods used in DOT image analysis to define brain activation have limitations because the selection of activation period is relatively subjective. General linear model (GLM)-based analysis can overcome this limitation. In this study, we combine the atlas-guided 3D DOT image reconstruction with GLM-based analysis (i.e., voxel-wise GLM analysis) to investigate the brain activity that is associated with risk decision-making processes. Risk decision-making is an important cognitive process and thus is an essential topic in the field of neuroscience. The Balloon Analog Risk Task (BART) is a valid experimental model and has been commonly used to assess human risk-taking actions and tendencies while facing risks. We have used the BART paradigm with a blocked design to investigate brain activations in the prefrontal and frontal cortical areas during decision-making from 37 human participants (22 males and 15 females). Voxel-wise GLM analysis was performed after a human brain atlas template and a depth compensation algorithm were combined to form atlas-guided DOT images. In this work, we wish to demonstrate the excellence of using voxel-wise GLM analysis with DOT to image and study cognitive functions in response to risk decision-making. Results have shown significant hemodynamic changes in the dorsal lateral prefrontal cortex (DLPFC) during the active-choice mode and a different activation pattern between genders; these findings correlate well with published literature in functional magnetic resonance imaging (fMRI) and fNIRS studies. PMID:24619964
Forstmeier, Wolfgang
2011-11-01
General linear models (GLM) have become such universal tools of statistical inference, that their applicability to a particular data set is rarely questioned. These models are designed to minimize residuals along the y-axis, while assuming that the predictor (x-axis) is free of statistical noise (ordinary least square regression, OLS). However, in practice, this assumption is often violated, which can lead to erroneous conclusions, particularly when two predictors are correlated with each other. This is best illustrated by two examples from the study of allometry, which have received great interest: (1) the question of whether men or women have relatively larger brains after accounting for body size differences, and (2) whether men indeed have shorter index fingers relative to ring fingers (digit ratio) than women. In depth analysis of these examples clearly shows that GLMs produce spurious sexual dimorphism in body shape where there is none (e.g. relative brain size). Likewise, they may fail to detect existing sexual dimorphisms in which the larger sex has the lower trait values (e.g. digit ratio) and, conversely, tend to exaggerate sexual dimorphism in which the larger sex has the relatively larger trait value (e.g. most sexually selected traits). These artifacts can be avoided with reduced major axis regression (RMA), which simultaneously minimizes residuals along both the x and the y-axis. Alternatively, in cases where isometry can be established there are no objections against and good reasons for the continued use of ratios as a simple means of correcting for size differences.
Inferring propagation paths for sparsely observed perturbations on complex networks
Massucci, Francesco Alessandro; Wheeler, Jonathan; Beltrán-Debón, Raúl; Joven, Jorge; Sales-Pardo, Marta; Guimerà, Roger
2016-01-01
In a complex system, perturbations propagate by following paths on the network of interactions among the system’s units. In contrast to what happens with the spreading of epidemics, observations of general perturbations are often very sparse in time (there is a single observation of the perturbed system) and in “space” (only a few perturbed and unperturbed units are observed). A major challenge in many areas, from biology to the social sciences, is to infer the propagation paths from observations of the effects of perturbation under these sparsity conditions. We address this problem and show that it is possible to go beyond the usual approach of using the shortest paths connecting the known perturbed nodes. Specifically, we show that a simple and general probabilistic model, which we solved using belief propagation, provides fast and accurate estimates of the probabilities of nodes being perturbed. PMID:27819038
Generalized subspace correction methods
Kolm, P.; Arbenz, P.; Gander, W.
1996-12-31
A fundamental problem in scientific computing is the solution of large sparse systems of linear equations. Often these systems arise from the discretization of differential equations by finite difference, finite volume or finite element methods. Iterative methods exploiting these sparse structures have proven to be very effective on conventional computers for a wide area of applications. Due to the rapid development and increasing demand for the large computing powers of parallel computers, it has become important to design iterative methods specialized for these new architectures.
A sparse grid based method for generative dimensionality reduction of high-dimensional data
NASA Astrophysics Data System (ADS)
Bohn, Bastian; Garcke, Jochen; Griebel, Michael
2016-03-01
Generative dimensionality reduction methods play an important role in machine learning applications because they construct an explicit mapping from a low-dimensional space to the high-dimensional data space. We discuss a general framework to describe generative dimensionality reduction methods, where the main focus lies on a regularized principal manifold learning variant. Since most generative dimensionality reduction algorithms exploit the representer theorem for reproducing kernel Hilbert spaces, their computational costs grow at least quadratically in the number n of data. Instead, we introduce a grid-based discretization approach which automatically scales just linearly in n. To circumvent the curse of dimensionality of full tensor product grids, we use the concept of sparse grids. Furthermore, in real-world applications, some embedding directions are usually more important than others and it is reasonable to refine the underlying discretization space only in these directions. To this end, we employ a dimension-adaptive algorithm which is based on the ANOVA (analysis of variance) decomposition of a function. In particular, the reconstruction error is used to measure the quality of an embedding. As an application, the study of large simulation data from an engineering application in the automotive industry (car crash simulation) is performed.
OPTIMAL COMPUTATIONAL AND STATISTICAL RATES OF CONVERGENCE FOR SPARSE NONCONVEX LEARNING PROBLEMS.
Wang, Zhaoran; Liu, Han; Zhang, Tong
2014-01-01
We provide theoretical analysis of the statistical and computational properties of penalized M-estimators that can be formulated as the solution to a possibly nonconvex optimization problem. Many important estimators fall in this category, including least squares regression with nonconvex regularization, generalized linear models with nonconvex regularization and sparse elliptical random design regression. For these problems, it is intractable to calculate the global solution due to the nonconvex formulation. In this paper, we propose an approximate regularization path-following method for solving a variety of learning problems with nonconvex objective functions. Under a unified analytic framework, we simultaneously provide explicit statistical and computational rates of convergence for any local solution attained by the algorithm. Computationally, our algorithm attains a global geometric rate of convergence for calculating the full regularization path, which is optimal among all first-order algorithms. Unlike most existing methods that only attain geometric rates of convergence for one single regularization parameter, our algorithm calculates the full regularization path with the same iteration complexity. In particular, we provide a refined iteration complexity bound to sharply characterize the performance of each stage along the regularization path. Statistically, we provide sharp sample complexity analysis for all the approximate local solutions along the regularization path. In particular, our analysis improves upon existing results by providing a more refined sample complexity bound as well as an exact support recovery result for the final estimator. These results show that the final estimator attains an oracle statistical property due to the usage of nonconvex penalty.
OPTIMAL COMPUTATIONAL AND STATISTICAL RATES OF CONVERGENCE FOR SPARSE NONCONVEX LEARNING PROBLEMS
Wang, Zhaoran; Liu, Han; Zhang, Tong
2014-01-01
We provide theoretical analysis of the statistical and computational properties of penalized M-estimators that can be formulated as the solution to a possibly nonconvex optimization problem. Many important estimators fall in this category, including least squares regression with nonconvex regularization, generalized linear models with nonconvex regularization and sparse elliptical random design regression. For these problems, it is intractable to calculate the global solution due to the nonconvex formulation. In this paper, we propose an approximate regularization path-following method for solving a variety of learning problems with nonconvex objective functions. Under a unified analytic framework, we simultaneously provide explicit statistical and computational rates of convergence for any local solution attained by the algorithm. Computationally, our algorithm attains a global geometric rate of convergence for calculating the full regularization path, which is optimal among all first-order algorithms. Unlike most existing methods that only attain geometric rates of convergence for one single regularization parameter, our algorithm calculates the full regularization path with the same iteration complexity. In particular, we provide a refined iteration complexity bound to sharply characterize the performance of each stage along the regularization path. Statistically, we provide sharp sample complexity analysis for all the approximate local solutions along the regularization path. In particular, our analysis improves upon existing results by providing a more refined sample complexity bound as well as an exact support recovery result for the final estimator. These results show that the final estimator attains an oracle statistical property due to the usage of nonconvex penalty. PMID:25544785
Solving large sparse eigenvalue problems on supercomputers
NASA Technical Reports Server (NTRS)
Philippe, Bernard; Saad, Youcef
1988-01-01
An important problem in scientific computing consists in finding a few eigenvalues and corresponding eigenvectors of a very large and sparse matrix. The most popular methods to solve these problems are based on projection techniques on appropriate subspaces. The main attraction of these methods is that they only require the use of the matrix in the form of matrix by vector multiplications. The implementations on supercomputers of two such methods for symmetric matrices, namely Lanczos' method and Davidson's method are compared. Since one of the most important operations in these two methods is the multiplication of vectors by the sparse matrix, methods of performing this operation efficiently are discussed. The advantages and the disadvantages of each method are compared and implementation aspects are discussed. Numerical experiments on a one processor CRAY 2 and CRAY X-MP are reported. Possible parallel implementations are also discussed.
Sparse representation for color image restoration.
Mairal, Julien; Elad, Michael; Sapiro, Guillermo
2008-01-01
Sparse representations of signals have drawn considerable interest in recent years. The assumption that natural signals, such as images, admit a sparse decomposition over a redundant dictionary leads to efficient algorithms for handling such sources of data. In particular, the design of well adapted dictionaries for images has been a major challenge. The K-SVD has been recently proposed for this task and shown to perform very well for various grayscale image processing tasks. In this paper, we address the problem of learning dictionaries for color images and extend the K-SVD-based grayscale image denoising algorithm that appears in. This work puts forward ways for handling nonhomogeneous noise and missing information, paving the way to state-of-the-art results in applications such as color image denoising, demosaicing, and inpainting, as demonstrated in this paper.
Statistical prediction with Kanerva's sparse distributed memory
NASA Technical Reports Server (NTRS)
Rogers, David
1989-01-01
A new viewpoint of the processing performed by Kanerva's sparse distributed memory (SDM) is presented. In conditions of near- or over-capacity, where the associative-memory behavior of the model breaks down, the processing performed by the model can be interpreted as that of a statistical predictor. Mathematical results are presented which serve as the framework for a new statistical viewpoint of sparse distributed memory and for which the standard formulation of SDM is a special case. This viewpoint suggests possible enhancements to the SDM model, including a procedure for improving the predictiveness of the system based on Holland's work with genetic algorithms, and a method for improving the capacity of SDM even when used as an associative memory.
Causal Network Inference Via Group Sparse Regularization
Bolstad, Andrew; Van Veen, Barry D.; Nowak, Robert
2011-01-01
This paper addresses the problem of inferring sparse causal networks modeled by multivariate autoregressive (MAR) processes. Conditions are derived under which the Group Lasso (gLasso) procedure consistently estimates sparse network structure. The key condition involves a “false connection score” ψ. In particular, we show that consistent recovery is possible even when the number of observations of the network is far less than the number of parameters describing the network, provided that ψ < 1. The false connection score is also demonstrated to be a useful metric of recovery in nonasymptotic regimes. The conditions suggest a modified gLasso procedure which tends to improve the false connection score and reduce the chances of reversing the direction of causal influence. Computational experiments and a real network based electrocorticogram (ECoG) simulation study demonstrate the effectiveness of the approach. PMID:21918591
Locality-preserving sparse representation-based classification in hyperspectral imagery
NASA Astrophysics Data System (ADS)
Gao, Lianru; Yu, Haoyang; Zhang, Bing; Li, Qingting
2016-10-01
This paper proposes to combine locality-preserving projections (LPP) and sparse representation (SR) for hyperspectral image classification. The LPP is first used to reduce the dimensionality of all the training and testing data by finding the optimal linear approximations to the eigenfunctions of the Laplace Beltrami operator on the manifold, where the high-dimensional data lies. Then, SR codes the projected testing pixels as sparse linear combinations of all the training samples to classify the testing pixels by evaluating which class leads to the minimum approximation error. The integration of LPP and SR represents an innovative contribution to the literature. The proposed approach, called locality-preserving SR-based classification, addresses the imbalance between high dimensionality of hyperspectral data and the limited number of training samples. Experimental results on three real hyperspectral data sets demonstrate that the proposed approach outperforms the original counterpart, i.e., SR-based classification.
A survey of packages for large linear systems
Wu, Kesheng; Milne, Brent
2000-02-11
This paper evaluates portable software packages for the iterative solution of very large sparse linear systems on parallel architectures. While we cannot hope to tell individual users which package will best suit their needs, we do hope that our systematic evaluation provides essential unbiased information about the packages and the evaluation process may serve as an example on how to evaluate these packages. The information contained here include feature comparisons, usability evaluations and performance characterizations. This review is primarily focused on self-contained packages that can be easily integrated into an existing program and are capable of computing solutions to very large sparse linear systems of equations. More specifically, it concentrates on portable parallel linear system solution packages that provide iterative solution schemes and related preconditioning schemes because iterative methods are more frequently used than competing schemes such as direct methods. The eight packages evaluated are: Aztec, BlockSolve,ISIS++, LINSOL, P-SPARSLIB, PARASOL, PETSc, and PINEAPL. Among the eight portable parallel iterative linear system solvers reviewed, we recommend PETSc and Aztec for most application programmers because they have well designed user interface, extensive documentation and very responsive user support. Both PETSc and Aztec are written in the C language and are callable from Fortran. For those users interested in using Fortran 90, PARASOL is a good alternative. ISIS++is a good alternative for those who prefer the C++ language. Both PARASOL and ISIS++ are relatively new and are continuously evolving. Thus their user interface may change. In general, those packages written in Fortran 77 are more cumbersome to use because the user may need to directly deal with a number of arrays of varying sizes. Languages like C++ and Fortran 90 offer more convenient data encapsulation mechanisms which make it easier to implement a clean and intuitive user
Tighten after Relax: Minimax-Optimal Sparse PCA in Polynomial Time
Wang, Zhaoran; Lu, Huanran; Liu, Han
2014-01-01
We provide statistical and computational analysis of sparse Principal Component Analysis (PCA) in high dimensions. The sparse PCA problem is highly nonconvex in nature. Consequently, though its global solution attains the optimal statistical rate of convergence, such solution is computationally intractable to obtain. Meanwhile, although its convex relaxations are tractable to compute, they yield estimators with suboptimal statistical rates of convergence. On the other hand, existing nonconvex optimization procedures, such as greedy methods, lack statistical guarantees. In this paper, we propose a two-stage sparse PCA procedure that attains the optimal principal subspace estimator in polynomial time. The main stage employs a novel algorithm named sparse orthogonal iteration pursuit, which iteratively solves the underlying nonconvex problem. However, our analysis shows that this algorithm only has desired computational and statistical guarantees within a restricted region, namely the basin of attraction. To obtain the desired initial estimator that falls into this region, we solve a convex formulation of sparse PCA with early stopping. Under an integrated analytic framework, we simultaneously characterize the computational and statistical performance of this two-stage procedure. Computationally, our procedure converges at the rate of 1∕t within the initialization stage, and at a geometric rate within the main stage. Statistically, the final principal subspace estimator achieves the minimax-optimal statistical rate of convergence with respect to the sparsity level s*, dimension d and sample size n. Our procedure motivates a general paradigm of tackling nonconvex statistical learning problems with provable statistical guarantees. PMID:25620858
NASA Astrophysics Data System (ADS)
Yu, Caixia; Zhao, Jingtao; Wang, Yanfei
2017-02-01
Studying small-scale geologic discontinuities, such as faults, cavities and fractures, plays a vital role in analyzing the inner conditions of reservoirs, as these geologic structures and elements can provide storage spaces and migration pathways for petroleum. However, these geologic discontinuities have weak energy and are easily contaminated with noises, and therefore effectively extracting them from seismic data becomes a challenging problem. In this paper, a method for detecting small-scale discontinuities using dictionary learning and sparse representation is proposed that can dig up high-resolution information by sparse coding. A K-SVD (K-means clustering via Singular Value Decomposition) sparse representation model that contains two stage of iteration procedure: sparse coding and dictionary updating, is suggested for mathematically expressing these seismic small-scale discontinuities. Generally, the orthogonal matching pursuit (OMP) algorithm is employed for sparse coding. However, the method can only update one dictionary atom at one time. In order to improve calculation efficiency, a regularized version of OMP algorithm is presented for simultaneously updating a number of atoms at one time. Two numerical experiments demonstrate the validity of the developed method for clarifying and enhancing small-scale discontinuities. The field example of carbonate reservoirs further demonstrates its effectiveness in revealing masked tiny faults and small-scale cavities.
Hyperspectral Image Classification via Kernel Sparse Representation
2013-01-01
and sparse representations, image processing, wavelets, multirate systems , and filter banks . Nasser M. Nasrabadi (S’80–M’84–SM’92–F’01) received the...ery, sampling, multirate systems , filter banks , transforms, wavelets, and their applications in signal analysis, compression, processing, and...University of Pavia and the Center of Pavia images, are urban images acquired by the Reflective Optics System Imaging Spectrom- eter (ROSIS). The ROSIS
Notes on implementation of sparsely distributed memory
NASA Technical Reports Server (NTRS)
Keeler, J. D.; Denning, P. J.
1986-01-01
The Sparsely Distributed Memory (SDM) developed by Kanerva is an unconventional memory design with very interesting and desirable properties. The memory works in a manner that is closely related to modern theories of human memory. The SDM model is discussed in terms of its implementation in hardware. Two appendices discuss the unconventional approaches of the SDM: Appendix A treats a resistive circuit for fast, parallel address decoding; and Appendix B treats a systolic array for high throughput read and write operations.
STENMIN: A software package for large, sparse unconstrained optimization using tensor methods
Bouaricha, A.
1996-11-01
We describe a new package for minimizing an unconstrained nonlinear function where the Hessian is large and sparse. The software allows the user to select between a tensor method and a standard method based upon a quadratic model. The tensor method models the objective function by a fourth-order model, where the third- and fourth-order terms are chosen such that the extra cost of forming and solving the model is small. The new contribution of this package consists of the incorporation of an entirely new way of minimizing the tensor model that makes it suitable for solving large, sparse optimization problems efficiently. The test results indicate that, in general, the tensor method is significantly more efficient and more reliable than the standard Newton method for solving large, sparse unconstrained optimization problems. 12 refs., 1 tab.
A joint sparse representation-based method for double-trial evoked potentials estimation.
Yu, Nannan; Liu, Haikuan; Wang, Xiaoyan; Lu, Hanbing
2013-12-01
In this paper, we present a novel approach to solving an evoked potentials estimating problem. Generally, the evoked potentials in two consecutive trials obtained by repeated identical stimuli of the nerves are extremely similar. In order to trace evoked potentials, we propose a joint sparse representation-based double-trial evoked potentials estimation method, taking full advantage of this similarity. The estimation process is performed in three stages: first, according to the similarity of evoked potentials and the randomness of a spontaneous electroencephalogram, the two consecutive observations of evoked potentials are considered as superpositions of the common component and the unique components; second, making use of their characteristics, the two sparse dictionaries are constructed; and finally, we apply the joint sparse representation method in order to extract the common component of double-trial observations, instead of the evoked potential in each trial. A series of experiments carried out on simulated and human test responses confirmed the superior performance of our method.
On interpolation of sparsely sampled sinograms
NASA Astrophysics Data System (ADS)
Schröder, Stephan; Stuke, Ingo; Aach, Til
2006-03-01
Certain situations, for instance in flat-panel cone beam CT, permit that only a relatively low number of projections are acquired. The reconstruction quality of the volume to be imaged is then compromised by streaking artifacts. To avoid these degradations, additional projections are interpolated between the genuinely acquired ones. Since straightforward linear, non-adaptive interpolation generally results in loss of sharpness, techniques were developed which adapt to, e.g., local orientation within the sinogram. So far, such directional interpolation algorithms consider only single local orientations. Especially in x-ray imaging, however, different non-opaque orientated structures may be superimposed. We therefore show how such multiply-oriented structures can be detected, estimated, and included in the interpolation process. Furthermore, genuine sinograms meet certain conditions regarding their moments as well as regarding their spectra. Moments of 2D sinograms depend on the projection angle in the form of sinosoids, while the Fourier spectrum of the sinogram takes the form of a 'bow tie'. The consistency of the interpolated data with these conditions may therefore be viewed as additional measures of the interpolation quality. For linear interpolation, we analyze how well the interpolated data comply with these constraints. We also show how the moment constraint can be integrated into the interpolation process.
Objective sea level pressure analysis for sparse data areas
NASA Technical Reports Server (NTRS)
Druyan, L. M.
1972-01-01
A computer procedure was used to analyze the pressure distribution over the North Pacific Ocean for eleven synoptic times in February, 1967. Independent knowledge of the central pressures of lows is shown to reduce the analysis errors for very sparse data coverage. The application of planned remote sensing of sea-level wind speeds is shown to make a significant contribution to the quality of the analysis especially in the high gradient mid-latitudes and for sparse coverage of conventional observations (such as over Southern Hemisphere oceans). Uniform distribution of the available observations of sea-level pressure and wind velocity yields results far superior to those derived from a random distribution. A generalization of the results indicates that the average lower limit for analysis errors is between 2 and 2.5 mb based on the perfect specification of the magnitude of the sea-level pressure gradient from a known verification analysis. A less than perfect specification will derive from wind-pressure relationships applied to satellite observed wind speeds.
Sparse tensor discriminant color space for face verification.
Wang, Su-Jing; Yang, Jian; Sun, Ming-Fang; Peng, Xu-Jun; Sun, Ming-Ming; Zhou, Chun-Guang
2012-06-01
As one of the fundamental features, color provides useful information and plays an important role for face recognition. Generally, the choice of a color space is different for different visual tasks. How can a color space be sought for the specific face recognition problem? To address this problem, we propose a sparse tensor discriminant color space (STDCS) model that represents a color image as a third-order tensor in this paper. The model cannot only keep the underlying spatial structure of color images but also enhance robustness and give intuitionistic or semantic interpretation. STDCS transforms the eigenvalue problem to a series of regression problems. Then one spare color space transformation matrix and two sparse discriminant projection matrices are obtained by applying lasso or elastic net on the regression problems. The experiments on three color face databases, AR, Georgia Tech, and Labeled Faces in the Wild face databases, show that both the performance and the robustness of the proposed method outperform those of the state-of-the-art TDCS model.
Slowness and sparseness have diverging effects on complex cell learning.
Lies, Jörn-Philipp; Häfner, Ralf M; Bethge, Matthias
2014-03-01
Following earlier studies which showed that a sparse coding principle may explain the receptive field properties of complex cells in primary visual cortex, it has been concluded that the same properties may be equally derived from a slowness principle. In contrast to this claim, we here show that slowness and sparsity drive the representations towards substantially different receptive field properties. To do so, we present complete sets of basis functions learned with slow subspace analysis (SSA) in case of natural movies as well as translations, rotations, and scalings of natural images. SSA directly parallels independent subspace analysis (ISA) with the only difference that SSA maximizes slowness instead of sparsity. We find a large discrepancy between the filter shapes learned with SSA and ISA. We argue that SSA can be understood as a generalization of the Fourier transform where the power spectrum corresponds to the maximally slow subspace energies in SSA. Finally, we investigate the trade-off between slowness and sparseness when combined in one objective function.
Sparse Bayesian extreme learning machine for multi-classification.
Luo, Jiahua; Vong, Chi-Man; Wong, Pak-Kin
2014-04-01
Extreme learning machine (ELM) has become a popular topic in machine learning in recent years. ELM is a new kind of single-hidden layer feedforward neural network with an extremely low computational cost. ELM, however, has two evident drawbacks: 1) the output weights solved by Moore-Penrose generalized inverse is a least squares minimization issue, which easily suffers from overfitting and 2) the accuracy of ELM is drastically sensitive to the number of hidden neurons so that a large model is usually generated. This brief presents a sparse Bayesian approach for learning the output weights of ELM in classification. The new model, called Sparse Bayesian ELM (SBELM), can resolve these two drawbacks by estimating the marginal likelihood of network outputs and automatically pruning most of the redundant hidden neurons during learning phase, which results in an accurate and compact model. The proposed SBELM is evaluated on wide types of benchmark classification problems, which verifies that the accuracy of SBELM model is relatively insensitive to the number of hidden neurons; and hence a much more compact model is always produced as compared with other state-of-the-art neural network classifiers.
Kinetics of diffusion-controlled annihilation with sparse initial conditions
Ben-Naim, Eli; Krapivsky, Paul
2016-12-16
Here, we study diffusion-controlled single-species annihilation with sparse initial conditions. In this random process, particles undergo Brownian motion, and when two particles meet, both disappear. We also focus on sparse initial conditions where particles occupy a subspace of dimension δ that is embedded in a larger space of dimension d. Furthermore, we find that the co-dimension Δ = d - δ governs the behavior. All particles disappear when the co-dimension is sufficiently small, Δ ≤ 2; otherwise, a finite fraction of particles indefinitely survive. We establish the asymptotic behavior of the probability S(t) that a test particle survives until time t. When the subspace is a line, δ = 1, we find inverse logarithmic decay,more » $$S\\sim {(\\mathrm{ln}t)}^{-1}$$, in three dimensions, and a modified power-law decay, $$S\\sim (\\mathrm{ln}t){t}^{-1/2}$$, in two dimensions. In general, the survival probability decays algebraically when Δ < 2, and there is an inverse logarithmic decay at the critical co-dimension Δ = 2.« less
Kinetics of diffusion-controlled annihilation with sparse initial conditions
Ben-Naim, Eli; Krapivsky, Paul
2016-12-16
Here, we study diffusion-controlled single-species annihilation with sparse initial conditions. In this random process, particles undergo Brownian motion, and when two particles meet, both disappear. We also focus on sparse initial conditions where particles occupy a subspace of dimension δ that is embedded in a larger space of dimension d. Furthermore, we find that the co-dimension Δ = d - δ governs the behavior. All particles disappear when the co-dimension is sufficiently small, Δ ≤ 2; otherwise, a finite fraction of particles indefinitely survive. We establish the asymptotic behavior of the probability S(t) that a test particle survives until time t. When the subspace is a line, δ = 1, we find inverse logarithmic decay, $S\\sim {(\\mathrm{ln}t)}^{-1}$, in three dimensions, and a modified power-law decay, $S\\sim (\\mathrm{ln}t){t}^{-1/2}$, in two dimensions. In general, the survival probability decays algebraically when Δ < 2, and there is an inverse logarithmic decay at the critical co-dimension Δ = 2.
Imaging black holes with sparse modeling
NASA Astrophysics Data System (ADS)
Honma, Mareki; Akiyama, Kazunori; Tazaki, Fumie; Kuramochi, Kazuki; Ikeda, Shiro; Hada, Kazuhiro; Uemura, Makoto
2016-03-01
We introduce a new imaging method for radio interferometry based on sparse- modeling. The direct observables in radio interferometry are visibilities, which are Fourier transformation of an astronomical image on the sky-plane, and incomplete sampling of visibilities in the spatial frequency domain results in an under-determined problem, which has been usually solved with 0 filling to un-sampled grids. In this paper we propose to directly solve this under-determined problem using sparse modeling without 0 filling, which realizes super resolution, i.e., resolution higher than the standard refraction limit. We show simulation results of sparse modeling for the Event Horizon Telescope (EHT) observations of super-massive black holes and demonstrate that our approach has significant merit in observations of black hole shadows expected to be realized in near future. We also present some results with the method applied to real data, and also discuss more advanced techniques for practical observations such as imaging with closure phase as well as treating the effect of interstellar scattering effect.
Leite-Martins, Liliana R; Mahú, Maria I M; Costa, Ana L; Mendes, Angelo; Lopes, Elisabete; Mendonça, Denisa M V; Niza-Ribeiro, João J R; de Matos, Augusto J F; da Costa, Paulo Martins
2014-11-01
Antimicrobial resistance (AMR) is a growing global public health problem, which is caused by the use of antimicrobials in both human and animal medical practice. The objectives of the present cross-sectional study were as follows: (1) to determine the prevalence of resistance in Escherichia coli isolated from the feces of pets from the Porto region of Portugal against 19 antimicrobial agents and (2) to assess the individual, clinical and environmental characteristics associated with each pet as risk markers for the AMR of the E. coli isolates. From September 2009 to May 2012, rectal swabs were collected from pets selected using a systematic random procedure from the ordinary population of animals attending the Veterinary Hospital of Porto University. A total of 78 dogs and 22 cats were sampled with the objective of isolating E. coli. The animals' owners, who allowed the collection of fecal samples from their pets, answered a questionnaire to collect information about the markers that could influence the AMR of the enteric E. coli. Chromocult tryptone bile X-glucuronide agar was used for E. coli isolation, and the disk diffusion method was used to determine the antimicrobial susceptibility. The data were analyzed using a multilevel, univariable and multivariable generalized linear mixed model (GLMM). Several (49.7%) of the 396 isolates obtained in this study were multidrug-resistant. The E. coli isolates exhibited resistance to the antimicrobial agent's ampicillin (51.3%), cephalothin (46.7%), tetracycline (45.2%) and streptomycin (43.4%). Previous quinolone treatment was the main risk marker for the presence of AMR for 12 (ampicillin, cephalothin, ceftazidime, cefotaxime, nalidixic acid, ciprofloxacin, gentamicin, tetracycline, streptomycin, chloramphenicol, trimethoprim-sulfamethoxazole and aztreonam) of the 15 antimicrobials assessed. Coprophagic habits were also positively associated with an increased risk of AMR for six drugs, ampicillin, amoxicillin
Efficient visual tracking via low-complexity sparse representation
NASA Astrophysics Data System (ADS)
Lu, Weizhi; Zhang, Jinglin; Kpalma, Kidiyo; Ronsin, Joseph
2015-12-01
Thanks to its good performance on object recognition, sparse representation has recently been widely studied in the area of visual object tracking. Up to now, little attention has been paid to the complexity of sparse representation, while most works are focused on the performance improvement. By reducing the computation load related to sparse representation hundreds of times, this paper proposes by far the most computationally efficient tracking approach based on sparse representation. The proposal simply consists of two stages of sparse representation, one is for object detection and the other for object validation. Experimentally, it achieves better performance than some state-of-the-art methods in both accuracy and speed.
Object-oriented algorithmic laboratory for ordering sparse matrices
Kumfert, Gary Karl
2000-05-01
We focus on two known NP-hard problems that have applications in sparse matrix computations: the envelope/wavefront reduction problem and the fill reduction problem. Envelope/wavefront reducing orderings have a wide range of applications including profile and frontal solvers, incomplete factorization preconditioning, graph reordering for cache performance, gene sequencing, and spatial databases. Fill reducing orderings are generally limited to--but an inextricable part of--sparse matrix factorization. Our major contribution to this field is the design of new and improved heuristics for these NP-hard problems and their efficient implementation in a robust, cross-platform, object-oriented software package. In this body of research, we (1) examine current ordering algorithms, analyze their asymptotic complexity, and characterize their behavior in model problems, (2) introduce new and improved algorithms that address deficiencies found in previous heuristics, (3) implement an object-oriented library of these algorithms in a robust, modular fashion without significant loss of efficiency, and (4) extend our algorithms and software to address both generalized and constrained problems. We stress that the major contribution is the algorithms and the implementation; the whole being greater than the sum of its parts. The initial motivation for implementing our algorithms in object-oriented software was to manage the inherent complexity. During our research came the realization that the object-oriented implementation enabled new possibilities augmented algorithms that would not have been as natural to generalize from a procedural implementation. Some extensions are constructed from a family of related algorithmic components, thereby creating a poly-algorithm that can adapt its strategy to the properties of the specific problem instance dynamically. Other algorithms are tailored for special constraints by aggregating algorithmic components and having them collaboratively
Noor, Amina; Ahmad, Aitzaz; Serpedin, Erchin
2015-10-27
Network component analysis (NCA) is an important method for inferring transcriptional regulatory networks (TRNs) and recovering transcription factor activities (TFAs) using gene expression data, and the prior information about the connectivity matrix. The algorithms currently available crucially depend on the completeness of this prior information. However, inaccuracies in the measurement process may render incompleteness in the available knowledge about the connectivity matrix. Hence, computationally efficient algorithms are needed to overcome the possible incompleteness in the available data. We present a sparse network component analysis algorithm (sparseNCA), which incorporates the effect of incompleteness in the estimation of TRNs by imposing an additional sparsity constraint using the `1 norm, which results in a greater estimation accuracy. In order to improve the computational efficiency, an iterative re-weighted `2 method is proposed for the NCA problem which not only promotes sparsity but is hundreds of times faster than the `1 norm based solution. The performance of sparseNCA is rigorously compared to that of FastNCA and NINCA using synthetic data as well as real data. It is shown that sparseNCA outperforms the existing state-of-the-art algorithms both in terms of estimation accuracy and consistency with the added advantage of low computational complexity. The performance of sparseNCA compared to its predecessors is particularly pronounced in case of incomplete prior information about the sparsity of the network. Subnetwork analysis is performed on the E.coli data which reiterates the superior consistency of the proposed algorithm.
On recovery of block-sparse signals via mixed l 2 /l q (0 < q ≤ 1)norm minimization
NASA Astrophysics Data System (ADS)
Wang, Yao; Wang, Jianjun; Xu, Zongben
2013-12-01
Compressed sensing (CS) states that a sparse signal can exactly be recovered from very few linear measurements. While in many applications, real-world signals also exhibit additional structures aside from standard sparsity. The typical example is the so-called block-sparse signals whose non-zero coefficients occur in a few blocks. In this article, we investigate the mixed l 2/ l q (0 < q ≤ 1) norm minimization method for the exact and robust recovery of such block-sparse signals. We mainly show that the non-convex l 2/ l q (0 < q < 1) minimization method has stronger sparsity promoting ability than the commonly used l 2/ l 1 minimization method both practically and theoretically. In terms of a block variant of the restricted isometry property of measurement matrix, we present weaker sufficient conditions for exact and robust block-sparse signal recovery than those known for l 2/ l 1 minimization. We also propose an efficient Iteratively Reweighted Least-Squares (IRLS) algorithm for the induced non-convex optimization problem. The obtained weaker conditions and the proposed IRLS algorithm are tested and compared with the mixed l 2/ l 1 minimization method and the standard l q minimization method on a series of noiseless and noisy block-sparse signals. All the comparisons demonstrate the outperformance of the mixed l 2/ l q (0 < q < 1) method for block-sparse signal recovery applications, and meaningfulness in the development of new CS technology.